Authors: Iuliia Kotseruba, John K. Tsotsos
Abstract: Driving is a visuomotor task, i.e., there is a connection between what drivers see and what they do. While some models of drivers' gaze account for top-down effects of drivers' actions, the majority learn only bottom-up correlations between human gaze and driving footage. The crux of the problem is lack of public data with annotations that could be used to train top-down models and evaluate how well models of any kind capture effects of task on attention. As a result, top-down models are trained and evaluated on private data and public benchmarks measure only the overall fit to human data. In this paper, we focus on data limitations by examining four large-scale public datasets, DR(eye)VE, BDD-A, MAAD, and LBW, used to train and evaluate algorithms for drivers' gaze prediction. We define a set of driving tasks (lateral and longitudinal maneuvers) and context elements (intersections and right-of-way) known to affect drivers' attention, augment the datasets with annotations based on the said definitions, and analyze the characteristics of data recording and processing pipelines w.r.t. capturing what the drivers see and do. In sum, the contributions of this work are: 1) quantifying biases of the public datasets, 2) examining performance of the SOTA bottom-up models on subsets of the data involving non-trivial drivers' actions, 3) linking shortcomings of the bottom-up models to data limitations, and 4) recommendations for future data collection and processing. The new annotations and code for reproducing the results is available at https://github.com/ykotseruba/SCOUT.
Authors: Iuliia Kotseruba, John K. Tsotsos
Abstract: Accurate prediction of drivers' gaze is an important component of vision-based driver monitoring and assistive systems. Of particular interest are safety-critical episodes, such as performing maneuvers or crossing intersections. In such scenarios, drivers' gaze distribution changes significantly and becomes difficult to predict, especially if the task and context information is represented implicitly, as is common in many state-of-the-art models. However, explicit modeling of top-down factors affecting drivers' attention often requires additional information and annotations that may not be readily available. In this paper, we address the challenge of effective modeling of task and context with common sources of data for use in practical systems. To this end, we introduce SCOUT+, a task- and context-aware model for drivers' gaze prediction, which leverages route and map information inferred from commonly available GPS data. We evaluate our model on two datasets, DR(eye)VE and BDD-A, and demonstrate that using maps improves results compared to bottom-up models and reaches performance comparable to the top-down model SCOUT which relies on privileged ground truth information. Code is available at https://github.com/ykotseruba/SCOUT.
Authors: Joshua Feinglass, Jayaraman J. Thiagarajan, Rushil Anirudh, T. S. Jayram, Yezhou Yang
Abstract: Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector representation over the entire image. This is an oversimplification of the process of novel category recognition, where different regions of the image may have properties from different seen classes and thus have different predominant attributes. With this in mind, we take a fundamentally different approach: a pre-trained Vision-Language detector (VINVL) sensitive to attribute information is employed to efficiently obtain region features. A learned function maps the region features to region-specific attribute attention used to construct class part prototypes. We conduct experiments on a popular GZSL benchmark consisting of the CUB, SUN, and AWA2 datasets where our proposed Part Prototype Network (PPN) achieves promising results when compared with other popular base models. Corresponding ablation studies and analysis show that our approach is highly practical and has a distinct advantage over global attribute attention when localized proposals are available.
Authors: Junchi Wang, Lei Ke
Abstract: Understanding human instructions to identify the target objects is vital for perception systems. In recent years, the advancements of Large Language Models (LLMs) have introduced new possibilities for image segmentation. In this work, we delve into reasoning segmentation, a novel task that enables segmentation system to reason and interpret implicit user intention via large language model reasoning and then segment the corresponding target. Our work on reasoning segmentation contributes on both the methodological design and dataset labeling. For the model, we propose a new framework named LLM-Seg. LLM-Seg effectively connects the current foundational Segmentation Anything Model and the LLM by mask proposals selection. For the dataset, we propose an automatic data generation pipeline and construct a new reasoning segmentation dataset named LLM-Seg40K. Experiments demonstrate that our LLM-Seg exhibits competitive performance compared with existing methods. Furthermore, our proposed pipeline can efficiently produce high-quality reasoning segmentation datasets. The LLM-Seg40K dataset, developed through this pipeline, serves as a new benchmark for training and evaluating various reasoning segmentation approaches. Our code, models and dataset are at https://github.com/wangjunchi/LLMSeg.
Authors: Xiaomeng Zhu, Talha Bilal, P\"ar M{\aa}rtensson, Lars Hanson, M{\aa}rten Bj\"orkman, Atsuto Maki
Abstract: This paper is about effectively utilizing synthetic data for training deep neural networks for industrial parts classification, in particular, by taking into account the domain gap against real-world images. To this end, we introduce a synthetic dataset that may serve as a preliminary testbed for the Sim-to-Real challenge; it contains 17 objects of six industrial use cases, including isolated and assembled parts. A few subsets of objects exhibit large similarities in shape and albedo for reflecting challenging cases of industrial parts. All the sample images come with and without random backgrounds and post-processing for evaluating the importance of domain randomization. We call it Synthetic Industrial Parts dataset (SIP-17). We study the usefulness of SIP-17 through benchmarking the performance of five state-of-the-art deep network models, supervised and self-supervised, trained only on the synthetic data while testing them on real data. By analyzing the results, we deduce some insights on the feasibility and challenges of using synthetic data for industrial parts classification and for further developing larger-scale synthetic datasets. Our dataset and code are publicly available.
Authors: Maurits Reitsma, Julian Keller, Kenneth Blomqvist, Roland Siegwart
Abstract: We propose an interpretable framework for reading analog gauges that is deployable on real world robotic systems. Our framework splits the reading task into distinct steps, such that we can detect potential failures at each step. Our system needs no prior knowledge of the type of gauge or the range of the scale and is able to extract the units used. We show that our gauge reading algorithm is able to extract readings with a relative reading error of less than 2%.
Authors: A. G. Moskowitz, T. Gaona, J. Peterson
Abstract: As AI-generated image (AIGI) methods become more powerful and accessible, it has become a critical task to determine if an image is real or AI-generated. Because AIGI lack the signatures of photographs and have their own unique patterns, new models are needed to determine if an image is AI-generated. In this paper, we investigate the ability of the Contrastive Language-Image Pre-training (CLIP) architecture, pre-trained on massive internet-scale data sets, to perform this differentiation. We fine-tune CLIP on real images and AIGI from several generative models, enabling CLIP to determine if an image is AI-generated and, if so, determine what generation method was used to create it. We show that the fine-tuned CLIP architecture is able to differentiate AIGI as well or better than models whose architecture is specifically designed to detect AIGI. Our method will significantly increase access to AIGI-detecting tools and reduce the negative effects of AIGI on society, as our CLIP fine-tuning procedures require no architecture changes from publicly available model repositories and consume significantly less GPU resources than other AIGI detection models.
Authors: Brinnae Bent
Abstract: In this study, we identify the need for an interpretable, quantitative score of the repeatability, or consistency, of image generation in diffusion models. We propose a semantic approach, using a pairwise mean CLIP (Contrastive Language-Image Pretraining) score as our semantic consistency score. We applied this metric to compare two state-of-the-art open-source image generation diffusion models, Stable Diffusion XL and PixArt-{\alpha}, and we found statistically significant differences between the semantic consistency scores for the models. Agreement between the Semantic Consistency Score selected model and aggregated human annotations was 94%. We also explored the consistency of SDXL and a LoRA-fine-tuned version of SDXL and found that the fine-tuned model had significantly higher semantic consistency in generated images. The Semantic Consistency Score proposed here offers a measure of image generation alignment, facilitating the evaluation of model architectures for specific tasks and aiding in informed decision-making regarding model selection.
Authors: Aref Azizpour, Tai D. Nguyen, Manil Shrestha, Kaidi Xu, Edward Kim, Matthew C. Stamm
Abstract: As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new techniques can vastly differ from those learned during training, and access to data for these new generators is often limited. To address these issues, we introduce the Ensemble of Expert Embedders (E3), a novel continual learning framework for updating synthetic image detectors. E3 enables the accurate detection of images from newly emerged generators using minimal training data. Our approach does this by first employing transfer learning to develop a suite of expert embedders, each specializing in the forensic traces of a specific generator. Then, all embeddings are jointly analyzed by an Expert Knowledge Fusion Network to produce accurate and reliable detection decisions. Our experiments demonstrate that E3 outperforms existing continual learning methods, including those developed specifically for synthetic image detection.
Authors: Yueh-Cheng Huang, Hsin-Yi Chen, Cheng-Jui Hung, Jen-Hui Chuang, Jenq-Neng Hwang
Abstract: Confronting the critical challenge of insufficient training data in the field of complex image recognition, this paper introduces a novel 3D viewpoint augmentation technique specifically tailored for wine label recognition. This method enhances deep learning model performance by generating visually realistic training samples from a single real-world wine label image, overcoming the challenges posed by the intricate combinations of text and logos. Classical Generative Adversarial Network (GAN) methods fall short in synthesizing such intricate content combination. Our proposed solution leverages time-tested computer vision and image processing strategies to expand our training dataset, thereby broadening the range of training samples for deep learning applications. This innovative approach to data augmentation circumvents the constraints of limited training resources. Using the augmented training images through batch-all triplet metric learning on a Vision Transformer (ViT) architecture, we can get the most discriminative embedding features for every wine label, enabling us to perform one-shot recognition of existing wine labels in the training classes or future newly collected wine labels unavailable in the training. Experimental results show a significant increase in recognition accuracy over conventional 2D data augmentation techniques.
Authors: Bala McRae-Posani, Andrei Holodny, Hrithwik Shalu, Joseph N Stember
Abstract: Uncertainty quantification plays a vital role in facilitating the practical implementation of AI in radiology by addressing growing concerns around trustworthiness. Given the challenges associated with acquiring large, annotated datasets in this field, there is a need for methods that enable uncertainty quantification in small data AI approaches tailored to radiology images. In this study, we focused on uncertainty quantification within the context of the small data evolutionary strategies-based technique of deep neuroevolution (DNE). Specifically, we employed DNE to train a simple Convolutional Neural Network (CNN) with MRI images of the eyes for binary classification. The goal was to distinguish between normal eyes and those with metastatic tumors called choroidal metastases. The training set comprised 18 images with choroidal metastases and 18 without tumors, while the testing set contained a tumor-to-normal ratio of 15:15. We trained CNN model weights via DNE for approximately 40,000 episodes, ultimately reaching a convergence of 100% accuracy on the training set. We saved all models that achieved maximal training set accuracy. Then, by applying these models to the testing set, we established an ensemble method for uncertainty quantification.The saved set of models produced distributions for each testing set image between the two classes of normal and tumor-containing. The relative frequencies permitted uncertainty quantification of model predictions. Intriguingly, we found that subjective features appreciated by human radiologists explained images for which uncertainty was high, highlighting the significance of uncertainty quantification in AI-driven radiological analyses.
Authors: Yan Ru Pei, Sasskia Br\"uers, S\'ebastien Crouzet, Douglas McLelland, Olivier Coenen
Abstract: Event-based data are commonly encountered in edge computing environments where efficiency and low latency are critical. To interface with such data and leverage their rich temporal features, we propose a causal spatiotemporal convolutional network. This solution targets efficient implementation on edge-appropriate hardware with limited resources in three ways: 1) deliberately targets a simple architecture and set of operations (convolutions, ReLU activations) 2) can be configured to perform online inference efficiently via buffering of layer outputs 3) can achieve more than 90% activation sparsity through regularization during training, enabling very significant efficiency gains on event-based processors. In addition, we propose a general affine augmentation strategy acting directly on the events, which alleviates the problem of dataset scarcity for event-based systems. We apply our model on the AIS 2024 event-based eye tracking challenge, reaching a score of 0.9916 p10 accuracy on the Kaggle private testset.
Authors: Henry Peng Zou, Gavin Heqing Yu, Ziwei Fan, Dan Bu, Han Liu, Peng Dai, Dongmei Jia, Cornelia Caragea
Abstract: In e-commerce, accurately extracting product attribute values from multimodal data is crucial for improving user experience and operational efficiency of retailers. However, previous approaches to multimodal attribute value extraction often struggle with implicit attribute values embedded in images or text, rely heavily on extensive labeled data, and can easily confuse similar attribute values. To address these issues, we introduce EIVEN, a data- and parameter-efficient generative framework that pioneers the use of multimodal LLM for implicit attribute value extraction. EIVEN leverages the rich inherent knowledge of a pre-trained LLM and vision encoder to reduce reliance on labeled data. We also introduce a novel Learning-by-Comparison technique to reduce model confusion by enforcing attribute value comparison and difference identification. Additionally, we construct initial open-source datasets for multimodal implicit attribute value extraction. Our extensive experiments reveal that EIVEN significantly outperforms existing methods in extracting implicit attribute values while requiring less labeled data.
Authors: Kai Tang, Jin Chen
Abstract: Remote sensing change detection (CD) is a pivotal technique that pinpoints changes on a global scale based on multi-temporal images. With the recent expansion of deep learning, supervised deep learning-based CD models have shown satisfactory performance. However, CD sample labeling is very time-consuming as it is densely labeled and requires expert knowledge. To alleviate this problem, we introduce ChangeAnywhere, a novel CD sample generation method using the semantic latent diffusion model and single-temporal images. Specifically, ChangeAnywhere leverages the relative ease of acquiring large single-temporal semantic datasets to generate large-scale, diverse, and semantically annotated bi-temporal CD datasets. ChangeAnywhere captures the two essentials of CD samples, i.e., change implies semantically different, and non-change implies reasonable change under the same semantic constraints. We generated ChangeAnywhere-100K, the largest synthesis CD dataset with 100,000 pairs of CD samples based on the proposed method. The ChangeAnywhere-100K significantly improved both zero-shot and few-shot performance on two CD benchmark datasets for various deep learning-based CD models, as demonstrated by transfer experiments. This paper delineates the enormous potential of ChangeAnywhere for CD sample generation and demonstrates the subsequent enhancement of model performance. Therefore, ChangeAnywhere offers a potent tool for remote sensing CD. All codes and pre-trained models will be available at https://github.com/tangkai-RS/ChangeAnywhere.
Authors: Yibo Zhong, Yao Zhou
Abstract: Prior computer vision research extensively explores adapting pre-trained vision transformers (ViT) to downstream tasks. However, the substantial number of parameters requiring adaptation has led to a focus on Parameter Efficient Transfer Learning (PETL) as an approach to efficiently adapt large pre-trained models by training only a subset of parameters, achieving both parameter and storage efficiency. Although the significantly reduced parameters have shown promising performance under transfer learning scenarios, the structural redundancy inherent in the model still leaves room for improvement, which warrants further investigation. In this paper, we propose Head-level Efficient Adaptation with Taylor-expansion importance score (HEAT): a simple method that efficiently fine-tuning ViTs at head levels. In particular, the first-order Taylor expansion is employed to calculate each head's importance score, termed Taylor-expansion Importance Score (TIS), indicating its contribution to specific tasks. Additionally, three strategies for calculating TIS have been employed to maximize the effectiveness of TIS. These strategies calculate TIS from different perspectives, reflecting varying contributions of parameters. Besides ViT, HEAT has also been applied to hierarchical transformers such as Swin Transformer, demonstrating its versatility across different transformer architectures. Through extensive experiments, HEAT has demonstrated superior performance over state-of-the-art PETL methods on the VTAB-1K benchmark.
Authors: Zhenwei Wang, Qiule Sun, Bingbing Zhang, Pengfei Wang, Jianxin Zhang, Qiang Zhang
Abstract: Few-shot learning has been successfully applied to medical image classification as only very few medical examples are available for training. Due to the challenging problem of limited number of annotated medical images, image representations should not be solely derived from a single image modality which is insufficient for characterizing concept classes. In this paper, we propose a new prompting multi-modal model paradigm on medical image classification based on multi-modal foundation models, called PM2. Besides image modality,PM2 introduces another supplementary text input, known as prompt, to further describe corresponding image or concept classes and facilitate few-shot learning across diverse modalities. To better explore the potential of prompt engineering, we empirically investigate five distinct prompt schemes under the new paradigm. Furthermore, linear probing in multi-modal models acts as a linear classification head taking as input only class token, which ignores completely merits of rich statistics inherent in high-level visual tokens. Thus, we alternatively perform a linear classification on feature distribution of visual tokens and class token simultaneously. To effectively mine such rich statistics, a global covariance pooling with efficient matrix power normalization is used to aggregate visual tokens. Then we study and combine two classification heads. One is shared for class token of image from vision encoder and prompt representation encoded by text encoder. The other is to classification on feature distribution of visual tokens from vision encoder. Extensive experiments on three medical datasets show that our PM2 significantly outperforms counterparts regardless of prompt schemes and achieves state-of-the-art performance.
Authors: Weidong Guo, Hantao Zhang, Shouhong Wan, Bingbing Zou, Wanqin Wang, Chenyang Qiu, Jun Li, Peiquan Jin
Abstract: Accurate segmentation of metastatic lymph nodes in rectal cancer is crucial for the staging and treatment of rectal cancer. However, existing segmentation approaches face challenges due to the absence of pixel-level annotated datasets tailored for lymph nodes around the rectum. Additionally, metastatic lymph nodes are characterized by their relatively small size, irregular shapes, and lower contrast compared to the background, further complicating the segmentation task. To address these challenges, we present the first large-scale perirectal metastatic lymph node CT image dataset called Meply, which encompasses pixel-level annotations of 269 patients diagnosed with rectal cancer. Furthermore, we introduce a novel lymph-node segmentation model named CoSAM. The CoSAM utilizes sequence-based detection to guide the segmentation of metastatic lymph nodes in rectal cancer, contributing to improved localization performance for the segmentation model. It comprises three key components: sequence-based detection module, segmentation module, and collaborative convergence unit. To evaluate the effectiveness of CoSAM, we systematically compare its performance with several popular segmentation methods using the Meply dataset. Our code and dataset will be publicly available at: https://github.com/kanydao/CoSAM.
Authors: Binghua Li, Jie Mao, Zhe Sun, Chao Li, Qibin Zhao, Toshihisa Tanaka
Abstract: Automated diagnosis with artificial intelligence has emerged as a promising area in the realm of medical imaging, while the interpretability of the introduced deep neural networks still remains an urgent concern. Although contemporary works, such as XProtoNet and MProtoNet, has sought to design interpretable prediction models for the issue, the localization precision of their resulting attribution maps can be further improved. To this end, we propose a Multi-scale Attentive Prototypical part Network, termed MAProtoNet, to provide more precise maps for attribution. Specifically, we introduce a concise multi-scale module to merge attentive features from quadruplet attention layers, and produces attribution maps. The proposed quadruplet attention layers can enhance the existing online class activation mapping loss via capturing interactions between the spatial and channel dimension, while the multi-scale module then fuses both fine-grained and coarse-grained information for precise maps generation. We also apply a novel multi-scale mapping loss for supervision on the proposed multi-scale module. Compared to existing interpretable prototypical part networks in medical imaging, MAProtoNet can achieve state-of-the-art performance in localization on brain tumor segmentation (BraTS) datasets, resulting in approximately 4% overall improvement on activation precision score (with a best score of 85.8%), without using additional annotated labels of segmentation. Our code will be released in https://github.com/TUAT-Novice/maprotonet.
Authors: Qi Zhao, M. Salman Asif, Zhan Ma
Abstract: The primary focus of Neural Representation for Videos (NeRV) is to effectively model its spatiotemporal consistency. However, current NeRV systems often face a significant issue of spatial inconsistency, leading to decreased perceptual quality. To address this issue, we introduce the Pyramidal Neural Representation for Videos (PNeRV), which is built on a multi-scale information connection and comprises a lightweight rescaling operator, Kronecker Fully-connected layer (KFc), and a Benign Selective Memory (BSM) mechanism. The KFc, inspired by the tensor decomposition of the vanilla Fully-connected layer, facilitates low-cost rescaling and global correlation modeling. BSM merges high-level features with granular ones adaptively. Furthermore, we provide an analysis based on the Universal Approximation Theory of the NeRV system and validate the effectiveness of the proposed PNeRV.We conducted comprehensive experiments to demonstrate that PNeRV surpasses the performance of contemporary NeRV models, achieving the best results in video regression on UVG and DAVIS under various metrics (PSNR, SSIM, LPIPS, and FVD). Compared to vanilla NeRV, PNeRV achieves a +4.49 dB gain in PSNR and a 231% increase in FVD on UVG, along with a +3.28 dB PSNR and 634% FVD increase on DAVIS.
Authors: Zhuyang Xie, Yan Yang, Jie Wang, Xiaorong Liu, Xiaofan Li
Abstract: Multimodal video sentiment analysis aims to integrate multiple modal information to analyze the opinions and attitudes of speakers. Most previous work focuses on exploring the semantic interactions of intra- and inter-modality. However, these works ignore the reliability of multimodality, i.e., modalities tend to contain noise, semantic ambiguity, missing modalities, etc. In addition, previous multimodal approaches treat different modalities equally, largely ignoring their different contributions. Furthermore, existing multimodal sentiment analysis methods directly regress sentiment scores without considering ordinal relationships within sentiment categories, with limited performance. To address the aforementioned problems, we propose a trustworthy multimodal sentiment ordinal network (TMSON) to improve performance in sentiment analysis. Specifically, we first devise a unimodal feature extractor for each modality to obtain modality-specific features. Then, an uncertainty distribution estimation network is customized, which estimates the unimodal uncertainty distributions. Next, Bayesian fusion is performed on the learned unimodal distributions to obtain multimodal distributions for sentiment prediction. Finally, an ordinal-aware sentiment space is constructed, where ordinal regression is used to constrain the multimodal distributions. Our proposed TMSON outperforms baselines on multimodal sentiment analysis tasks, and empirical results demonstrate that TMSON is capable of reducing uncertainty to obtain more robust predictions.
Authors: Yidan Liu, Jun Yue, Shaobo Xia, Pedram Ghamisi, Weiying Xie, Leyuan Fang
Abstract: As a newly emerging advance in deep generative models, diffusion models have achieved state-of-the-art results in many fields, including computer vision, natural language processing, and molecule design. The remote sensing community has also noticed the powerful ability of diffusion models and quickly applied them to a variety of tasks for image processing. Given the rapid increase in research on diffusion models in the field of remote sensing, it is necessary to conduct a comprehensive review of existing diffusion model-based remote sensing papers, to help researchers recognize the potential of diffusion models and provide some directions for further exploration. Specifically, this paper first introduces the theoretical background of diffusion models, and then systematically reviews the applications of diffusion models in remote sensing, including image generation, enhancement, and interpretation. Finally, the limitations of existing remote sensing diffusion models and worthy research directions for further exploration are discussed and summarized.
Authors: Johan Edstedt, Georg B\"okman, Zhenjun Zhao
Abstract: In this paper, we analyze and improve into the recently proposed DeDoDe keypoint detector. We focus our analysis on some key issues. First, we find that DeDoDe keypoints tend to cluster together, which we fix by performing non-max suppression on the target distribution of the detector during training. Second, we address issues related to data augmentation. In particular, the DeDoDe detector is sensitive to large rotations. We fix this by including 90-degree rotations as well as horizontal flips. Finally, the decoupled nature of the DeDoDe detector makes evaluation of downstream usefulness problematic. We fix this by matching the keypoints with a pretrained dense matcher (RoMa) and evaluating two-view pose estimates. We find that the original long training is detrimental to performance, and therefore propose a much shorter training schedule. We integrate all these improvements into our proposed detector DeDoDe v2 and evaluate it with the original DeDoDe descriptor on the MegaDepth-1500 and IMC2022 benchmarks. Our proposed detector significantly increases pose estimation results, notably from 75.9 to 78.3 mAA on the IMC2022 challenge. Code and weights are available at https://github.com/Parskatt/DeDoDe
Authors: Sambal Shikhar, Anupam Sobti
Abstract: Detecting various types of stresses (nutritional, water, nitrogen, etc.) in agricultural fields is critical for farmers to ensure maximum productivity. However, stresses show up in different shapes and sizes across different crop types and varieties. Hence, this is posed as an anomaly detection task in agricultural images. Accurate anomaly detection in agricultural UAV images is vital for early identification of field irregularities. Traditional supervised learning faces challenges in adapting to diverse anomalies, necessitating extensive annotated data. In this work, we overcome this limitation with self-supervised learning using a masked image modeling approach. Masked Autoencoders (MAE) extract meaningful normal features from unlabeled image samples which produces high reconstruction error for the abnormal pixels during reconstruction. To remove the need of using only ``normal" data while training, we use an anomaly suppression loss mechanism that effectively minimizes the reconstruction of anomalous pixels and allows the model to learn anomalous areas without explicitly separating ``normal" images for training. Evaluation on the Agriculture-Vision data challenge shows a mIOU score improvement in comparison to prior state of the art in unsupervised and self-supervised methods. A single model generalizes across all the anomaly categories in the Agri-Vision Challenge Dataset
Authors: Yang Hu, Jinxia Zhang, Kaihua Zhang, Yin Yuan
Abstract: Efficient and accurate camouflaged object detection (COD) poses a challenge in the field of computer vision. Recent approaches explored the utility of edge information for network co-supervision, achieving notable advancements. However, these approaches introduce an extra branch for complex edge extraction, complicate the model architecture and increases computational demands. Addressing this issue, our work replicates the effect that animal's camouflage can be easily revealed under a shifting spotlight, and leverages it for network co-supervision to form a compact yet efficient single-branch network, the Co-Supervised Spotlight Shifting Network (CS$^3$Net). The spotlight shifting strategy allows CS$^3$Net to learn additional prior within a single-branch framework, obviating the need for resource demanding multi-branch design. To leverage the prior of spotlight shifting co-supervision, we propose Shadow Refinement Module (SRM) and Projection Aware Attention (PAA) for feature refinement and enhancement. To ensure the continuity of multi-scale features aggregation, we utilize the Extended Neighbor Connection Decoder (ENCD) for generating the final predictions. Empirical evaluations on public datasets confirm that our CS$^3$Net offers an optimal balance between efficiency and performance: it accomplishes a 32.13% reduction in Multiply-Accumulate (MACs) operations compared to leading efficient COD models, while also delivering superior performance.
Authors: Otto Brookes, Majid Mirmehdi, Hjalmar Kuhl, Tilo Burghardt
Abstract: We show that chimpanzee behaviour understanding from camera traps can be enhanced by providing visual architectures with access to an embedding of text descriptions that detail species behaviours. In particular, we present a vision-language model which employs multi-modal decoding of visual features extracted directly from camera trap videos to process query tokens representing behaviours and output class predictions. Query tokens are initialised using a standardised ethogram of chimpanzee behaviour, rather than using random or name-based initialisations. In addition, the effect of initialising query tokens using a masked language model fine-tuned on a text corpus of known behavioural patterns is explored. We evaluate our system on the PanAf500 and PanAf20K datasets and demonstrate the performance benefits of our multi-modal decoding approach and query initialisation strategy on multi-class and multi-label recognition tasks, respectively. Results and ablations corroborate performance improvements. We achieve state-of-the-art performance over vision and vision-language models in top-1 accuracy (+6.34%) on PanAf500 and overall (+1.1%) and tail-class (+2.26%) mean average precision on PanAf20K. We share complete source code and network weights for full reproducibility of results and easy utilisation.
Authors: Qinghe Ma, Jian Zhang, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao
Abstract: Both limited annotation and domain shift are prevalent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised domain adaptation methods address one of these issues separately. However, the coexistence of limited annotation and domain shift is quite common, which motivates us to introduce a novel and challenging scenario: Mixed Domain Semi-supervised medical image Segmentation (MiDSS). In this scenario, we handle data from multiple medical centers, with limited annotations available for a single domain and a large amount of unlabeled data from multiple domains. We found that the key to solving the problem lies in how to generate reliable pseudo labels for the unlabeled data in the presence of domain shift with labeled data. To tackle this issue, we employ Unified Copy-Paste (UCP) between images to construct intermediate domains, facilitating the knowledge transfer from the domain of labeled data to the domains of unlabeled data. To fully utilize the information within the intermediate domain, we propose a symmetric Guidance training strategy (SymGD), which additionally offers direct guidance to unlabeled data by merging pseudo labels from intermediate samples. Subsequently, we introduce a Training Process aware Random Amplitude MixUp (TP-RAM) to progressively incorporate style-transition components into intermediate samples. Compared with existing state-of-the-art approaches, our method achieves a notable 13.57% improvement in Dice score on Prostate dataset, as demonstrated on three public datasets. Our code is available at https://github.com/MQinghe/MiDSS .
Authors: Yuwei Tang, Zhenyi Lin, Qilong Wang, Pengfei Zhu, Qinghua Hu
Abstract: Recently, pre-trained vision-language models (e.g., CLIP) have shown great potential in few-shot learning and attracted a lot of research interest. Although efforts have been made to improve few-shot ability of CLIP, key factors on the effectiveness of existing methods have not been well studied, limiting further exploration of CLIP's potential in few-shot learning. In this paper, we first introduce a unified formulation to analyze CLIP-based few-shot learning methods from a perspective of logit bias, which encourages us to learn an effective logit bias for further improving performance of CLIP-based few-shot learning methods. To this end, we disassemble three key components involved in computation of logit bias (i.e., logit features, logit predictor, and logit fusion) and empirically analyze the effect on performance of few-shot classification. Based on analysis of key components, this paper proposes a novel AMU-Tuning method to learn effective logit bias for CLIP-based few-shot classification. Specifically, our AMU-Tuning predicts logit bias by exploiting the appropriate $\underline{\textbf{A}}$uxiliary features, which are fed into an efficient feature-initialized linear classifier with $\underline{\textbf{M}}$ulti-branch training. Finally, an $\underline{\textbf{U}}$ncertainty-based fusion is developed to incorporate logit bias into CLIP for few-shot classification. The experiments are conducted on several widely used benchmarks, and the results show AMU-Tuning clearly outperforms its counterparts while achieving state-of-the-art performance of CLIP-based few-shot learning without bells and whistles.
Authors: Chenming Shang, Hengyuan Zhang, Hao Wen, Yujiu Yang
Abstract: The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to the complex structure and the massive pre-training data, it is often regarded as a black-box model that is too difficult to understand and interpret. Concept-based models map the black-box visual representations extracted by deep neural networks onto a set of human-understandable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making process. However, these methods involve the datasets labeled with fine-grained attributes by expert knowledge, which incur high costs and introduce excessive human prior knowledge and bias. In this paper, we observe the long-tail distribution of concepts, based on which we propose a two-stage Concept Selection Model (CSM) to mine core concepts without introducing any human priors. The concept greedy rough selection algorithm is applied to extract head concepts, and then the concept mask fine selection method performs the extraction of core concepts. Experiments show that our approach achieves comparable performance to end-to-end black-box models, and human evaluation demonstrates that the concepts discovered by our method are interpretable and comprehensible for humans.
Authors: Chengpei Xu, Hao Fu, Long Ma, Wenjing Jia, Chengqi Zhang, Feng Xia, Xiaoyu Ai, Binghao Li, Wenjie Zhang
Abstract: Localizing text in low-light environments is challenging due to visual degradations. Although a straightforward solution involves a two-stage pipeline with low-light image enhancement (LLE) as the initial step followed by detector, LLE is primarily designed for human vision instead of machine and can accumulate errors. In this work, we propose an efficient and effective single-stage approach for localizing text in dark that circumvents the need for LLE. We introduce a constrained learning module as an auxiliary mechanism during the training stage of the text detector. This module is designed to guide the text detector in preserving textual spatial features amidst feature map resizing, thus minimizing the loss of spatial information in texts under low-light visual degradations. Specifically, we incorporate spatial reconstruction and spatial semantic constraints within this module to ensure the text detector acquires essential positional and contextual range knowledge. Our approach enhances the original text detector's ability to identify text's local topological features using a dynamic snake feature pyramid network and adopts a bottom-up contour shaping strategy with a novel rectangular accumulation technique for accurate delineation of streamlined text features. In addition, we present a comprehensive low-light dataset for arbitrary-shaped text, encompassing diverse scenes and languages. Notably, our method achieves state-of-the-art results on this low-light dataset and exhibits comparable performance on standard normal light datasets. The code and dataset will be released.
Authors: Jiyang Li, Lechao Cheng, Zhangye Wang, Tingting Mu, Jingxuan He
Abstract: Cinemagraph is a unique form of visual media that combines elements of still photography and subtle motion to create a captivating experience. However, the majority of videos generated by recent works lack depth information and are confined to the constraints of 2D image space. In this paper, inspired by significant progress in the field of novel view synthesis (NVS) achieved by 3D Gaussian Splatting (3D-GS), we propose LoopGaussian to elevate cinemagraph from 2D image space to 3D space using 3D Gaussian modeling. To achieve this, we first employ the 3D-GS method to reconstruct 3D Gaussian point clouds from multi-view images of static scenes,incorporating shape regularization terms to prevent blurring or artifacts caused by object deformation. We then adopt an autoencoder tailored for 3D Gaussian to project it into feature space. To maintain the local continuity of the scene, we devise SuperGaussian for clustering based on the acquired features. By calculating the similarity between clusters and employing a two-stage estimation method, we derive an Eulerian motion field to describe velocities across the entire scene. The 3D Gaussian points then move within the estimated Eulerian motion field. Through bidirectional animation techniques, we ultimately generate a 3D Cinemagraph that exhibits natural and seamlessly loopable dynamics. Experiment results validate the effectiveness of our approach, demonstrating high-quality and visually appealing scene generation. The project is available at https://pokerlishao.github.io/LoopGaussian/.
Authors: Bor-Shiun Wang, Chien-Yi Wang, Wei-Chen Chiu
Abstract: Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model training. Although being effective in bridging the semantic gap between a model's latent space and human interpretation, these explanation methods only partially reveal the model's decision-making process. The outcome is typically limited to high-level semantics derived from the last feature map. We argue that the explanations lacking insights into the decision processes at low and mid-level features are neither fully faithful nor useful. Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model. MCPNet autonomously learns meaningful concept prototypes across multiple feature map levels using Centered Kernel Alignment (CKA) loss and an energy-based weighted PCA mechanism, and it does so without reliance on predefined concept labels. Further, we propose a novel classifier paradigm that learns and aligns multi-level concept prototype distributions for classification purposes via Class-aware Concept Distribution (CCD) loss. Our experiments reveal that our proposed MCPNet while being adaptable to various model architectures, offers comprehensive multi-level explanations while maintaining classification accuracy. Additionally, its concept distribution-based classification approach shows improved generalization capabilities in few-shot classification scenarios.
Authors: Jian Zhang, Ruiteng Zhang, Xinyue Yan, Xiting Zhuang, Ruicheng Cao
Abstract: Degraded underwater images decrease the accuracy of underwater object detection. However, existing methods for underwater image enhancement mainly focus on improving the indicators in visual aspects, which may not benefit the tasks of underwater image detection, and may lead to serious degradation in performance. To alleviate this problem, we proposed a bidirectional-guided method for underwater object detection, referred to as BG-YOLO. In the proposed method, network is organized by constructing an enhancement branch and a detection branch in a parallel way. The enhancement branch consists of a cascade of an image enhancement subnet and an object detection subnet. And the detection branch only consists of a detection subnet. A feature guided module connects the shallow convolution layer of the two branches. When training the enhancement branch, the object detection subnet in the enhancement branch guides the image enhancement subnet to be optimized towards the direction that is most conducive to the detection task. The shallow feature map of the trained enhancement branch will be output to the feature guided module, constraining the optimization of detection branch through consistency loss and prompting detection branch to learn more detailed information of the objects. And hence the detection performance will be refined. During the detection tasks, only detection branch will be reserved so that no additional cost of computation will be introduced. Extensive experiments demonstrate that the proposed method shows significant improvement in performance of the detector in severely degraded underwater scenes while maintaining a remarkable detection speed.
Authors: Denis Huseljic, Paul Hahn, Marek Herde, Lukas Rauch, Bernhard Sick
Abstract: Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. BAIT, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, BAIT's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting BAIT in their evaluation. This paper introduces two methods to enhance BAIT's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of BAIT on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at https://github.com/dhuseljic/dal-toolbox.
Authors: Zezhao Guo (College of information and Engineering, Hebei GEO University), Yanzhong Guo (Beijing Yingrui Pioneer Medical Technology Co., Ltd), Zhanfang Zhao (College of information and Engineering, Hebei GEO University)
Abstract: Navigation for thoracoabdominal puncture surgery is used to locate the needle entry point on the patient's body surface. The traditional reflective ball navigation method is difficult to position the needle entry point on the soft, irregular, smooth chest and abdomen. Due to the lack of clear characteristic points on the body surface using structured light technology, it is difficult to identify and locate arbitrary needle insertion points. Based on the high stability and high accuracy requirements of surgical navigation, this paper proposed a novel method, a muti-modal 3D small object medical marker detection method, which identifies the center of a small single ring as the needle insertion point. Moreover, this novel method leverages Fourier transform enhancement technology to augment the dataset, enrich image details, and enhance the network's capability. The method extracts the Region of Interest (ROI) of the feature image from both enhanced and original images, followed by generating a mask map. Subsequently, the point cloud of the ROI from the depth map is obtained through the registration of ROI point cloud contour fitting. In addition, this method employs Tukey loss for optimal precision. The experimental results show this novel method proposed in this paper not only achieves high-precision and high-stability positioning, but also enables the positioning of any needle insertion point.
Authors: Yingjie Zhou, Zicheng Zhang, Wei Sun, Xiaohong Liu, Xiongkuo Min, Zhihua Wang, Xiao-Ping Zhang, Guangtao Zhai
Abstract: In the realm of media technology, digital humans have gained prominence due to rapid advancements in computer technology. However, the manual modeling and control required for the majority of digital humans pose significant obstacles to efficient development. The speech-driven methods offer a novel avenue for manipulating the mouth shape and expressions of digital humans. Despite the proliferation of driving methods, the quality of many generated talking head (TH) videos remains a concern, impacting user visual experiences. To tackle this issue, this paper introduces the Talking Head Quality Assessment (THQA) database, featuring 800 TH videos generated through 8 diverse speech-driven methods. Extensive experiments affirm the THQA database's richness in character and speech features. Subsequent subjective quality assessment experiments analyze correlations between scoring results and speech-driven methods, ages, and genders. In addition, experimental results show that mainstream image and video quality assessment methods have limitations for the THQA database, underscoring the imperative for further research to enhance TH video quality assessment. The THQA database is publicly accessible at https://github.com/zyj-2000/THQA.
Authors: Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj
Abstract: Dynamic Facial Expression Recognition (DFER) has received significant interest in the recent years dictated by its pivotal role in enabling empathic and human-compatible technologies. Achieving robustness towards in-the-wild data in DFER is particularly important for real-world applications. One of the directions aimed at improving such models is multimodal emotion recognition based on audio and video data. Multimodal learning in DFER increases the model capabilities by leveraging richer, complementary data representations. Within the field of multimodal DFER, recent methods have focused on exploiting advances of self-supervised learning (SSL) for pre-training of strong multimodal encoders. Another line of research has focused on adapting pre-trained static models for DFER. In this work, we propose a different perspective on the problem and investigate the advancement of multimodal DFER performance by adapting SSL-pre-trained disjoint unimodal encoders. We identify main challenges associated with this task, namely, intra-modality adaptation, cross-modal alignment, and temporal adaptation, and propose solutions to each of them. As a result, we demonstrate improvement over current state-of-the-art on two popular DFER benchmarks, namely DFEW and MFAW.
Authors: Zining Chen, Weiqiu Wang, Zhicheng Zhao, Fei Su, Aidong Men, Hongying Meng
Abstract: Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target domains share identical categories. Nevertheless, there exists unseen classes from target domains in practical scenarios. To address this issue, Open Set Domain Generalization (OSDG) has emerged and several methods have been exclusively proposed. However, most existing methods adopt complex architectures with slight improvement compared with DG methods. Recently, vision-language models (VLMs) have been introduced in DG following the fine-tuning paradigm, but consume huge training overhead with large vision models. Therefore, in this paper, we innovate to transfer knowledge from VLMs to lightweight vision models and improve the robustness by introducing Perturbation Distillation (PD) from three perspectives, including Score, Class and Instance (SCI), named SCI-PD. Moreover, previous methods are oriented by the benchmarks with identical and fixed splits, ignoring the divergence between source domains. These methods are revealed to suffer from sharp performance decay with our proposed new benchmark Hybrid Domain Generalization (HDG) and a novel metric $H^{2}$-CV, which construct various splits to comprehensively assess the robustness of algorithms. Extensive experiments demonstrate that our method outperforms state-of-the-art algorithms on multiple datasets, especially improving the robustness when confronting data scarcity.
Authors: Yuguang Shi
Abstract: Recently, iteration-based stereo matching has shown great potential. However, these models optimize the disparity map using RNN variants. The discrete optimization process poses a challenge of information loss, which restricts the level of detail that can be expressed in the generated disparity map. In order to address these issues, we propose a novel training approach that incorporates diffusion models into the iterative optimization process. We designed a Time-based Gated Recurrent Unit (T-GRU) to correlate temporal and disparity outputs. Unlike standard recurrent units, we employ Agent Attention to generate more expressive features. We also designed an attention-based context network to capture a large amount of contextual information. Experiments on several public benchmarks show that we have achieved competitive stereo matching performance. Our model ranks first in the Scene Flow dataset, achieving over a 7% improvement compared to competing methods, and requires only 8 iterations to achieve state-of-the-art results.
Authors: Avinab Saha, Shashank Gupta, Sravan Kumar Ankireddy, Karl Chahine, Joydeep Ghosh
Abstract: Image Classification and Video Action Recognition are perhaps the two most foundational tasks in computer vision. Consequently, explaining the inner workings of trained deep neural networks is of prime importance. While numerous efforts focus on explaining the decisions of trained deep neural networks in image classification, exploration in the domain of its temporal version, video action recognition, has been scant. In this work, we take a deeper look at this problem. We begin by revisiting Grad-CAM, one of the popular feature attribution methods for Image Classification, and its extension to Video Action Recognition tasks and examine the method's limitations. To address these, we introduce Video-TCAV, by building on TCAV for Image Classification tasks, which aims to quantify the importance of specific concepts in the decision-making process of Video Action Recognition models. As the scalable generation of concepts is still an open problem, we propose a machine-assisted approach to generate spatial and spatiotemporal concepts relevant to Video Action Recognition for testing Video-TCAV. We then establish the importance of temporally-varying concepts by demonstrating the superiority of dynamic spatiotemporal concepts over trivial spatial concepts. In conclusion, we introduce a framework for investigating hypotheses in action recognition and quantitatively testing them, thus advancing research in the explainability of deep neural networks used in video action recognition.
Authors: Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson
Abstract: In modern computer vision, the optimal representation of 3D shape continues to be task-dependent. One fundamental operation applied to such representations is differentiable rendering, as it enables inverse graphics approaches in learning frameworks. Standard explicit shape representations (voxels, point clouds, or meshes) are often easily rendered, but can suffer from limited geometric fidelity, among other issues. On the other hand, implicit representations (occupancy, distance, or radiance fields) preserve greater fidelity, but suffer from complex or inefficient rendering processes, limiting scalability. In this work, we devise Directed Distance Fields (DDFs), a novel neural shape representation that builds upon classical distance fields. The fundamental operation in a DDF maps an oriented point (position and direction) to surface visibility and depth. This enables efficient differentiable rendering, obtaining depth with a single forward pass per pixel, as well as differential geometric quantity extraction (e.g., surface normals), with only additional backward passes. Using probabilistic DDFs (PDDFs), we show how to model inherent discontinuities in the underlying field. We then apply DDFs to several applications, including single-shape fitting, generative modelling, and single-image 3D reconstruction, showcasing strong performance with simple architectural components via the versatility of our representation. Finally, since the dimensionality of DDFs permits view-dependent geometric artifacts, we conduct a theoretical investigation of the constraints necessary for view consistency. We find a small set of field properties that are sufficient to guarantee a DDF is consistent, without knowing, for instance, which shape the field is expressing.
Authors: Yuanhao Gong
Abstract: The Gaussian splatting methods are getting popular. However, their loss function only contains the $\ell_1$ norm and the structural similarity between the rendered and input images, without considering the edges in these images. It is well-known that the edges in an image provide important information. Therefore, in this paper, we propose an Edge Guided Gaussian Splatting (EGGS) method that leverages the edges in the input images. More specifically, we give the edge region a higher weight than the flat region. With such edge guidance, the resulting Gaussian particles focus more on the edges instead of the flat regions. Moreover, such edge guidance does not crease the computation cost during the training and rendering stage. The experiments confirm that such simple edge-weighted loss function indeed improves about $1\sim2$ dB on several difference data sets. With simply plugging in the edge guidance, the proposed method can improve all Gaussian splatting methods in different scenarios, such as human head modeling, building 3D reconstruction, etc.
Authors: Haonan Zhao, Yiting Wang, Thomas Bashford-Rogers, Valentina Donzella, Kurt Debattista
Abstract: Datasets are essential for training and testing vehicle perception algorithms. However, the collection and annotation of real-world images is time-consuming and expensive. Driving simulators offer a solution by automatically generating various driving scenarios with corresponding annotations, but the simulation-to-reality (Sim2Real) domain gap remains a challenge. While most of the Generative Artificial Intelligence (AI) follows the de facto Generative Adversarial Nets (GANs)-based methods, the recent emerging diffusion probabilistic models have not been fully explored in mitigating Sim2Real challenges for driving data synthesis. To explore the performance, this paper applied three different generative AI methods to leverage semantic label maps from a driving simulator as a bridge for the creation of realistic datasets. A comparative analysis of these methods is presented from the perspective of image quality and perception. New synthetic datasets, which include driving images and auto-generated high-quality annotations, are produced with low costs and high scene variability. The experimental results show that although GAN-based methods are adept at generating high-quality images when provided with manually annotated labels, ControlNet produces synthetic datasets with fewer artefacts and more structural fidelity when using simulator-generated labels. This suggests that the diffusion-based approach may provide improved stability and an alternative method for addressing Sim2Real challenges.
Authors: Haifeng Xia, Hai Huang, Zhengming Ding
Abstract: Deep clustering as an important branch of unsupervised representation learning focuses on embedding semantically similar samples into the identical feature space. This core demand inspires the exploration of contrastive learning and subspace clustering. However, these solutions always rely on the basic assumption that there are sufficient and category-balanced samples for generating valid high-level representation. This hypothesis actually is too strict to be satisfied for real-world applications. To overcome such a challenge, the natural strategy is utilizing generative models to augment considerable instances. How to use these novel samples to effectively fulfill clustering performance improvement is still difficult and under-explored. In this paper, we propose a novel Generative Calibration Clustering (GCC) method to delicately incorporate feature learning and augmentation into clustering procedure. First, we develop a discriminative feature alignment mechanism to discover intrinsic relationship across real and generated samples. Second, we design a self-supervised metric learning to generate more reliable cluster assignment to boost the conditional diffusion generation. Extensive experimental results on three benchmarks validate the effectiveness and advantage of our proposed method over the state-of-the-art methods.
Authors: Wenhao Dong, Haodong Zhu, Shaohui Lin, Xiaoyan Luo, Yunhang Shen, Xuhui Liu, Juan Zhang, Guodong Guo, Baochang Zhang
Abstract: Cross-modality fusing complementary information from different modalities effectively improves object detection performance, making it more useful and robust for a wider range of applications. Existing fusion strategies combine different types of images or merge different backbone features through elaborated neural network modules. However, these methods neglect that modality disparities affect cross-modality fusion performance, as different modalities with different camera focal lengths, placements, and angles are hardly fused. In this paper, we investigate cross-modality fusion by associating cross-modal features in a hidden state space based on an improved Mamba with a gating mechanism. We design a Fusion-Mamba block (FMB) to map cross-modal features into a hidden state space for interaction, thereby reducing disparities between cross-modal features and enhancing the representation consistency of fused features. FMB contains two modules: the State Space Channel Swapping (SSCS) module facilitates shallow feature fusion, and the Dual State Space Fusion (DSSF) enables deep fusion in a hidden state space. Through extensive experiments on public datasets, our proposed approach outperforms the state-of-the-art methods on $m$AP with 5.9% on $M^3FD$ and 4.9% on FLIR-Aligned datasets, demonstrating superior object detection performance. To the best of our knowledge, this is the first work to explore the potential of Mamba for cross-modal fusion and establish a new baseline for cross-modality object detection.
Authors: Xuelong Li, Hongjun An, Guangying Li, Xing Wang, Guanghua Cheng, Zhe Sun
Abstract: In this paper, we introduce StreakNet-Arch, a novel signal processing architecture designed for Underwater Carrier LiDAR-Radar (UCLR) imaging systems, to address the limitations in scatter suppression and real-time imaging. StreakNet-Arch formulates the signal processing as a real-time, end-to-end binary classification task, enabling real-time image acquisition. To achieve this, we leverage Self-Attention networks and propose a novel Double Branch Cross Attention (DBC-Attention) mechanism that surpasses the performance of traditional methods. Furthermore, we present a method for embedding streak-tube camera images into attention networks, effectively acting as a learned bandpass filter. To facilitate further research, we contribute a publicly available streak-tube camera image dataset. The dataset contains 2,695,168 real-world underwater 3D point cloud data. These advancements significantly improve UCLR capabilities, enhancing its performance and applicability in underwater imaging tasks. The source code and dataset can be found at https://github.com/BestAnHongjun/StreakNet .
Authors: Hojun Lee, Suyoung Kim, Junhoo Lee, Jaeyoung Yoo, Nojun Kwak
Abstract: Coreset selection is a method for selecting a small, representative subset of an entire dataset. It has been primarily researched in image classification, assuming there is only one object per image. However, coreset selection for object detection is more challenging as an image can contain multiple objects. As a result, much research has yet to be done on this topic. Therefore, we introduce a new approach, Coreset Selection for Object Detection (CSOD). CSOD generates imagewise and classwise representative feature vectors for multiple objects of the same class within each image. Subsequently, we adopt submodular optimization for considering both representativeness and diversity and utilize the representative vectors in the submodular optimization process to select a subset. When we evaluated CSOD on the Pascal VOC dataset, CSOD outperformed random selection by +6.4%p in AP$_{50}$ when selecting 200 images.
Authors: Fanyi Wang, Peng Liu, Haotian Hu, Dan Meng, Jingwen Su, Jinjin Xu, Yanhao Zhang, Xiaoming Ren, Zhiwang Zhang
Abstract: Research on diffusion model-based video generation has advanced rapidly. However, limitations in object fidelity and generation length hinder its practical applications. Additionally, specific domains like animated wallpapers require seamless looping, where the first and last frames of the video match seamlessly. To address these challenges, this paper proposes LoopAnimate, a novel method for generating videos with consistent start and end frames. To enhance object fidelity, we introduce a framework that decouples multi-level image appearance and textual semantic information. Building upon an image-to-image diffusion model, our approach incorporates both pixel-level and feature-level information from the input image, injecting image appearance and textual semantic embeddings at different positions of the diffusion model. Existing UNet-based video generation models require to input the entire videos during training to encode temporal and positional information at once. However, due to limitations in GPU memory, the number of frames is typically restricted to 16. To address this, this paper proposes a three-stage training strategy with progressively increasing frame numbers and reducing fine-tuning modules. Additionally, we introduce the Temporal E nhanced Motion Module(TEMM) to extend the capacity for encoding temporal and positional information up to 36 frames. The proposed LoopAnimate, which for the first time extends the single-pass generation length of UNet-based video generation models to 35 frames while maintaining high-quality video generation. Experiments demonstrate that LoopAnimate achieves state-of-the-art performance in both objective metrics, such as fidelity and temporal consistency, and subjective evaluation results.
Authors: Chengxi Han, Chen Wu, Haonan Guo, Meiqi Hu, Hongruixuan Chen
Abstract: Benefiting from the developments in deep learning technology, deep-learning-based algorithms employing automatic feature extraction have achieved remarkable performance on the change detection (CD) task. However, the performance of existing deep-learning-based CD methods is hindered by the imbalance between changed and unchanged pixels. To tackle this problem, a progressive foreground-balanced sampling strategy on the basis of not adding change information is proposed in this article to help the model accurately learn the features of the changed pixels during the early training process and thereby improve detection performance.Furthermore, we design a discriminative Siamese network, hierarchical attention network (HANet), which can integrate multiscale features and refine detailed features. The main part of HANet is the HAN module, which is a lightweight and effective self-attention mechanism. Extensive experiments and ablation studies on two CDdatasets with extremely unbalanced labels validate the effectiveness and efficiency of the proposed method.
Authors: Chengxi Han, Chen Wu, Haonan Guo, Meiqi Hu, Jiepan Li, Hongruixuan Chen
Abstract: The rapid advancement of automated artificial intelligence algorithms and remote sensing instruments has benefited change detection (CD) tasks. However, there is still a lot of space to study for precise detection, especially the edge integrity and internal holes phenomenon of change features. In order to solve these problems, we design the Change Guiding Network (CGNet), to tackle the insufficient expression problem of change features in the conventional U-Net structure adopted in previous methods, which causes inaccurate edge detection and internal holes. Change maps from deep features with rich semantic information are generated and used as prior information to guide multi-scale feature fusion, which can improve the expression ability of change features. Meanwhile, we propose a self-attention module named Change Guide Module (CGM), which can effectively capture the long-distance dependency among pixels and effectively overcome the problem of the insufficient receptive field of traditional convolutional neural networks. On four major CD datasets, we verify the usefulness and efficiency of the CGNet, and a large number of experiments and ablation studies demonstrate the effectiveness of CGNet. We're going to open-source our code at https://github.com/ChengxiHAN/CGNet-CD.
Authors: Jiawei Chen, Xiao Yang, Yinpeng Dong, Hang Su, Jianteng Peng, Zhaoxia Yin
Abstract: Face anti-spoofing (FAS) and adversarial detection (FAD) have been regarded as critical technologies to ensure the safety of face recognition systems. As a consequence of their limited practicality and generalization, some existing methods aim to devise a framework capable of concurrently detecting both threats to address the challenge. Nevertheless, these methods still encounter challenges of insufficient generalization and suboptimal robustness, potentially owing to the inherent drawback of discriminative models. Motivated by the rich structural and detailed features of face generative models, we propose FaceCat which utilizes the face generative model as a pre-trained model to improve the performance of FAS and FAD. Specifically, FaceCat elaborately designs a hierarchical fusion mechanism to capture rich face semantic features of the generative model. These features then serve as a robust foundation for a lightweight head, designed to execute FAS and FAD tasks simultaneously. As relying solely on single-modality data often leads to suboptimal performance, we further propose a novel text-guided multi-modal alignment strategy that utilizes text prompts to enrich feature representation, thereby enhancing performance. For fair evaluations, we build a comprehensive protocol with a wide range of 28 attack types to benchmark the performance. Extensive experiments validate the effectiveness of FaceCat generalizes significantly better and obtains excellent robustness against input transformations.
Authors: Ya-Qi Yu, Minghui Liao, Jihao Wu, Yongxin Liao, Xiaoyu Zheng, Wei Zeng
Abstract: Multimodal Large Language Models (MLLMs) have shown impressive results on various multimodal tasks. However, most existing MLLMs are not well suited for document-oriented tasks, which require fine-grained image perception and information compression. In this paper, we present TextHawk, a MLLM that is specifically designed for document-oriented tasks, while preserving the general capabilities of MLLMs. TextHawk is aimed to explore efficient fine-grained perception by designing four dedicated components. Firstly, a ReSampling and ReArrangement (ReSA) module is proposed to reduce the redundancy in the document texts and lower the computational cost of the MLLM. We explore encoding the positions of each local feature by presenting Scalable Positional Embeddings (SPEs), which can preserve the scalability of various image sizes. A Query Proposal Network (QPN) is then adopted to initialize the queries dynamically among different sub-images. To further enhance the fine-grained visual perceptual ability of the MLLM, we design a Multi-Level Cross-Attention (MLCA) mechanism that captures the hierarchical structure and semantic relations of document images. Furthermore, we create a new instruction-tuning dataset for document-oriented tasks by enriching the multimodal document data with Gemini Pro. We conduct extensive experiments on both general and document-oriented MLLM benchmarks, and show that TextHawk outperforms the state-of-the-art methods, demonstrating its effectiveness and superiority in fine-grained document perception and general abilities.
Authors: Lewei Yao, Renjie Pi, Jianhua Han, Xiaodan Liang, Hang Xu, Wei Zhang, Zhenguo Li, Dan Xu
Abstract: Existing open-vocabulary object detectors typically require a predefined set of categories from users, significantly confining their application scenarios. In this paper, we introduce DetCLIPv3, a high-performing detector that excels not only at both open-vocabulary object detection, but also generating hierarchical labels for detected objects. DetCLIPv3 is characterized by three core designs: 1. Versatile model architecture: we derive a robust open-set detection framework which is further empowered with generation ability via the integration of a caption head. 2. High information density data: we develop an auto-annotation pipeline leveraging visual large language model to refine captions for large-scale image-text pairs, providing rich, multi-granular object labels to enhance the training. 3. Efficient training strategy: we employ a pre-training stage with low-resolution inputs that enables the object captioner to efficiently learn a broad spectrum of visual concepts from extensive image-text paired data. This is followed by a fine-tuning stage that leverages a small number of high-resolution samples to further enhance detection performance. With these effective designs, DetCLIPv3 demonstrates superior open-vocabulary detection performance, \eg, our Swin-T backbone model achieves a notable 47.0 zero-shot fixed AP on the LVIS minival benchmark, outperforming GLIPv2, GroundingDINO, and DetCLIPv2 by 18.0/19.6/6.6 AP, respectively. DetCLIPv3 also achieves a state-of-the-art 19.7 AP in dense captioning task on VG dataset, showcasing its strong generative capability.
Authors: Xuening Yuan, Hongyu Yang, Yueming Zhao, Di Huang
Abstract: Recent progress in text-to-3D creation has been propelled by integrating the potent prior of Diffusion Models from text-to-image generation into the 3D domain. Nevertheless, generating 3D scenes characterized by multiple instances and intricate arrangements remains challenging. In this study, we present DreamScape, a method for creating highly consistent 3D scenes solely from textual descriptions, leveraging the strong 3D representation capabilities of Gaussian Splatting and the complex arrangement abilities of large language models (LLMs). Our approach involves a 3D Gaussian Guide ($3{DG^2}$) for scene representation, consisting of semantic primitives (objects) and their spatial transformations and relationships derived directly from text prompts using LLMs. This compositional representation allows for local-to-global optimization of the entire scene. A progressive scale control is tailored during local object generation, ensuring that objects of different sizes and densities adapt to the scene, which addresses training instability issue arising from simple blending in the subsequent global optimization stage. To mitigate potential biases of LLM priors, we model collision relationships between objects at the global level, enhancing physical correctness and overall realism. Additionally, to generate pervasive objects like rain and snow distributed extensively across the scene, we introduce a sparse initialization and densification strategy. Experiments demonstrate that DreamScape offers high usability and controllability, enabling the generation of high-fidelity 3D scenes from only text prompts and achieving state-of-the-art performance compared to other methods.
Authors: Diandian Guo, Manxi Lin, Jialun Pei, He Tang, Yueming Jin, Pheng-Ann Heng
Abstract: A comprehensive understanding of surgical scenes allows for monitoring of the surgical process, reducing the occurrence of accidents and enhancing efficiency for medical professionals. Semantic modeling within operating rooms, as a scene graph generation (SGG) task, is challenging since it involves consecutive recognition of subtle surgical actions over prolonged periods. To address this challenge, we propose a Tri-modal (i.e., images, point clouds, and language) confluence with Temporal dynamics framework, termed TriTemp-OR. Diverging from previous approaches that integrated temporal information via memory graphs, our method embraces two advantages: 1) we directly exploit bi-modal temporal information from the video streaming for hierarchical feature interaction, and 2) the prior knowledge from Large Language Models (LLMs) is embedded to alleviate the class-imbalance problem in the operating theatre. Specifically, our model performs temporal interactions across 2D frames and 3D point clouds, including a scale-adaptive multi-view temporal interaction (ViewTemp) and a geometric-temporal point aggregation (PointTemp). Furthermore, we transfer knowledge from the biomedical LLM, LLaVA-Med, to deepen the comprehension of intraoperative relations. The proposed TriTemp-OR enables the aggregation of tri-modal features through relation-aware unification to predict relations so as to generate scene graphs. Experimental results on the 4D-OR benchmark demonstrate the superior performance of our model for long-term OR streaming.
Authors: Wiktor Mucha, Florin Cuconasu, Naome A. Etori, Valia Kalokyri, Giovanni Trappolini
Abstract: The ability to read, understand and find important information from written text is a critical skill in our daily lives for our independence, comfort and safety. However, a significant part of our society is affected by partial vision impairment, which leads to discomfort and dependency in daily activities. To address the limitations of this part of society, we propose an intelligent reading assistant based on smart glasses with embedded RGB cameras and a Large Language Model (LLM), whose functionality goes beyond corrective lenses. The video recorded from the egocentric perspective of a person wearing the glasses is processed to localise text information using object detection and optical character recognition methods. The LLM processes the data and allows the user to interact with the text and responds to a given query, thus extending the functionality of corrective lenses with the ability to find and summarize knowledge from the text. To evaluate our method, we create a chat-based application that allows the user to interact with the system. The evaluation is conducted in a real-world setting, such as reading menus in a restaurant, and involves four participants. The results show robust accuracy in text retrieval. The system not only provides accurate meal suggestions but also achieves high user satisfaction, highlighting the potential of smart glasses and LLMs in assisting people with special needs.
Authors: Yu Qiao, Huy Q. Le, Mengchun Zhang, Apurba Adhikary, Chaoning Zhang, Choong Seon Hong
Abstract: Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge is that the distributed data is not independently and identically distributed (non-IID), typically including both intra-domain and inter-domain heterogeneity. However, recent research is limited to simply using averaged signals as a form of regularization and only focusing on one aspect of these non-IID challenges. Given these limitations, this paper clarifies these two non-IID challenges and attempts to introduce cluster representation to address them from both local and global perspectives. Specifically, we propose a dual-clustered feature contrast-based FL framework with dual focuses. First, we employ clustering on the local representations of each client, aiming to capture intra-class information based on these local clusters at a high level of granularity. Then, we facilitate cross-client knowledge sharing by pulling the local representation closer to clusters shared by clients with similar semantics while pushing them away from clusters with dissimilar semantics. Second, since the sizes of local clusters belonging to the same class may differ for each client, we further utilize clustering on the global side and conduct averaging to create a consistent global signal for guiding each local training in a contrastive manner. Experimental results on multiple datasets demonstrate that our proposal achieves comparable or superior performance gain under intra-domain and inter-domain heterogeneity.
Authors: Jin Yang, Ping Wei, Huan Li, Ziyang Ren
Abstract: Video moment retrieval and highlight detection are two highly valuable tasks in video understanding, but until recently they have been jointly studied. Although existing studies have made impressive advancement recently, they predominantly follow the data-driven bottom-up paradigm. Such paradigm overlooks task-specific and inter-task effects, resulting in poor model performance. In this paper, we propose a novel task-driven top-down framework TaskWeave for joint moment retrieval and highlight detection. The framework introduces a task-decoupled unit to capture task-specific and common representations. To investigate the interplay between the two tasks, we propose an inter-task feedback mechanism, which transforms the results of one task as guiding masks to assist the other task. Different from existing methods, we present a task-dependent joint loss function to optimize the model. Comprehensive experiments and in-depth ablation studies on QVHighlights, TVSum, and Charades-STA datasets corroborate the effectiveness and flexibility of the proposed framework. Codes are available at https://github.com/EdenGabriel/TaskWeave.
Authors: Chih-Ling Chang, Fu-Jen Tsai, Zi-Ling Huang, Lin Gu, Chia-Wen Lin
Abstract: Image dehazing faces challenges when dealing with hazy images in real-world scenarios. A huge domain gap between synthetic and real-world haze images degrades dehazing performance in practical settings. However, collecting real-world image datasets for training dehazing models is challenging since both hazy and clean pairs must be captured under the same conditions. In this paper, we propose a Physics-guided Parametric Augmentation Network (PANet) that generates photo-realistic hazy and clean training pairs to effectively enhance real-world dehazing performance. PANet comprises a Haze-to-Parameter Mapper (HPM) to project hazy images into a parameter space and a Parameter-to-Haze Mapper (PHM) to map the resampled haze parameters back to hazy images. In the parameter space, we can pixel-wisely resample individual haze parameter maps to generate diverse hazy images with physically-explainable haze conditions unseen in the training set. Our experimental results demonstrate that PANet can augment diverse realistic hazy images to enrich existing hazy image benchmarks so as to effectively boost the performances of state-of-the-art image dehazing models.
Authors: Fei Xue, Ignas Budvytis, Daniel Olmeda Reino, Roberto Cipolla
Abstract: Visual relocalization is a key technique to autonomous driving, robotics, and virtual/augmented reality. After decades of explorations, absolute pose regression (APR), scene coordinate regression (SCR), and hierarchical methods (HMs) have become the most popular frameworks. However, in spite of high efficiency, APRs and SCRs have limited accuracy especially in large-scale outdoor scenes; HMs are accurate but need to store a large number of 2D descriptors for matching, resulting in poor efficiency. In this paper, we propose an efficient and accurate framework, called VRS-NeRF, for visual relocalization with sparse neural radiance field. Precisely, we introduce an explicit geometric map (EGM) for 3D map representation and an implicit learning map (ILM) for sparse patches rendering. In this localization process, EGP provides priors of spare 2D points and ILM utilizes these sparse points to render patches with sparse NeRFs for matching. This allows us to discard a large number of 2D descriptors so as to reduce the map size. Moreover, rendering patches only for useful points rather than all pixels in the whole image reduces the rendering time significantly. This framework inherits the accuracy of HMs and discards their low efficiency. Experiments on 7Scenes, CambridgeLandmarks, and Aachen datasets show that our method gives much better accuracy than APRs and SCRs, and close performance to HMs but is much more efficient.
Authors: Quang Minh Dinh, Minh Khoi Ho, Anh Quan Dang, Hung Phong Tran
Abstract: Traffic video description and analysis have received much attention recently due to the growing demand for efficient and reliable urban surveillance systems. Most existing methods only focus on locating traffic event segments, which severely lack descriptive details related to the behaviour and context of all the subjects of interest in the events. In this paper, we present TrafficVLM, a novel multi-modal dense video captioning model for vehicle ego camera view. TrafficVLM models traffic video events at different levels of analysis, both spatially and temporally, and generates long fine-grained descriptions for the vehicle and pedestrian at different phases of the event. We also propose a conditional component for TrafficVLM to control the generation outputs and a multi-task fine-tuning paradigm to enhance TrafficVLM's learning capability. Experiments show that TrafficVLM performs well on both vehicle and overhead camera views. Our solution achieved outstanding results in Track 2 of the AI City Challenge 2024, ranking us third in the challenge standings. Our code is publicly available at https://github.com/quangminhdinh/TrafficVLM.
Authors: Vasudha Venkatesan, Daniel Panangian, Mario Fuentes Reyes, Ksenia Bittner
Abstract: In the field of remote sensing, the scarcity of stereo-matched and particularly lack of accurate ground truth data often hinders the training of deep neural networks. The use of synthetically generated images as an alternative, alleviates this problem but suffers from the problem of domain generalization. Unifying the capabilities of image-to-image translation and stereo-matching presents an effective solution to address the issue of domain generalization. Current methods involve combining two networks, an unpaired image-to-image translation network and a stereo-matching network, while jointly optimizing them. We propose an edge-aware GAN-based network that effectively tackles both tasks simultaneously. We obtain edge maps of input images from the Sobel operator and use it as an additional input to the encoder in the generator to enforce geometric consistency during translation. We additionally include a warping loss calculated from the translated images to maintain the stereo consistency. We demonstrate that our model produces qualitatively and quantitatively superior results than existing models, and its applicability extends to diverse domains, including autonomous driving.
Authors: Kyle Shih-Huang Lo, J\"org Peters, Eric Spellman
Abstract: Accurate completion and denoising of roof height maps are crucial to reconstructing high-quality 3D buildings. Repairing sparse points can enhance low-cost sensor use and reduce UAV flight overlap. RoofDiffusion is a new end-to-end self-supervised diffusion technique for robustly completing, in particular difficult, roof height maps. RoofDiffusion leverages widely-available curated footprints and can so handle up to 99\% point sparsity and 80\% roof area occlusion (regional incompleteness). A variant, No-FP RoofDiffusion, simultaneously predicts building footprints and heights. Both quantitatively outperform state-of-the-art unguided depth completion and representative inpainting methods for Digital Elevation Models (DEM), on both a roof-specific benchmark and the BuildingNet dataset. Qualitative assessments show the effectiveness of RoofDiffusion for datasets with real-world scans including AHN3, Dales3D, and USGS 3DEP LiDAR. Tested with the leading City3D algorithm, preprocessing height maps with RoofDiffusion noticeably improves 3D building reconstruction. RoofDiffusion is complemented by a new dataset of 13k complex roof geometries, focusing on long-tail issues in remote sensing; a novel simulation of tree occlusion; and a wide variety of large-area roof cut-outs for data augmentation and benchmarking.
Authors: Jieyi Tan, Yansheng Li, Sergey A. Bartalev, Bo Dang, Wei Chen, Yongjun Zhang, Liangqi Yuan
Abstract: Remote sensing semantic segmentation (RSS) is an essential task in Earth Observation missions. Due to data privacy concerns, high-quality remote sensing images with annotations cannot be well shared among institutions, making it difficult to fully utilize RSS data to train a generalized model. Federated Learning (FL), a privacy-preserving collaborative learning technology, is a potential solution. However, the current research on how to effectively apply FL in RSS is still scarce and requires further investigation. Remote sensing images in various institutions often exhibit strong geographical heterogeneity. More specifically, it is reflected in terms of class-distribution heterogeneity and object-appearance heterogeneity. Unfortunately, most existing FL studies show inadequate focus on geographical heterogeneity, thus leading to performance degradation in the global model. Considering the aforementioned issues, we propose a novel Geographic Heterogeneity-Aware Federated Learning (GeoFed) framework to address privacy-preserving RSS. Through Global Feature Extension and Tail Regeneration modules, class-distribution heterogeneity is alleviated. Additionally, we design an Essential Feature Mining strategy to alleviate object-appearance heterogeneity by constructing essential features. Extensive experiments on three datasets (i.e., FBP, CASID, Inria) show that our GeoFed consistently outperforms the current state-of-the-art methods. The code will be available publicly.
Authors: Zihan Cao, Xiao Wu, Liang-Jian Deng, Yu Zhong
Abstract: In image fusion tasks, images from different sources possess distinct characteristics. This has driven the development of numerous methods to explore better ways of fusing them while preserving their respective characteristics. Mamba, as a state space model, has emerged in the field of natural language processing. Recently, many studies have attempted to extend Mamba to vision tasks. However, due to the nature of images different from casual language sequences, the limited state capacity of Mamba weakens its ability to model image information. Additionally, the sequence modeling ability of Mamba is only capable of spatial information and cannot effectively capture the rich spectral information in images. Motivated by these challenges, we customize and improve the vision Mamba network designed for the image fusion task. Specifically, we propose the local-enhanced vision Mamba block, dubbed as LEVM. The LEVM block can improve local information perception of the network and simultaneously learn local and global spatial information. Furthermore, we propose the state sharing technique to enhance spatial details and integrate spatial and spectral information. Finally, the overall network is a multi-scale structure based on vision Mamba, called LE-Mamba. Extensive experiments show the proposed methods achieve state-of-the-art results on multispectral pansharpening and multispectral and hyperspectral image fusion datasets, and demonstrate the effectiveness of the proposed approach. Code will be made available.
Authors: Yafei Mao, Xuelu Li, Brandon Smith, Jinjin Li, Raja Bala
Abstract: Virtual try-on and product personalization have become increasingly important in modern online shopping, highlighting the need for accurate body measurement estimation. Although previous research has advanced in estimating 3D body shapes from RGB images, the task is inherently ambiguous as the observed scale of human subjects in the images depends on two unknown factors: capture distance and body dimensions. This ambiguity is particularly pronounced in partial-view scenarios. To address this challenge, we propose a modular and simple height normalization solution. This solution relocates the subject skeleton to the desired position, thereby normalizing the scale and disentangling the relationship between the two variables. Our experimental results demonstrate that integrating this technique into state-of-the-art human mesh reconstruction models significantly enhances partial body measurement estimation. Additionally, we illustrate the applicability of this approach to multi-view settings, showcasing its versatility.
Authors: Wiktor Mucha, Martin Kampel
Abstract: Action recognition is essential for egocentric video understanding, allowing automatic and continuous monitoring of Activities of Daily Living (ADLs) without user effort. Existing literature focuses on 3D hand pose input, which requires computationally intensive depth estimation networks or wearing an uncomfortable depth sensor. In contrast, there has been insufficient research in understanding 2D hand pose for egocentric action recognition, despite the availability of user-friendly smart glasses in the market capable of capturing a single RGB image. Our study aims to fill this research gap by exploring the field of 2D hand pose estimation for egocentric action recognition, making two contributions. Firstly, we introduce two novel approaches for 2D hand pose estimation, namely EffHandNet for single-hand estimation and EffHandEgoNet, tailored for an egocentric perspective, capturing interactions between hands and objects. Both methods outperform state-of-the-art models on H2O and FPHA public benchmarks. Secondly, we present a robust action recognition architecture from 2D hand and object poses. This method incorporates EffHandEgoNet, and a transformer-based action recognition method. Evaluated on H2O and FPHA datasets, our architecture has a faster inference time and achieves an accuracy of 91.32% and 94.43%, respectively, surpassing state of the art, including 3D-based methods. Our work demonstrates that using 2D skeletal data is a robust approach for egocentric action understanding. Extensive evaluation and ablation studies show the impact of the hand pose estimation approach, and how each input affects the overall performance.
Authors: Diana-Nicoleta Grigore, Mariana-Iuliana Georgescu, Jon Alvarez Justo, Tor Johansen, Andreea Iuliana Ionescu, Radu Tudor Ionescu
Abstract: Few-shot knowledge distillation recently emerged as a viable approach to harness the knowledge of large-scale pre-trained models, using limited data and computational resources. In this paper, we propose a novel few-shot feature distillation approach for vision transformers. Our approach is based on two key steps. Leveraging the fact that vision transformers have a consistent depth-wise structure, we first copy the weights from intermittent layers of existing pre-trained vision transformers (teachers) into shallower architectures (students), where the intermittence factor controls the complexity of the student transformer with respect to its teacher. Next, we employ an enhanced version of Low-Rank Adaptation (LoRA) to distill knowledge into the student in a few-shot scenario, aiming to recover the information processing carried out by the skipped teacher layers. We present comprehensive experiments with supervised and self-supervised transformers as teachers, on five data sets from various domains, including natural, medical and satellite images. The empirical results confirm the superiority of our approach over competitive baselines. Moreover, the ablation results demonstrate the usefulness of each component of the proposed pipeline.
Authors: Muhammad Saad Saeed, Shah Nawaz, Muhammad Salman Tahir, Rohan Kumar Das, Muhammad Zaigham Zaheer, Marta Moscati, Markus Schedl, Muhammad Haris Khan, Karthik Nandakumar, Muhammad Haroon Yousaf
Abstract: The advancements of technology have led to the use of multimodal systems in various real-world applications. Among them, the audio-visual systems are one of the widely used multimodal systems. In the recent years, associating face and voice of a person has gained attention due to presence of unique correlation between them. The Face-voice Association in Multilingual Environments (FAME) Challenge 2024 focuses on exploring face-voice association under a unique condition of multilingual scenario. This condition is inspired from the fact that half of the world's population is bilingual and most often people communicate under multilingual scenario. The challenge uses a dataset namely, Multilingual Audio-Visual (MAV-Celeb) for exploring face-voice association in multilingual environments. This report provides the details of the challenge, dataset, baselines and task details for the FAME Challenge.
Authors: Tal Hakim
Abstract: The application of machine-learning solutions to movement assessment from skeleton videos has attracted significant research attention in recent years. This advancement has made rehabilitation at home more accessible, utilizing movement assessment algorithms that can operate on affordable equipment for human pose detection from 2D or 3D videos. While the primary objective of automatic assessment tasks is to score movements, the automatic generation of feedback highlighting key movement issues has the potential to significantly enhance and accelerate the rehabilitation process. In this study, we explain the types of feedback that can be generated, review existing solutions for automatic feedback generation, and discuss future research directions. To our knowledge, this is the first comprehensive review of feedback generation in skeletal movement assessment.
Authors: David Geissb\"uhler, Sushil Bhattacharjee, Ketan Kotwal, Guillaume Clivaz, S\'ebastien Marcel
Abstract: Current finger-vein or palm-vein recognition systems usually require direct contact of the subject with the apparatus. This can be problematic in environments where hygiene is of primary importance. In this work we present a contactless vascular biometrics sensor platform named \sweet which can be used for hand vascular biometrics studies (wrist-, palm- and finger-vein) and surface features such as palmprint. It supports several acquisition modalities such as multi-spectral Near-Infrared (NIR), RGB-color, Stereo Vision (SV) and Photometric Stereo (PS). Using this platform we collect a dataset consisting of the fingers, palm and wrist vascular data of 120 subjects and develop a powerful 3D pipeline for the pre-processing of this data. We then present biometric experimental results, focusing on Finger-Vein Recognition (FVR). Finally, we discuss fusion of multiple modalities, such palm-vein combined with palm-print biometrics. The acquisition software, parts of the hardware design, the new FV dataset, as well as source-code for our experiments are publicly available for research purposes.
Authors: Sam Cantrill, David Ahmedt-Aristizabal, Lars Petersson, Hanna Suominen, Mohammad Ali Armin
Abstract: Camera-based remote photoplethysmography (rPPG) enables contactless measurement of important physiological signals such as pulse rate (PR). However, dynamic and unconstrained subject motion introduces significant variability into the facial appearance in video, confounding the ability of video-based methods to accurately extract the rPPG signal. In this study, we leverage the 3D facial surface to construct a novel orientation-conditioned facial texture video representation which improves the motion robustness of existing video-based facial rPPG estimation methods. Our proposed method achieves a significant 18.2% performance improvement in cross-dataset testing on MMPD over our baseline using the PhysNet model trained on PURE, highlighting the efficacy and generalization benefits of our designed video representation. We demonstrate significant performance improvements of up to 29.6% in all tested motion scenarios in cross-dataset testing on MMPD, even in the presence of dynamic and unconstrained subject motion, emphasizing the benefits of disentangling motion through modeling the 3D facial surface for motion robust facial rPPG estimation. We validate the efficacy of our design decisions and the impact of different video processing steps through an ablation study. Our findings illustrate the potential strengths of exploiting the 3D facial surface as a general strategy for addressing dynamic and unconstrained subject motion in videos. The code is available at https://samcantrill.github.io/orientation-uv-rppg/.
Authors: Yiming Zhang, Zhuokai Zhao, Zhaorun Chen, Zhili Feng, Zenghui Ding, Yining Sun
Abstract: Among the ever-evolving development of vision-language models, contrastive language-image pretraining (CLIP) has set new benchmarks in many downstream tasks such as zero-shot classifications by leveraging self-supervised contrastive learning on large amounts of text-image pairs. However, its dependency on rigid one-to-one mappings overlooks the complex and often multifaceted relationships between and within texts and images. To this end, we introduce RankCLIP, a novel pretraining method that extends beyond the rigid one-to-one matching framework of CLIP and its variants. By leveraging both in-modal and cross-modal ranking consistency, RankCLIP improves the alignment process, enabling it to capture the nuanced many-to-many relationships between and within each modality. Through comprehensive experiments, we demonstrate the enhanced capability of RankCLIP to effectively improve performance across various downstream tasks, notably achieving significant gains in zero-shot classifications over state-of-the-art methods, underscoring the potential of RankCLIP in further advancing vision-language pretraining.
Authors: Hamadi Chihaoui, Paolo Favaro
Abstract: We introduce a novel approach to single image denoising based on the Blind Spot Denoising principle, which we call MAsked and SHuffled Blind Spot Denoising (MASH). We focus on the case of correlated noise, which often plagues real images. MASH is the result of a careful analysis to determine the relationships between the level of blindness (masking) of the input and the (unknown) noise correlation. Moreover, we introduce a shuffling technique to weaken the local correlation of noise, which in turn yields an additional denoising performance improvement. We evaluate MASH via extensive experiments on real-world noisy image datasets. We demonstrate on par or better results compared to existing self-supervised denoising methods.
Authors: Peifei Zhu, Tsubasa Takahashi, Hirokatsu Kataoka
Abstract: Diffusion Models (DMs) have shown remarkable capabilities in various image-generation tasks. However, there are growing concerns that DMs could be used to imitate unauthorized creations and thus raise copyright issues. To address this issue, we propose a novel framework that embeds personal watermarks in the generation of adversarial examples. Such examples can force DMs to generate images with visible watermarks and prevent DMs from imitating unauthorized images. We construct a generator based on conditional adversarial networks and design three losses (adversarial loss, GAN loss, and perturbation loss) to generate adversarial examples that have subtle perturbation but can effectively attack DMs to prevent copyright violations. Training a generator for a personal watermark by our method only requires 5-10 samples within 2-3 minutes, and once the generator is trained, it can generate adversarial examples with that watermark significantly fast (0.2s per image). We conduct extensive experiments in various conditional image-generation scenarios. Compared to existing methods that generate images with chaotic textures, our method adds visible watermarks on the generated images, which is a more straightforward way to indicate copyright violations. We also observe that our adversarial examples exhibit good transferability across unknown generative models. Therefore, this work provides a simple yet powerful way to protect copyright from DM-based imitation.
Authors: Scarlett Raine, Ross Marchant, Brano Kusy, Frederic Maire, Niko Suenderhauf, Tobias Fischer
Abstract: Broad-scale marine surveys performed by underwater vehicles significantly increase the availability of coral reef imagery, however it is costly and time-consuming for domain experts to label images. Point label propagation is an approach used to leverage existing image data labeled with sparse point labels. The resulting augmented ground truth generated is then used to train a semantic segmentation model. Here, we first demonstrate that recent advances in foundation models enable generation of multi-species coral augmented ground truth masks using denoised DINOv2 features and K-Nearest Neighbors (KNN), without the need for any pre-training or custom-designed algorithms. For extremely sparsely labeled images, we propose a labeling regime based on human-in-the-loop principles, resulting in significant improvement in annotation efficiency: If only 5 point labels per image are available, our proposed human-in-the-loop approach improves on the state-of-the-art by 17.3% for pixel accuracy and 22.6% for mIoU; and by 10.6% and 19.1% when 10 point labels per image are available. Even if the human-in-the-loop labeling regime is not used, the denoised DINOv2 features with a KNN outperforms the prior state-of-the-art by 3.5% for pixel accuracy and 5.7% for mIoU (5 grid points). We also provide a detailed analysis of how point labeling style and the quantity of points per image affects the point label propagation quality and provide general recommendations on maximizing point label efficiency.
Authors: Tong Wu, Jia-Mu Sun, Yu-Kun Lai, Yuewen Ma, Leif Kobbelt, Lin Gao
Abstract: Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGS in novel view synthesis and editing tasks.
Authors: Nurul Rafi, Pablo Rivas
Abstract: Dust storms are associated with certain respiratory illnesses across different areas in the world. Researchers have devoted time and resources to study the elements surrounding dust storm phenomena. This paper reviews the efforts of those who have investigated dust aerosols using sensors onboard of satellites using machine learning-based approaches. We have reviewed the most common issues revolving dust aerosol modeling using different datasets and different sensors from a historical perspective. Our findings suggest that multi-spectral approaches based on linear and non-linear combinations of spectral bands are some of the most successful for visualization and quantitative analysis; however, when researchers have leveraged machine learning, performance has been improved and new opportunities to solve unique problems arise.
Authors: Tianhan Xu, Takuya Ikeda, Koichi Nishiwaki
Abstract: In this paper, we propose a method to segment and recover a static, clean background and multiple 360$^\circ$ objects from observations of scenes at different timestamps. Recent works have used neural radiance fields to model 3D scenes and improved the quality of novel view synthesis, while few studies have focused on modeling the invisible or occluded parts of the training images. These under-reconstruction parts constrain both scene editing and rendering view selection, thereby limiting their utility for synthetic data generation for downstream tasks. Our basic idea is that, by observing the same set of objects in various arrangement, so that parts that are invisible in one scene may become visible in others. By fusing the visible parts from each scene, occlusion-free rendering of both background and foreground objects can be achieved. We decompose the multi-scene fusion task into two main components: (1) objects/background segmentation and alignment, where we leverage point cloud-based methods tailored to our novel problem formulation; (2) radiance fields fusion, where we introduce visibility field to quantify the visible information of radiance fields, and propose visibility-aware rendering for the fusion of series of scenes, ultimately obtaining clean background and 360$^\circ$ object rendering. Comprehensive experiments were conducted on synthetic and real datasets, and the results demonstrate the effectiveness of our method.
Authors: Bonan Ding, Jin Xie, Jing Nie, Jiale Cao
Abstract: Due to its cost-effectiveness and widespread availability, monocular 3D object detection, which relies solely on a single camera during inference, holds significant importance across various applications, including autonomous driving and robotics. Nevertheless, directly predicting the coordinates of objects in 3D space from monocular images poses challenges. Therefore, an effective solution involves transforming monocular images into LiDAR-like representations and employing a LiDAR-based 3D object detector to predict the 3D coordinates of objects. The key step in this method is accurately converting the monocular image into a reliable point cloud form. In this paper, we present VFMM3D, an innovative approach that leverages the capabilities of Vision Foundation Models (VFMs) to accurately transform single-view images into LiDAR point cloud representations. VFMM3D utilizes the Segment Anything Model (SAM) and Depth Anything Model (DAM) to generate high-quality pseudo-LiDAR data enriched with rich foreground information. Specifically, the Depth Anything Model (DAM) is employed to generate dense depth maps. Subsequently, the Segment Anything Model (SAM) is utilized to differentiate foreground and background regions by predicting instance masks. These predicted instance masks and depth maps are then combined and projected into 3D space to generate pseudo-LiDAR points. Finally, any object detectors based on point clouds can be utilized to predict the 3D coordinates of objects. Comprehensive experiments are conducted on the challenging 3D object detection dataset KITTI. Our VFMM3D establishes a new state-of-the-art performance. Additionally, experimental results demonstrate the generality of VFMM3D, showcasing its seamless integration into various LiDAR-based 3D object detectors.
Authors: Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Pranamesh Chakraborty, Sanjita Prajapati, Quan Kong, Norimasa Kobori, Munkhjargal Gochoo, Munkh-Erdene Otgonbold, Fady Alnajjar, Ganzorig Batnasan, Ping-Yang Chen, Jun-Wei Hsieh, Xunlei Wu, Sameer Satish Pusegaonkar, Yizhou Wang, Sujit Biswas, Rama Chellappa
Abstract: The eighth AI City Challenge highlighted the convergence of computer vision and artificial intelligence in areas like retail, warehouse settings, and Intelligent Traffic Systems (ITS), presenting significant research opportunities. The 2024 edition featured five tracks, attracting unprecedented interest from 726 teams in 47 countries and regions. Track 1 dealt with multi-target multi-camera (MTMC) people tracking, highlighting significant enhancements in camera count, character number, 3D annotation, and camera matrices, alongside new rules for 3D tracking and online tracking algorithm encouragement. Track 2 introduced dense video captioning for traffic safety, focusing on pedestrian accidents using multi-camera feeds to improve insights for insurance and prevention. Track 3 required teams to classify driver actions in a naturalistic driving analysis. Track 4 explored fish-eye camera analytics using the FishEye8K dataset. Track 5 focused on motorcycle helmet rule violation detection. The challenge utilized two leaderboards to showcase methods, with participants setting new benchmarks, some surpassing existing state-of-the-art achievements.
Authors: Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, Philip Torr
Abstract: Rapid advancements in continual segmentation have yet to bridge the gap of scaling to large continually expanding vocabularies under compute-constrained scenarios. We discover that traditional continual training leads to catastrophic forgetting under compute constraints, unable to outperform zero-shot segmentation methods. We introduce a novel strategy for semantic and panoptic segmentation with zero forgetting, capable of adapting to continually growing vocabularies without the need for retraining or large memory costs. Our training-free approach, kNN-CLIP, leverages a database of instance embeddings to enable open-vocabulary segmentation approaches to continually expand their vocabulary on any given domain with a single-pass through data, while only storing embeddings minimizing both compute and memory costs. This method achieves state-of-the-art mIoU performance across large-vocabulary semantic and panoptic segmentation datasets. We hope kNN-CLIP represents a step forward in enabling more efficient and adaptable continual segmentation, paving the way for advances in real-world large-vocabulary continual segmentation methods.
Authors: Sua Choi, Dahyun Kang, Minsu Cho
Abstract: We address the problem of generalized category discovery (GCD) that aims to partition a partially labeled collection of images; only a small part of the collection is labeled and the total number of target classes is unknown. To address this generalized image clustering problem, we revisit the mean-shift algorithm, i.e., a classic, powerful technique for mode seeking, and incorporate it into a contrastive learning framework. The proposed method, dubbed Contrastive Mean-Shift (CMS) learning, trains an image encoder to produce representations with better clustering properties by an iterative process of mean shift and contrastive update. Experiments demonstrate that our method, both in settings with and without the total number of clusters being known, achieves state-of-the-art performance on six public GCD benchmarks without bells and whistles.
Authors: Sepehr Dehdashtian, Bashir Sadeghi, Vishnu Naresh Boddeti
Abstract: When building classification systems with demographic fairness considerations, there are two objectives to satisfy: 1) maximizing utility for the specific task and 2) ensuring fairness w.r.t. a known demographic attribute. These objectives often compete, so optimizing both can lead to a trade-off between utility and fairness. While existing works acknowledge the trade-offs and study their limits, two questions remain unanswered: 1) What are the optimal trade-offs between utility and fairness? and 2) How can we numerically quantify these trade-offs from data for a desired prediction task and demographic attribute of interest? This paper addresses these questions. We introduce two utility-fairness trade-offs: the Data-Space and Label-Space Trade-off. The trade-offs reveal three regions within the utility-fairness plane, delineating what is fully and partially possible and impossible. We propose U-FaTE, a method to numerically quantify the trade-offs for a given prediction task and group fairness definition from data samples. Based on the trade-offs, we introduce a new scheme for evaluating representations. An extensive evaluation of fair representation learning methods and representations from over 1000 pre-trained models revealed that most current approaches are far from the estimated and achievable fairness-utility trade-offs across multiple datasets and prediction tasks.
Authors: Xiangrui Liu, Xinju Wu, Pingping Zhang, Shiqi Wang, Zhu Li, Sam Kwong
Abstract: Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. Herein, we propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. To ensure the compactness of Gaussian primitives, we devise a hybrid primitive structure that captures predictive relationships between each other. Then, we exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Moreover, we develop a rate-constrained optimization scheme to eliminate redundancies within such hybrid primitives, steering our CompGS towards an optimal trade-off between bitrate consumption and representation efficacy. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Our code will be released on GitHub for further research.
Authors: Harshmohan Kulkarni, Om Khare, Ninad Barve, Sunil Mane
Abstract: This research paper proposes a novel methodology for image-to-image style transfer on objects utilizing a single deep convolutional neural network. The proposed approach leverages the You Only Look Once version 8 (YOLOv8) segmentation model and the backbone neural network of YOLOv8 for style transfer. The primary objective is to enhance the visual appeal of objects in images by seamlessly transferring artistic styles while preserving the original object characteristics. The proposed approach's novelty lies in combining segmentation and style transfer in a single deep convolutional neural network. This approach omits the need for multiple stages or models, thus resulting in simpler training and deployment of the model for practical applications. The results of this approach are shown on two content images by applying different style images. The paper also demonstrates the ability to apply style transfer on multiple objects in the same image.
Authors: Yandan Yang, Baoxiong Jia, Peiyuan Zhi, Siyuan Huang
Abstract: With recent developments in Embodied Artificial Intelligence (EAI) research, there has been a growing demand for high-quality, large-scale interactive scene generation. While prior methods in scene synthesis have prioritized the naturalness and realism of the generated scenes, the physical plausibility and interactivity of scenes have been largely left unexplored. To address this disparity, we introduce PhyScene, a novel method dedicated to generating interactive 3D scenes characterized by realistic layouts, articulated objects, and rich physical interactivity tailored for embodied agents. Based on a conditional diffusion model for capturing scene layouts, we devise novel physics- and interactivity-based guidance mechanisms that integrate constraints from object collision, room layout, and object reachability. Through extensive experiments, we demonstrate that PhyScene effectively leverages these guidance functions for physically interactable scene synthesis, outperforming existing state-of-the-art scene synthesis methods by a large margin. Our findings suggest that the scenes generated by PhyScene hold considerable potential for facilitating diverse skill acquisition among agents within interactive environments, thereby catalyzing further advancements in embodied AI research. Project website: http://physcene.github.io.
Authors: Dmitry Ignatov, Andrey Ignatov, Radu Timofte
Abstract: We present ANYU, a new virtually augmented version of the NYU depth v2 dataset, designed for monocular depth estimation. In contrast to the well-known approach where full 3D scenes of a virtual world are utilized to generate artificial datasets, ANYU was created by incorporating RGB-D representations of virtual reality objects into the original NYU depth v2 images. We specifically did not match each generated virtual object with an appropriate texture and a suitable location within the real-world image. Instead, an assignment of texture, location, lighting, and other rendering parameters was randomized to maximize a diversity of the training data, and to show that it is randomness that can improve the generalizing ability of a dataset. By conducting extensive experiments with our virtually modified dataset and validating on the original NYU depth v2 and iBims-1 benchmarks, we show that ANYU improves the monocular depth estimation performance and generalization of deep neural networks with considerably different architectures, especially for the current state-of-the-art VPD model. To the best of our knowledge, this is the first work that augments a real-world dataset with randomly generated virtual 3D objects for monocular depth estimation. We make our ANYU dataset publicly available in two training configurations with 10% and 100% additional synthetically enriched RGB-D pairs of training images, respectively, for efficient training and empirical exploration of virtual augmentation at https://github.com/ABrain-One/ANYU
Authors: Jiahao Yu, Li Chen
Abstract: Recent medical image segmentation methods apply implicit neural representation (INR) to the decoder for achieving a continuous coordinate decoding to tackle the drawback of conventional discrete grid-based data representations. However, the INR-based decoder cannot well handle the feature misalignment problem brought about by the naive latent code acquisition strategy in INR. Although there exist many feature alignment works, they all adopt a progressive multi-step aligning paradigm on a discrete feature pyramid, which is incompatible with the continuous one-step characteristics of INR-based decoder, and thus fails to be the solution. Therefore, we propose Q2A, a novel one-step query-based aligning paradigm, to solve the feature misalignment problem in the INR-based decoder. Specifically, for each target coordinate, Q2A first generates several queries depicting the spatial offsets and the cell resolutions of the contextual features aligned to the coordinate, then calculates the corresponding aligned features by feeding the queries into a novel implicit fully continuous feature pyramid (FCFP), finally fuses the aligned features to predict the class distribution. In FCFP, we further propose a novel universal partition-and-aggregate strategy (P&A) to replace the naive interpolation strategy for latent code acquisition in INR, which mitigates the information loss problem that occurs when the query cell resolution is relatively large and achieves an effective feature decoding at arbitrary continuous resolution. We conduct extensive experiments on two medical datasets, i.e. Glas and Synapse, and a universal dataset, i.e. Cityscapes, and they show the superiority of the proposed Q2A.
Authors: Alexander Vedernikov, Puneet Kumar, Haoyu Chen, Tapio Seppanen, Xiaobai Li
Abstract: Engagement analysis finds various applications in healthcare, education, advertisement, services. Deep Neural Networks, used for analysis, possess complex architecture and need large amounts of input data, computational power, inference time. These constraints challenge embedding systems into devices for real-time use. To address these limitations, we present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain and boost processing speed, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form. Evaluated on the EngageNet dataset, the proposed method outperforms existing baselines, utilizing only two behavioral features (head pose rotations) compared to the 98 used in baseline models. Furthermore, comparative analysis shows TCCT-Net's architecture offers an order-of-magnitude improvement in inference speed compared to state-of-the-art image-based Recurrent Neural Network (RNN) methods. The code will be released at https://github.com/vedernikovphoto/TCCT_Net.
Authors: Byeongkeun Kang, Sinhae Cha, Yeejin Lee
Abstract: Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object localization, which aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels. The proposed framework consists of a shared feature extractor, a classifier, and a localizer. The localizer predicts pixel-level class probabilities, while the classifier predicts the object class at the image level. Since image-level class labels are insufficient for training the localizer, weakly-supervised object localization methods often encounter challenges in accurately localizing the entire object region. To address this issue, the proposed method incorporates adversarial erasing and pseudo labels to improve localization accuracy. Specifically, novel losses are designed to utilize adversarially erased foreground features and adversarially erased feature maps, reducing dependence on the most discriminative region. Additionally, the proposed method employs pseudo labels to suppress activation values in the background while increasing them in the foreground. The proposed method is applied to two backbone networks (MobileNetV1 and InceptionV3) and is evaluated on three publicly available datasets (ILSVRC-2012, CUB-200-2011, and PASCAL VOC 2012). The experimental results demonstrate that the proposed method outperforms previous state-of-the-art methods across all evaluated metrics.
Authors: Zou Zhen, Yu Hu, Zhao Feng
Abstract: Images corrupted by rain streaks often lose vital frequency information for perception, and image deraining aims to solve this issue which relies on global and local degradation modeling. Recent studies have witnessed the effectiveness and efficiency of Mamba for perceiving global and local information based on its exploiting local correlation among patches, however, rarely attempts have been explored to extend it with frequency analysis for image deraining, limiting its ability to perceive global degradation that is relevant to frequency modeling (e.g. Fourier transform). In this paper, we propose FreqMamba, an effective and efficient paradigm that leverages the complementary between Mamba and frequency analysis for image deraining. The core of our method lies in extending Mamba with frequency analysis from two perspectives: extending it with frequency-band for exploiting frequency correlation, and connecting it with Fourier transform for global degradation modeling. Specifically, FreqMamba introduces complementary triple interaction structures including spatial Mamba, frequency band Mamba, and Fourier global modeling. Frequency band Mamba decomposes the image into sub-bands of different frequencies to allow 2D scanning from the frequency dimension. Furthermore, leveraging Mamba's unique data-dependent properties, we use rainy images at different scales to provide degradation priors to the network, thereby facilitating efficient training. Extensive experiments show that our method outperforms state-of-the-art methods both visually and quantitatively.
Authors: Minji Kim, Dongyoon Han, Taekyung Kim, Bohyung Han
Abstract: Pretrained vision-language models have shown effectiveness in video understanding. However, recent studies have not sufficiently leveraged essential temporal information from videos, simply averaging frame-wise representations or referencing consecutive frames. We introduce Temporally Contextualized CLIP (TC-CLIP), a pioneering framework for video understanding that effectively and efficiently leverages comprehensive video information. We propose Temporal Contextualization (TC), a novel layer-wise temporal information infusion mechanism for video that extracts core information from each frame, interconnects relevant information across the video to summarize into context tokens, and ultimately leverages the context tokens during the feature encoding process. Furthermore, our Video-conditional Prompting (VP) module manufactures context tokens to generate informative prompts in text modality. We conduct extensive experiments in zero-shot, few-shot, base-to-novel, and fully-supervised action recognition to validate the superiority of our TC-CLIP. Ablation studies for TC and VP guarantee our design choices. Code is available at https://github.com/naver-ai/tc-clip
Authors: Genjia Liu, Yue Hu, Chenxin Xu, Weibo Mao, Junhao Ge, Zhengxiang Huang, Yifan Lu, Yinda Xu, Junkai Xia, Yafei Wang, Siheng Chen
Abstract: Vehicle-to-everything-aided autonomous driving (V2X-AD) has a huge potential to provide a safer driving solution. Despite extensive researches in transportation and communication to support V2X-AD, the actual utilization of these infrastructures and communication resources in enhancing driving performances remains largely unexplored. This highlights the necessity of collaborative autonomous driving: a machine learning approach that optimizes the information sharing strategy to improve the driving performance of each vehicle. This effort necessitates two key foundations: a platform capable of generating data to facilitate the training and testing of V2X-AD, and a comprehensive system that integrates full driving-related functionalities with mechanisms for information sharing. From the platform perspective, we present V2Xverse, a comprehensive simulation platform for collaborative autonomous driving. This platform provides a complete pipeline for collaborative driving. From the system perspective, we introduce CoDriving, a novel end-to-end collaborative driving system that properly integrates V2X communication over the entire autonomous pipeline, promoting driving with shared perceptual information. The core idea is a novel driving-oriented communication strategy. Leveraging this strategy, CoDriving improves driving performance while optimizing communication efficiency. We make comprehensive benchmarks with V2Xverse, analyzing both modular performance and closed-loop driving performance. Experimental results show that CoDriving: i) significantly improves the driving score by 62.49% and drastically reduces the pedestrian collision rate by 53.50% compared to the SOTA end-to-end driving method, and ii) achieves sustaining driving performance superiority over dynamic constraint communication conditions.
Authors: Xinyu Xie, Yawen Cui, Chio-In Ieong, Tao Tan, Xiaozhi Zhang, Xubin Zheng, Zitong Yu
Abstract: Multi-modal image fusion aims to combine information from different modes to create a single image with comprehensive information and detailed textures. However, fusion models based on convolutional neural networks encounter limitations in capturing global image features due to their focus on local convolution operations. Transformer-based models, while excelling in global feature modeling, confront computational challenges stemming from their quadratic complexity. Recently, the Selective Structured State Space Model has exhibited significant potential for long-range dependency modeling with linear complexity, offering a promising avenue to address the aforementioned dilemma. In this paper, we propose FusionMamba, a novel dynamic feature enhancement method for multimodal image fusion with Mamba. Specifically, we devise an improved efficient Mamba model for image fusion, integrating efficient visual state space model with dynamic convolution and channel attention. This refined model not only upholds the performance of Mamba and global modeling capability but also diminishes channel redundancy while enhancing local enhancement capability. Additionally, we devise a dynamic feature fusion module (DFFM) comprising two dynamic feature enhancement modules (DFEM) and a cross modality fusion mamba module (CMFM). The former serves for dynamic texture enhancement and dynamic difference perception, whereas the latter enhances correlation features between modes and suppresses redundant intermodal information. FusionMamba has yielded state-of-the-art (SOTA) performance across various multimodal medical image fusion tasks (CT-MRI, PET-MRI, SPECT-MRI), infrared and visible image fusion task (IR-VIS) and multimodal biomedical image fusion dataset (GFP-PC), which is proved that our model has generalization ability. The code for FusionMamba is available at https://github.com/millieXie/FusionMamba.
Authors: Shuaiying Hou, Hongyu Tao, Junheng Fang, Changqing Zou, Hujun Bao, Weiwei Xu
Abstract: Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics. Many previous methods grapple with this inherently ambiguous task by introducing motion priors into the learning process. However, these approaches face difficulties in defining the complete configurations of such priors or training a robust model. In this paper, we present the Video-to-Motion Generator (VTM), which leverages motion priors through cross-modal latent feature space alignment between 3D human motion and 2D inputs, namely videos and 2D keypoints. To reduce the complexity of modeling motion priors, we model the motion data separately for the upper and lower body parts. Additionally, we align the motion data with a scale-invariant virtual skeleton to mitigate the interference of human skeleton variations to the motion priors. Evaluated on AIST++, the VTM showcases state-of-the-art performance in reconstructing 3D human motion from monocular videos. Notably, our VTM exhibits the capabilities for generalization to unseen view angles and in-the-wild videos.
Authors: Pin Tang, Zhongdao Wang, Guoqing Wang, Jilai Zheng, Xiangxuan Ren, Bailan Feng, Chao Ma
Abstract: Vision-based perception for autonomous driving requires an explicit modeling of a 3D space, where 2D latent representations are mapped and subsequent 3D operators are applied. However, operating on dense latent spaces introduces a cubic time and space complexity, which limits scalability in terms of perception range or spatial resolution. Existing approaches compress the dense representation using projections like Bird's Eye View (BEV) or Tri-Perspective View (TPV). Although efficient, these projections result in information loss, especially for tasks like semantic occupancy prediction. To address this, we propose SparseOcc, an efficient occupancy network inspired by sparse point cloud processing. It utilizes a lossless sparse latent representation with three key innovations. Firstly, a 3D sparse diffuser performs latent completion using spatially decomposed 3D sparse convolutional kernels. Secondly, a feature pyramid and sparse interpolation enhance scales with information from others. Finally, the transformer head is redesigned as a sparse variant. SparseOcc achieves a remarkable 74.9% reduction on FLOPs over the dense baseline. Interestingly, it also improves accuracy, from 12.8% to 14.1% mIOU, which in part can be attributed to the sparse representation's ability to avoid hallucinations on empty voxels.
Authors: Qiangqiang Wu, Antoni B. Chan
Abstract: Existing deep trackers are typically trained with largescale video frames with annotated bounding boxes. However, these bounding boxes are expensive and time-consuming to annotate, in particular for large scale datasets. In this paper, we propose to learn tracking representations from single point annotations (i.e., 4.5x faster to annotate than the traditional bounding box) in a weakly supervised manner. Specifically, we propose a soft contrastive learning (SoCL) framework that incorporates target objectness prior into end-to-end contrastive learning. Our SoCL consists of adaptive positive and negative sample generation, which is memory-efficient and effective for learning tracking representations. We apply the learned representation of SoCL to visual tracking and show that our method can 1) achieve better performance than the fully supervised baseline trained with box annotations under the same annotation time cost; 2) achieve comparable performance of the fully supervised baseline by using the same number of training frames and meanwhile reducing annotation time cost by 78% and total fees by 85%; 3) be robust to annotation noise.
Authors: Jiahe Zhao, Ruibing Hou, Hong Chang, Xinqian Gu, Bingpeng Ma, Shiguang Shan, Xilin Chen
Abstract: Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relevant features. However, we observe that relying solely on clothes-irrelevant features for clothes-changing re-id is limited, since they often lack adequate identity information and suffer from large intra-class variations. On the contrary, clothes-relevant features can be used to discover same-clothes intermediaries that possess informative identity clues. Based on this observation, we propose a Feasibility-Aware Intermediary Matching (FAIM) framework to additionally utilize clothes-relevant features for retrieval. Firstly, an Intermediary Matching (IM) module is designed to perform an intermediary-assisted matching process. This process involves using clothes-relevant features to find informative intermediates, and then using clothes-irrelevant features of these intermediates to complete the matching. Secondly, in order to reduce the negative effect of low-quality intermediaries, an Intermediary-Based Feasibility Weighting (IBFW) module is designed to evaluate the feasibility of intermediary matching process by assessing the quality of intermediaries. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on several widely-used clothes-changing re-id benchmarks.
Authors: Chong Peng, Liqiang He, Dan Su
Abstract: Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate the likeness of voices and faces following contrastive learning, subsequently applied to retrieval and matching tasks. This method only considers the embeddings as high-dimensional vectors, utilizing a minimal scope of available information. This paper introduces a novel framework within an unsupervised setting for learning voice-face associations. By employing a multimodal encoder after contrastive learning and addressing the problem through binary classification, we can learn the implicit information within the embeddings in a more effective and varied manner. Furthermore, by introducing an effective pair selection method, we enhance the learning outcomes of both contrastive learning and the matching task. Empirical evidence demonstrates that our framework achieves state-of-the-art results in voice-face matching, verification, and retrieval tasks, improving verification by approximately 3%, matching by about 2.5%, and retrieval by around 1.3%.
Authors: Weifeng Chen, Tao Gu, Yuhao Xu, Chengcai Chen
Abstract: We propose Magic Clothing, a latent diffusion model (LDM)-based network architecture for an unexplored garment-driven image synthesis task. Aiming at generating customized characters wearing the target garments with diverse text prompts, the image controllability is the most critical issue, i.e., to preserve the garment details and maintain faithfulness to the text prompts. To this end, we introduce a garment extractor to capture the detailed garment features, and employ self-attention fusion to incorporate them into the pretrained LDMs, ensuring that the garment details remain unchanged on the target character. Then, we leverage the joint classifier-free guidance to balance the control of garment features and text prompts over the generated results. Meanwhile, the proposed garment extractor is a plug-in module applicable to various finetuned LDMs, and it can be combined with other extensions like ControlNet and IP-Adapter to enhance the diversity and controllability of the generated characters. Furthermore, we design Matched-Points-LPIPS (MP-LPIPS), a robust metric for evaluating the consistency of the target image to the source garment. Extensive experiments demonstrate that our Magic Clothing achieves state-of-the-art results under various conditional controls for garment-driven image synthesis. Our source code is available at https://github.com/ShineChen1024/MagicClothing.
Authors: Yuexing Han, Guanxin Wan, Bing Wang, Yi Liu
Abstract: Understanding how the structure of materials affects their properties is a cornerstone of materials science and engineering. However, traditional methods have struggled to accurately describe the quantitative structure-property relationships for complex structures. In our study, we bridge this gap by leveraging machine learning to analyze images of materials' microstructures, thus offering a novel way to understand and predict the properties of materials based on their microstructures. We introduce a method known as FAGC (Feature Augmentation on Geodesic Curves), specifically demonstrated for Cu-Cr-Zr alloys. This approach utilizes machine learning to examine the shapes within images of the alloys' microstructures and predict their mechanical and electronic properties. This generative FAGC approach can effectively expand the relatively small training datasets due to the limited availability of materials images labeled with quantitative properties. The process begins with extracting features from the images using neural networks. These features are then mapped onto the Pre-shape space to construct the Geodesic curves. Along these curves, new features are generated, effectively increasing the dataset. Moreover, we design a pseudo-labeling mechanism for these newly generated features to further enhance the training dataset. Our FAGC method has shown remarkable results, significantly improving the accuracy of predicting the electronic conductivity and hardness of Cu-Cr-Zr alloys, with R-squared values of 0.978 and 0.998, respectively. These outcomes underscore the potential of FAGC to address the challenge of limited image data in materials science, providing a powerful tool for establishing detailed and quantitative relationships between complex microstructures and material properties.
Authors: Avinash Anand, Raj Jaiswal, Mohit Gupta, Siddhesh S Bangar, Pijush Bhuyan, Naman Lal, Rajeev Singh, Ritika Jha, Rajiv Ratn Shah, Shin'ichi Satoh
Abstract: Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of annotated instances, which is both expensive and time-consuming. As a result, differences between the source and target domains may significantly impact how well these models function. To solve this problem, domain adaptation approaches have been developed that use a small quantity of labeled data to adjust the model to the target domain. In this research, we introduced a synthetic document dataset called RanLayNet, enriched with automatically assigned labels denoting spatial positions, ranges, and types of layout elements. The primary aim of this endeavor is to develop a versatile dataset capable of training models with robustness and adaptability to diverse document formats. Through empirical experimentation, we demonstrate that a deep layout identification model trained on our dataset exhibits enhanced performance compared to a model trained solely on actual documents. Moreover, we conduct a comparative analysis by fine-tuning inference models using both PubLayNet and IIIT-AR-13K datasets on the Doclaynet dataset. Our findings emphasize that models enriched with our dataset are optimal for tasks such as achieving 0.398 and 0.588 mAP95 score in the scientific document domain for the TABLE class.
Authors: Xiaoyi Zeng, Kaiwen Song, Leyuan Yang, Bailin Deng, Juyong Zhang
Abstract: Neural implicit fields have established a new paradigm for scene representation, with subsequent work achieving high-quality real-time rendering. However, reconstructing 3D scenes from oblique aerial photography presents unique challenges, such as varying spatial scale distributions and a constrained range of tilt angles, often resulting in high memory consumption and reduced rendering quality at extrapolated viewpoints. In this paper, we enhance MERF to accommodate these data characteristics by introducing an innovative adaptive occupancy plane optimized during the volume rendering process and a smoothness regularization term for view-dependent color to address these issues. Our approach, termed Oblique-MERF, surpasses state-of-the-art real-time methods by approximately 0.7 dB, reduces VRAM usage by about 40%, and achieves higher rendering frame rates with more realistic rendering outcomes across most viewpoints.
Authors: Haojun Sun, Chen Tang, Zhi Wang, Yuan Meng, Jingyan jiang, Xinzhu Ma, Wenwu Zhu
Abstract: Diffusion models have emerged as preeminent contenders in the realm of generative models. Distinguished by their distinctive sequential generative processes, characterized by hundreds or even thousands of timesteps, diffusion models progressively reconstruct images from pure Gaussian noise, with each timestep necessitating full inference of the entire model. However, the substantial computational demands inherent to these models present challenges for deployment, quantization is thus widely used to lower the bit-width for reducing the storage and computing overheads. Current quantization methodologies primarily focus on model-side optimization, disregarding the temporal dimension, such as the length of the timestep sequence, thereby allowing redundant timesteps to continue consuming computational resources, leaving substantial scope for accelerating the generative process. In this paper, we introduce TMPQ-DM, which jointly optimizes timestep reduction and quantization to achieve a superior performance-efficiency trade-off, addressing both temporal and model optimization aspects. For timestep reduction, we devise a non-uniform grouping scheme tailored to the non-uniform nature of the denoising process, thereby mitigating the explosive combinations of timesteps. In terms of quantization, we adopt a fine-grained layer-wise approach to allocate varying bit-widths to different layers based on their respective contributions to the final generative performance, thus rectifying performance degradation observed in prior studies. To expedite the evaluation of fine-grained quantization, we further devise a super-network to serve as a precision solver by leveraging shared quantization results. These two design components are seamlessly integrated within our framework, enabling rapid joint exploration of the exponentially large decision space via a gradient-free evolutionary search algorithm.
Authors: Bin Wang, Fei Deng, Peifan Jiang, Shuang Wang, Xiao Han, Hongjie Zheng
Abstract: Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy. To address this, advanced deep learning-based LDCT denoising algorithms have been developed, primarily using Convolutional Neural Networks (CNNs) or Transformer Networks with the Unet architecture. This architecture enhances image detail by integrating feature maps from the encoder and decoder via skip connections. However, current methods often overlook enhancements to the Unet architecture itself, focusing instead on optimizing encoder and decoder structures. This approach can be problematic due to the significant differences in feature map characteristics between the encoder and decoder, where simple fusion strategies may not effectively reconstruct images.In this paper, we introduce WiTUnet, a novel LDCT image denoising method that utilizes nested, dense skip pathways instead of traditional skip connections to improve feature integration. WiTUnet also incorporates a windowed Transformer structure to process images in smaller, non-overlapping segments, reducing computational load. Additionally, the integration of a Local Image Perception Enhancement (LiPe) module in both the encoder and decoder replaces the standard multi-layer perceptron (MLP) in Transformers, enhancing local feature capture and representation. Through extensive experimental comparisons, WiTUnet has demonstrated superior performance over existing methods in key metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Root Mean Square Error (RMSE), significantly improving noise removal and image quality.
Authors: Chi Wang, Junming Huang, Rong Zhang, Qi Wang, Haotian Yang, Haibin Huang, Chongyang Ma, Weiwei Xu
Abstract: Automatic 3D facial texture generation has gained significant interest recently. Existing approaches may not support the traditional physically based rendering pipeline or rely on 3D data captured by Light Stage. Our key contribution is a progressive latent space refinement approach that can bootstrap from 3D Morphable Models (3DMMs)-based texture maps generated from facial images to generate high-quality and diverse PBR textures, including albedo, normal, and roughness. It starts with enhancing Generative Adversarial Networks (GANs) for text-guided and diverse texture generation. To this end, we design a self-supervised paradigm to overcome the reliance on ground truth 3D textures and train the generative model with only entangled texture maps. Besides, we foster mutual enhancement between GANs and Score Distillation Sampling (SDS). SDS boosts GANs with more generative modes, while GANs promote more efficient optimization of SDS. Furthermore, we introduce an edge-aware SDS for multi-view consistent facial structure. Experiments demonstrate that our method outperforms existing 3D texture generation methods regarding photo-realistic quality, diversity, and efficiency.
Authors: \v{Z}iga Babnik, Fadi Boutros, Naser Damer, Peter Peer, Vitomir \v{S}truc
Abstract: Face Image Quality Assessment (FIQA) techniques have seen steady improvements over recent years, but their performance still deteriorates if the input face samples are not properly aligned. This alignment sensitivity comes from the fact that most FIQA techniques are trained or designed using a specific face alignment procedure. If the alignment technique changes, the performance of most existing FIQA techniques quickly becomes suboptimal. To address this problem, we present in this paper a novel knowledge distillation approach, termed AI-KD that can extend on any existing FIQA technique, improving its robustness to alignment variations and, in turn, performance with different alignment procedures. To validate the proposed distillation approach, we conduct comprehensive experiments on 6 face datasets with 4 recent face recognition models and in comparison to 7 state-of-the-art FIQA techniques. Our results show that AI-KD consistently improves performance of the initial FIQA techniques not only with misaligned samples, but also with properly aligned facial images. Furthermore, it leads to a new state-of-the-art, when used with a competitive initial FIQA approach. The code for AI-KD is made publicly available from: https://github.com/LSIbabnikz/AI-KD.
Authors: Fabian Isensee, Tassilo Wald, Constantin Ulrich, Michael Baumgartner, Saikat Roy, Klaus Maier-Hein, Paul F. Jaeger
Abstract: The release of nnU-Net marked a paradigm shift in 3D medical image segmentation, demonstrating that a properly configured U-Net architecture could still achieve state-of-the-art results. Despite this, the pursuit of novel architectures, and the respective claims of superior performance over the U-Net baseline, continued. In this study, we demonstrate that many of these recent claims fail to hold up when scrutinized for common validation shortcomings, such as the use of inadequate baselines, insufficient datasets, and neglected computational resources. By meticulously avoiding these pitfalls, we conduct a thorough and comprehensive benchmarking of current segmentation methods including CNN-based, Transformer-based, and Mamba-based approaches. In contrast to current beliefs, we find that the recipe for state-of-the-art performance is 1) employing CNN-based U-Net models, including ResNet and ConvNeXt variants, 2) using the nnU-Net framework, and 3) scaling models to modern hardware resources. These results indicate an ongoing innovation bias towards novel architectures in the field and underscore the need for more stringent validation standards in the quest for scientific progress.
Authors: Gabriele Rosi, Claudia Cuttano, Niccol\`o Cavagnero, Giuseppe Averta, Fabio Cermelli
Abstract: Recent advancements in image segmentation have focused on enhancing the efficiency of the models to meet the demands of real-time applications, especially on edge devices. However, existing research has primarily concentrated on single-task settings, especially on semantic segmentation, leading to redundant efforts and specialized architectures for different tasks. To address this limitation, we propose a novel architecture for efficient multi-task image segmentation, capable of handling various segmentation tasks without sacrificing efficiency or accuracy. We introduce BiSeNetFormer, that leverages the efficiency of two-stream semantic segmentation architectures and it extends them into a mask classification framework. Our approach maintains the efficient spatial and context paths to capture detailed and semantic information, respectively, while leveraging an efficient transformed-based segmentation head that computes the binary masks and class probabilities. By seamlessly supporting multiple tasks, namely semantic and panoptic segmentation, BiSeNetFormer offers a versatile solution for multi-task segmentation. We evaluate our approach on popular datasets, Cityscapes and ADE20K, demonstrating impressive inference speeds while maintaining competitive accuracy compared to state-of-the-art architectures. Our results indicate that BiSeNetFormer represents a significant advancement towards fast, efficient, and multi-task segmentation networks, bridging the gap between model efficiency and task adaptability.
Authors: Masahito Toba, Seiichi Uchida, Hideaki Hayashi
Abstract: In pseudo-labeling (PL), which is a type of semi-supervised learning, pseudo-labels are assigned based on the confidence scores provided by the classifier; therefore, accurate confidence is important for successful PL. In this study, we propose a PL algorithm based on an energy-based model (EBM), which is referred to as the energy-based PL (EBPL). In EBPL, a neural network-based classifier and an EBM are jointly trained by sharing their feature extraction parts. This approach enables the model to learn both the class decision boundary and input data distribution, enhancing confidence calibration during network training. The experimental results demonstrate that EBPL outperforms the existing PL method in semi-supervised image classification tasks, with superior confidence calibration error and recognition accuracy.
Authors: Song Xia, Yu Yi, Xudong Jiang, Henghui Ding
Abstract: Randomized Smoothing (RS) has been proven a promising method for endowing an arbitrary image classifier with certified robustness. However, the substantial uncertainty inherent in the high-dimensional isotropic Gaussian noise imposes the curse of dimensionality on RS. Specifically, the upper bound of ${\ell_2}$ certified robustness radius provided by RS exhibits a diminishing trend with the expansion of the input dimension $d$, proportionally decreasing at a rate of $1/\sqrt{d}$. This paper explores the feasibility of providing ${\ell_2}$ certified robustness for high-dimensional input through the utilization of dual smoothing in the lower-dimensional space. The proposed Dual Randomized Smoothing (DRS) down-samples the input image into two sub-images and smooths the two sub-images in lower dimensions. Theoretically, we prove that DRS guarantees a tight ${\ell_2}$ certified robustness radius for the original input and reveal that DRS attains a superior upper bound on the ${\ell_2}$ robustness radius, which decreases proportionally at a rate of $(1/\sqrt m + 1/\sqrt n )$ with $m+n=d$. Extensive experiments demonstrate the generalizability and effectiveness of DRS, which exhibits a notable capability to integrate with established methodologies, yielding substantial improvements in both accuracy and ${\ell_2}$ certified robustness baselines of RS on the CIFAR-10 and ImageNet datasets. Code is available at https://github.com/xiasong0501/DRS.
Authors: Shakiba Kheradmand, Daniel Rebain, Gopal Sharma, Weiwei Sun, Jeff Tseng, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi
Abstract: While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which does not always generalize and may lead to poor-quality renderings. In addition, for real-world scenes, they rely on a good initial point cloud to perform well. In this work, we rethink 3D Gaussians as random samples drawn from an underlying probability distribution describing the physical representation of the scene -- in other words, Markov Chain Monte Carlo (MCMC) samples. Under this view, we show that the 3D Gaussian updates are strikingly similar to a Stochastic Langevin Gradient Descent (SGLD) update. As with MCMC, samples are nothing but past visit locations, adding new Gaussians under our framework can simply be realized without heuristics as placing Gaussians at existing Gaussian locations. To encourage using fewer Gaussians for efficiency, we introduce an L1-regularizer on the Gaussians. On various standard evaluation scenes, we show that our method provides improved rendering quality, easy control over the number of Gaussians, and robustness to initialization.
Authors: Julian Lorenz, Robin Sch\"on, Katja Ludwig, Rainer Lienhart
Abstract: Scene graph generation has emerged as a prominent research field in computer vision, witnessing significant advancements in the recent years. However, despite these strides, precise and thorough definitions for the metrics used to evaluate scene graph generation models are lacking. In this paper, we address this gap in the literature by providing a review and precise definition of commonly used metrics in scene graph generation. Our comprehensive examination clarifies the underlying principles of these metrics and can serve as a reference or introduction to scene graph metrics. Furthermore, to facilitate the usage of these metrics, we introduce a standalone Python package called SGBench that efficiently implements all defined metrics, ensuring their accessibility to the research community. Additionally, we present a scene graph benchmarking web service, that enables researchers to compare scene graph generation methods and increase visibility of new methods in a central place. All of our code can be found at https://lorjul.github.io/sgbench/.
Authors: Zhaokun Zhou, Qiulin Wang, Bin Lin, Yiwei Su, Rui Chen, Xin Tao, Amin Zheng, Li Yuan, Pengfei Wan, Di Zhang
Abstract: As an alternative to expensive expert evaluation, Image Aesthetic Assessment (IAA) stands out as a crucial task in computer vision. However, traditional IAA methods are typically constrained to a single data source or task, restricting the universality and broader application. In this work, to better align with human aesthetics, we propose a Unified Multi-modal Image Aesthetic Assessment (UNIAA) framework, including a Multi-modal Large Language Model (MLLM) named UNIAA-LLaVA and a comprehensive benchmark named UNIAA-Bench. We choose MLLMs with both visual perception and language ability for IAA and establish a low-cost paradigm for transforming the existing datasets into unified and high-quality visual instruction tuning data, from which the UNIAA-LLaVA is trained. To further evaluate the IAA capability of MLLMs, we construct the UNIAA-Bench, which consists of three aesthetic levels: Perception, Description, and Assessment. Extensive experiments validate the effectiveness and rationality of UNIAA. UNIAA-LLaVA achieves competitive performance on all levels of UNIAA-Bench, compared with existing MLLMs. Specifically, our model performs better than GPT-4V in aesthetic perception and even approaches the junior-level human. We find MLLMs have great potential in IAA, yet there remains plenty of room for further improvement. The UNIAA-LLaVA and UNIAA-Bench will be released.
Authors: Yipo Huang, Xiangfei Sheng, Zhichao Yang, Quan Yuan, Zhichao Duan, Pengfei Chen, Leida Li, Weisi Lin, Guangming Shi
Abstract: The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerbates this dilemma, resulting in MLLMs falling short of aesthetics perception capabilities. To address the above challenge, we first introduce a comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset, which serves as the footstone for building multi-modality aesthetics foundation models. Specifically, to align MLLMs with human aesthetics perception, we construct a corpus-rich aesthetic critique database with 21,904 diverse-sourced images and 88K human natural language feedbacks, which are collected via progressive questions, ranging from coarse-grained aesthetic grades to fine-grained aesthetic descriptions. To ensure that MLLMs can handle diverse queries, we further prompt GPT to refine the aesthetic critiques and assemble the large-scale aesthetic instruction tuning dataset, i.e. AesMMIT, which consists of 409K multi-typed instructions to activate stronger aesthetic capabilities. Based on the AesMMIT database, we fine-tune the open-sourced general foundation models, achieving multi-modality Aesthetic Expert models, dubbed AesExpert. Extensive experiments demonstrate that the proposed AesExpert models deliver significantly better aesthetic perception performances than the state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision. Source data will be available at https://github.com/yipoh/AesExpert.
Authors: Jungin Park, Jiyoung Lee, Kwanghoon Sohn
Abstract: This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the LLMs' word embedding space using a single linear layer for efficient and general-purpose visual and language understanding. Specifically, we harness well-established word embeddings to bridge two modality embedding spaces. The visual and text representations are simultaneously assigned to a set of word embeddings within pretrained LLMs by formulating the assigning procedure as an optimal transport problem. We predict the assignment of one modality from the representation of another modality data, enforcing consistent assignments for paired multimodal data. This allows vision and language representations to contain the same information, grounding the frozen LLMs' word embedding space in visual data. Moreover, a robust semantic taxonomy of LLMs can be preserved with visual data since the LLMs interpret and reason linguistic information from correlations between word embeddings. Experimental results show that VLAP achieves substantial improvements over the previous linear transformation-based approaches across a range of vision-language tasks, including image captioning, visual question answering, and cross-modal retrieval. We also demonstrate the learned visual representations hold a semantic taxonomy of LLMs, making visual semantic arithmetic possible.
Authors: Han Xue, Qianru Sun, Li Song, Wenjun Zhang, Zhiwu Huang
Abstract: We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and conditional image generation (e.g., edge-to-image synthesis). Thanks to unification, ICT significantly reduces the inherent inductive bias that comes with designing models for specific tasks, and it maximizes mutual enhancement across similar tasks. However, the unification across a large number of tasks is non-trivial due to various data formats and training pipelines. To this end, ICT introduces two designs. Firstly, it standardizes input-output data of different tasks into RGB image pairs, e.g., semantic segmentation data pairs an RGB image with its segmentation mask in the same RGB format. This turns different tasks into a general translation task between two RGB images. Secondly, it standardizes the training of different tasks into a general in-context learning, where "in-context" means the input comprises an example input-output pair of the target task and a query image. The learning objective is to generate the "missing" data paired with the query. The implicit translation process is thus between the query and the generated image. In experiments, ICT unifies ten vision tasks and showcases impressive performance on their respective benchmarks. Notably, compared to its competitors, e.g., Painter and PromptDiffusion, ICT trained on only 4 RTX 3090 GPUs is shown to be more efficient and less costly in training.
Authors: Haojian Huang, Xiaozhen Qiao, Zhuo Chen, Haodong Chen, Bingyu Li, Zhe Sun, Mulin Chen, Xuelong Li
Abstract: Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories. This knowledge, typically encapsulated in attribute descriptions, aids in identifying class-specific visual features, thus facilitating visual-semantic alignment and improving ZSL performance. However, real-world challenges such as distribution imbalances and attribute co-occurrence among instances often hinder the discernment of local variances in images, a problem exacerbated by the scarcity of fine-grained, region-specific attribute annotations. Moreover, the variability in visual presentation within categories can also skew attribute-category associations. In response, we propose a bidirectional cross-modal ZSL approach CREST. It begins by extracting representations for attribute and visual localization and employs Evidential Deep Learning (EDL) to measure underlying epistemic uncertainty, thereby enhancing the model's resilience against hard negatives. CREST incorporates dual learning pathways, focusing on both visual-category and attribute-category alignments, to ensure robust correlation between latent and observable spaces. Moreover, we introduce an uncertainty-informed cross-modal fusion technique to refine visual-attribute inference. Extensive experiments demonstrate our model's effectiveness and unique explainability across multiple datasets. Our code and data are available at: https://github.com/JethroJames/CREST.
Authors: Jiaqi Zhu, Shaofeng Cai, Fang Deng, Junran Wu
Abstract: Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing images with textual descriptions indicative of normal and abnormal conditions, referred to as anomaly prompts. However, existing approaches depend on static anomaly prompts that are prone to cross-semantic ambiguity, and prioritize global image-level representations over crucial local pixel-level image-to-text alignment that is necessary for accurate anomaly localization. In this paper, we present ALFA, a training-free approach designed to address these challenges via a unified model. We propose a run-time prompt adaptation strategy, which first generates informative anomaly prompts to leverage the capabilities of a large language model (LLM). This strategy is enhanced by a contextual scoring mechanism for per-image anomaly prompt adaptation and cross-semantic ambiguity mitigation. We further introduce a novel fine-grained aligner to fuse local pixel-level semantics for precise anomaly localization, by projecting the image-text alignment from global to local semantic spaces. Extensive evaluations on the challenging MVTec and VisA datasets confirm ALFA's effectiveness in harnessing the language potential for zero-shot VAD, achieving significant PRO improvements of 12.1% on MVTec AD and 8.9% on VisA compared to state-of-the-art zero-shot VAD approaches.
Authors: Chenwei Lin, Hanjia Lyu, Jiebo Luo, Xian Xu
Abstract: The emergence of Large Multimodal Models (LMMs) marks a significant milestone in the development of artificial intelligence. Insurance, as a vast and complex discipline, involves a wide variety of data forms in its operational processes, including text, images, and videos, thereby giving rise to diverse multimodal tasks. Despite this, there has been limited systematic exploration of multimodal tasks specific to insurance, nor a thorough investigation into how LMMs can address these challenges. In this paper, we explore GPT-4V's capabilities in the insurance domain. We categorize multimodal tasks by focusing primarily on visual aspects based on types of insurance (e.g., auto, household/commercial property, health, and agricultural insurance) and insurance stages (e.g., risk assessment, risk monitoring, and claims processing). Our experiment reveals that GPT-4V exhibits remarkable abilities in insurance-related tasks, demonstrating not only a robust understanding of multimodal content in the insurance domain but also a comprehensive knowledge of insurance scenarios. However, there are notable shortcomings: GPT-4V struggles with detailed risk rating and loss assessment, suffers from hallucination in image understanding, and shows variable support for different languages. Through this work, we aim to bridge the insurance domain with cutting-edge LMM technology, facilitate interdisciplinary exchange and development, and provide a foundation for the continued advancement and evolution of future research endeavors.
Authors: \"Onder Tuzcuo\u{g}lu, Aybora K\"oksal, Bu\u{g}ra Sofu, Sinan Kalkan, A. Ayd{\i}n Alatan
Abstract: We introduce, XoFTR, a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images. Unlike visible images, TIR images are less susceptible to adverse lighting and weather conditions but present difficulties in matching due to significant texture and intensity differences. Current hand-crafted and learning-based methods for visible-TIR matching fall short in handling viewpoint, scale, and texture diversities. To address this, XoFTR incorporates masked image modeling pre-training and fine-tuning with pseudo-thermal image augmentation to handle the modality differences. Additionally, we introduce a refined matching pipeline that adjusts for scale discrepancies and enhances match reliability through sub-pixel level refinement. To validate our approach, we collect a comprehensive visible-thermal dataset, and show that our method outperforms existing methods on many benchmarks.
Authors: Yang Liu, Jiahua Xiao, Yu Guo, Peilin Jiang, Haiwei Yang, Fei Wang
Abstract: Effectively discerning spatial-spectral dependencies in HSI denoising is crucial, but prevailing methods using convolution or transformers still face computational efficiency limitations. Recently, the emerging Selective State Space Model(Mamba) has risen with its nearly linear computational complexity in processing natural language sequences, which inspired us to explore its potential in handling long spectral sequences. In this paper, we propose HSIDMamba(HSDM), tailored to exploit the linear complexity for effectively capturing spatial-spectral dependencies in HSI denoising. In particular, HSDM comprises multiple Hyperspectral Continuous Scan Blocks, incorporating BCSM(Bidirectional Continuous Scanning Mechanism), scale residual, and spectral attention mechanisms to enhance the capture of long-range and local spatial-spectral information. BCSM strengthens spatial-spectral interactions by linking forward and backward scans and enhancing information from eight directions through SSM, significantly enhancing the perceptual capability of HSDM and improving denoising performance more effectively. Extensive evaluations against HSI denoising benchmarks validate the superior performance of HSDM, achieving state-of-the-art results in performance and surpassing the efficiency of the latest transformer architectures by $30\%$.
Authors: Enzhi Zhang, Isaac Lyngaas, Peng Chen, Xiao Wang, Jun Igarashi, Yuankai Huo, Mohamed Wahib, Masaharu Munetomo
Abstract: Attention-based models are proliferating in the space of image analytics, including segmentation. The standard method of feeding images to transformer encoders is to divide the images into patches and then feed the patches to the model as a linear sequence of tokens. For high-resolution images, e.g. microscopic pathology images, the quadratic compute and memory cost prohibits the use of an attention-based model, if we are to use smaller patch sizes that are favorable in segmentation. The solution is to either use custom complex multi-resolution models or approximate attention schemes. We take inspiration from Adapative Mesh Refinement (AMR) methods in HPC by adaptively patching the images, as a pre-processing step, based on the image details to reduce the number of patches being fed to the model, by orders of magnitude. This method has a negligible overhead, and works seamlessly with any attention-based model, i.e. it is a pre-processing step that can be adopted by any attention-based model without friction. We demonstrate superior segmentation quality over SoTA segmentation models for real-world pathology datasets while gaining a geomean speedup of $6.9\times$ for resolutions up to $64K^2$, on up to $2,048$ GPUs.
Authors: Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sj\"olund, Thomas B. Sch\"on
Abstract: Though diffusion models have been successfully applied to various image restoration (IR) tasks, their performance is sensitive to the choice of training datasets. Typically, diffusion models trained in specific datasets fail to recover images that have out-of-distribution degradations. To address this problem, this work leverages a capable vision-language model and a synthetic degradation pipeline to learn image restoration in the wild (wild IR). More specifically, all low-quality images are simulated with a synthetic degradation pipeline that contains multiple common degradations such as blur, resize, noise, and JPEG compression. Then we introduce robust training for a degradation-aware CLIP model to extract enriched image content features to assist high-quality image restoration. Our base diffusion model is the image restoration SDE (IR-SDE). Built upon it, we further present a posterior sampling strategy for fast noise-free image generation. We evaluate our model on both synthetic and real-world degradation datasets. Moreover, experiments on the unified image restoration task illustrate that the proposed posterior sampling improves image generation quality for various degradations.
Authors: Wenyi Lian, Wenjing Lian, Ziwei Luo
Abstract: Image restoration, which aims to recover high-quality images from their corrupted counterparts, often faces the challenge of being an ill-posed problem that allows multiple solutions for a single input. However, most deep learning based works simply employ l1 loss to train their network in a deterministic way, resulting in over-smoothed predictions with inferior perceptual quality. In this work, we propose a novel method that shifts the focus from a deterministic pixel-by-pixel comparison to a statistical perspective, emphasizing the learning of distributions rather than individual pixel values. The core idea is to introduce spatial entropy into the loss function to measure the distribution difference between predictions and targets. To make this spatial entropy differentiable, we employ kernel density estimation (KDE) to approximate the probabilities for specific intensity values of each pixel with their neighbor areas. Specifically, we equip the entropy with diffusion models and aim for superior accuracy and enhanced perceptual quality over l1 based noise matching loss. In the experiments, we evaluate the proposed method for low light enhancement on two datasets and the NTIRE challenge 2024. All these results illustrate the effectiveness of our statistic-based entropy loss. Code is available at https://github.com/shermanlian/spatial-entropy-loss.
Authors: Andre Rochow, Max Schwarz, Sven Behnke
Abstract: The task of face reenactment is to transfer the head motion and facial expressions from a driving video to the appearance of a source image, which may be of a different person (cross-reenactment). Most existing methods are CNN-based and estimate optical flow from the source image to the current driving frame, which is then inpainted and refined to produce the output animation. We propose a transformer-based encoder for computing a set-latent representation of the source image(s). We then predict the output color of a query pixel using a transformer-based decoder, which is conditioned with keypoints and a facial expression vector extracted from the driving frame. Latent representations of the source person are learned in a self-supervised manner that factorize their appearance, head pose, and facial expressions. Thus, they are perfectly suited for cross-reenactment. In contrast to most related work, our method naturally extends to multiple source images and can thus adapt to person-specific facial dynamics. We also propose data augmentation and regularization schemes that are necessary to prevent overfitting and support generalizability of the learned representations. We evaluated our approach in a randomized user study. The results indicate superior performance compared to the state-of-the-art in terms of motion transfer quality and temporal consistency.
Authors: Jiadi Cui, Junming Cao, Yuhui Zhong, Liao Wang, Fuqiang Zhao, Penghao Wang, Yifan Chen, Zhipeng He, Lan Xu, Yujiao Shi, Yingliang Zhang, Jingyi Yu
Abstract: Large garages are ubiquitous yet intricate scenes in our daily lives, posing challenges characterized by monotonous colors, repetitive patterns, reflective surfaces, and transparent vehicle glass. Conventional Structure from Motion (SfM) methods for camera pose estimation and 3D reconstruction fail in these environments due to poor correspondence construction. To address these challenges, this paper introduces LetsGo, a LiDAR-assisted Gaussian splatting approach for large-scale garage modeling and rendering. We develop a handheld scanner, Polar, equipped with IMU, LiDAR, and a fisheye camera, to facilitate accurate LiDAR and image data scanning. With this Polar device, we present a GarageWorld dataset consisting of five expansive garage scenes with diverse geometric structures and will release the dataset to the community for further research. We demonstrate that the collected LiDAR point cloud by the Polar device enhances a suite of 3D Gaussian splatting algorithms for garage scene modeling and rendering. We also propose a novel depth regularizer for 3D Gaussian splatting algorithm training, effectively eliminating floating artifacts in rendered images, and a lightweight Level of Detail (LOD) Gaussian renderer for real-time viewing on web-based devices. Additionally, we explore a hybrid representation that combines the advantages of traditional mesh in depicting simple geometry and colors (e.g., walls and the ground) with modern 3D Gaussian representations capturing complex details and high-frequency textures. This strategy achieves an optimal balance between memory performance and rendering quality. Experimental results on our dataset, along with ScanNet++ and KITTI-360, demonstrate the superiority of our method in rendering quality and resource efficiency.
Authors: Shruthi Gowda, Elahe Arani, Bahram Zonooz
Abstract: Self-supervised learning (SSL) has emerged as a promising solution for addressing the challenge of limited labeled data in deep neural networks (DNNs), offering scalability potential. However, the impact of design dependencies within the SSL framework remains insufficiently investigated. In this study, we comprehensively explore SSL behavior across a spectrum of augmentations, revealing their crucial role in shaping SSL model performance and learning mechanisms. Leveraging these insights, we propose a novel learning approach that integrates prior knowledge, with the aim of curtailing the need for extensive data augmentations and thereby amplifying the efficacy of learned representations. Notably, our findings underscore that SSL models imbued with prior knowledge exhibit reduced texture bias, diminished reliance on shortcuts and augmentations, and improved robustness against both natural and adversarial corruptions. These findings not only illuminate a new direction in SSL research, but also pave the way for enhancing DNN performance while concurrently alleviating the imperative for intensive data augmentation, thereby enhancing scalability and real-world problem-solving capabilities.
Authors: Ivica Obadic, Alex Levering, Lars Pennig, Dario Oliveira, Diego Marcos, Xiaoxiang Zhu
Abstract: Predicting socioeconomic indicators from satellite imagery with deep learning has become an increasingly popular research direction. Post-hoc concept-based explanations can be an important step towards broader adoption of these models in policy-making as they enable the interpretation of socioeconomic outcomes based on visual concepts that are intuitive to humans. In this paper, we study the interplay between representation learning using an additional task-specific contrastive loss and post-hoc concept explainability for socioeconomic studies. Our results on two different geographical locations and tasks indicate that the task-specific pretraining imposes a continuous ordering of the latent space embeddings according to the socioeconomic outcomes. This improves the model's interpretability as it enables the latent space of the model to associate urban concepts with continuous intervals of socioeconomic outcomes. Further, we illustrate how analyzing the model's conceptual sensitivity for the intervals of socioeconomic outcomes can shed light on new insights for urban studies.
Authors: Yaohui Li, Qifeng Zhou, Haoxing Chen, Jianbing Zhang, Xinyu Dai, Hao Zhou
Abstract: Contrastive Language-Image Pre-training (CLIP) has shown powerful zero-shot learning performance. Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'. Most existing methods either implicitly learn from the few shots by incorporating learnable prompts or adapters, or explicitly embed them in a cache model for inference. However, the narrow distribution of few shots often contains incomplete class information, leading to biased visual knowledge with high risk of misclassification. To tackle this problem, recent methods propose to supplement visual knowledge by generative models or extra databases, which can be costly and time-consuming. In this paper, we propose an Iterative Visual Knowledge CompLetion (KCL) method to complement visual knowledge by properly taking advantages of unlabeled samples without access to any auxiliary or synthetic data. Specifically, KCL first measures the similarities between unlabeled samples and each category. Then, the samples with top confidence to each category is selected and collected by a designed confidence criterion. Finally, the collected samples are treated as labeled ones and added to few shots to jointly re-estimate the remaining unlabeled ones. The above procedures will be repeated for a certain number of iterations with more and more samples being collected until convergence, ensuring a progressive and robust knowledge completion process. Extensive experiments on 11 benchmark datasets demonstrate the effectiveness and efficiency of KCL as a plug-and-play module under both few-shot and zero-shot learning settings. Code is available at https://github.com/Mark-Sky/KCL.
Authors: Zheng Chen, Zongwei Wu, Eduard Zamfir, Kai Zhang, Yulun Zhang, Radu Timofte, Xiaokang Yang, Hongyuan Yu, Cheng Wan, Yuxin Hong, Zhijuan Huang, Yajun Zou, Yuan Huang, Jiamin Lin, Bingnan Han, Xianyu Guan, Yongsheng Yu, Daoan Zhang, Xuanwu Yin, Kunlong Zuo, Jinhua Hao, Kai Zhao, Kun Yuan, Ming Sun, Chao Zhou, Hongyu An, Xinfeng Zhang, Zhiyuan Song, Ziyue Dong, Qing Zhao, Xiaogang Xu, Pengxu Wei, Zhi-chao Dou, Gui-ling Wang, Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou, Cansu Korkmaz, A. Murat Tekalp, Yubin Wei, Xiaole Yan, Binren Li, Haonan Chen, Siqi Zhang, Sihan Chen, Amogh Joshi, Nikhil Akalwadi, Sampada Malagi, Palani Yashaswini, Chaitra Desai, Ramesh Ashok Tabib, Ujwala Patil, Uma Mudenagudi, Anjali Sarvaiya, Pooja Choksy, Jagrit Joshi, Shubh Kawa, Kishor Upla, Sushrut Patwardhan, Raghavendra Ramachandra, Sadat Hossain, Geongi Park, S. M. Nadim Uddin, Hao Xu, Yanhui Guo, Aman Urumbekov, Xingzhuo Yan, Wei Hao, Minghan Fu, Isaac Orais, Samuel Smith, Ying Liu, Wangwang Jia, Qisheng Xu, Kele Xu, Weijun Yuan, Zhan Li, Wenqin Kuang, Ruijin Guan, Ruting Deng, Zhao Zhang, Bo Wang, Suiyi Zhao, Yan Luo, Yanyan Wei, Asif Hussain Khan, Christian Micheloni, Niki Martinel
Abstract: This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.
Authors: Bozhi Luan, Hao Feng, Hong Chen, Yonghui Wang, Wengang Zhou, Houqiang Li
Abstract: The advent of Large Multimodal Models (LMMs) has sparked a surge in research aimed at harnessing their remarkable reasoning abilities. However, for understanding text-rich images, challenges persist in fully leveraging the potential of LMMs, and existing methods struggle with effectively processing high-resolution images. In this work, we propose TextCoT, a novel Chain-of-Thought framework for text-rich image understanding. TextCoT utilizes the captioning ability of LMMs to grasp the global context of the image and the grounding capability to examine local textual regions. This allows for the extraction of both global and local visual information, facilitating more accurate question-answering. Technically, TextCoT consists of three stages, including image overview, coarse localization, and fine-grained observation. The image overview stage provides a comprehensive understanding of the global scene information, and the coarse localization stage approximates the image area containing the answer based on the question asked. Then, integrating the obtained global image descriptions, the final stage further examines specific regions to provide accurate answers. Our method is free of extra training, offering immediate plug-and-play functionality. Extensive experiments are conducted on a series of text-rich image question-answering benchmark datasets based on several advanced LMMs, and the results demonstrate the effectiveness and strong generalization ability of our method. Code is available at https://github.com/bzluan/TextCoT.
Authors: Floriane Magera, Thomas Hoyoux, Olivier Barnich, Marc Van Droogenbroeck
Abstract: Camera calibration is a crucial component in the realm of sports analytics, as it serves as the foundation to extract 3D information out of the broadcast images. Despite the significance of camera calibration research in sports analytics, progress is impeded by outdated benchmarking criteria. Indeed, the annotation data and evaluation metrics provided by most currently available benchmarks strongly favor and incite the development of sports field registration methods, i.e. methods estimating homographies that map the sports field plane to the image plane. However, such homography-based methods are doomed to overlook the broader capabilities of camera calibration in bridging the 3D world to the image. In particular, real-world non-planar sports field elements (such as goals, corner flags, baskets, ...) and image distortion caused by broadcast camera lenses are out of the scope of sports field registration methods. To overcome these limitations, we designed a new benchmarking protocol, named ProCC, based on two principles: (1) the protocol should be agnostic to the camera model chosen for a camera calibration method, and (2) the protocol should fairly evaluate camera calibration methods using the reprojection of arbitrary yet accurately known 3D objects. Indirectly, we also provide insights into the metric used in SoccerNet-calibration, which solely relies on image annotation data of viewed 3D objects as ground truth, thus implementing our protocol. With experiments on the World Cup 2014, CARWC, and SoccerNet datasets, we show that our benchmarking protocol provides fairer evaluations of camera calibration methods. By defining our requirements for proper benchmarking, we hope to pave the way for a new stage in camera calibration for sports applications with high accuracy standards.
Authors: Felix Taubner, Prashant Raina, Mathieu Tuli, Eu Wern Teh, Chul Lee, Jinmiao Huang
Abstract: When working with 3D facial data, improving fidelity and avoiding the uncanny valley effect is critically dependent on accurate 3D facial performance capture. Because such methods are expensive and due to the widespread availability of 2D videos, recent methods have focused on how to perform monocular 3D face tracking. However, these methods often fall short in capturing precise facial movements due to limitations in their network architecture, training, and evaluation processes. Addressing these challenges, we propose a novel face tracker, FlowFace, that introduces an innovative 2D alignment network for dense per-vertex alignment. Unlike prior work, FlowFace is trained on high-quality 3D scan annotations rather than weak supervision or synthetic data. Our 3D model fitting module jointly fits a 3D face model from one or many observations, integrating existing neutral shape priors for enhanced identity and expression disentanglement and per-vertex deformations for detailed facial feature reconstruction. Additionally, we propose a novel metric and benchmark for assessing tracking accuracy. Our method exhibits superior performance on both custom and publicly available benchmarks. We further validate the effectiveness of our tracker by generating high-quality 3D data from 2D videos, which leads to performance gains on downstream tasks.
Authors: Tsung-Han Chou, Brian Wang, Wei-Chen Chiu, Jun-Cheng Chen
Abstract: Class agnostic counting (CAC) is a vision task that can be used to count the total occurrence number of any given reference objects in the query image. The task is usually formulated as a density map estimation problem through similarity computation among a few image samples of the reference object and the query image. In this paper, we point out a severe issue of the existing CAC framework: Given a multi-class setting, models don't consider reference images and instead blindly match all dominant objects in the query image. Moreover, the current evaluation metrics and dataset cannot be used to faithfully assess the model's generalization performance and robustness. To this end, we discover that the combination of mosaic augmentation with generalized loss is essential for addressing the aforementioned issue of CAC models to count objects of majority (i.e. dominant objects) regardless of the references. Furthermore, we introduce a new evaluation protocol and metrics for resolving the problem behind the existing CAC evaluation scheme and better benchmarking CAC models in a more fair manner. Besides, extensive evaluation results demonstrate that our proposed recipe can consistently improve the performance of different CAC models. The code will be released upon acceptance.
Authors: Jiyuan Wang, Chunyu Lin, Lang Nie, Kang Liao, Shuwei Shao, Yao Zhao
Abstract: Recently, diffusion-based depth estimation methods have drawn widespread attention due to their elegant denoising patterns and promising performance. However, they are typically unreliable under adverse conditions prevalent in real-world scenarios, such as rainy, snowy, etc. In this paper, we propose a novel robust depth estimation method called D4RD, featuring a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments. Concretely, we integrate the strength of knowledge distillation into contrastive learning, building the `trinity' contrastive scheme. This scheme utilizes the sampled noise of the forward diffusion process as a natural reference, guiding the predicted noise in diverse scenes toward a more stable and precise optimum. Moreover, we extend noise-level trinity to encompass more generic feature and image levels, establishing a multi-level contrast to distribute the burden of robust perception across the overall network. Before addressing complex scenarios, we enhance the stability of the baseline diffusion model with three straightforward yet effective improvements, which facilitate convergence and remove depth outliers. Extensive experiments demonstrate that D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions. The code for D4RD will be made available for further exploration and adoption.
Authors: Hongchi Xia, Zhi-Hao Lin, Wei-Chiu Ma, Shenlong Wang
Abstract: Creating high-quality and interactive virtual environments, such as games and simulators, often involves complex and costly manual modeling processes. In this paper, we present Video2Game, a novel approach that automatically converts videos of real-world scenes into realistic and interactive game environments. At the heart of our system are three core components:(i) a neural radiance fields (NeRF) module that effectively captures the geometry and visual appearance of the scene; (ii) a mesh module that distills the knowledge from NeRF for faster rendering; and (iii) a physics module that models the interactions and physical dynamics among the objects. By following the carefully designed pipeline, one can construct an interactable and actionable digital replica of the real world. We benchmark our system on both indoor and large-scale outdoor scenes. We show that we can not only produce highly-realistic renderings in real-time, but also build interactive games on top.
Authors: Tao Wu, Mengqi Cao, Ziteng Gao, Gangshan Wu, Limin Wang
Abstract: Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference, and the feature sampling is constrained inside the box, failing to effectively leverage richer context information outside. Recently, a few query-based action detectors have been proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or slower convergence. In this paper, we propose two core designs for a more flexible one-stage sparse action detector. First, we present a query-based adaptive feature sampling module, which endows the detector with the flexibility of mining a group of discriminative features from the entire spatio-temporal domain. Second, we devise a decoupled feature mixing module, which dynamically attends to and mixes video features along the spatial and temporal dimensions respectively for better feature decoding. Based on these designs, we instantiate two detection pipelines, that is, STMixer-K for keyframe action detection and STMixer-T for action tubelet detection. Without bells and whistles, our STMixer detectors obtain state-of-the-art results on five challenging spatio-temporal action detection benchmarks for keyframe action detection or action tube detection.
Authors: Eran Bamani, Eden Nissinman, Lisa Koenigsberg, Inbar Meir, Avishai Sintov
Abstract: Object recognition, commonly performed by a camera, is a fundamental requirement for robots to complete complex tasks. Some tasks require recognizing objects far from the robot's camera. A challenging example is Ultra-Range Gesture Recognition (URGR) in human-robot interaction where the user exhibits directive gestures at a distance of up to 25~m from the robot. However, training a model to recognize hardly visible objects located in ultra-range requires an exhaustive collection of a significant amount of labeled samples. The generation of synthetic training datasets is a recent solution to the lack of real-world data, while unable to properly replicate the realistic visual characteristics of distant objects in images. In this letter, we propose the Diffusion in Ultra-Range (DUR) framework based on a Diffusion model to generate labeled images of distant objects in various scenes. The DUR generator receives a desired distance and class (e.g., gesture) and outputs a corresponding synthetic image. We apply DUR to train a URGR model with directive gestures in which fine details of the gesturing hand are challenging to distinguish. DUR is compared to other types of generative models showcasing superiority both in fidelity and in recognition success rate when training a URGR model. More importantly, training a DUR model on a limited amount of real data and then using it to generate synthetic data for training a URGR model outperforms directly training the URGR model on real data. The synthetic-based URGR model is also demonstrated in gesture-based direction of a ground robot.
Authors: Fangwei Zhong, Kui Wu, Hai Ci, Churan Wang, Hao Chen
Abstract: Embodied visual tracking is to follow a target object in dynamic 3D environments using an agent's egocentric vision. This is a vital and challenging skill for embodied agents. However, existing methods suffer from inefficient training and poor generalization. In this paper, we propose a novel framework that combines visual foundation models (VFM) and offline reinforcement learning (offline RL) to empower embodied visual tracking. We use a pre-trained VFM, such as ``Tracking Anything", to extract semantic segmentation masks with text prompts. We then train a recurrent policy network with offline RL, e.g., Conservative Q-Learning, to learn from the collected demonstrations without online agent-environment interactions. To further improve the robustness and generalization of the policy network, we also introduce a mask re-targeting mechanism and a multi-level data collection strategy. In this way, we can train a robust tracker within an hour on a consumer-level GPU, e.g., Nvidia RTX 3090. Such efficiency is unprecedented for RL-based visual tracking methods. We evaluate our tracker on several high-fidelity environments with challenging situations, such as distraction and occlusion. The results show that our agent outperforms state-of-the-art methods in terms of sample efficiency, robustness to distractors, and generalization to unseen scenarios and targets. We also demonstrate the transferability of the learned tracker from the virtual world to real-world scenarios.
Authors: Thomas Gossard, Julian Krismer, Andreas Ziegler, Jonas Tebbe, Andreas Zell
Abstract: Spin plays a pivotal role in ball-based sports. Estimating spin becomes a key skill due to its impact on the ball's trajectory and bouncing behavior. Spin cannot be observed directly, making it inherently challenging to estimate. In table tennis, the combination of high velocity and spin renders traditional low frame rate cameras inadequate for quickly and accurately observing the ball's logo to estimate the spin due to the motion blur. Event cameras do not suffer as much from motion blur, thanks to their high temporal resolution. Moreover, the sparse nature of the event stream solves communication bandwidth limitations many frame cameras face. To the best of our knowledge, we present the first method for table tennis spin estimation using an event camera. We use ordinal time surfaces to track the ball and then isolate the events generated by the logo on the ball. Optical flow is then estimated from the extracted events to infer the ball's spin. We achieved a spin magnitude mean error of $10.7 \pm 17.3$ rps and a spin axis mean error of $32.9 \pm 38.2\deg$ in real time for a flying ball.
Authors: Haoxing Chen, Yaohui Li, Zizheng Huang, Yan Hong, Zhuoer Xu, Zhangxuan Gu, Jun Lan, Huijia Zhu, Weiqiang Wang
Abstract: Pre-trained large-scale vision-language models (VLMs) have acquired profound understanding of general visual concepts. Recent advancements in efficient transfer learning (ETL) have shown remarkable success in fine-tuning VLMs within the scenario of limited data, introducing only a few parameters to harness task-specific insights from VLMs. Despite significant progress, current leading ETL methods tend to overfit the narrow distributions of base classes seen during training and encounter two primary challenges: (i) only utilizing uni-modal information to modeling task-specific knowledge; and (ii) using costly and time-consuming methods to supplement knowledge. To address these issues, we propose a Conditional Prototype Rectification Prompt Learning (CPR) method to correct the bias of base examples and augment limited data in an effective way. Specifically, we alleviate overfitting on base classes from two aspects. First, each input image acquires knowledge from both textual and visual prototypes, and then generates sample-conditional text tokens. Second, we extract utilizable knowledge from unlabeled data to further refine the prototypes. These two strategies mitigate biases stemming from base classes, yielding a more effective classifier. Extensive experiments on 11 benchmark datasets show that our CPR achieves state-of-the-art performance on both few-shot classification and base-to-new generalization tasks. Our code is avaliable at \url{https://github.com/chenhaoxing/CPR}.
Authors: Shuai Chen, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann
Abstract: Pose regression networks predict the camera pose of a query image relative to a known environment. Within this family of methods, absolute pose regression (APR) has recently shown promising accuracy in the range of a few centimeters in position error. APR networks encode the scene geometry implicitly in their weights. To achieve high accuracy, they require vast amounts of training data that, realistically, can only be created using novel view synthesis in a days-long process. This process has to be repeated for each new scene again and again. We present a new approach to pose regression, map-relative pose regression (marepo), that satisfies the data hunger of the pose regression network in a scene-agnostic fashion. We condition the pose regressor on a scene-specific map representation such that its pose predictions are relative to the scene map. This allows us to train the pose regressor across hundreds of scenes to learn the generic relation between a scene-specific map representation and the camera pose. Our map-relative pose regressor can be applied to new map representations immediately or after mere minutes of fine-tuning for the highest accuracy. Our approach outperforms previous pose regression methods by far on two public datasets, indoor and outdoor. Code is available: https://nianticlabs.github.io/marepo
Authors: Luisa Gall\'ee, Catharina Silvia Lisson, Christoph Gerhard Lisson, Daniela Drees, Felix Weig, Daniel Vogele, Meinrad Beer, Michael G\"otz
Abstract: Due to the sensitive nature of medicine, it is particularly important and highly demanded that AI methods are explainable. This need has been recognised and there is great research interest in xAI solutions with medical applications. However, there is a lack of user-centred evaluation regarding the actual impact of the explanations. We evaluate attribute- and prototype-based explanations with the Proto-Caps model. This xAI model reasons the target classification with human-defined visual features of the target object in the form of scores and attribute-specific prototypes. The model thus provides a multimodal explanation that is intuitively understandable to humans thanks to predefined attributes. A user study involving six radiologists shows that the explanations are subjectivly perceived as helpful, as they reflect their decision-making process. The results of the model are considered a second opinion that radiologists can discuss using the model's explanations. However, it was shown that the inclusion and increased magnitude of model explanations objectively can increase confidence in the model's predictions when the model is incorrect. We can conclude that attribute scores and visual prototypes enhance confidence in the model. However, additional development and repeated user studies are needed to tailor the explanation to the respective use case.
Authors: Min-Hui Lin, Mahesh Reddy, Guillaume Berger, Michel Sarkis, Fatih Porikli, Ning Bi
Abstract: In this paper, we present EdgeRelight360, an approach for real-time video portrait relighting on mobile devices, utilizing text-conditioned generation of 360-degree high dynamic range image (HDRI) maps. Our method proposes a diffusion-based text-to-360-degree image generation in the HDR domain, taking advantage of the HDR10 standard. This technique facilitates the generation of high-quality, realistic lighting conditions from textual descriptions, offering flexibility and control in portrait video relighting task. Unlike the previous relighting frameworks, our proposed system performs video relighting directly on-device, enabling real-time inference with real 360-degree HDRI maps. This on-device processing ensures both privacy and guarantees low runtime, providing an immediate response to changes in lighting conditions or user inputs. Our approach paves the way for new possibilities in real-time video applications, including video conferencing, gaming, and augmented reality, by allowing dynamic, text-based control of lighting conditions.
Authors: Zichao Zeng, June Moh Goo, Xinglei Wang, Bin Chi, Meihui Wang, Jan Boehm
Abstract: A building's age of construction is crucial for supporting many geospatial applications. Much current research focuses on estimating building age from facade images using deep learning. However, building an accurate deep learning model requires a considerable amount of labelled training data, and the trained models often have geographical constraints. Recently, large pre-trained vision language models (VLMs) such as GPT-4 Vision, which demonstrate significant generalisation capabilities, have emerged as potential training-free tools for dealing with specific vision tasks, but their applicability and reliability for building information remain unexplored. In this study, a zero-shot building age classifier for facade images is developed using prompts that include logical instructions. Taking London as a test case, we introduce a new dataset, FI-London, comprising facade images and building age epochs. Although the training-free classifier achieved a modest accuracy of 39.69%, the mean absolute error of 0.85 decades indicates that the model can predict building age epochs successfully albeit with a small bias. The ensuing discussion reveals that the classifier struggles to predict the age of very old buildings and is challenged by fine-grained predictions within 2 decades. Overall, the classifier utilising GPT-4 Vision is capable of predicting the rough age epoch of a building from a single facade image without any training.
Authors: June Moh Goo, Zichao Zeng, Jan Boehm
Abstract: Recent advances have demonstrated that Language Vision Models (LVMs) surpass the existing State-of-the-Art (SOTA) in two-dimensional (2D) computer vision tasks, motivating attempts to apply LVMs to three-dimensional (3D) data. While LVMs are efficient and effective in addressing various downstream 2D vision tasks without training, they face significant challenges when it comes to point clouds, a representative format for representing 3D data. It is more difficult to extract features from 3D data and there are challenges due to large data sizes and the cost of the collection and labelling, resulting in a notably limited availability of datasets. Moreover, constructing LVMs for point clouds is even more challenging due to the requirements for large amounts of data and training time. To address these issues, our research aims to 1) apply the Grounded SAM through Spherical Projection to transfer 3D to 2D, and 2) experiment with synthetic data to evaluate its effectiveness in bridging the gap between synthetic and real-world data domains. Our approach exhibited high performance with an accuracy of 0.96, an IoU of 0.85, precision of 0.92, recall of 0.91, and an F1 score of 0.92, confirming its potential. However, challenges such as occlusion problems and pixel-level overlaps of multi-label points during spherical image generation remain to be addressed in future studies.
Authors: Siddhant Bansal, Michael Wray, Dima Damen
Abstract: Large Vision Language Models (VLMs) are now the de facto state-of-the-art for a number of tasks including visual question answering, recognising objects, and spatial referral. In this work, we propose the HOI-Ref task for egocentric images that aims to understand interactions between hands and objects using VLMs. To enable HOI-Ref, we curate the HOI-QA dataset that consists of 3.9M question-answer pairs for training and evaluating VLMs. HOI-QA includes questions relating to locating hands, objects, and critically their interactions (e.g. referring to the object being manipulated by the hand). We train the first VLM for HOI-Ref on this dataset and call it VLM4HOI. Our results demonstrate that VLMs trained for referral on third person images fail to recognise and refer hands and objects in egocentric images. When fine-tuned on our egocentric HOI-QA dataset, performance improves by 27.9% for referring hands and objects, and by 26.7% for referring interactions.
Authors: Omar Ikne, Benjamin Allaert, Ioan Marius Bilasco, Hazem Wannous
Abstract: Many existing facial expression recognition (FER) systems encounter substantial performance degradation when faced with variations in head pose. Numerous frontalization methods have been proposed to enhance these systems' performance under such conditions. However, they often introduce undesirable deformations, rendering them less suitable for precise facial expression analysis. In this paper, we present eMotion-GAN, a novel deep learning approach designed for frontal view synthesis while preserving facial expressions within the motion domain. Considering the motion induced by head variation as noise and the motion induced by facial expression as the relevant information, our model is trained to filter out the noisy motion in order to retain only the motion related to facial expression. The filtered motion is then mapped onto a neutral frontal face to generate the corresponding expressive frontal face. We conducted extensive evaluations using several widely recognized dynamic FER datasets, which encompass sequences exhibiting various degrees of head pose variations in both intensity and orientation. Our results demonstrate the effectiveness of our approach in significantly reducing the FER performance gap between frontal and non-frontal faces. Specifically, we achieved a FER improvement of up to +5\% for small pose variations and up to +20\% improvement for larger pose variations. Code available at \url{https://github.com/o-ikne/eMotion-GAN.git}.
Authors: Mia Chiquier, Utkarsh Mall, Carl Vondrick
Abstract: Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class labels, are largely black-box, with limited interpretability, risk for bias, and inability to discover new visual concepts not written down. Moreover, in practical settings, the vocabulary for class names and attributes of specialized concepts will not be known, preventing these methods from performing well on images uncommon in large-scale vision-language datasets. To address these limitations, we present a novel method that discovers interpretable yet discriminative sets of attributes for visual recognition. We introduce an evolutionary search algorithm that uses a large language model and its in-context learning abilities to iteratively mutate a concept bottleneck of attributes for classification. Our method produces state-of-the-art, interpretable fine-grained classifiers. We outperform the latest baselines by 18.4% on five fine-grained iNaturalist datasets and by 22.2% on two KikiBouba datasets, despite the baselines having access to privileged information about class names.
Authors: Xiao Zhou, Xiaoman Zhang, Chaoyi Wu, Ya Zhang, Weidi Xie, Yanfeng Wang
Abstract: In this paper, we consider the problem of visual representation learning for computational pathology, by exploiting large-scale image-text pairs gathered from public resources, along with the domain specific knowledge in pathology. Specifically, we make the following contributions: (i) We curate a pathology knowledge tree that consists of 50,470 informative attributes for 4,718 diseases requiring pathology diagnosis from 32 human tissues. To our knowledge, this is the first comprehensive structured pathology knowledge base; (ii) We develop a knowledge-enhanced visual-language pretraining approach, where we first project pathology-specific knowledge into latent embedding space via language model, and use it to guide the visual representation learning; (iii) We conduct thorough experiments to validate the effectiveness of our proposed components, demonstrating significant performance improvement on various downstream tasks, including cross-modal retrieval, zero-shot classification on pathology patches, and zero-shot tumor subtyping on whole slide images (WSIs). All codes, models and the pathology knowledge tree will be released to the research community
Authors: Kim Hoang Tran, Phuc Vuong Do, Ngoc Quoc Ly, Ngan Le
Abstract: Sports videos pose complex challenges, including cluttered backgrounds, camera angle changes, small action-representing objects, and imbalanced action class distribution. Existing methods for detecting actions in sports videos heavily rely on global features, utilizing a backbone network as a black box that encompasses the entire spatial frame. However, these approaches tend to overlook the nuances of the scene and struggle with detecting actions that occupy a small portion of the frame. In particular, they face difficulties when dealing with action classes involving small objects, such as balls or yellow/red cards in soccer, which only occupy a fraction of the screen space. To address these challenges, we introduce a novel approach that analyzes and models scene entities using an adaptive attention mechanism. Particularly, our model disentangles the scene content into the global environment feature and local relevant scene entities feature. To efficiently extract environmental features while considering temporal information with less computational cost, we propose the use of a 2D backbone network with a time-shift mechanism. To accurately capture relevant scene entities, we employ a Vision-Language model in conjunction with the adaptive attention mechanism. Our model has demonstrated outstanding performance, securing the 1st place in the SoccerNet-v2 Action Spotting, FineDiving, and FineGym challenge with a substantial performance improvement of 1.6, 2.0, and 1.3 points in avg-mAP compared to the runner-up methods. Furthermore, our approach offers interpretability capabilities in contrast to other deep learning models, which are often designed as black boxes. Our code and models are released at: https://github.com/Fsoft-AIC/unifying-global-local-feature.
URLs: https://github.com/Fsoft-AIC/unifying-global-local-feature.
Authors: Hanxue Gu, Haoyu Dong, Jichen Yang, Maciej A. Mazurowski
Abstract: Automated segmentation is a fundamental medical image analysis task, which enjoys significant advances due to the advent of deep learning. While foundation models have been useful in natural language processing and some vision tasks for some time, the foundation model developed with image segmentation in mind - Segment Anything Model (SAM) - has been developed only recently and has shown similar promise. However, there are still no systematic analyses or ``best-practice'' guidelines for optimal fine-tuning of SAM for medical image segmentation. This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and fine-tuning algorithms across 18 combinations, and evaluates them on 17 datasets covering all common radiology modalities. Our study reveals that (1) fine-tuning SAM leads to slightly better performance than previous segmentation methods, (2) fine-tuning strategies that use parameter-efficient learning in both the encoder and decoder are superior to other strategies, (3) network architecture has a small impact on final performance, (4) further training SAM with self-supervised learning can improve final model performance. We also demonstrate the ineffectiveness of some methods popular in the literature and further expand our experiments into few-shot and prompt-based settings. Lastly, we released our code and MRI-specific fine-tuned weights, which consistently obtained superior performance over the original SAM, at https://github.com/mazurowski-lab/finetune-SAM.
Authors: Victoria Leonenkova, Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin
Abstract: Objective no-reference image- and video-quality metrics are crucial in many computer vision tasks. However, state-of-the-art no-reference metrics have become learning-based and are vulnerable to adversarial attacks. The vulnerability of quality metrics imposes restrictions on using such metrics in quality control systems and comparing objective algorithms. Also, using vulnerable metrics as a loss for deep learning model training can mislead training to worsen visual quality. Because of that, quality metrics testing for vulnerability is a task of current interest. This paper proposes a new method for testing quality metrics vulnerability in the physical space. To our knowledge, quality metrics were not previously tested for vulnerability to this attack; they were only tested in the pixel space. We applied a physical adversarial Ti-Patch (Tiled Patch) attack to quality metrics and did experiments both in pixel and physical space. We also performed experiments on the implementation of physical adversarial wallpaper. The proposed method can be used as additional quality metrics in vulnerability evaluation, complementing traditional subjective comparison and vulnerability tests in the pixel space. We made our code and adversarial videos available on GitHub: https://github.com/leonenkova/Ti-Patch.
Authors: Masato Tamura
Abstract: Social group activity recognition is a challenging task extended from group activity recognition, where social groups must be recognized with their activities and group members. Existing methods tackle this task by leveraging region features of individuals following existing group activity recognition methods. However, the effectiveness of region features is susceptible to person localization and variable semantics of individual actions. To overcome these issues, we propose leveraging attention modules in transformers to generate social group features. In this method, multiple embeddings are used to aggregate features for a social group, each of which is assigned to a group member without duplication. Due to this non-duplicated assignment, the number of embeddings must be significant to avoid missing group members and thus renders attention in transformers ineffective. To find optimal attention designs with a large number of embeddings, we explore several design choices of queries for feature aggregation and self-attention modules in transformer decoders. Extensive experimental results show that the proposed method achieves state-of-the-art performance and verify that the proposed attention designs are highly effective on social group activity recognition.
Authors: Han Lin, Jaemin Cho, Abhay Zala, Mohit Bansal
Abstract: ControlNets are widely used for adding spatial control in image generation with different conditions, such as depth maps, canny edges, and human poses. However, there are several challenges when leveraging the pretrained image ControlNets for controlled video generation. First, pretrained ControlNet cannot be directly plugged into new backbone models due to the mismatch of feature spaces, and the cost of training ControlNets for new backbones is a big burden. Second, ControlNet features for different frames might not effectively handle the temporal consistency. To address these challenges, we introduce Ctrl-Adapter, an efficient and versatile framework that adds diverse controls to any image/video diffusion models, by adapting pretrained ControlNets (and improving temporal alignment for videos). Ctrl-Adapter provides diverse capabilities including image control, video control, video control with sparse frames, multi-condition control, compatibility with different backbones, adaptation to unseen control conditions, and video editing. In Ctrl-Adapter, we train adapter layers that fuse pretrained ControlNet features to different image/video diffusion models, while keeping the parameters of the ControlNets and the diffusion models frozen. Ctrl-Adapter consists of temporal and spatial modules so that it can effectively handle the temporal consistency of videos. We also propose latent skipping and inverse timestep sampling for robust adaptation and sparse control. Moreover, Ctrl-Adapter enables control from multiple conditions by simply taking the (weighted) average of ControlNet outputs. With diverse image/video diffusion backbones (SDXL, Hotshot-XL, I2VGen-XL, and SVD), Ctrl-Adapter matches ControlNet for image control and outperforms all baselines for video control (achieving the SOTA accuracy on the DAVIS 2017 dataset) with significantly lower computational costs (less than 10 GPU hours).
Authors: Nithin Gopalakrishnan Nair, Jeya Maria Jose Valanarasu, Vishal M. Patel
Abstract: Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have shown better generalization capability compared to CNN-based models for general vision tasks. However, much less has been explored in the existing literature regarding the capabilities of transformer-based diffusion backbones and expanding their generative prowess to other datasets. This paper focuses on enabling a single pre-trained diffusion transformer model to scale across multiple datasets swiftly, allowing for the completion of diverse generative tasks using just one model. To this end, we propose DiffScaler, an efficient scaling strategy for diffusion models where we train a minimal amount of parameters to adapt to different tasks. In particular, we learn task-specific transformations at each layer by incorporating the ability to utilize the learned subspaces of the pre-trained model, as well as the ability to learn additional task-specific subspaces, which may be absent in the pre-training dataset. As these parameters are independent, a single diffusion model with these task-specific parameters can be used to perform multiple tasks simultaneously. Moreover, we find that transformer-based diffusion models significantly outperform CNN-based diffusion models methods while performing fine-tuning over smaller datasets. We perform experiments on four unconditional image generation datasets. We show that using our proposed method, a single pre-trained model can scale up to perform these conditional and unconditional tasks, respectively, with minimal parameter tuning while performing as close as fine-tuning an entire diffusion model for that particular task.
Authors: Nithin Gopalakrishnan Nair, Jeya Maria Jose Valanarasu, Vishal M Patel
Abstract: Large diffusion-based Text-to-Image (T2I) models have shown impressive generative powers for text-to-image generation as well as spatially conditioned image generation. For most applications, we can train the model end-toend with paired data to obtain photorealistic generation quality. However, to add an additional task, one often needs to retrain the model from scratch using paired data across all modalities to retain good generation performance. In this paper, we tackle this issue and propose a novel strategy to scale a generative model across new tasks with minimal compute. During our experiments, we discovered that the variance maps of intermediate feature maps of diffusion models capture the intensity of conditioning. Utilizing this prior information, we propose MaxFusion, an efficient strategy to scale up text-to-image generation models to accommodate new modality conditions. Specifically, we combine aligned features of multiple models, hence bringing a compositional effect. Our fusion strategy can be integrated into off-the-shelf models to enhance their generative prowess.
Authors: Yueyu Hu, Onur G. Guleryuz, Philip A. Chou, Danhang Tang, Jonathan Taylor, Rus Maxham, Yao Wang
Abstract: Stereoscopic video conferencing is still challenging due to the need to compress stereo RGB-D video in real-time. Though hardware implementations of standard video codecs such as H.264 / AVC and HEVC are widely available, they are not designed for stereoscopic videos and suffer from reduced quality and performance. Specific multiview or 3D extensions of these codecs are complex and lack efficient implementations. In this paper, we propose a new approach to upgrade a 2D video codec to support stereo RGB-D video compression, by wrapping it with a neural pre- and post-processor pair. The neural networks are end-to-end trained with an image codec proxy, and shown to work with a more sophisticated video codec. We also propose a geometry-aware loss function to improve rendering quality. We train the neural pre- and post-processors on a synthetic 4D people dataset, and evaluate it on both synthetic and real-captured stereo RGB-D videos. Experimental results show that the neural networks generalize well to unseen data and work out-of-box with various video codecs. Our approach saves about 30% bit-rate compared to a conventional video coding scheme and MV-HEVC at the same level of rendering quality from a novel view, without the need of a task-specific hardware upgrade.
Authors: Jinyue Chen, Lingyu Kong, Haoran Wei, Chenglong Liu, Zheng Ge, Liang Zhao, Jianjian Sun, Chunrui Han, Xiangyu Zhang
Abstract: Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information. Similar to popular LVLMs, OneChart incorporates an autoregressive main body. Uniquely, to enhance the reliability of the numerical parts of the output, we introduce an auxiliary token placed at the beginning of the total tokens along with an additional decoder. The numerically optimized (auxiliary) token allows subsequent tokens for chart parsing to capture enhanced numerical features through causal attention. Furthermore, with the aid of the auxiliary token, we have devised a self-evaluation mechanism that enables the model to gauge the reliability of its chart parsing results by providing confidence scores for the generated content. Compared to current state-of-the-art (SOTA) chart parsing models, e.g., DePlot, ChartVLM, ChartAst, OneChart significantly outperforms in Average Precision (AP) for chart structural extraction across multiple public benchmarks, despite enjoying only 0.2 billion parameters. Moreover, as a chart parsing agent, it also brings 10%+ accuracy gains for the popular LVLM (LLaVA-1.6) in the downstream ChartQA benchmark.
Authors: Pablo Ruiz Ponce, German Barquero, Cristina Palmero, Sergio Escalera, Jose Garcia-Rodriguez
Abstract: Generating human-human motion interactions conditioned on textual descriptions is a very useful application in many areas such as robotics, gaming, animation, and the metaverse. Alongside this utility also comes a great difficulty in modeling the highly dimensional inter-personal dynamics. In addition, properly capturing the intra-personal diversity of interactions has a lot of challenges. Current methods generate interactions with limited diversity of intra-person dynamics due to the limitations of the available datasets and conditioning strategies. For this, we introduce in2IN, a novel diffusion model for human-human motion generation which is conditioned not only on the textual description of the overall interaction but also on the individual descriptions of the actions performed by each person involved in the interaction. To train this model, we use a large language model to extend the InterHuman dataset with individual descriptions. As a result, in2IN achieves state-of-the-art performance in the InterHuman dataset. Furthermore, in order to increase the intra-personal diversity on the existing interaction datasets, we propose DualMDM, a model composition technique that combines the motions generated with in2IN and the motions generated by a single-person motion prior pre-trained on HumanML3D. As a result, DualMDM generates motions with higher individual diversity and improves control over the intra-person dynamics while maintaining inter-personal coherence.
Authors: Mude Hui, Siwei Yang, Bingchen Zhao, Yichun Shi, Heng Wang, Peng Wang, Yuyin Zhou, Cihang Xie
Abstract: This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data collection pipeline leveraging advanced foundation models, namely GPT-4V and DALL-E 3. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs featuring input and output images with detailed text prompts, followed by precise alignment ensured through post-processing. In addition, we propose two evaluation metrics, Alignment and Coherence, to quantitatively assess the quality of image edit pairs using GPT-4V. HQ-Edits high-resolution images, rich in detail and accompanied by comprehensive editing prompts, substantially enhance the capabilities of existing image editing models. For example, an HQ-Edit finetuned InstructPix2Pix can attain state-of-the-art image editing performance, even surpassing those models fine-tuned with human-annotated data. The project page is https://thefllood.github.io/HQEdit_web.
Authors: Ziniu Zhang, Shulin Tian, Liangyu Chen, Ziwei Liu
Abstract: Autonomous embodied agents live on an Internet of multimedia websites. Can they hop around multimodal websites to complete complex user tasks? Existing benchmarks fail to assess them in a realistic, evolving environment for their embodiment across websites. To answer this question, we present MMInA, a multihop and multimodal benchmark to evaluate the embodied agents for compositional Internet tasks, with several appealing properties: 1) Evolving real-world multimodal websites. Our benchmark uniquely operates on evolving real-world websites, ensuring a high degree of realism and applicability to natural user tasks. Our data includes 1,050 human-written tasks covering various domains such as shopping and travel, with each task requiring the agent to autonomously extract multimodal information from web pages as observations; 2) Multihop web browsing. Our dataset features naturally compositional tasks that require information from or actions on multiple websites to solve, to assess long-range reasoning capabilities on web tasks; 3) Holistic evaluation. We propose a novel protocol for evaluating an agent's progress in completing multihop tasks. We experiment with both standalone (multimodal) language models and heuristic-based web agents. Extensive experiments demonstrate that while long-chain multihop web tasks are easy for humans, they remain challenging for state-of-the-art web agents. We identify that agents are more likely to fail on the early hops when solving tasks of more hops, which results in lower task success rates. To address this issue, we propose a simple memory augmentation approach replaying past action trajectories to reflect. Our method significantly improved both the single-hop and multihop web browsing abilities of agents. See our code and data at https://mmina.cliangyu.com
Authors: Yu-Ju Tsai, Jin-Cheng Jhang, Jingjing Zheng, Wei Wang, Albert Y. C. Chen, Min Sun, Cheng-Hao Kuo, Ming-Hsuan Yang
Abstract: Inherent ambiguity in layout annotations poses significant challenges to developing accurate 360{\deg} room layout estimation models. To address this issue, we propose a novel Bi-Layout model capable of predicting two distinct layout types. One stops at ambiguous regions, while the other extends to encompass all visible areas. Our model employs two global context embeddings, where each embedding is designed to capture specific contextual information for each layout type. With our novel feature guidance module, the image feature retrieves relevant context from these embeddings, generating layout-aware features for precise bi-layout predictions. A unique property of our Bi-Layout model is its ability to inherently detect ambiguous regions by comparing the two predictions. To circumvent the need for manual correction of ambiguous annotations during testing, we also introduce a new metric for disambiguating ground truth layouts. Our method demonstrates superior performance on benchmark datasets, notably outperforming leading approaches. Specifically, on the MatterportLayout dataset, it improves 3DIoU from 81.70% to 82.57% across the full test set and notably from 54.80% to 59.97% in subsets with significant ambiguity. Project page: https://liagm.github.io/Bi_Layout/
Authors: Chieh Hubert Lin, Changil Kim, Jia-Bin Huang, Qinbo Li, Chih-Yao Ma, Johannes Kopf, Ming-Hsuan Yang, Hung-Yu Tseng
Abstract: Neural Radiance Field (NeRF) is a representation for 3D reconstruction from multi-view images. Despite some recent work showing preliminary success in editing a reconstructed NeRF with diffusion prior, they remain struggling to synthesize reasonable geometry in completely uncovered regions. One major reason is the high diversity of synthetic contents from the diffusion model, which hinders the radiance field from converging to a crisp and deterministic geometry. Moreover, applying latent diffusion models on real data often yields a textural shift incoherent to the image condition due to auto-encoding errors. These two problems are further reinforced with the use of pixel-distance losses. To address these issues, we propose tempering the diffusion model's stochasticity with per-scene customization and mitigating the textural shift with masked adversarial training. During the analyses, we also found the commonly used pixel and perceptual losses are harmful in the NeRF inpainting task. Through rigorous experiments, our framework yields state-of-the-art NeRF inpainting results on various real-world scenes. Project page: https://hubert0527.github.io/MALD-NeRF
Authors: Drici Mourad, Kazeem Oluwakemi Oseni
Abstract: Magnetic Resonance Imaging (MRI) is a vital modality for gaining precise anatomical information, and it plays a significant role in medical imaging for diagnosis and therapy planning. Image synthesis problems have seen a revolution in recent years due to the introduction of deep learning techniques, specifically Generative Adversarial Networks (GANs). This work investigates the use of Deep Convolutional Generative Adversarial Networks (DCGAN) for producing high-fidelity and realistic MRI image slices. The suggested approach uses a dataset with a variety of brain MRI scans to train a DCGAN architecture. While the discriminator network discerns between created and real slices, the generator network learns to synthesise realistic MRI image slices. The generator refines its capacity to generate slices that closely mimic real MRI data through an adversarial training approach. The outcomes demonstrate that the DCGAN promise for a range of uses in medical imaging research, since they show that it can effectively produce MRI image slices if we train them for a consequent number of epochs. This work adds to the expanding corpus of research on the application of deep learning techniques for medical image synthesis. The slices that are could be produced possess the capability to enhance datasets, provide data augmentation in the training of deep learning models, as well as a number of functions are made available to make MRI data cleaning easier, and a three ready to use and clean dataset on the major anatomical plans.
Authors: Noel Jeffrey Pinton, Alexandre Bousse, Catherine Cheze-Le-Rest, Dimitris Visvikis
Abstract: This paper presents a proof-of-concept approach for learned synergistic reconstruction of medical images using multi-branch generative models. Leveraging variational autoencoders (VAEs) and generative adversarial networks (GANs), our models learn from pairs of images simultaneously, enabling effective denoising and reconstruction. Synergistic image reconstruction is achieved by incorporating the trained models in a regularizer that evaluates the distance between the images and the model, in a similar fashion to multichannel dictionary learning (DiL). We demonstrate the efficacy of our approach on both Modified National Institute of Standards and Technology (MNIST) and positron emission tomography (PET)/computed tomography (CT) datasets, showcasing improved image quality and information sharing between modalities. Despite challenges such as patch decomposition and model limitations, our results underscore the potential of generative models for enhancing medical imaging reconstruction.
Authors: Nicolai Dorka, Janusz Marecki, Ammar Anwar
Abstract: Addressing the challenge of a digital assistant capable of executing a wide array of user tasks, our research focuses on the realm of instruction-based mobile device control. We leverage recent advancements in large language models (LLMs) and present a visual language model (VLM) that can fulfill diverse tasks on mobile devices. Our model functions by interacting solely with the user interface (UI). It uses the visual input from the device screen and mimics human-like interactions, encompassing gestures such as tapping and swiping. This generality in the input and output space allows our agent to interact with any application on the device. Unlike previous methods, our model operates not only on a single screen image but on vision-language sentences created from sequences of past screenshots along with corresponding actions. Evaluating our method on the challenging Android in the Wild benchmark demonstrates its promising efficacy and potential.
Authors: Baochang Zhang, Mai Bui, Cheng Wang, Felix Bourier, Heribert Schunkert, Nassir Navab
Abstract: During endovascular interventions, physicians have to perform accurate and immediate operations based on the available real-time information, such as the shape and position of guidewires observed on the fluoroscopic images, haptic information and the patients' physiological signals. For this purpose, real-time and accurate guidewire segmentation and tracking can enhance the visualization of guidewires and provide visual feedback for physicians during the intervention as well as for robot-assisted interventions. Nevertheless, this task often comes with the challenge of elongated deformable structures that present themselves with low contrast in the noisy fluoroscopic image sequences. To address these issues, a two-stage deep learning framework for real-time guidewire segmentation and tracking is proposed. In the first stage, a Yolov5s detector is trained, using the original X-ray images as well as synthetic ones, which is employed to output the bounding boxes of possible target guidewires. More importantly, a refinement module based on spatiotemporal constraints is incorporated to robustly localize the guidewire and remove false detections. In the second stage, a novel and efficient network is proposed to segment the guidewire in each detected bounding box. The network contains two major modules, namely a hessian-based enhancement embedding module and a dual self-attention module. Quantitative and qualitative evaluations on clinical intra-operative images demonstrate that the proposed approach significantly outperforms our baselines as well as the current state of the art and, in comparison, shows higher robustness to low quality images.
Authors: James F. Mullen Jr, Prasoon Goyal, Robinson Piramuthu, Michael Johnston, Dinesh Manocha, Reza Ghanadan
Abstract: Home robots intend to make their users lives easier. Our work assists in this goal by enabling robots to inform their users of dangerous or unsanitary anomalies in their home. Some examples of these anomalies include the user leaving their milk out, forgetting to turn off the stove, or leaving poison accessible to children. To move towards enabling home robots with these abilities, we have created a new dataset, which we call SafetyDetect. The SafetyDetect dataset consists of 1000 anomalous home scenes, each of which contains unsafe or unsanitary situations for an agent to detect. Our approach utilizes large language models (LLMs) alongside both a graph representation of the scene and the relationships between the objects in the scene. Our key insight is that this connected scene graph and the object relationships it encodes enables the LLM to better reason about the scene -- especially as it relates to detecting dangerous or unsanitary situations. Our most promising approach utilizes GPT-4 and pursues a categorization technique where object relations from the scene graph are classified as normal, dangerous, unsanitary, or dangerous for children. This method is able to correctly identify over 90% of anomalous scenarios in the SafetyDetect Dataset. Additionally, we conduct real world experiments on a ClearPath TurtleBot where we generate a scene graph from visuals of the real world scene, and run our approach with no modification. This setup resulted in little performance loss. The SafetyDetect Dataset and code will be released to the public upon this papers publication.
Authors: Mohammed Adnan, Qinle Ba, Nazim Shaikh, Shivam Kalra, Satarupa Mukherjee, Auranuch Lorsakul
Abstract: Recent years have seen significant efforts to adopt Artificial Intelligence (AI) in healthcare for various use cases, from computer-aided diagnosis to ICU triage. However, the size of AI models has been rapidly growing due to scaling laws and the success of foundational models, which poses an increasing challenge to leverage advanced models in practical applications. It is thus imperative to develop efficient models, especially for deploying AI solutions under resource-constrains or with time sensitivity. One potential solution is to perform model compression, a set of techniques that remove less important model components or reduce parameter precision, to reduce model computation demand. In this work, we demonstrate that model pruning, as a model compression technique, can effectively reduce inference cost for computational and digital pathology based analysis with a negligible loss of analysis performance. To this end, we develop a methodology for pruning the widely used U-Net-style architectures in biomedical imaging, with which we evaluate multiple pruning heuristics on nuclei instance segmentation and classification, and empirically demonstrate that pruning can compress models by at least 70% with a negligible drop in performance.
Authors: Ye Wang, Yaxiong Wang, Yujiao Wu, Bingchen Zhao, Xueming Qian
Abstract: Generalized Class Discovery (GCD) aims to dynamically assign labels to unlabelled data partially based on knowledge learned from labelled data, where the unlabelled data may come from known or novel classes. The prevailing approach generally involves clustering across all data and learning conceptions by prototypical contrastive learning. However, existing methods largely hinge on the performance of clustering algorithms and are thus subject to their inherent limitations. Firstly, the estimated cluster number is often smaller than the ground truth, making the existing methods suffer from the lack of prototypes for comprehensive conception learning. To address this issue, we propose an adaptive probing mechanism that introduces learnable potential prototypes to expand cluster prototypes (centers). As there is no ground truth for the potential prototype, we develop a self-supervised prototype learning framework to optimize the potential prototype in an end-to-end fashion. Secondly, clustering is computationally intensive, and the conventional strategy of clustering both labelled and unlabelled instances exacerbates this issue. To counteract this inefficiency, we opt to cluster only the unlabelled instances and subsequently expand the cluster prototypes with our introduced potential prototypes to fast explore novel classes. Despite the simplicity of our proposed method, extensive empirical analysis on a wide range of datasets confirms that our method consistently delivers state-of-the-art results. Specifically, our method surpasses the nearest competitor by a significant margin of \textbf{9.7}$\%$ within the Stanford Cars dataset and \textbf{12$\times$} clustering efficiency within the Herbarium 19 dataset. We will make the code and checkpoints publicly available at \url{https://github.com/xjtuYW/PNP.git}.
Authors: Yingjie Xi, Boyuan Cheng, Jingyao Cai, Jian Jun Zhang, Xiaosong Yang
Abstract: The human whole-body X-rays could offer a valuable reference for various applications, including medical diagnostics, digital animation modeling, and ergonomic design. The traditional method of obtaining X-ray information requires the use of CT (Computed Tomography) scan machines, which emit potentially harmful radiation. Thus it faces a significant limitation for realistic applications because it lacks adaptability and safety. In our work, We proposed a new method to directly generate the 2D human whole-body X-rays from the human masking images. The predicted images will be similar to the real ones with the same image style and anatomic structure. We employed a data-driven strategy. By leveraging advanced generative techniques, our model MaSkel(Masking image to Skeleton X-rays) could generate a high-quality X-ray image from a human masking image without the need for invasive and harmful radiation exposure, which not only provides a new path to generate highly anatomic and customized data but also reduces health risks. To our knowledge, our model MaSkel is the first work for predicting whole-body X-rays. In this paper, we did two parts of the work. The first one is to solve the data limitation problem, the diffusion-based techniques are utilized to make a data augmentation, which provides two synthetic datasets for preliminary pretraining. Then we designed a two-stage training strategy to train MaSkel. At last, we make qualitative and quantitative evaluations of the generated X-rays. In addition, we invite some professional doctors to assess our predicted data. These evaluations demonstrate the MaSkel's superior ability to generate anatomic X-rays from human masking images. The related code and links of the dataset are available at https://github.com/2022yingjie/MaSkel.
Authors: Zhihao Cao, Zidong Wang, Siwen Xie, Anji Liu, Lifeng Fan
Abstract: Despite the significant demand for assistive technology among vulnerable groups (e.g., the elderly, children, and the disabled) in daily tasks, research into advanced AI-driven assistive solutions that genuinely accommodate their diverse needs remains sparse. Traditional human-machine interaction tasks often require machines to simply help without nuanced consideration of human abilities and feelings, such as their opportunity for practice and learning, sense of self-improvement, and self-esteem. Addressing this gap, we define a pivotal and novel challenge Smart Help, which aims to provide proactive yet adaptive support to human agents with diverse disabilities and dynamic goals in various tasks and environments. To establish this challenge, we leverage AI2-THOR to build a new interactive 3D realistic household environment for the Smart Help task. We introduce an innovative opponent modeling module that provides a nuanced understanding of the main agent's capabilities and goals, in order to optimize the assisting agent's helping policy. Rigorous experiments validate the efficacy of our model components and show the superiority of our holistic approach against established baselines. Our findings illustrate the potential of AI-imbued assistive robots in improving the well-being of vulnerable groups.
Authors: Melike Nur Ye\u{g}in, Mehmet Fatih Amasyal{\i}
Abstract: Generative diffusion models showed high success in many fields with a powerful theoretical background. They convert the data distribution to noise and remove the noise back to obtain a similar distribution. Many existing reviews focused on the specific application areas without concentrating on the research about the algorithm. Unlike them we investigated the theoretical developments of the generative diffusion models. These approaches mainly divide into two: training-based and sampling-based. Awakening to this allowed us a clear and understandable categorization for the researchers who will make new developments in the future.
Authors: Munachiso Nwadike, Jialin Li, Hanan Salam
Abstract: In the field of emotion recognition and Human-Machine Interaction (HMI), personalised approaches have exhibited their efficacy in capturing individual-specific characteristics and enhancing affective prediction accuracy. However, personalisation techniques often face the challenge of limited data for target individuals. This paper presents our work on an enhanced personalisation strategy, that leverages data augmentation to develop tailored models for continuous valence and arousal prediction. Our proposed approach, Distance Weighting Augmentation (DWA), employs a weighting-based augmentation method that expands a target individual's dataset, leveraging distance metrics to identify similar samples at the segment-level. Experimental results on the MuSe-Personalisation 2023 Challenge dataset demonstrate that our method significantly improves the performance of features sets which have low baseline performance, on the test set. This improvement in poor-performing features comes without sacrificing performance on high-performing features. In particular, our method achieves a maximum combined testing CCC of 0.78, compared to the reported baseline score of 0.76 (reproduced at 0.72). It also achieved a peak arousal and valence scores of 0.81 and 0.76, compared to reproduced baseline scores of 0.76 and 0.67 respectively. Through this work, we make significant contributions to the advancement of personalised affective computing models, enhancing the practicality and adaptability of data-level personalisation in real world contexts.
Authors: Changlin Song, Divya Saxena, Jiannong Cao, Yuqing Zhao
Abstract: Federated Learning (FL) is a novel approach that allows for collaborative machine learning while preserving data privacy by leveraging models trained on decentralized devices. However, FL faces challenges due to non-uniformly distributed (non-iid) data across clients, which impacts model performance and its generalization capabilities. To tackle the non-iid issue, recent efforts have utilized the global model as a teaching mechanism for local models. However, our pilot study shows that their effectiveness is constrained by imbalanced data distribution, which induces biases in local models and leads to a 'local forgetting' phenomenon, where the ability of models to generalize degrades over time, particularly for underrepresented classes. This paper introduces FedDistill, a framework enhancing the knowledge transfer from the global model to local models, focusing on the issue of imbalanced class distribution. Specifically, FedDistill employs group distillation, segmenting classes based on their frequency in local datasets to facilitate a focused distillation process to classes with fewer samples. Additionally, FedDistill dissects the global model into a feature extractor and a classifier. This separation empowers local models with more generalized data representation capabilities and ensures more accurate classification across all classes. FedDistill mitigates the adverse effects of data imbalance, ensuring that local models do not forget underrepresented classes but instead become more adept at recognizing and classifying them accurately. Our comprehensive experiments demonstrate FedDistill's effectiveness, surpassing existing baselines in accuracy and convergence speed across several benchmark datasets.
Authors: Weimin Wang, Min Gao, Mingxuan Xiao, Xu Yan, Yufeng Li
Abstract: To address the issues of limited samples, time-consuming feature design, and low accuracy in detection and classification of breast cancer pathological images, a breast cancer image classification model algorithm combining deep learning and transfer learning is proposed. This algorithm is based on the DenseNet structure of deep neural networks, and constructs a network model by introducing attention mechanisms, and trains the enhanced dataset using multi-level transfer learning. Experimental results demonstrate that the algorithm achieves an efficiency of over 84.0\% in the test set, with a significantly improved classification accuracy compared to previous models, making it applicable to medical breast cancer detection tasks.
Authors: Haosong Peng, Wei Feng, Hao Li, Yufeng Zhan, Qihua Zhou, Yuanqing Xia
Abstract: The advent of edge computing has made real-time intelligent video analytics feasible. Previous works, based on traditional model architecture (e.g., CNN, RNN, etc.), employ various strategies to filter out non-region-of-interest content to minimize bandwidth and computation consumption but show inferior performance in adverse environments. Recently, visual foundation models based on transformers have shown great performance in adverse environments due to their amazing generalization capability. However, they require a large amount of computation power, which limits their applications in real-time intelligent video analytics. In this paper, we find visual foundation models like Vision Transformer (ViT) also have a dedicated acceleration mechanism for video analytics. To this end, we introduce Arena, an end-to-end edge-assisted video inference acceleration system based on ViT. We leverage the capability of ViT that can be accelerated through token pruning by only offloading and feeding Patches-of-Interest (PoIs) to the downstream models. Additionally, we employ probability-based patch sampling, which provides a simple but efficient mechanism for determining PoIs where the probable locations of objects are in subsequent frames. Through extensive evaluations on public datasets, our findings reveal that Arena can boost inference speeds by up to $1.58\times$ and $1.82\times$ on average while consuming only 54% and 34% of the bandwidth, respectively, all with high inference accuracy.
Authors: Brian R. Bartoldson, James Diffenderfer, Konstantinos Parasyris, Bhavya Kailkhura
Abstract: This paper revisits the simple, long-studied, yet still unsolved problem of making image classifiers robust to imperceptible perturbations. Taking CIFAR10 as an example, SOTA clean accuracy is about $100$%, but SOTA robustness to $\ell_{\infty}$-norm bounded perturbations barely exceeds $70$%. To understand this gap, we analyze how model size, dataset size, and synthetic data quality affect robustness by developing the first scaling laws for adversarial training. Our scaling laws reveal inefficiencies in prior art and provide actionable feedback to advance the field. For instance, we discovered that SOTA methods diverge notably from compute-optimal setups, using excess compute for their level of robustness. Leveraging a compute-efficient setup, we surpass the prior SOTA with $20$% ($70$%) fewer training (inference) FLOPs. We trained various compute-efficient models, with our best achieving $74$% AutoAttack accuracy ($+3$% gain). However, our scaling laws also predict robustness slowly grows then plateaus at $90$%: dwarfing our new SOTA by scaling is impractical, and perfect robustness is impossible. To better understand this predicted limit, we carry out a small-scale human evaluation on the AutoAttack data that fools our top-performing model. Concerningly, we estimate that human performance also plateaus near $90$%, which we show to be attributable to $\ell_{\infty}$-constrained attacks' generation of invalid images not consistent with their original labels. Having characterized limiting roadblocks, we outline promising paths for future research.
Authors: Cheng Jiang, Alexander Gedeon, Yiwei Lyu, Eric Landgraf, Yufeng Zhang, Xinhai Hou, Akhil Kondepudi, Asadur Chowdury, Honglak Lee, Todd Hollon
Abstract: Volumetric biomedical microscopy has the potential to increase the diagnostic information extracted from clinical tissue specimens and improve the diagnostic accuracy of both human pathologists and computational pathology models. Unfortunately, barriers to integrating 3-dimensional (3D) volumetric microscopy into clinical medicine include long imaging times, poor depth / z-axis resolution, and an insufficient amount of high-quality volumetric data. Leveraging the abundance of high-resolution 2D microscopy data, we introduce masked slice diffusion for super-resolution (MSDSR), which exploits the inherent equivalence in the data-generating distribution across all spatial dimensions of biological specimens. This intrinsic characteristic allows for super-resolution models trained on high-resolution images from one plane (e.g., XY) to effectively generalize to others (XZ, YZ), overcoming the traditional dependency on orientation. We focus on the application of MSDSR to stimulated Raman histology (SRH), an optical imaging modality for biological specimen analysis and intraoperative diagnosis, characterized by its rapid acquisition of high-resolution 2D images but slow and costly optical z-sectioning. To evaluate MSDSR's efficacy, we introduce a new performance metric, SliceFID, and demonstrate MSDSR's superior performance over baseline models through extensive evaluations. Our findings reveal that MSDSR not only significantly enhances the quality and resolution of 3D volumetric data, but also addresses major obstacles hindering the broader application of 3D volumetric microscopy in clinical diagnostics and biomedical research.
Authors: Jenny Sheng, Matthieu Lin, Andrew Zhao, Kevin Pruvost, Yu-Hui Wen, Yangguang Li, Gao Huang, Yong-Jin Liu
Abstract: This paper presents an exploration of preference learning in text-to-motion generation. We find that current improvements in text-to-motion generation still rely on datasets requiring expert labelers with motion capture systems. Instead, learning from human preference data does not require motion capture systems; a labeler with no expertise simply compares two generated motions. This is particularly efficient because evaluating the model's output is easier than gathering the motion that performs a desired task (e.g. backflip). To pioneer the exploration of this paradigm, we annotate 3,528 preference pairs generated by MotionGPT, marking the first effort to investigate various algorithms for learning from preference data. In particular, our exploration highlights important design choices when using preference data. Additionally, our experimental results show that preference learning has the potential to greatly improve current text-to-motion generative models. Our code and dataset are publicly available at https://github.com/THU-LYJ-Lab/InstructMotion}{https://github.com/THU-LYJ-Lab/InstructMotion to further facilitate research in this area.
URLs: https://github.com/THU-LYJ-Lab/InstructMotion, https://github.com/THU-LYJ-Lab/InstructMotion
Authors: Kaixin Li, Yuchen Tian, Qisheng Hu, Ziyang Luo, Jing Ma
Abstract: Programming often involves converting detailed and complex specifications into code, a process during which developers typically utilize visual aids to more effectively convey concepts. While recent developments in Large Multimodal Models have demonstrated remarkable abilities in visual reasoning and mathematical tasks, there is little work on investigating whether these models can effectively interpret visual elements for code generation. To this end, we present MMCode, the first multi-modal coding dataset for evaluating algorithmic problem-solving skills in visually rich contexts. MMCode contains 3,548 questions and 6,620 images collected from real-world programming challenges harvested from 10 code competition websites, presenting significant challenges due to the extreme demand for reasoning abilities. Our experiment results show that current state-of-the-art models struggle to solve these problems. The results highlight the lack of powerful vision-code models, and we hope MMCode can serve as an inspiration for future works in this domain. The data and code are publicly available at https://github.com/happylkx/MMCode.
Authors: Xiao Wang, Shiao Wang, Yuhe Ding, Yuehang Li, Wentao Wu, Yao Rong, Weizhe Kong, Ju Huang, Shihao Li, Haoxiang Yang, Ziwen Wang, Bo Jiang, Chenglong Li, Yaowei Wang, Yonghong Tian, Jin Tang
Abstract: In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred many researchers. To further reduce the complexity of attention models, numerous efforts have been made to design more efficient methods. Among them, the State Space Model (SSM), as a possible replacement for the self-attention based Transformer model, has drawn more and more attention in recent years. In this paper, we give the first comprehensive review of these works and also provide experimental comparisons and analysis to better demonstrate the features and advantages of SSM. Specifically, we first give a detailed description of principles to help the readers quickly capture the key ideas of SSM. After that, we dive into the reviews of existing SSMs and their various applications, including natural language processing, computer vision, graph, multi-modal and multi-media, point cloud/event stream, time series data, and other domains. In addition, we give statistical comparisons and analysis of these models and hope it helps the readers to understand the effectiveness of different structures on various tasks. Then, we propose possible research points in this direction to better promote the development of the theoretical model and application of SSM. More related works will be continuously updated on the following GitHub: https://github.com/Event-AHU/Mamba_State_Space_Model_Paper_List.
URLs: https://github.com/Event-AHU/Mamba_State_Space_Model_Paper_List.
Authors: Yuxuan Jiang, Chen Feng, Fan Zhang, David Bull
Abstract: Knowledge distillation (KD) has emerged as a promising technique in deep learning, typically employed to enhance a compact student network through learning from their high-performance but more complex teacher variant. When applied in the context of image super-resolution, most KD approaches are modified versions of methods developed for other computer vision tasks, which are based on training strategies with a single teacher and simple loss functions. In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) framework specifically for image super-resolution. It exploits the advantages of multiple teachers by combining and enhancing the outputs of these teacher models, which then guides the learning process of the compact student network. To achieve more effective learning performance, we have also developed a new wavelet-based loss function for MTKD, which can better optimize the training process by observing differences in both the spatial and frequency domains. We fully evaluate the effectiveness of the proposed method by comparing it to five commonly used KD methods for image super-resolution based on three popular network architectures. The results show that the proposed MTKD method achieves evident improvements in super-resolution performance, up to 0.46dB (based on PSNR), over state-of-the-art KD approaches across different network structures. The source code of MTKD will be made available here for public evaluation.
Authors: Dilyara Bareeva, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sebastian Lapuschkin
Abstract: Deep Neural Networks are prone to learning and relying on spurious correlations in the training data, which, for high-risk applications, can have fatal consequences. Various approaches to suppress model reliance on harmful features have been proposed that can be applied post-hoc without additional training. Whereas those methods can be applied with efficiency, they also tend to harm model performance by globally shifting the distribution of latent features. To mitigate unintended overcorrection of model behavior, we propose a reactive approach conditioned on model-derived knowledge and eXplainable Artificial Intelligence (XAI) insights. While the reactive approach can be applied to many post-hoc methods, we demonstrate the incorporation of reactivity in particular for P-ClArC (Projective Class Artifact Compensation), introducing a new method called R-ClArC (Reactive Class Artifact Compensation). Through rigorous experiments in controlled settings (FunnyBirds) and with a real-world dataset (ISIC2019), we show that introducing reactivity can minimize the detrimental effect of the applied correction while simultaneously ensuring low reliance on spurious features.
Authors: Taichi Sakaguchi, Akira Taniguchi, Yoshinobu Hagiwara, Lotfi El Hafi, Shoichi Hasegawa, Tadahiro Taniguchi
Abstract: Improving instance-specific image goal navigation (InstanceImageNav), which locates the identical object in a real-world environment from a query image, is essential for robotic systems to assist users in finding desired objects. The challenge lies in the domain gap between low-quality images observed by the moving robot, characterized by motion blur and low-resolution, and high-quality query images provided by the user. Such domain gaps could significantly reduce the task success rate but have not been the focus of previous work. To address this, we propose a novel method called Few-shot Cross-quality Instance-aware Adaptation (CrossIA), which employs contrastive learning with an instance classifier to align features between massive low- and few high-quality images. This approach effectively reduces the domain gap by bringing the latent representations of cross-quality images closer on an instance basis. Additionally, the system integrates an object image collection with a pre-trained deblurring model to enhance the observed image quality. Our method fine-tunes the SimSiam model, pre-trained on ImageNet, using CrossIA. We evaluated our method's effectiveness through an InstanceImageNav task with 20 different types of instances, where the robot identifies the same instance in a real-world environment as a high-quality query image. Our experiments showed that our method improves the task success rate by up to three times compared to the baseline, a conventional approach based on SuperGlue. These findings highlight the potential of leveraging contrastive learning and image enhancement techniques to bridge the domain gap and improve object localization in robotic applications. The project website is https://emergentsystemlabstudent.github.io/DomainBridgingNav/.
URLs: https://emergentsystemlabstudent.github.io/DomainBridgingNav/.
Authors: Alessa Hering, Sarah de Boer, Anindo Saha, Jasper J. Twilt, Derya Yakar, Maarten de Rooij, Henkjan Huisman, Joeran S. Bosma
Abstract: The PI-CAI (Prostate Imaging: Cancer AI) challenge led to expert-level diagnostic algorithms for clinically significant prostate cancer detection. The algorithms receive biparametric MRI scans as input, which consist of T2-weighted and diffusion-weighted scans. These scans can be misaligned due to multiple factors in the scanning process. Image registration can alleviate this issue by predicting the deformation between the sequences. We investigate the effect of image registration on the diagnostic performance of AI-based prostate cancer diagnosis. First, the image registration algorithm, developed in MeVisLab, is analyzed using a dataset with paired lesion annotations. Second, the effect on diagnosis is evaluated by comparing case-level cancer diagnosis performance between using the original dataset, rigidly aligned diffusion-weighted scans, or deformably aligned diffusion-weighted scans. Rigid registration showed no improvement. Deformable registration demonstrated a substantial improvement in lesion overlap (+10% median Dice score) and a positive yet non-significant improvement in diagnostic performance (+0.3% AUROC, p=0.18). Our investigation shows that a substantial improvement in lesion alignment does not directly lead to a significant improvement in diagnostic performance. Qualitative analysis indicated that jointly developing image registration methods and diagnostic AI algorithms could enhance diagnostic accuracy and patient outcomes.
Authors: Tobias Weber, Jakob Dexl, David R\"ugamer, Michael Ingrisch
Abstract: We address the computational barrier of deploying advanced deep learning segmentation models in clinical settings by studying the efficacy of network compression through tensor decomposition. We propose a post-training Tucker factorization that enables the decomposition of pre-existing models to reduce computational requirements without impeding segmentation accuracy. We applied Tucker decomposition to the convolutional kernels of the TotalSegmentator (TS) model, an nnU-Net model trained on a comprehensive dataset for automatic segmentation of 117 anatomical structures. Our approach reduced the floating-point operations (FLOPs) and memory required during inference, offering an adjustable trade-off between computational efficiency and segmentation quality. This study utilized the publicly available TS dataset, employing various downsampling factors to explore the relationship between model size, inference speed, and segmentation performance. The application of Tucker decomposition to the TS model substantially reduced the model parameters and FLOPs across various compression rates, with limited loss in segmentation accuracy. We removed up to 88% of the model's parameters with no significant performance changes in the majority of classes after fine-tuning. Practical benefits varied across different graphics processing unit (GPU) architectures, with more distinct speed-ups on less powerful hardware. Post-hoc network compression via Tucker decomposition presents a viable strategy for reducing the computational demand of medical image segmentation models without substantially sacrificing accuracy. This approach enables the broader adoption of advanced deep learning technologies in clinical practice, offering a way to navigate the constraints of hardware capabilities.
Authors: Monika G\'orka, Daniel Jaworek, Marek Wodzinski
Abstract: Cancer is one of the leading causes of death globally, and early diagnosis is crucial for patient survival. Deep learning algorithms have great potential for automatic cancer analysis. Artificial intelligence has achieved high performance in recognizing and segmenting single lesions. However, diagnosing multiple lesions remains a challenge. This study examines and compares various neural network architectures and training strategies for automatically segmentation of cancer lesions using PET/CT images from the head, neck, and whole body. The authors analyzed datasets from the AutoPET and HECKTOR challenges, exploring popular single-step segmentation architectures and presenting a two-step approach. The results indicate that the V-Net and nnU-Net models were the most effective for their respective datasets. The results for the HECKTOR dataset ranged from 0.75 to 0.76 for the aggregated Dice coefficient. Eliminating cancer-free cases from the AutoPET dataset was found to improve the performance of most models. In the case of AutoPET data, the average segmentation efficiency after training only on images containing cancer lesions increased from 0.55 to 0.66 for the classic Dice coefficient and from 0.65 to 0.73 for the aggregated Dice coefficient. The research demonstrates the potential of artificial intelligence in precise oncological diagnostics and may contribute to the development of more targeted and effective cancer assessment techniques.
Authors: Haimin Zhang, Min Xu
Abstract: Studies continually find that message-passing graph convolutional networks suffer from the over-smoothing issue. Basically, the issue of over-smoothing refers to the phenomenon that the learned embeddings for all nodes can become very similar to one another and therefore are uninformative after repeatedly applying message passing iterations. Intuitively, we can expect the generated embeddings become smooth asymptotically layerwisely, that is each layer of graph convolution generates a smoothed version of embeddings as compared to that generated by the previous layer. Based on this intuition, we propose RandAlign, a stochastic regularization method for graph convolutional networks. The idea of RandAlign is to randomly align the learned embedding for each node with that of the previous layer using randomly interpolation in each graph convolution layer. Through alignment, the smoothness of the generated embeddings is explicitly reduced. To better maintain the benefit yielded by the graph convolution, in the alignment step we introduce to first scale the embedding of the previous layer to the same norm as the generated embedding and then perform random interpolation for aligning the generated embedding. RandAlign is a parameter-free method and can be directly applied without introducing additional trainable weights or hyper-parameters. We experimentally evaluate RandAlign on different graph domain tasks on seven benchmark datasets. The experimental results show that RandAlign is a general method that improves the generalization performance of various graph convolutional network models and also improves the numerical stability of optimization, advancing the state of the art performance for graph representation learning.
Authors: Haimin Zhang, Min Xu
Abstract: Message passing has become the dominant framework in graph representation learning. The essential idea of the message-passing framework is to update node embeddings based on the information aggregated from local neighbours. However, most existing aggregation methods have not encoded neighbour-level message interactions into the aggregated message, resulting in an information lost in embedding generation. And this information lost could be accumulated and become more serious as more layers are added to the graph network model. To address this issue, we propose a neighbour-level message interaction information encoding method for improving graph representation learning. For messages that are aggregated at a node, we explicitly generate an encoding between each message and the rest messages using an encoding function. Then we aggregate these learned encodings and take the sum of the aggregated encoding and the aggregated message to update the embedding for the node. By this way, neighbour-level message interaction information is integrated into the generated node embeddings. The proposed encoding method is a generic method which can be integrated into message-passing graph convolutional networks. Extensive experiments are conducted on six popular benchmark datasets across four highly-demanded tasks. The results show that integrating neighbour-level message interactions achieves improved performance of the base models, advancing the state of the art results for representation learning over graphs.
Authors: Hyeonggeun Yun
Abstract: In computer vision, explainable AI (xAI) methods seek to mitigate the 'black-box' problem by making the decision-making process of deep learning models more interpretable and transparent. Traditional xAI methods concentrate on visualizing input features that influence model predictions, providing insights primarily suited for experts. In this work, we present an interaction-based xAI method that enhances user comprehension of image classification models through their interaction. Thus, we developed a web-based prototype allowing users to modify images via painting and erasing, thereby observing changes in classification results. Our approach enables users to discern critical features influencing the model's decision-making process, aligning their mental models with the model's logic. Experiments conducted with five images demonstrate the potential of the method to reveal feature importance through user interaction. Our work contributes a novel perspective to xAI by centering on end-user engagement and understanding, paving the way for more intuitive and accessible explainability in AI systems.
Authors: Divyang Doshi, Jung-Eun Kim
Abstract: In this research, we propose an innovative method to boost Knowledge Distillation efficiency without the need for resource-heavy teacher models. Knowledge Distillation trains a smaller ``student'' model with guidance from a larger ``teacher'' model, which is computationally costly. However, the main benefit comes from the soft labels provided by the teacher, helping the student grasp nuanced class similarities. In our work, we propose an efficient method for generating these soft labels, thereby eliminating the need for a large teacher model. We employ a compact autoencoder to extract essential features and calculate similarity scores between different classes. Afterward, we apply the softmax function to these similarity scores to obtain a soft probability vector. This vector serves as valuable guidance during the training of the student model. Our extensive experiments on various datasets, including CIFAR-100, Tiny Imagenet, and Fashion MNIST, demonstrate the superior resource efficiency of our approach compared to traditional knowledge distillation methods that rely on large teacher models. Importantly, our approach consistently achieves similar or even superior performance in terms of model accuracy. We also perform a comparative study with various techniques recently developed for knowledge distillation showing our approach achieves competitive performance with using significantly less resources. We also show that our approach can be easily added to any logit based knowledge distillation method. This research contributes to making knowledge distillation more accessible and cost-effective for practical applications, making it a promising avenue for improving the efficiency of model training. The code for this work is available at, https://github.com/JEKimLab/ReffAKD.
Authors: Amir Bar, Arya Bakhtiar, Danny Tran, Antonio Loquercio, Jathushan Rajasegaran, Yann LeCun, Amir Globerson, Trevor Darrell
Abstract: Animals perceive the world to plan their actions and interact with other agents to accomplish complex tasks, demonstrating capabilities that are still unmatched by AI systems. To advance our understanding and reduce the gap between the capabilities of animals and AI systems, we introduce a dataset of pet egomotion imagery with diverse examples of simultaneous egomotion and multi-agent interaction. Current video datasets separately contain egomotion and interaction examples, but rarely both at the same time. In addition, EgoPet offers a radically distinct perspective from existing egocentric datasets of humans or vehicles. We define two in-domain benchmark tasks that capture animal behavior, and a third benchmark to assess the utility of EgoPet as a pretraining resource to robotic quadruped locomotion, showing that models trained from EgoPet outperform those trained from prior datasets.
Authors: Mikolaj Czerkawski, Javier Cardona, Robert Atkinson, Craig Michie, Ivan Andonovic, Carmine Clemente, Christos Tachtatzis
Abstract: Coordinate-based Multilayer Perceptron (MLP) networks, despite being capable of learning neural implicit representations, are not performant for internal image synthesis applications. Convolutional Neural Networks (CNNs) are typically used instead for a variety of internal generative tasks, at the cost of a larger model. We propose Neural Knitwork, an architecture for neural implicit representation learning of natural images that achieves image synthesis by optimizing the distribution of image patches in an adversarial manner and by enforcing consistency between the patch predictions. To the best of our knowledge, this is the first implementation of a coordinate-based MLP tailored for synthesis tasks such as image inpainting, super-resolution, and denoising. We demonstrate the utility of the proposed technique by training on these three tasks. The results show that modeling natural images using patches, rather than pixels, produces results of higher fidelity. The resulting model requires 80% fewer parameters than alternative CNN-based solutions while achieving comparable performance and training time.
Authors: Lin Li, Jun Xiao, Hanrong Shi, Hanwang Zhang, Yi Yang, Wei Liu, Long Chen
Abstract: Nearly all existing scene graph generation (SGG) models have overlooked the ground-truth annotation qualities of mainstream SGG datasets, i.e., they assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-annotated negative samples are absolutely background. In this paper, we argue that neither of the assumptions applies to SGG: there are numerous noisy ground-truth predicate labels that break these two assumptions and harm the training of unbiased SGG models. To this end, we propose a novel NoIsy label CorrEction and Sample Training strategy for SGG: NICEST. Specifically, it consists of two parts: NICE and NIST, which rule out these noisy label issues by generating high-quality samples and the effective training strategy, respectively. NICE first detects noisy samples and then reassigns them more high-quality soft predicate labels. NIST is a multi-teacher knowledge distillation based training strategy, which enables the model to learn unbiased fusion knowledge. And a dynamic trade-off weighting strategy in NIST is designed to penalize the bias of different teachers. Due to the model-agnostic nature of both NICE and NIST, our NICEST can be seamlessly incorporated into any SGG architecture to boost its performance on different predicate categories. In addition, to better evaluate the generalization of SGG models, we further propose a new benchmark VG-OOD, by re-organizing the prevalent VG dataset and deliberately making the predicate distributions of the training and test sets as different as possible for each subject-object category pair. This new benchmark helps disentangle the influence of subject-object category based frequency biases. Extensive ablations and results on different backbones and tasks have attested to the effectiveness and generalization ability of each component of NICEST.
Authors: Yeying Jin, Wei Ye, Wenhan Yang, Yuan Yuan, Robby T. Tan
Abstract: Removing soft and self shadows that lack clear boundaries from a single image is still challenging. Self shadows are shadows that are cast on the object itself. Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows. In this paper, we present DeS3, a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our novel ViT similarity loss utilizes features extracted from a pre-trained Vision Transformer. This loss helps guide the reverse sampling towards recovering scene structures. Our adaptive attention is able to differentiate shadow regions from the underlying objects, as well as shadow regions from the object casting the shadow. This capability enables DeS3 to better recover the structures of objects even when they are partially occluded by shadows. Different from existing methods that rely on constraints during the training phase, we incorporate the ViT similarity during the sampling stage. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets, removing hard, soft, and self shadows robustly. Specifically, our method outperforms the SOTA method by 16\% of the RMSE of the whole image on the LRSS dataset. Our data and code is available at: \url{https://github.com/jinyeying/DeS3_Deshadow}
Authors: Kenan Jiang, Xuehai He, Ruize Xu, Xin Eric Wang
Abstract: Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositional image and text matching -- a more challenging image and text matching task requiring the model understanding of compositional word concepts and visual components. Towards better compositional generalization in zero-shot image and text matching, in this paper, we study the problem from a causal perspective: the erroneous semantics of individual entities are essentially confounders that cause the matching failure. Therefore, we propose a novel \textbf{\textit{training-free}} compositional CLIP model (ComCLIP). ComCLIP disentangles input images into subjects, objects, and action sub-images and composes CLIP's vision encoder and text encoder to perform evolving matching over compositional text embedding and sub-image embeddings. In this way, ComCLIP can mitigate spurious correlations introduced by the pretrained CLIP models and dynamically evaluate the importance of each component. Experiments on four compositional image-text matching datasets: SVO, ComVG, Winoground, and VL-checklist, and two general image-text retrieval datasets: Flick30K, and MSCOCO demonstrate the effectiveness of our plug-and-play method, which boosts the \textbf{\textit{zero-shot}} inference ability of CLIP, SLIP, and BLIP2 even without further training or fine-tuning. Our codes can be found at https://github.com/eric-ai-lab/ComCLIP.
Authors: Thanh-Dat Truong, Pierce Helton, Ahmed Moustafa, Jackson David Cothren, Khoa Luu
Abstract: Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases. In practice, the segmentation models may encounter new data that have not been seen yet. Also, the previous data training of segmentation models may be inaccessible due to privacy problems. Therefore, to address these problems, in this work, we propose a Continual Unsupervised Domain Adaptation (CONDA) approach that allows the model to continuously learn and adapt with respect to the presence of the new data. Moreover, our proposed approach is designed without the requirement of accessing previous training data. To avoid the catastrophic forgetting problem and maintain the performance of the segmentation models, we present a novel Bijective Maximum Likelihood loss to impose the constraint of predicted segmentation distribution shifts. The experimental results on the benchmark of continual unsupervised domain adaptation have shown the advanced performance of the proposed CONDA method.
Authors: Yutaro Yamada, Yingtian Tang, Yoyo Zhang, Ilker Yildirim
Abstract: Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such performance does not realize in tasks that require a finer-grained correspondence between vision and language, such as Visual Question Answering (VQA). As a potential cause of the difficulty of applying these models to VQA and similar tasks, we report an interesting phenomenon of vision-language models, which we call the Concept Association Bias (CAB). We find that models with CAB tend to treat input as a bag of concepts and attempt to fill in the other missing concept crossmodally, leading to an unexpected zero-shot prediction. We demonstrate CAB by showing that CLIP's zero-shot classification performance greatly suffers when there is a strong concept association between an object (e.g. eggplant) and an attribute (e.g. color purple). We also show that the strength of CAB predicts the performance on VQA. We observe that CAB is prevalent in vision-language models trained with contrastive losses, even when autoregressive losses are jointly employed. However, a model that solely relies on autoregressive loss seems to exhibit minimal or no signs of CAB.
Authors: Senran Fan, Haotai Liang, Chen Dong, Xiaodong Xu, Geng Liu
Abstract: Intelligent inspection robots are widely used in substation patrol inspection, which can help check potential safety hazards by patrolling the substation and sending back scene images. However, when patrolling some marginal areas with weak signal, the scene images cannot be sucessfully transmissted to be used for hidden danger elimination, which greatly reduces the quality of robots'daily work. To solve such problem, a Specific Task-oriented Semantic Communication System for Imag-STSCI is designed, which involves the semantic features extraction, transmission, restoration and enhancement to get clearer images sent by intelligent robots under weak signals. Inspired by that only some specific details of the image are needed in such substation patrol inspection task, we proposed a new paradigm of semantic enhancement in such specific task to ensure the clarity of key semantic information when facing a lower bit rate or a low signal-to-noise ratio situation. Across the reality-based simulation, experiments show our STSCI can generally surpass traditional image-compression-based and channel-codingbased or other semantic communication system in the substation patrol inspection task with a lower bit rate even under a low signal-to-noise ratio situation.
Authors: Yiran Xu, Zhixin Shu, Cameron Smith, Seoung Wug Oh, Jia-Bin Huang
Abstract: 3D-aware GANs offer new capabilities for view synthesis while preserving the editing functionalities of their 2D counterparts. GAN inversion is a crucial step that seeks the latent code to reconstruct input images or videos, subsequently enabling diverse editing tasks through manipulation of this latent code. However, a model pre-trained on a particular dataset (e.g., FFHQ) often has difficulty reconstructing images with out-of-distribution (OOD) objects such as faces with heavy make-up or occluding objects. We address this issue by explicitly modeling OOD objects from the input in 3D-aware GANs. Our core idea is to represent the image using two individual neural radiance fields: one for the in-distribution content and the other for the out-of-distribution object. The final reconstruction is achieved by optimizing the composition of these two radiance fields with carefully designed regularization. We demonstrate that our explicit decomposition alleviates the inherent trade-off between reconstruction fidelity and editability. We evaluate reconstruction accuracy and editability of our method on challenging real face images and videos and showcase favorable results against other baselines.
Authors: Alexandra Dana, Nadav Carmel, Amit Shomer, Ofer Manela, Tomer Peleg
Abstract: Transferring the absolute depth prediction capabilities of an estimator to a new domain is a task with significant real-world applications. This task is specifically challenging when images from the new domain are collected without ground-truth depth measurements, and possibly with sensors of different intrinsics. To overcome such limitations, a recent zero-shot solution was trained on an extensive training dataset and encoded the various camera intrinsics. Other solutions generated synthetic data with depth labels that matched the intrinsics of the new target data to enable depth-scale transfer between the domains. In this work we present an alternative solution that can utilize any existing synthetic or real dataset, that has a small number of images annotated with ground truth depth labels. Specifically, we show that self-supervised depth estimators result in up-to-scale predictions that are linearly correlated to their absolute depth values across the domain, a property that we model in this work using a single scalar. In addition, aligning the field-of-view of two datasets prior to training, results in a common linear relationship for both domains. We use this observed property to transfer the depth-scale from source datasets that have absolute depth labels to new target datasets that lack these measurements, enabling absolute depth predictions in the target domain. The suggested method was successfully demonstrated on the KITTI, DDAD and nuScenes datasets, while using other existing real or synthetic source datasets, that have a different field-of-view, other image style or structural content, achieving comparable or better accuracy than other existing methods that do not use target ground-truth depths.
Authors: Senqiao Yang, Jiarui Wu, Jiaming Liu, Xiaoqi Li, Qizhe Zhang, Mingjie Pan, Yulu Gan, Zehui Chen, Shanghang Zhang
Abstract: The visual prompts have provided an efficient manner in addressing visual cross-domain problems. In previous works, Visual Domain Prompt (VDP) first introduces domain prompts to tackle the classification Test-Time Adaptation (TTA) problem by warping image-level prompts on the input and fine-tuning prompts for each target domain. However, since the image-level prompts mask out continuous spatial details in the prompt-allocated region, it will suffer from inaccurate contextual information and limited domain knowledge extraction, particularly when dealing with dense prediction TTA problems. To overcome these challenges, we propose a novel Sparse Visual Domain Prompts (SVDP) approach, which holds minimal trainable parameters (e.g., 0.1\%) in the image-level prompt and reserves more spatial information of the input. To better apply SVDP in extracting domain-specific knowledge, we introduce the Domain Prompt Placement (DPP) method to adaptively allocates trainable parameters of SVDP on the pixels with large distribution shifts. Furthermore, recognizing that each target domain sample exhibits a unique domain shift, we design Domain Prompt Updating (DPU) strategy to optimize prompt parameters differently for each sample, facilitating efficient adaptation to the target domain. Extensive experiments were conducted on widely-used TTA and continual TTA benchmarks, and our proposed method achieves state-of-the-art performance in both semantic segmentation and depth estimation tasks.
Authors: Yanbiao Ma, Licheng Jiao, Fang Liu, Shuyuan Yang, Xu Liu, Lingling Li
Abstract: To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes. However, recent studies have shown that tail classes are not always hard to learn, and model bias has been observed on sample-balanced datasets, suggesting the existence of other factors that affect model bias. In this work, we systematically propose a series of geometric measurements for perceptual manifolds in deep neural networks, and then explore the effect of the geometric characteristics of perceptual manifolds on classification difficulty and how learning shapes the geometric characteristics of perceptual manifolds. An unanticipated finding is that the correlation between the class accuracy and the separation degree of perceptual manifolds gradually decreases during training, while the negative correlation with the curvature gradually increases, implying that curvature imbalance leads to model bias. Therefore, we propose curvature regularization to facilitate the model to learn curvature-balanced and flatter perceptual manifolds. Evaluations on multiple long-tailed and non-long-tailed datasets show the excellent performance and exciting generality of our approach, especially in achieving significant performance improvements based on current state-of-the-art techniques. Our work opens up a geometric analysis perspective on model bias and reminds researchers to pay attention to model bias on non-long-tailed and even sample-balanced datasets. The code and model will be made public.
Authors: Chi Wang, Min Zhou, Tiezheng Ge, Yuning Jiang, Hujun Bao, Weiwei Xu
Abstract: Content and style disentanglement is an effective way to achieve few-shot font generation. It allows to transfer the style of the font image in a source domain to the style defined with a few reference images in a target domain. However, the content feature extracted using a representative font might not be optimal. In light of this, we propose a content fusion module (CFM) to project the content feature into a linear space defined by the content features of basis fonts, which can take the variation of content features caused by different fonts into consideration. Our method also allows to optimize the style representation vector of reference images through a lightweight iterative style-vector refinement (ISR) strategy. Moreover, we treat the 1D projection of a character image as a probability distribution and leverage the distance between two distributions as the reconstruction loss (namely projected character loss, PCL). Compared to L2 or L1 reconstruction loss, the distribution distance pays more attention to the global shape of characters. We have evaluated our method on a dataset of 300 fonts with 6.5k characters each. Experimental results verify that our method outperforms existing state-of-the-art few-shot font generation methods by a large margin. The source code can be found at https://github.com/wangchi95/CF-Font.
Authors: Junkai Deng, Fei Hou, Xuhui Chen, Wencheng Wang, Ying He
Abstract: Recently, building on the foundation of neural radiance field, various techniques have emerged to learn unsigned distance fields (UDF) to reconstruct 3D non-watertight models from multi-view images. Yet, a central challenge in UDF-based volume rendering is formulating a proper way to convert unsigned distance values into volume density, ensuring that the resulting weight function remains unbiased and sensitive to occlusions. Falling short on these requirements often results in incorrect topology or large reconstruction errors in resulting models. This paper addresses this challenge by presenting a novel two-stage algorithm, 2S-UDF, for learning a high-quality UDF from multi-view images. Initially, the method applies an easily trainable density function that, while slightly biased and transparent, aids in coarse reconstruction. The subsequent stage then refines the geometry and appearance of the object to achieve a high-quality reconstruction by directly adjusting the weight function used in volume rendering to ensure that it is unbiased and occlusion-aware. Decoupling density and weight in two stages makes our training stable and robust, distinguishing our technique from existing UDF learning approaches. Evaluations on the DeepFashion3D, DTU, and BlendedMVS datasets validate the robustness and effectiveness of our proposed approach. In both quantitative metrics and visual quality, the results indicate our superior performance over other UDF learning techniques in reconstructing 3D non-watertight models from multi-view images. Our code is available at https://bitbucket.org/jkdeng/2sudf/.
Authors: Kaifeng Zou, Sylvain Faisan, Boyang Yu, S\'ebastien Valette, Hyewon Seo
Abstract: Facial expression generation is one of the most challenging and long-sought aspects of character animation, with many interesting applications. The challenging task, traditionally having relied heavily on digital craftspersons, remains yet to be explored. In this paper, we introduce a generative framework for generating 3D facial expression sequences (i.e. 4D faces) that can be conditioned on different inputs to animate an arbitrary 3D face mesh. It is composed of two tasks: (1) Learning the generative model that is trained over a set of 3D landmark sequences, and (2) Generating 3D mesh sequences of an input facial mesh driven by the generated landmark sequences. The generative model is based on a Denoising Diffusion Probabilistic Model (DDPM), which has achieved remarkable success in generative tasks of other domains. While it can be trained unconditionally, its reverse process can still be conditioned by various condition signals. This allows us to efficiently develop several downstream tasks involving various conditional generation, by using expression labels, text, partial sequences, or simply a facial geometry. To obtain the full mesh deformation, we then develop a landmark-guided encoder-decoder to apply the geometrical deformation embedded in landmarks on a given facial mesh. Experiments show that our model has learned to generate realistic, quality expressions solely from the dataset of relatively small size, improving over the state-of-the-art methods. Videos and qualitative comparisons with other methods can be found at \url{https://github.com/ZOUKaifeng/4DFM}.
Authors: Simone Angarano, Mauro Martini, Alessandro Navone, Marcello Chiaberge
Abstract: In recent years, precision agriculture has gradually oriented farming closer to automation processes to support all the activities related to field management. Service robotics plays a predominant role in this evolution by deploying autonomous agents that can navigate fields while performing tasks such as monitoring, spraying, and harvesting without human intervention. To execute these precise actions, mobile robots need a real-time perception system that understands their surroundings and identifies their targets in the wild. Existing methods, however, often fall short in generalizing to new crops and environmental conditions. This limit is critical for practical applications where labeled samples are rarely available. In this paper, we investigate the problem of crop segmentation and propose a novel approach to enhance domain generalization using knowledge distillation. In the proposed framework, we transfer knowledge from a standardized ensemble of models individually trained on source domains to a student model that can adapt to unseen realistic scenarios. To support the proposed method, we present a synthetic multi-domain dataset for crop segmentation containing plants of variegate species and covering different terrain styles, weather conditions, and light scenarios for more than 70,000 samples. We demonstrate significant improvements in performance over state-of-the-art methods and superior sim-to-real generalization. Our approach provides a promising solution for domain generalization in crop segmentation and has the potential to enhance a wide variety of agriculture applications.
Authors: Guillaume Jaume, Anurag Vaidya, Richard Chen, Drew Williamson, Paul Liang, Faisal Mahmood
Abstract: Integrating whole-slide images (WSIs) and bulk transcriptomics for predicting patient survival can improve our understanding of patient prognosis. However, this multimodal task is particularly challenging due to the different nature of these data: WSIs represent a very high-dimensional spatial description of a tumor, while bulk transcriptomics represent a global description of gene expression levels within that tumor. In this context, our work aims to address two key challenges: (1) how can we tokenize transcriptomics in a semantically meaningful and interpretable way?, and (2) how can we capture dense multimodal interactions between these two modalities? Specifically, we propose to learn biological pathway tokens from transcriptomics that can encode specific cellular functions. Together with histology patch tokens that encode the different morphological patterns in the WSI, we argue that they form appropriate reasoning units for downstream interpretability analyses. We propose fusing both modalities using a memory-efficient multimodal Transformer that can model interactions between pathway and histology patch tokens. Our proposed model, SURVPATH, achieves state-of-the-art performance when evaluated against both unimodal and multimodal baselines on five datasets from The Cancer Genome Atlas. Our interpretability framework identifies key multimodal prognostic factors, and, as such, can provide valuable insights into the interaction between genotype and phenotype, enabling a deeper understanding of the underlying biological mechanisms at play. We make our code public at: https://github.com/ajv012/SurvPath.
Authors: Bruce X. B. Yu, Jianlong Chang, Haixin Wang, Lingbo Liu, Shijie Wang, Zhiyu Wang, Junfan Lin, Lingxi Xie, Haojie Li, Zhouchen Lin, Qi Tian, Chang Wen Chen
Abstract: Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning.
Authors: Kim Hoang Tran, Anh Duy Le Dinh, Tien Phat Nguyen, Thinh Phan, Pha Nguyen, Khoa Luu, Donald Adjeroh, Gianfranco Doretto, Ngan Hoang Le
Abstract: Despite recent significant progress, Multi-Object Tracking (MOT) faces limitations such as reliance on prior knowledge and predefined categories and struggles with unseen objects. To address these issues, Generic Multiple Object Tracking (GMOT) has emerged as an alternative approach, requiring less prior information. However, current GMOT methods often rely on initial bounding boxes and struggle to handle variations in factors such as viewpoint, lighting, occlusion, and scale, among others. Our contributions commence with the introduction of the \textit{Referring GMOT dataset} a collection of videos, each accompanied by detailed textual descriptions of their attributes. Subsequently, we propose $\mathtt{Z-GMOT}$, a cutting-edge tracking solution capable of tracking objects from \textit{never-seen categories} without the need of initial bounding boxes or predefined categories. Within our $\mathtt{Z-GMOT}$ framework, we introduce two novel components: (i) $\mathtt{iGLIP}$, an improved Grounded language-image pretraining, for accurately detecting unseen objects with specific characteristics. (ii) $\mathtt{MA-SORT}$, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking objects with high similarity. Our contributions are benchmarked through extensive experiments conducted on the Referring GMOT dataset for GMOT task. Additionally, to assess the generalizability of the proposed $\mathtt{Z-GMOT}$, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models are released at: https://fsoft-aic.github.io/Z-GMOT.
Authors: Sainan Liu, Shan Lin, Jingpei Lu, Alexey Supikov, Michael Yip
Abstract: Implicit neural representations have become pivotal in robotic perception, enabling robots to comprehend 3D environments from 2D images. Given a set of camera poses and associated images, the models can be trained to synthesize novel, unseen views. To successfully navigate and interact in dynamic settings, robots require the understanding of their spatial surroundings driven by unassisted reconstruction of 3D scenes and camera poses from real-time video footage. Existing approaches like COLMAP and bundle-adjusting neural radiance field methods take hours to days to process due to the high computational demands of feature matching, dense point sampling, and training of a multi-layer perceptron structure with a large number of parameters. To address these challenges, we propose a framework called bundle-adjusting accelerated neural graphics primitives (BAA-NGP) which leverages accelerated sampling and hash encoding to expedite automatic pose refinement/estimation and 3D scene reconstruction. Experimental results demonstrate 10 to 20 x speed improvement compared to other bundle-adjusting neural radiance field methods without sacrificing the quality of pose estimation. The github repository can be found here https://github.com/IntelLabs/baa-ngp.
Authors: Jiabao Wang, Yuming Chen, Zhaohui Zheng, Xiang Li, Ming-Ming Cheng, Qibin Hou
Abstract: Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this paper, we present a general and effective prediction mimicking distillation scheme, called CrossKD, which delivers the intermediate features of the student's detection head to the teacher's detection head. The resulting cross-head predictions are then forced to mimic the teacher's predictions. This manner relieves the student's head from receiving contradictory supervision signals from the annotations and the teacher's predictions, greatly improving the student's detection performance. Moreover, as mimicking the teacher's predictions is the target of KD, CrossKD offers more task-oriented information in contrast with feature imitation. On MS COCO, with only prediction mimicking losses applied, our CrossKD boosts the average precision of GFL ResNet-50 with 1x training schedule from 40.2 to 43.7, outperforming all existing KD methods. In addition, our method also works well when distilling detectors with heterogeneous backbones. Code is available at https://github.com/jbwang1997/CrossKD.
Authors: Tong Li, Hansen Feng, Lizhi Wang, Zhiwei Xiong, Hua Huang
Abstract: Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion. Recently, the emerging diffusion model has achieved state-of-the-art performance in various tasks and demonstrates great potential for image denoising. However, stimulating diffusion models for image denoising is not straightforward and requires solving several critical problems. For one thing, the input inconsistency hinders the connection between diffusion models and image denoising. For another, the content inconsistency between the generated image and the desired denoised image introduces distortion. To tackle these problems, we present a novel strategy called the Diffusion Model for Image Denoising (DMID) by understanding and rethinking the diffusion model from a denoising perspective. Our DMID strategy includes an adaptive embedding method that embeds the noisy image into a pre-trained unconditional diffusion model and an adaptive ensembling method that reduces distortion in the denoised image. Our DMID strategy achieves state-of-the-art performance on both distortion-based and perception-based metrics, for both Gaussian and real-world image denoising.The code is available at https://github.com/Li-Tong-621/DMID.
Authors: Sagnik Majumder, Ziad Al-Halah, Kristen Grauman
Abstract: We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio through the synergy of audio and vision, thereby learning useful spatial relationships between the two modalities. We use our pretrained features to tackle two downstream video tasks requiring spatial understanding in social scenarios: active speaker detection and spatial audio denoising. Through extensive experiments, we show that our features are generic enough to improve over multiple state-of-the-art baselines on both tasks on two challenging egocentric video datasets that offer binaural audio, EgoCom and EasyCom. Project: http://vision.cs.utexas.edu/projects/ego_av_corr.
Authors: Xingzhe Su, Daixi Jia, Fengge Wu, Junsuo Zhao, Changwen Zheng, Wenwen Qiang
Abstract: Diffusion Models are a potent class of generative models capable of producing high-quality images. However, they often inadvertently favor certain data attributes, undermining the diversity of generated images. This issue is starkly apparent in skewed datasets like CelebA, where the initial dataset disproportionately favors females over males by 57.9%, this bias amplified in generated data where female representation outstrips males by 148%. In response, we propose a plug-and-play method named Manifold Guidance Sampling, which is also the first unsupervised method to mitigate bias issue in DDPMs. Leveraging the inherent structure of the data manifold, this method steers the sampling process towards a more uniform distribution, effectively dispersing the clustering of biased data. Without the need for modifying the existing model or additional training, it significantly mitigates data bias and enhances the quality and unbiasedness of the generated images.
Authors: Chaoyang Zhu, Long Chen
Abstract: As the most fundamental scene understanding tasks, object detection and segmentation have made tremendous progress in deep learning era. Due to the expensive manual labeling cost, the annotated categories in existing datasets are often small-scale and pre-defined, i.e., state-of-the-art fully-supervised detectors and segmentors fail to generalize beyond the closed vocabulary. To resolve this limitation, in the last few years, the community has witnessed an increasing attention toward Open-Vocabulary Detection (OVD) and Segmentation (OVS). By ``open-vocabulary'', we mean that the models can classify objects beyond pre-defined categories. In this survey, we provide a comprehensive review on recent developments of OVD and OVS. A taxonomy is first developed to organize different tasks and methodologies. We find that the permission and usage of weak supervision signals can well discriminate different methodologies, including: visual-semantic space mapping, novel visual feature synthesis, region-aware training, pseudo-labeling, knowledge distillation, and transfer learning. The proposed taxonomy is universal across different tasks, covering object detection, semantic/instance/panoptic segmentation, 3D and video understanding. The main design principles, key challenges, development routes, methodology strengths, and weaknesses are thoroughly analyzed. In addition, we benchmark each task along with the vital components of each method in appendix and updated online at https://github.com/seanzhuh/awesome-open-vocabulary-detection-and-segmentation. Finally, several promising directions are provided and discussed to stimulate future research.
URLs: https://github.com/seanzhuh/awesome-open-vocabulary-detection-and-segmentation.
Authors: Nikhil U. Shinde, Xiao Liang, Florian Richter, Michael C. Yip
Abstract: The ability to predict future states is crucial to informed decision-making while interacting with dynamic environments. With cameras providing a prevalent and information-rich sensing modality, the problem of predicting future states from image sequences has garnered a lot of attention. Current state-of-the-art methods typically train large parametric models for their predictions. Though often able to predict with accuracy these models often fail to provide interpretable confidence metrics around their predictions. Additionally these methods are reliant on the availability of large training datasets to converge to useful solutions. In this paper, we focus on the problem of predicting future images of an image sequence with interpretable confidence bounds from very little training data. To approach this problem, we use non-parametric models to take a probabilistic approach to image prediction. We generate probability distributions over sequentially predicted images, and propagate uncertainty through time to generate a confidence metric for our predictions. Gaussian Processes are used for their data efficiency and ability to readily incorporate new training data online. Our methods predictions are evaluated on a smooth fluid simulation environment. We showcase the capabilities of our approach on real world data by predicting pedestrian flows and weather patterns from satellite imagery.
Authors: Zixuan Pan, Jianxu Chen, Yiyu Shi
Abstract: Denoising diffusion probabilistic models have recently demonstrated state-of-the-art generative performance and have been used as strong pixel-level representation learners. This paper decomposes the interrelation between the generative capability and representation learning ability inherent in diffusion models. We present the masked diffusion model (MDM), a scalable self-supervised representation learner for semantic segmentation, substituting the conventional additive Gaussian noise of traditional diffusion with a masking mechanism. Our proposed approach convincingly surpasses prior benchmarks, demonstrating remarkable advancements in both medical and natural image semantic segmentation tasks, particularly in few-shot scenarios.
Authors: Shiyu Zhao, Samuel Schulter, Long Zhao, Zhixing Zhang, Vijay Kumar B. G, Yumin Suh, Manmohan Chandraker, Dimitris N. Metaxas
Abstract: Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). However, teacher-student self-training, a powerful and widely used paradigm to leverage PLs, is rarely explored for OVD. This work identifies two challenges of using self-training in OVD: noisy PLs from VLMs and frequent distribution changes of PLs. To address these challenges, we propose SAS-Det that tames self-training for OVD from two key perspectives. First, we present a split-and-fusion (SAF) head that splits a standard detection into an open-branch and a closed-branch. This design can reduce noisy supervision from pseudo boxes. Moreover, the two branches learn complementary knowledge from different training data, significantly enhancing performance when fused together. Second, in our view, unlike in closed-set tasks, the PL distributions in OVD are solely determined by the teacher model. We introduce a periodic update strategy to decrease the number of updates to the teacher, thereby decreasing the frequency of changes in PL distributions, which stabilizes the training process. Extensive experiments demonstrate SAS-Det is both efficient and effective. SAS-Det outperforms recent models of the same scale by a clear margin and achieves 37.4 AP50 and 29.1 APr on novel categories of the COCO and LVIS benchmarks, respectively. Code is available at \url{https://github.com/xiaofeng94/SAS-Det}.
Authors: Tonghui Zou, Lei Chen
Abstract: The translation of thermal infrared (TIR) images into visible light (VI) images plays a critical role in enhancing model performance and generalization capability, particularly in various fields such as registration and fusion of TIR and VI images. However, current research in this field faces challenges of insufficiently realistic image quality after translation and the difficulty of existing models in adapting to unseen scenarios. In order to develop a more generalizable image translation architecture, we conducted an analysis of existing translation architectures. By exploring the interpretability of intermediate modalities in existing translation architectures, we found that the intermediate modality in the image translation process for street scene images essentially performs semantic segmentation, distinguishing street images based on background and foreground patterns before assigning color information. Based on these principles, we propose an improved algorithm based on U-net called LadleNet. This network utilizes a two-stage U-net concatenation structure, consisting of Handle and Bowl modules. The Handle module is responsible for constructing an abstract semantic space, while the Bowl module decodes the semantic space to obtain the mapped VI image. Due to the characteristic of semantic segmentation, the Handle module has strong extensibility. Therefore, we also propose LadleNet+, which replaces the Handle module in LadleNet with a pre-trained DeepLabv3+ network, enabling the model to have a more powerful capability in constructing semantic space. The proposed methods were trained and tested on the KAIST dataset, followed by quantitative and qualitative analysis. Compared to existing methods, LadleNet and LadleNet+ achieved an average improvement of 12.4% and 15.2% in SSIM metrics, and 37.9% and 50.6% in MS-SSIM metrics, respectively.
Authors: Hu Yu, Jie Huang, Kaiwen Zheng, Feng Zhao
Abstract: Image dehazing is quite challenging in dense-haze scenarios, where quite less original information remains in the hazy image. Though previous methods have made marvelous progress, they still suffer from information loss in content and color in dense-haze scenarios. The recently emerged Denoising Diffusion Probabilistic Model (DDPM) exhibits strong generation ability, showing potential for solving this problem. However, DDPM fails to consider the physics property of dehazing task, limiting its information completion capacity. In this work, we propose DehazeDDPM: A DDPM-based and physics-aware image dehazing framework that applies to complex hazy scenarios. Specifically, DehazeDDPM works in two stages. The former stage physically models the dehazing task with the Atmospheric Scattering Model (ASM), pulling the distribution closer to the clear data and endowing DehazeDDPM with fog-aware ability. The latter stage exploits the strong generation ability of DDPM to compensate for the haze-induced huge information loss, by working in conjunction with the physical modelling. Extensive experiments demonstrate that our method attains state-of-the-art performance on both synthetic and real-world hazy datasets.
Authors: Ryota Yoshihashi, Yuya Otsuka, Kenji Doi, Tomohiro Tanaka, Hirokatsu Kataoka
Abstract: The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images. In semantic segmentation, one promising approach is extracting pseudo-masks from attention maps in text-to-image diffusion models, which enables real-image-and-annotation-free training. However, the pioneering training method using the diffusion-synthetic images and pseudo-masks, i.e., DiffuMask has limitations in terms of mask quality, scalability, and ranges of applicable domains. To overcome these limitations, this work introduces three techniques for diffusion-synthetic semantic segmentation training. First, reliability-aware robust training, originally used in weakly supervised learning, helps segmentation with insufficient synthetic mask quality. %Second, large-scale pretraining of whole segmentation models, not only backbones, on synthetic ImageNet-1k-class images with pixel-labels benefits downstream segmentation tasks. Second, we introduce prompt augmentation, data augmentation to the prompt text set to scale up and diversify training images with a limited text resources. Finally, LoRA-based adaptation of Stable Diffusion enables the transfer to a distant domain, e.g., auto-driving images. Experiments in PASCAL VOC, ImageNet-S, and Cityscapes show that our method effectively closes gap between real and synthetic training in semantic segmentation.
Authors: Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, Wenping Wang
Abstract: In this paper, we present a novel diffusion model called that generates multiview-consistent images from a single-view image. Using pretrained large-scale 2D diffusion models, recent work Zero123 demonstrates the ability to generate plausible novel views from a single-view image of an object. However, maintaining consistency in geometry and colors for the generated images remains a challenge. To address this issue, we propose a synchronized multiview diffusion model that models the joint probability distribution of multiview images, enabling the generation of multiview-consistent images in a single reverse process. SyncDreamer synchronizes the intermediate states of all the generated images at every step of the reverse process through a 3D-aware feature attention mechanism that correlates the corresponding features across different views. Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D.
Authors: Marcel B\"usching, Josef Bengtson, David Nilsson, M{\aa}rten Bj\"orkman
Abstract: We introduce FlowIBR, a novel approach for efficient monocular novel view synthesis of dynamic scenes. Existing techniques already show impressive rendering quality but tend to focus on optimization within a single scene without leveraging prior knowledge, resulting in long optimization times per scene. FlowIBR circumvents this limitation by integrating a neural image-based rendering method, pre-trained on a large corpus of widely available static scenes, with a per-scene optimized scene flow field. Utilizing this flow field, we bend the camera rays to counteract the scene dynamics, thereby presenting the dynamic scene as if it were static to the rendering network. The proposed method reduces per-scene optimization time by an order of magnitude, achieving comparable rendering quality to existing methods -- all on a single consumer-grade GPU.
Authors: Rong Li, ShiJie Li, Xieyuanli Chen, Teli Ma, Juergen Gall, Junwei Liang
Abstract: LiDAR semantic segmentation plays a crucial role in enabling autonomous driving and robots to understand their surroundings accurately and robustly. A multitude of methods exist within this domain, including point-based, range-image-based, polar-coordinate-based, and hybrid strategies. Among these, range-image-based techniques have gained widespread adoption in practical applications due to their efficiency. However, they face a significant challenge known as the ``many-to-one'' problem caused by the range image's limited horizontal and vertical angular resolution. As a result, around 20% of the 3D points can be occluded. In this paper, we present TFNet, a range-image-based LiDAR semantic segmentation method that utilizes temporal information to address this issue. Specifically, we incorporate a temporal fusion layer to extract useful information from previous scans and integrate it with the current scan. We then design a max-voting-based post-processing technique to correct false predictions, particularly those caused by the ``many-to-one'' issue. We evaluated the approach on two benchmarks and demonstrated that the plug-in post-processing technique is generic and can be applied to various networks.
Authors: Fei Pan, Xu Yin, Seokju Lee, Axi Niu, Sungeui Yoon, In So Kweon
Abstract: Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain contains unlabeled video frames. Drawing upon recent advancements of self-supervised learning of the object motion from unlabeled videos with geometric constraint, we design a \textbf{Mo}tion-guided \textbf{D}omain \textbf{A}daptive semantic segmentation framework (MoDA). MoDA harnesses the self-supervised object motion cues to facilitate cross-domain alignment for segmentation task. First, we present an object discovery module to localize and segment target moving objects using object motion information. Then, we propose a semantic mining module that takes the object masks to refine the pseudo labels in the target domain. Subsequently, these high-quality pseudo labels are used in the self-training loop to bridge the cross-domain gap. On domain adaptive video and image segmentation experiments, MoDA shows the effectiveness utilizing object motion as guidance for domain alignment compared with optical flow information. Moreover, MoDA exhibits versatility as it can complement existing state-of-the-art UDA approaches. Code at https://github.com/feipanir/MoDA.
Authors: Ben Lonnqvist, Zhengqing Wu, Michael H. Herzog
Abstract: Humans are able to segment images effortlessly without supervision using perceptual grouping. In this work, we propose a counter-intuitive computational approach to solving unsupervised perceptual grouping and segmentation: that they arise \textit{because} of neural noise, rather than in spite of it. We (1) mathematically demonstrate that under realistic assumptions, neural noise can be used to separate objects from each other; (2) that adding noise in a DNN enables the network to segment images even though it was never trained on any segmentation labels; and (3) that segmenting objects using noise results in segmentation performance that aligns with the perceptual grouping phenomena observed in humans, and is sample-efficient. We introduce the Good Gestalt (GG) datasets -- six datasets designed to specifically test perceptual grouping, and show that our DNN models reproduce many important phenomena in human perception, such as illusory contours, closure, continuity, proximity, and occlusion. Finally, we (4) show that our model improves performance on our GG datasets compared to other tested unsupervised models by $24.9\%$. Together, our results suggest a novel unsupervised segmentation method requiring few assumptions, a new explanation for the formation of perceptual grouping, and a novel potential benefit of neural noise.
Authors: Nokyung Park, Daewon Chae, Jeongyong Shim, Sangpil Kim, Eun-Sol Kim, Jinkyu Kim
Abstract: Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and such auxiliary semantic cues can be used as effective pivot embedding for domain generalization problem. However, they use pivot embedding in global manner (i.e., aligning an image embedding with sentence-level text embedding), not fully utilizing the semantic cues of given text description. In this work, we advocate for the use of local alignment between image regions and corresponding textual descriptions. To this end, we first represent image and text inputs with graphs. We subsequently cluster nodes in those graphs and match the graph-based image node features into textual graphs. This matching process is conducted globally and locally, tightly aligning visual and textual semantic sub-structures. We experiment with large-scale public datasets, such as CUB-DG and DomainBed, and our model achieves matched or better state-of-the-art performance on these datasets. Our code will be publicly available upon publication.
Authors: Yefei He, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang
Abstract: Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues. Quantization is a dominant way to compress and accelerate diffusion models, where post-training quantization (PTQ) and quantization-aware training (QAT) are two main approaches, each bearing its own properties. While PTQ exhibits efficiency in terms of both time and data usage, it may lead to diminished performance in low bit-width. On the other hand, QAT can alleviate performance degradation but comes with substantial demands on computational and data resources. In this paper, we introduce a data-free and parameter-efficient fine-tuning framework for low-bit diffusion models, dubbed EfficientDM, to achieve QAT-level performance with PTQ-like efficiency. Specifically, we propose a quantization-aware variant of the low-rank adapter (QALoRA) that can be merged with model weights and jointly quantized to low bit-width. The fine-tuning process distills the denoising capabilities of the full-precision model into its quantized counterpart, eliminating the requirement for training data. We also introduce scale-aware optimization and temporal learned step-size quantization to further enhance performance. Extensive experimental results demonstrate that our method significantly outperforms previous PTQ-based diffusion models while maintaining similar time and data efficiency. Specifically, there is only a 0.05 sFID increase when quantizing both weights and activations of LDM-4 to 4-bit on ImageNet 256x256. Compared to QAT-based methods, our EfficientDM also boasts a 16.2x faster quantization speed with comparable generation quality. Code is available at \href{https://github.com/ThisisBillhe/EfficientDM}{this hrl}.
Authors: Haiping Wang, Yuan Liu, Bing Wang, Yujing Sun, Zhen Dong, Wenping Wang, Bisheng Yang
Abstract: Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration. However, due to the modality difference between images and points, it is difficult to learn robust and discriminative cross-modality features by existing metric learning methods for feature matching. Instead of applying metric learning on cross-modality data, we propose to unify the modality between images and point clouds by pretrained large-scale models first, and then establish robust correspondence within the same modality. We show that the intermediate features, called diffusion features, extracted by depth-to-image diffusion models are semantically consistent between images and point clouds, which enables the building of coarse but robust cross-modality correspondences. We further extract geometric features on depth maps produced by the monocular depth estimator. By matching such geometric features, we significantly improve the accuracy of the coarse correspondences produced by diffusion features. Extensive experiments demonstrate that without any task-specific training, direct utilization of both features produces accurate image-to-point cloud registration. On three public indoor and outdoor benchmarks, the proposed method averagely achieves a 20.6 percent improvement in Inlier Ratio, a three-fold higher Inlier Number, and a 48.6 percent improvement in Registration Recall than existing state-of-the-arts.
Authors: Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, Huaizu Jiang
Abstract: We present a novel approach named OmniControl for incorporating flexible spatial control signals into a text-conditioned human motion generation model based on the diffusion process. Unlike previous methods that can only control the pelvis trajectory, OmniControl can incorporate flexible spatial control signals over different joints at different times with only one model. Specifically, we propose analytic spatial guidance that ensures the generated motion can tightly conform to the input control signals. At the same time, realism guidance is introduced to refine all the joints to generate more coherent motion. Both the spatial and realism guidance are essential and they are highly complementary for balancing control accuracy and motion realism. By combining them, OmniControl generates motions that are realistic, coherent, and consistent with the spatial constraints. Experiments on HumanML3D and KIT-ML datasets show that OmniControl not only achieves significant improvement over state-of-the-art methods on pelvis control but also shows promising results when incorporating the constraints over other joints.
Authors: Iuliia Kotseruba, John K. Tsotsos
Abstract: To further advance driver monitoring and assistance systems, it is important to understand how drivers allocate their attention, in other words, where do they tend to look and why. Traditionally, factors affecting human visual attention have been divided into bottom-up (involuntary attraction to salient regions) and top-down (driven by the demands of the task being performed). Although both play a role in directing drivers' gaze, most of the existing models for drivers' gaze prediction apply techniques developed for bottom-up saliency and do not consider influences of the drivers' actions explicitly. Likewise, common driving attention benchmarks lack relevant annotations for drivers' actions and the context in which they are performed. Therefore, to enable analysis and modeling of these factors for drivers' gaze prediction, we propose the following: 1) we correct the data processing pipeline used in DR(eye)VE to reduce noise in the recorded gaze data; 2) we then add per-frame labels for driving task and context; 3) we benchmark a number of baseline and SOTA models for saliency and driver gaze prediction and use new annotations to analyze how their performance changes in scenarios involving different tasks; and, lastly, 4) we develop a novel model that modulates drivers' gaze prediction with explicit action and context information. While reducing noise in the DR(eye)VE gaze data improves results of all models, we show that using task information in our proposed model boosts performance even further compared to bottom-up models on the cleaned up data, both overall (by 24% KLD and 89% NSS) and on scenarios that involve performing safety-critical maneuvers and crossing intersections (by up to 10--30% KLD). Extended annotations and code are available at https://github.com/ykotseruba/SCOUT.
Authors: Yangyang Guo, Fangkai Jiao, Zhiqi Shen, Liqiang Nie, Mohan Kankanhalli
Abstract: Teaching Visual Question Answering (VQA) models to refrain from answering unanswerable questions is necessary for building a trustworthy AI system. Existing studies, though have explored various aspects of VQA but somewhat ignored this particular attribute. This paper aims to bridge the research gap by contributing a comprehensive dataset, called UNK-VQA. The dataset is specifically designed to address the challenge of questions that models do not know. To this end, we first augment the existing data via deliberate perturbations on either the image or question. In specific, we carefully ensure that the question-image semantics remain close to the original unperturbed distribution. By this means, the identification of unanswerable questions becomes challenging, setting our dataset apart from others that involve mere image replacement. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models and discover their significant limitations when applied to our dataset. Additionally, we also propose a straightforward method to tackle these unanswerable questions. This dataset, we believe, will serve as a valuable benchmark for enhancing the abstention capability of VQA models, thereby leading to increased trustworthiness of AI systems. We have made the dataset (https://github.com/guoyang9/UNK-VQA) available to facilitate further exploration in this area.
Authors: Yue Cao, Tianlin Li, Xiaofeng Cao, Ivor Tsang, Yang Liu, Qing Guo
Abstract: We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical transformation. The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks. To validate this concept, we present a comprehensive study on leveraging image resampling to defend against adversarial attacks. We have developed basic resampling methods that employ interpolation strategies and coordinate shifting magnitudes. Our analysis reveals that these basic methods can partially mitigate adversarial attacks. However, they come with apparent limitations: the accuracy of clean images noticeably decreases, while the improvement in accuracy on adversarial examples is not substantial. We propose implicit representation-driven image resampling (IRAD) to overcome these limitations. First, we construct an implicit continuous representation that enables us to represent any input image within a continuous coordinate space. Second, we introduce SampleNet, which automatically generates pixel-wise shifts for resampling in response to different inputs. Furthermore, we can extend our approach to the state-of-the-art diffusion-based method, accelerating it with fewer time steps while preserving its defense capability. Extensive experiments demonstrate that our method significantly enhances the adversarial robustness of diverse deep models against various attacks while maintaining high accuracy on clean images.
Authors: David Stotko, Nils Wandel, Reinhard Klein
Abstract: 3D reconstruction of dynamic scenes is a long-standing problem in computer graphics and increasingly difficult the less information is available. Shape-from-Template (SfT) methods aim to reconstruct a template-based geometry from RGB images or video sequences, often leveraging just a single monocular camera without depth information, such as regular smartphone recordings. Unfortunately, existing reconstruction methods are either unphysical and noisy or slow in optimization. To solve this problem, we propose a novel SfT reconstruction algorithm for cloth using a pre-trained neural surrogate model that is fast to evaluate, stable, and produces smooth reconstructions due to a regularizing physics simulation. Differentiable rendering of the simulated mesh enables pixel-wise comparisons between the reconstruction and a target video sequence that can be used for a gradient-based optimization procedure to extract not only shape information but also physical parameters such as stretching, shearing, or bending stiffness of the cloth. This allows to retain a precise, stable, and smooth reconstructed geometry while reducing the runtime by a factor of 400-500 compared to $\phi$-SfT, a state-of-the-art physics-based SfT approach.
Authors: Kecen Li, Chen Gong, Zhixiang Li, Yuzhong Zhao, Xinwen Hou, Tianhao Wang
Abstract: Differential Privacy (DP) image data synthesis, which leverages the DP technique to generate synthetic data to replace the sensitive data, allowing organizations to share and utilize synthetic images without privacy concerns. Previous methods incorporate the advanced techniques of generative models and pre-training on a public dataset to produce exceptional DP image data, but suffer from problems of unstable training and massive computational resource demands. This paper proposes a novel DP image synthesis method, termed PRIVIMAGE, which meticulously selects pre-training data, promoting the efficient creation of DP datasets with high fidelity and utility. PRIVIMAGE first establishes a semantic query function using a public dataset. Then, this function assists in querying the semantic distribution of the sensitive dataset, facilitating the selection of data from the public dataset with analogous semantics for pre-training. Finally, we pre-train an image generative model using the selected data and then fine-tune this model on the sensitive dataset using Differentially Private Stochastic Gradient Descent (DP-SGD). PRIVIMAGE allows us to train a lightly parameterized generative model, reducing the noise in the gradient during DP-SGD training and enhancing training stability. Extensive experiments demonstrate that PRIVIMAGE uses only 1% of the public dataset for pre-training and 7.6% of the parameters in the generative model compared to the state-of-the-art method, whereas achieves superior synthetic performance and conserves more computational resources. On average, PRIVIMAGE achieves 30.1% lower FID and 12.6% higher Classification Accuracy than the state-of-the-art method. The replication package and datasets can be accessed online.
Authors: Konstantin Klemmer, Esther Rolf, Caleb Robinson, Lester Mackey, Marc Ru{\ss}wurm
Abstract: Geographic information is essential for modeling tasks in fields ranging from ecology to epidemiology. However, extracting relevant location characteristics for a given task can be challenging, often requiring expensive data fusion or distillation from massive global imagery datasets. To address this challenge, we introduce Satellite Contrastive Location-Image Pretraining (SatCLIP). This global, general-purpose geographic location encoder learns an implicit representation of locations by matching CNN and ViT inferred visual patterns of openly available satellite imagery with their geographic coordinates. The resulting SatCLIP location encoder efficiently summarizes the characteristics of any given location for convenient use in downstream tasks. In our experiments, we use SatCLIP embeddings to improve prediction performance on nine diverse location-dependent tasks including temperature prediction, animal recognition, and population density estimation. Across tasks, SatCLIP consistently outperforms alternative location encoders and improves geographic generalization by encoding visual similarities of spatially distant environments. These results demonstrate the potential of vision-location models to learn meaningful representations of our planet from the vast, varied, and largely untapped modalities of geospatial data.
Authors: Zuoyan Zhao, Hui Xue, Pengfei Fang, Shipeng Zhu
Abstract: Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task. Two factors in scene text images, visual structure and semantic information, affect the recognition performance significantly. To mitigate the effects from these factors, this paper proposes a Prior-Enhanced Attention Network (PEAN). Specifically, an attention-based modulation module is leveraged to understand scene text images by neatly perceiving the local and global dependence of images, despite the shape of the text. Meanwhile, a diffusion-based module is developed to enhance the text prior, hence offering better guidance for the SR network to generate SR images with higher semantic accuracy. Additionally, a multi-task learning paradigm is employed to optimize the network, enabling the model to generate legible SR images. As a result, PEAN establishes new SOTA results on the TextZoom benchmark. Experiments are also conducted to analyze the importance of the enhanced text prior as a means of improving the performance of the SR network. Code will be made available at https://github.com/jdfxzzy/PEAN.
Authors: Xiaowei Chi, Rongyu Zhang, Zhengkai Jiang, Yijiang Liu, Yatian Wang, Xingqun Qi, Wenhan Luo, Peng Gao, Shanghang Zhang, Qifeng Liu, Yike Guo
Abstract: While current LLM chatbots like GPT-4V bridge the gap between human instructions and visual representations to enable text-image generations, they still lack efficient alignment methods for high-fidelity performance on multiple downstream tasks. In this paper, we propose \textbf{$M^{2}Chat$}, a novel unified multimodal LLM framework for generating interleaved text-image conversation across various scenarios. Specifically, we propose an $M^{3}Adapter$ that efficiently integrates granular low-level visual information and high-level semantic features from multi-modality prompts. Upon the well-aligned fused feature, $M^{3}Adapter$ tailors a learnable gating strategy to balance the model creativity and consistency across various tasks adaptively. Moreover, to further enhance the effectiveness of $M^{3}Adapter$ while preserving the coherence of semantic context comprehension, we introduce a two-stage $M^{3}FT$ fine-tuning strategy. This strategy optimizes disjoint groups of parameters for image-text alignment and visual-instruction respectively. Extensive experiments demonstrate our $M^{2}Chat$ surpasses state-of-the-art counterparts across diverse benchmarks, showcasing its prowess in interleaving generation, storytelling, and multimodal dialogue systems. The demo and code are available at \red{https://mattie-e.github.io/M2Chat.github.io}.
Authors: Ziyu Wang, Yue Xu, Cewu Lu, Yong-Lu Li
Abstract: Recently, dataset distillation has paved the way towards efficient machine learning, especially for image datasets. However, the distillation for videos, characterized by an exclusive temporal dimension, remains an underexplored domain. In this work, we provide the first systematic study of video distillation and introduce a taxonomy to categorize temporal compression. Our investigation reveals that the temporal information is usually not well learned during distillation, and the temporal dimension of synthetic data contributes little. The observations motivate our unified framework of disentangling the dynamic and static information in the videos. It first distills the videos into still images as static memory and then compensates the dynamic and motion information with a learnable dynamic memory block. Our method achieves state-of-the-art on video datasets at different scales, with a notably smaller memory storage budget. Our code is available at https://github.com/yuz1wan/video_distillation.
Authors: Michael A. Alcorn, Noah Schwartz
Abstract: To achieve strong real world performance, neural networks must be trained on large, diverse datasets; however, obtaining and annotating such datasets is costly and time-consuming, particularly for 3D point clouds. In this paper, we describe Paved2Paradise, a simple, cost-effective approach for generating fully labeled, diverse, and realistic lidar datasets from scratch, all while requiring minimal human annotation. Our key insight is that, by deliberately collecting separate "background" and "object" datasets (i.e., "factoring the real world"), we can intelligently combine them to produce a combinatorially large and diverse training set. The Paved2Paradise pipeline thus consists of four steps: (1) collecting copious background data, (2) recording individuals from the desired object class(es) performing different behaviors in an isolated environment (like a parking lot), (3) bootstrapping labels for the object dataset, and (4) generating samples by placing objects at arbitrary locations in backgrounds. To demonstrate the utility of Paved2Paradise, we generated synthetic datasets for two tasks: (1) human detection in orchards (a task for which no public data exists) and (2) pedestrian detection in urban environments. Qualitatively, we find that a model trained exclusively on Paved2Paradise synthetic data is highly effective at detecting humans in orchards, including when individuals are heavily occluded by tree branches. Quantitatively, a model trained on Paved2Paradise data that sources backgrounds from KITTI performs comparably to a model trained on the actual dataset. These results suggest the Paved2Paradise synthetic data pipeline can help accelerate point cloud model development in sectors where acquiring lidar datasets has previously been cost-prohibitive.
Authors: Min Yang, Huan Gao, Ping Guo, Limin Wang
Abstract: Vision Transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it remains unclear how to adapt these pre-trained short-term ViTs for temporal action detection (TAD) in untrimmed videos. The existing works treat them as off-the-shelf feature extractors for each short-trimmed snippet without capturing the fine-grained relation among different snippets in a broader temporal context. To mitigate this issue, this paper focuses on designing a new mechanism for adapting these pre-trained ViT models as a unified long-form video transformer to fully unleash its modeling power in capturing inter-snippet relation, while still keeping low computation overhead and memory consumption for efficient TAD. To this end, we design effective cross-snippet propagation modules to gradually exchange short-term video information among different snippets from two levels. For inner-backbone information propagation, we introduce a cross-snippet propagation strategy to enable multi-snippet temporal feature interaction inside the backbone.For post-backbone information propagation, we propose temporal transformer layers for further clip-level modeling. With the plain ViT-B pre-trained with VideoMAE, our end-to-end temporal action detector (ViT-TAD) yields a very competitive performance to previous temporal action detectors, riching up to 69.5 average mAP on THUMOS14, 37.40 average mAP on ActivityNet-1.3 and 17.20 average mAP on FineAction.
Authors: Haodong Zhang, ZhiKe Chen, Haocheng Xu, Lei Hao, Xiaofei Wu, Songcen Xu, Zhensong Zhang, Yue Wang, Rong Xiong
Abstract: Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level representations. Here, we present a novel Semantics-aware Motion reTargeting (SMT) method with the advantage of vision-language models to extract and maintain meaningful motion semantics. We utilize a differentiable module to render 3D motions. Then the high-level motion semantics are incorporated into the motion retargeting process by feeding the vision-language model with the rendered images and aligning the extracted semantic embeddings. To ensure the preservation of fine-grained motion details and high-level semantics, we adopt a two-stage pipeline consisting of skeleton-aware pre-training and fine-tuning with semantics and geometry constraints. Experimental results show the effectiveness of the proposed method in producing high-quality motion retargeting results while accurately preserving motion semantics.
Authors: Guofeng Mei, Luigi Riz, Yiming Wang, Fabio Poiesi
Abstract: Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs). Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking the inherent and expressible point cloud geometric structure. Geometrically similar or close regions can be exploited for bolstering point cloud understanding as they are likely to share semantic information. To this end, we introduce the first training-free aggregation technique that leverages the point cloud's 3D geometric structure to improve the quality of the transferred Vision-Language Models. Our approach operates iteratively, performing local-to-global aggregation based on geometric and semantic point-level reasoning. We benchmark our approach on three downstream tasks, including classification, part segmentation, and semantic segmentation, with a variety of datasets representing both synthetic/real-world, and indoor/outdoor scenarios. Our approach achieves new state-of-the-art results in all benchmarks. Our approach operates iteratively, performing local-to-global aggregation based on geometric and semantic point-level reasoning. Code and dataset are available at https://luigiriz.github.io/geoze-website/
Authors: Jialong Zuo, Hanyu Zhou, Ying Nie, Feng Zhang, Tianyu Guo, Nong Sang, Yunhe Wang, Changxin Gao
Abstract: Existing text-based person retrieval datasets often have relatively coarse-grained text annotations. This hinders the model to comprehend the fine-grained semantics of query texts in real scenarios. To address this problem, we contribute a new benchmark named \textbf{UFineBench} for text-based person retrieval with ultra-fine granularity. Firstly, we construct a new \textbf{dataset} named UFine6926. We collect a large number of person images and manually annotate each image with two detailed textual descriptions, averaging 80.8 words each. The average word count is three to four times that of the previous datasets. In addition of standard in-domain evaluation, we also propose a special \textbf{evaluation paradigm} more representative of real scenarios. It contains a new evaluation set with cross domains, cross textual granularity and cross textual styles, named UFine3C, and a new evaluation metric for accurately measuring retrieval ability, named mean Similarity Distribution (mSD). Moreover, we propose CFAM, a more efficient \textbf{algorithm} especially designed for text-based person retrieval with ultra fine-grained texts. It achieves fine granularity mining by adopting a shared cross-modal granularity decoder and hard negative match mechanism. With standard in-domain evaluation, CFAM establishes competitive performance across various datasets, especially on our ultra fine-grained UFine6926. Furthermore, by evaluating on UFine3C, we demonstrate that training on our UFine6926 significantly improves generalization to real scenarios compared with other coarse-grained datasets. The dataset and code will be made publicly available at \url{https://github.com/Zplusdragon/UFineBench}.
Authors: Sachit Menon, Ishan Misra, Rohit Girdhar
Abstract: We introduce the new task of generating Illustrated Instructions, i.e., visual instructions customized to a user's needs. We identify desiderata unique to this task, and formalize it through a suite of automatic and human evaluation metrics, designed to measure the validity, consistency, and efficacy of the generations. We combine the power of large language models (LLMs) together with strong text-to-image generation diffusion models to propose a simple approach called StackedDiffusion, which generates such illustrated instructions given text as input. The resulting model strongly outperforms baseline approaches and state-of-the-art multimodal LLMs; and in 30% of cases, users even prefer it to human-generated articles. Most notably, it enables various new and exciting applications far beyond what static articles on the web can provide, such as personalized instructions complete with intermediate steps and pictures in response to a user's individual situation.
Authors: Thuan Hoang Nguyen, Anh Tran
Abstract: Despite their ability to generate high-resolution and diverse images from text prompts, text-to-image diffusion models often suffer from slow iterative sampling processes. Model distillation is one of the most effective directions to accelerate these models. However, previous distillation methods fail to retain the generation quality while requiring a significant amount of images for training, either from real data or synthetically generated by the teacher model. In response to this limitation, we present a novel image-free distillation scheme named $\textbf{SwiftBrush}$. Drawing inspiration from text-to-3D synthesis, in which a 3D neural radiance field that aligns with the input prompt can be obtained from a 2D text-to-image diffusion prior via a specialized loss without the use of any 3D data ground-truth, our approach re-purposes that same loss for distilling a pretrained multi-step text-to-image model to a student network that can generate high-fidelity images with just a single inference step. In spite of its simplicity, our model stands as one of the first one-step text-to-image generators that can produce images of comparable quality to Stable Diffusion without reliance on any training image data. Remarkably, SwiftBrush achieves an FID score of $\textbf{16.67}$ and a CLIP score of $\textbf{0.29}$ on the COCO-30K benchmark, achieving competitive results or even substantially surpassing existing state-of-the-art distillation techniques.
Authors: Haokai Pang, Heming Zhu, Adam Kortylewski, Christian Theobalt, Marc Habermann
Abstract: Real-time rendering of photorealistic and controllable human avatars stands as a cornerstone in Computer Vision and Graphics. While recent advances in neural implicit rendering have unlocked unprecedented photorealism for digital avatars, real-time performance has mostly been demonstrated for static scenes only. To address this, we propose ASH, an animatable Gaussian splatting approach for photorealistic rendering of dynamic humans in real-time. We parameterize the clothed human as animatable 3D Gaussians, which can be efficiently splatted into image space to generate the final rendering. However, naively learning the Gaussian parameters in 3D space poses a severe challenge in terms of compute. Instead, we attach the Gaussians onto a deformable character model, and learn their parameters in 2D texture space, which allows leveraging efficient 2D convolutional architectures that easily scale with the required number of Gaussians. We benchmark ASH with competing methods on pose-controllable avatars, demonstrating that our method outperforms existing real-time methods by a large margin and shows comparable or even better results than offline methods.
Authors: Ravidu Suien Rammuni Silva, Jordan J. Bird
Abstract: Explainability is an aspect of modern AI that is vital for impact and usability in the real world. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network (CNN) based models. Existing methods of explaining CNN predictions are mostly based on Gradient-weighted Class Activation Maps (Grad-CAM) and solely focus on a single target class. We show that from the point of the target class selection, we make an assumption on the prediction process, hence neglecting a large portion of the predictor CNN model's thinking process. In this paper, we present an exhaustive methodology called Fused Multi-class Gradient-weighted Class Activation Map (FM-G-CAM) that considers multiple top predicted classes, which provides a holistic explanation of the predictor CNN's thinking rationale. We also provide a detailed and comprehensive mathematical and algorithmic description of our method. Furthermore, along with a concise comparison of existing methods, we compare FM-G-CAM with Grad-CAM, highlighting its benefits through real-world practical use cases. Finally, we present an open-source Python library with FM-G-CAM implementation to conveniently generate saliency maps for CNN-based model predictions.
Authors: Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov
Abstract: A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for various downstream tasks. We find that despite their conceptual differences, these models can be effectively merged into a unified model through multi-teacher distillation. We name this approach AM-RADIO (Agglomerative Model -- Reduce All Domains Into One). This integrative approach not only surpasses the performance of individual teacher models but also amalgamates their distinctive features, such as zero-shot vision-language comprehension, detailed pixel-level understanding, and open vocabulary segmentation capabilities. In pursuit of the most hardware-efficient backbone, we evaluated numerous architectures in our multi-teacher distillation pipeline using the same training recipe. This led to the development of a novel architecture (E-RADIO) that exceeds the performance of its predecessors and is at least 7x faster than the teacher models. Our comprehensive benchmarking process covers downstream tasks including ImageNet classification, ADE20k semantic segmentation, COCO object detection and LLaVa-1.5 framework. Code: https://github.com/NVlabs/RADIO
Authors: Hidenobu Matsuki, Riku Murai, Paul H. J. Kelly, Andrew J. Davison
Abstract: We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the required representation for accurate, efficient tracking, mapping, and high-quality rendering. Designed for challenging monocular settings, our approach is seamlessly extendable to RGB-D SLAM when an external depth sensor is available. Several innovations are required to continuously reconstruct 3D scenes with high fidelity from a live camera. First, to move beyond the original 3DGS algorithm, which requires accurate poses from an offline Structure from Motion (SfM) system, we formulate camera tracking for 3DGS using direct optimisation against the 3D Gaussians, and show that this enables fast and robust tracking with a wide basin of convergence. Second, by utilising the explicit nature of the Gaussians, we introduce geometric verification and regularisation to handle the ambiguities occurring in incremental 3D dense reconstruction. Finally, we introduce a full SLAM system which not only achieves state-of-the-art results in novel view synthesis and trajectory estimation but also reconstruction of tiny and even transparent objects.
Authors: Hallee E. Wong, Marianne Rakic, John Guttag, Adrian V. Dalca
Abstract: Biomedical image segmentation is a crucial part of both scientific research and clinical care. With enough labelled data, deep learning models can be trained to accurately automate specific biomedical image segmentation tasks. However, manually segmenting images to create training data is highly labor intensive and requires domain expertise. We present ScribblePrompt, a flexible neural network based interactive segmentation tool for biomedical imaging that enables human annotators to segment previously unseen structures using scribbles, clicks, and bounding boxes. Through rigorous quantitative experiments, we demonstrate that given comparable amounts of interaction, ScribblePrompt produces more accurate segmentations than previous methods on datasets unseen during training. In a user study with domain experts, ScribblePrompt reduced annotation time by 28% while improving Dice by 15% compared to the next best method. ScribblePrompt's success rests on a set of careful design decisions. These include a training strategy that incorporates both a highly diverse set of images and tasks, novel algorithms for simulated user interactions and labels, and a network that enables fast inference. We showcase ScribblePrompt in an online demo and provide code at https://scribbleprompt.csail.mit.edu
Authors: Zixian Su, Jingwei Guo, Kai Yao, Xi Yang, Qiufeng Wang, Kaizhu Huang
Abstract: While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely introduce source statistics to mitigate this issue, the fundamental problem of inaccurate target estimation still persists, leaving the intrinsic test-time domain shifts unresolved. This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from the substantially reduced class diversity in batch. Drawing upon this insight, we introduce a straightforward tool, Test-time Exponential Moving Average (TEMA), to bridge the class diversity gap between training and testing batches. Importantly, our TEMA adaptively extends the scope of typical methods beyond the current batch to incorporate a diverse set of class information, which in turn boosts an accurate target estimation. Built upon this foundation, we further design a novel layer-wise rectification strategy to consistently promote test-time performance. Our proposed method enjoys a unique advantage as it requires neither training nor tuning parameters, offering a truly hassle-free solution. It significantly enhances model robustness against shifted domains and maintains resilience in diverse real-world scenarios with various batch sizes, achieving state-of-the-art performance on several major benchmarks. Code is available at \url{https://github.com/kiwi12138/RealisticTTA}.
Authors: Xiaoxu Xu, Yitian Yuan, Qiudan Zhang, Wenhui Wu, Zequn Jie, Lin Ma, Xu Wang
Abstract: Learning to ground natural language queries to target objects or regions in 3D point clouds is quite essential for 3D scene understanding. Nevertheless, existing 3D visual grounding approaches require a substantial number of bounding box annotations for text queries, which is time-consuming and labor-intensive to obtain. In this paper, we propose \textbf{3D-VLA}, a weakly supervised approach for \textbf{3D} visual grounding based on \textbf{V}isual \textbf{L}inguistic \textbf{A}lignment. Our 3D-VLA exploits the superior ability of current large-scale vision-language models (VLMs) on aligning the semantics between texts and 2D images, as well as the naturally existing correspondences between 2D images and 3D point clouds, and thus implicitly constructs correspondences between texts and 3D point clouds with no need for fine-grained box annotations in the training procedure. During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images. To the best of our knowledge, this is the first work to investigate 3D visual grounding in a weakly supervised manner by involving large scale vision-language models, and extensive experiments on ReferIt3D and ScanRefer datasets demonstrate that our 3D-VLA achieves comparable and even superior results over the fully supervised methods.
Authors: Soopil Kim, Sion An, Philip Chikontwe, Myeongkyun Kang, Ehsan Adeli, Kilian M. Pohl, Sang Hyun Park
Abstract: Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately such anomalies requires models to reason about various component types through segmentation. However, curation of pixel-level annotations for semantic segmentation is both time-consuming and expensive. Although there are some prior few-shot or unsupervised co-part segmentation algorithms, they often fail on images with industrial object. These images have components with similar textures and shapes, and a precise differentiation proves challenging. In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints. To ensure consistent segmentation across unlabeled images, we employ a histogram matching loss in conjunction with an entropy loss. As segmentation predictions play a crucial role, we propose to enhance both local and global sample validity detection by capturing key aspects from visual semantics via three memory banks: class histograms, component composition embeddings and patch-level representations. For effective LA detection, we propose an adaptive scaling strategy to standardize anomaly scores from different memory banks in inference. Extensive experiments on the public benchmark MVTec LOCO AD reveal our method achieves 98.1% AUROC in LA detection vs. 89.6% from competing methods.
Authors: Shiyu Zhao, Long Zhao, Vijay Kumar B. G, Yumin Suh, Dimitris N. Metaxas, Manmohan Chandraker, Samuel Schulter
Abstract: The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective function has proven successful, but requires good positive and negative samples. However, the free-form nature and the open vocabulary of object descriptions make the space of negatives extremely large. Prior works randomly sample negatives or use rule-based techniques to build them. In contrast, we propose to leverage the vast knowledge built into modern generative models to automatically build negatives that are more relevant to the original data. Specifically, we use large-language-models to generate negative text descriptions, and text-to-image diffusion models to also generate corresponding negative images. Our experimental analysis confirms the relevance of the generated negative data, and its use in language-based detectors improves performance on two complex benchmarks. Code is available at \url{https://github.com/xiaofeng94/Gen-Enhanced-Negs}.
Authors: Rongqin Liang, Yuanman Li, Jiantao Zhou, Xia Li
Abstract: Traffic anomaly detection (TAD) in driving videos is critical for ensuring the safety of autonomous driving and advanced driver assistance systems. Previous single-stage TAD methods primarily rely on frame prediction, making them vulnerable to interference from dynamic backgrounds induced by the rapid movement of the dashboard camera. While two-stage TAD methods appear to be a natural solution to mitigate such interference by pre-extracting background-independent features (such as bounding boxes and optical flow) using perceptual algorithms, they are susceptible to the performance of first-stage perceptual algorithms and may result in error propagation. In this paper, we introduce TTHF, a novel single-stage method aligning video clips with text prompts, offering a new perspective on traffic anomaly detection. Unlike previous approaches, the supervised signal of our method is derived from languages rather than orthogonal one-hot vectors, providing a more comprehensive representation. Further, concerning visual representation, we propose to model the high frequency of driving videos in the temporal domain. This modeling captures the dynamic changes of driving scenes, enhances the perception of driving behavior, and significantly improves the detection of traffic anomalies. In addition, to better perceive various types of traffic anomalies, we carefully design an attentive anomaly focusing mechanism that visually and linguistically guides the model to adaptively focus on the visual context of interest, thereby facilitating the detection of traffic anomalies. It is shown that our proposed TTHF achieves promising performance, outperforming state-of-the-art competitors by +5.4% AUC on the DoTA dataset and achieving high generalization on the DADA dataset.
Authors: Ziwei Sun, Zexi Hua, Hengchao Li, Yan Li
Abstract: Aiming at the characteristics of the flying bird object in surveillance video, such as the single frame image feature is not obvious, the size is small in most cases, and asymmetric, this paper proposes a Flying Bird Object Detection method in Surveillance Video (FBOD-SV). Firstly, a new feature aggregation module, the Correlation Attention Feature Aggregation (Co-Attention-FA) module, is designed to aggregate the features of the flying bird object according to the bird object's correlation on multiple consecutive frames of images. Secondly, a Flying Bird Object Detection Network (FBOD-Net) with down-sampling and then up-sampling is designed, which uses a large feature layer that fuses fine spatial information and large receptive field information to detect special multi-scale (mostly small-scale) bird objects. Finally, the SimOTA dynamic label allocation method is applied to One-Category object detection, and the SimOTA-OC dynamic label strategy is proposed to solve the difficult problem of label allocation caused by irregular flying bird objects. In this paper, the algorithm's performance is verified by the experimental data set of the surveillance video of the flying bird object of the traction substation. The experimental results show that the surveillance video flying bird object detection method proposed in this paper effectively improves the detection performance of flying bird objects.
Authors: Guikun Chen, Wenguan Wang
Abstract: 3D Gaussian splatting (GS) has recently emerged as a transformative technique in the realm of explicit radiance field and computer graphics. This innovative approach, characterized by the utilization of millions of learnable 3D Gaussians, represents a significant departure from mainstream neural radiance field approaches, which predominantly use implicit, coordinate-based models to map spatial coordinates to pixel values. 3D GS, with its explicit scene representation and differentiable rendering algorithm, not only promises real-time rendering capability but also introduces unprecedented levels of editability. This positions 3D GS as a potential game-changer for the next generation of 3D reconstruction and representation. In the present paper, we provide the first systematic overview of the recent developments and critical contributions in the domain of 3D GS. We begin with a detailed exploration of the underlying principles and the driving forces behind the emergence of 3D GS, laying the groundwork for understanding its significance. A focal point of our discussion is the practical applicability of 3D GS. By enabling unprecedented rendering speed, 3D GS opens up a plethora of applications, ranging from virtual reality to interactive media and beyond. This is complemented by a comparative analysis of leading 3D GS models, evaluated across various benchmark tasks to highlight their performance and practical utility. The survey concludes by identifying current challenges and suggesting potential avenues for future research in this domain. Through this survey, we aim to provide a valuable resource for both newcomers and seasoned researchers, fostering further exploration and advancement in applicable and explicit radiance field representation.
Authors: Benjamin Hou, Tejas Sudharshan Mathai, Jianfei Liu, Christopher Parnell, Ronald M. Summers
Abstract: Purpose: Body composition measurements from routine abdominal CT can yield personalized risk assessments for asymptomatic and diseased patients. In particular, attenuation and volume measures of muscle and fat are associated with important clinical outcomes, such as cardiovascular events, fractures, and death. This study evaluates the reliability of an Internal tool for the segmentation of muscle and fat (subcutaneous and visceral) as compared to the well-established public TotalSegmentator tool. Methods: We assessed the tools across 900 CT series from the publicly available SAROS dataset, focusing on muscle, subcutaneous fat, and visceral fat. The Dice score was employed to assess accuracy in subcutaneous fat and muscle segmentation. Due to the lack of ground truth segmentations for visceral fat, Cohen's Kappa was utilized to assess segmentation agreement between the tools. Results: Our Internal tool achieved a 3% higher Dice (83.8 vs. 80.8) for subcutaneous fat and a 5% improvement (87.6 vs. 83.2) for muscle segmentation respectively. A Wilcoxon signed-rank test revealed that our results were statistically different with p<0.01. For visceral fat, the Cohen's kappa score of 0.856 indicated near-perfect agreement between the two tools. Our internal tool also showed very strong correlations for muscle volume (R^2=0.99), muscle attenuation (R^2=0.93), and subcutaneous fat volume (R^2=0.99) with a moderate correlation for subcutaneous fat attenuation (R^2=0.45). Conclusion: Our findings indicated that our Internal tool outperformed TotalSegmentator in measuring subcutaneous fat and muscle. The high Cohen's Kappa score for visceral fat suggests a reliable level of agreement between the two tools. These results demonstrate the potential of our tool in advancing the accuracy of body composition analysis.
Authors: Wei Cao, Chang Luo, Biao Zhang, Matthias Nie{\ss}ner, Jiapeng Tang
Abstract: We introduce Motion2VecSets, a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. While existing state-of-the-art methods have demonstrated success in reconstructing non-rigid objects using neural field representations, conventional feed-forward networks encounter challenges with ambiguous observations from noisy, partial, or sparse point clouds. To address these challenges, we introduce a diffusion model that explicitly learns the shape and motion distribution of non-rigid objects through an iterative denoising process of compressed latent representations. The diffusion-based priors enable more plausible and probabilistic reconstructions when handling ambiguous inputs. We parameterize 4D dynamics with latent sets instead of using global latent codes. This novel 4D representation allows us to learn local shape and deformation patterns, leading to more accurate non-linear motion capture and significantly improving generalizability to unseen motions and identities. For more temporally-coherent object tracking, we synchronously denoise deformation latent sets and exchange information across multiple frames. To avoid computational overhead, we designed an interleaved space and time attention block to alternately aggregate deformation latents along spatial and temporal domains. Extensive comparisons against state-of-the-art methods demonstrate the superiority of our Motion2VecSets in 4D reconstruction from various imperfect observations. More detailed information can be found at https://vveicao.github.io/projects/Motion2VecSets/.
Authors: Rongyu Zhang, Zefan Cai, Huanrui Yang, Zidong Liu, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Baobao Chang, Yuan Du, Li Du, Shanghang Zhang
Abstract: Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks. However, the conventional finetuning process with randomly sampled data points results in diminished training efficiency. To address this drawback, we propose a novel approach, Vision-language Collaborative Active Finetuning (VeCAF). With the emerging availability of labels and natural language annotations of images through web-scale crawling or controlled generation, VeCAF makes use of these information to perform parametric data selection for PVM finetuning. VeCAF incorporates the finetuning objective to select significant data points that effectively guide the PVM towards faster convergence to meet the performance goal. This process is assisted by the inherent semantic richness of the text embedding space which we use to augment image features. Furthermore, the flexibility of text-domain augmentation allows VeCAF to handle out-of-distribution scenarios without external data. Extensive experiments show the leading performance and high computational efficiency of VeCAF that is superior to baselines in both in-distribution and out-of-distribution image classification tasks. On ImageNet, VeCAF uses up to 3.3x less training batches to reach the target performance compared to full finetuning, and achieves an accuracy improvement of 2.7% over the state-of-the-art active finetuning method with the same number of batches.
Authors: Hanjia Lyu, Weihong Qi, Zhongyu Wei, Jiebo Luo
Abstract: Leveraging Large Multimodal Models (LMMs) to simulate human behaviors when processing multimodal information, especially in the context of social media, has garnered immense interest due to its broad potential and far-reaching implications. Emojis, as one of the most unique aspects of digital communication, are pivotal in enriching and often clarifying the emotional and tonal dimensions. Yet, there is a notable gap in understanding how these advanced models, such as GPT-4V, interpret and employ emojis in the nuanced context of online interaction. This study intends to bridge this gap by examining the behavior of GPT-4V in replicating human-like use of emojis. The findings reveal a discernible discrepancy between human and GPT-4V behaviors, likely due to the subjective nature of human interpretation and the limitations of GPT-4V's English-centric training, suggesting cultural biases and inadequate representation of non-English cultures.
Authors: Siwei Zhang, Bharat Lal Bhatnagar, Yuanlu Xu, Alexander Winkler, Petr Kadlecek, Siyu Tang, Federica Bogo
Abstract: We propose RoHM, an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos in the presence of noise and occlusions. Most previous approaches either train neural networks to directly regress motion in 3D or learn data-driven motion priors and combine them with optimization at test time. The former do not recover globally coherent motion and fail under occlusions; the latter are time-consuming, prone to local minima, and require manual tuning. To overcome these shortcomings, we exploit the iterative, denoising nature of diffusion models. RoHM is a novel diffusion-based motion model that, conditioned on noisy and occluded input data, reconstructs complete, plausible motions in consistent global coordinates. Given the complexity of the problem -- requiring one to address different tasks (denoising and infilling) in different solution spaces (local and global motion) -- we decompose it into two sub-tasks and learn two models, one for global trajectory and one for local motion. To capture the correlations between the two, we then introduce a novel conditioning module, combining it with an iterative inference scheme. We apply RoHM to a variety of tasks -- from motion reconstruction and denoising to spatial and temporal infilling. Extensive experiments on three popular datasets show that our method outperforms state-of-the-art approaches qualitatively and quantitatively, while being faster at test time. The code is available at https://sanweiliti.github.io/ROHM/ROHM.html.
Authors: Benjamin Ummenhofer, Sanskar Agrawal, Rene Sepulveda, Yixing Lao, Kai Zhang, Tianhang Cheng, Stephan Richter, Shenlong Wang, German Ros
Abstract: Reconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also to the new lighting conditions and yet evaluations of inverse rendering methods rely on novel view synthesis data or simplistic synthetic datasets for quantitative analysis. This work presents a real-world dataset for measuring the reconstruction and rendering of objects for relighting. To this end, we capture the environment lighting and ground truth images of the same objects in multiple environments allowing to reconstruct the objects from images taken in one environment and quantify the quality of the rendered views for the unseen lighting environments. Further, we introduce a simple baseline composed of off-the-shelf methods and test several state-of-the-art methods on the relighting task and show that novel view synthesis is not a reliable proxy to measure performance. Code and dataset are available at https://github.com/isl-org/objects-with-lighting .
Authors: Michael R. H. Vorndran, Bernhard F. Roeck
Abstract: Efficiently generating sufficient labeled data remains a major bottleneck in deep learning, particularly for image segmentation tasks where labeling requires significant time and effort. This study tackles this issue in a resource-constrained environment, devoid of extensive datasets or pre-existing models. We introduce Inconsistency Masks (IM), a novel approach that filters uncertainty in image-pseudo-label pairs to substantially enhance segmentation quality, surpassing traditional semi-supervised learning techniques. Employing IM, we achieve strong segmentation results with as little as 10% labeled data, across four diverse datasets and it further benefits from integration with other techniques, indicating broad applicability. Notably on the ISIC 2018 dataset, three of our hybrid approaches even outperform models trained on the fully labeled dataset. We also present a detailed comparative analysis of prevalent semi-supervised learning strategies, all under uniform starting conditions, to underline our approach's effectiveness and robustness. The full code is available at: https://github.com/MichaelVorndran/InconsistencyMasks
Authors: Wenhui Chang, Hongming Chen, Xin He, Xiang Chen, Liangduo Shen
Abstract: Raindrops adhering to the lens of UAVs can obstruct visibility of the background scene and degrade image quality. Despite recent progress in image deraining methods and datasets, there is a lack of focus on raindrop removal from UAV aerial imagery due to the unique challenges posed by varying angles and rapid movement during drone flight. To fill the gap in this research, we first construct a new benchmark dataset for removing raindrops from UAV images, called UAV-Rain1k. In this letter, we provide a dataset generation pipeline, which includes modeling raindrop shapes using Blender, collecting background images from various UAV angles, random sampling of rain masks and etc. Based on the proposed benchmark, we further present a comprehensive evaluation of existing representative image deraining algorithms, and reveal future research opportunities worth exploring. The proposed dataset is publicly available at https://github.com/cschenxiang/UAV-Rain1k.
Authors: Max Meyer, Amadeus Langer, Max Mehltretter, Dries Beyer, Max Coenen, Tobias Schack, Michael Haist, Christian Heipke
Abstract: Increasing the degree of digitisation and automation in the concrete production process can play a crucial role in reducing the CO$_2$ emissions that are associated with the production of concrete. In this paper, a method is presented that makes it possible to predict the properties of fresh concrete during the mixing process based on stereoscopic image sequences of the concretes flow behaviour. A Convolutional Neural Network (CNN) is used for the prediction, which receives the images supported by information on the mix design as input. In addition, the network receives temporal information in the form of the time difference between the time at which the images are taken and the time at which the reference values of the concretes are carried out. With this temporal information, the network implicitly learns the time-dependent behaviour of the concretes properties. The network predicts the slump flow diameter, the yield stress and the plastic viscosity. The time-dependent prediction potentially opens up the pathway to determine the temporal development of the fresh concrete properties already during mixing. This provides a huge advantage for the concrete industry. As a result, countermeasures can be taken in a timely manner. It is shown that an approach based on depth and optical flow images, supported by information of the mix design, achieves the best results.
Authors: Yang Liu, Tongfei Shen, Dong Zhang, Qingying Sun, Shoushan Li, Guodong Zhou
Abstract: The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video humor detection (SVHD), named Comment-aided Video-Language Alignment (CVLA) via data-augmented multi-modal contrastive pre-training. Notably, our CVLA not only operates on raw signals across various modal channels but also yields an appropriate multi-modal representation by aligning the video and language components within a consistent semantic space. The experimental results on two humor detection datasets, including DY11k and UR-FUNNY, demonstrate that CVLA dramatically outperforms state-of-the-art and several competitive baseline approaches. Our dataset, code and model release at https://github.com/yliu-cs/CVLA.
Authors: Byung-Kwan Lee, Beomchan Park, Chae Won Kim, Yong Man Ro
Abstract: The remarkable success of Large Language Models (LLMs) and instruction tuning drives the evolution of Vision Language Models (VLMs) towards a versatile general-purpose model. Yet, it remains unexplored whether current VLMs genuinely possess quality object-level image understanding capabilities determined from `what objects are in the image?' or `which object corresponds to a specified bounding box?'. Our findings reveal that the image understanding capabilities of current VLMs are strongly correlated with their zero-shot performance on vision language (VL) tasks. This suggests that prioritizing basic image understanding is crucial for VLMs to excel at VL tasks. To enhance object-level image understanding, we propose Crayon Large Language and Vision mOdel (CoLLaVO), which incorporates instruction tuning with Crayon Prompt as a new visual prompt tuning scheme based on panoptic color maps. Furthermore, we present a learning strategy of Dual QLoRA to preserve object-level image understanding without forgetting it during visual instruction tuning, thereby achieving a significant leap in numerous VL benchmarks in a zero-shot setting.
Authors: Haofeng Zhong, Yuchen Hong, Shuchen Weng, Jinxiu Liang, Boxin Shi
Abstract: This paper studies the problem of language-guided reflection separation, which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content. We propose a unified framework to solve this problem, which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a randomized training strategy are employed to tackle the recognizable layer ambiguity. The effectiveness of the proposed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons.
Authors: Xinyi Fang, Xu Yang, Chak Fong Chong, Kei Long Wong, Yapeng Wang, Tiankui Zhang, Sio-Kei Im
Abstract: Accurate classification of laryngeal vascular as benign or malignant is crucial for early detection of laryngeal cancer. However, organizations with limited access to laryngeal vascular images face challenges due to the lack of large and homogeneous public datasets for effective learning. Distinguished from the most familiar works, which directly transfer the ImageNet pre-trained models to the target domain for fine-tuning, this work pioneers exploring two-step heterogeneous transfer learning (THTL) for laryngeal lesion classification with nine deep-learning models, utilizing the diabetic retinopathy color fundus images, semantically non-identical yet vascular images, as the intermediate domain. Attention visualization technique, Layer Class Activate Map (LayerCAM), reveals a novel finding that yet the intermediate and the target domain both reflect vascular structure to a certain extent, the prevalent radial vascular pattern in the intermediate domain prevents learning the features of twisted and tangled vessels that distinguish the malignant class in the target domain, summarizes a vital rule for laryngeal lesion classification using THTL. To address this, we introduce an enhanced fine-tuning strategy in THTL called Step-Wise Fine-Tuning (SWFT) and apply it to the ResNet models. SWFT progressively refines model performance by accumulating fine-tuning layers from back to front, guided by the visualization results of LayerCAM. Comparison with the original THTL approach shows significant improvements. For ResNet18, the accuracy and malignant recall increases by 26.1% and 79.8%, respectively, while for ResNet50, these indicators improve by 20.4% and 62.2%, respectively.
Authors: Jianbin Zheng, Minghui Hu, Zhongyi Fan, Chaoyue Wang, Changxing Ding, Dacheng Tao, Tat-Jen Cham
Abstract: Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed that LCM struggles to generate images with both clarity and detailed intricacy. Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling. The trajectory consistency function diminishes the parameterisation and distillation errors by broadening the scope of the self-consistency boundary condition with trajectory mapping and endowing the TCD with the ability to accurately trace the entire trajectory of the Probability Flow ODE in semi-linear form with an Exponential Integrator. Additionally, strategic stochastic sampling provides explicit control of stochastic and circumvents the accumulated errors inherent in multi-step consistency sampling. Experiments demonstrate that TCD not only significantly enhances image quality at low NFEs but also yields more detailed results compared to the teacher model at high NFEs.
Authors: Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Xiaojun Wan
Abstract: News image captioning requires model to generate an informative caption rich in entities, with the news image and the associated news article. Though Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in addressing various vision-language tasks, our research finds that current MLLMs still bear limitations in handling entity information on news image captioning task. Besides, while MLLMs have the ability to process long inputs, generating high-quality news image captions still requires a trade-off between sufficiency and conciseness of textual input information. To explore the potential of MLLMs and address problems we discovered, we propose : an Entity-Aware Multimodal Alignment based approach for news image captioning. Our approach first aligns the MLLM through Balance Training Strategy with two extra alignment tasks: Entity-Aware Sentence Selection task and Entity Selection task, together with News Image Captioning task, to enhance its capability in handling multimodal entity information. The aligned MLLM will utilizes the additional entity-related information it explicitly extract to supplement its textual input while generating news image captions. Our approach achieves better results than all previous models in CIDEr score on GoodNews dataset (72.33 -> 88.39) and NYTimes800k dataset (70.83 -> 85.61).
Authors: Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, Bin Cui
Abstract: Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces hurdles such as updating knowledge, handling long-tail data, mitigating data leakage, and managing high training and inference costs. Retrieval-Augmented Generation (RAG) has recently emerged as a paradigm to address such challenges. In particular, RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness. In this paper, we comprehensively review existing efforts that integrate RAG technique into AIGC scenarios. We first classify RAG foundations according to how the retriever augments the generator, distilling the fundamental abstractions of the augmentation methodologies for various retrievers and generators. This unified perspective encompasses all RAG scenarios, illuminating advancements and pivotal technologies that help with potential future progress. We also summarize additional enhancements methods for RAG, facilitating effective engineering and implementation of RAG systems. Then from another view, we survey on practical applications of RAG across different modalities and tasks, offering valuable references for researchers and practitioners. Furthermore, we introduce the benchmarks for RAG, discuss the limitations of current RAG systems, and suggest potential directions for future research. Github: https://github.com/PKU-DAIR/RAG-Survey.
Authors: Kaituo Feng, Changsheng Li, Dongchun Ren, Ye Yuan, Guoren Wang
Abstract: End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference.To handle this, knowledge distillation offers a promising approach that compresses models by enabling a smaller student model to learn from a larger teacher model. Nevertheless, how to apply knowledge distillation to compress motion planners has not been explored so far. In this paper, we propose PlanKD, the first knowledge distillation framework tailored for compressing end-to-end motion planners. First, considering that driving scenes are inherently complex, often containing planning-irrelevant or even noisy information, transferring such information is not beneficial for the student planner. Thus, we design an information bottleneck based strategy to only distill planning-relevant information, rather than transfer all information indiscriminately. Second, different waypoints in an output planned trajectory may hold varying degrees of importance for motion planning, where a slight deviation in certain crucial waypoints might lead to a collision. Therefore, we devise a safety-aware waypoint-attentive distillation module that assigns adaptive weights to different waypoints based on the importance, to encourage the student to accurately mimic more crucial waypoints, thereby improving overall safety. Experiments demonstrate that our PlanKD can boost the performance of smaller planners by a large margin, and significantly reduce their reference time.
Authors: Hongjian Liu, Qingsong Xie, Zhijie Deng, Chen Chen, Shixiang Tang, Fueyang Fu, Zheng-jun Zha, Haonan Lu
Abstract: The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where high-quality generations can be achieved with just 1-2 sampling steps, and further improvements can be obtained by adding additional steps. In contrast to vanilla consistency distillation (CD) which distills the ordinary differential equation solvers-based sampling process of a pretrained teacher model into a student, SCott explores the possibility and validates the efficacy of integrating stochastic differential equation (SDE) solvers into CD to fully unleash the potential of the teacher. SCott is augmented with elaborate strategies to control the noise strength and sampling process of the SDE solver. An adversarial loss is further incorporated to strengthen the sample quality with rare sampling steps. Empirically, on the MSCOCO-2017 5K dataset with a Stable Diffusion-V1.5 teacher, SCott achieves an FID (Frechet Inceptio Distance) of 22.1, surpassing that (23.4) of the 1-step InstaFlow (Liu et al., 2023) and matching that of 4-step UFOGen (Xue et al., 2023b). Moreover, SCott can yield more diverse samples than other consistency models for high-resolution image generation (Luo et al., 2023a), with up to 16% improvement in a qualified metric. The code and checkpoints are coming soon.
Authors: Iryna Hartsock, Ghulam Rasool
Abstract: Medical vision-language models (VLMs) combine computer vision (CV) and natural language processing (NLP) to analyze visual and textual medical data. Our paper reviews recent advancements in developing VLMs specialized for healthcare, focusing on models designed for medical report generation and visual question answering (VQA). We provide background on NLP and CV, explaining how techniques from both fields are integrated into VLMs to enable learning from multimodal data. Key areas we address include the exploration of medical vision-language datasets, in-depth analyses of architectures and pre-training strategies employed in recent noteworthy medical VLMs, and comprehensive discussion on evaluation metrics for assessing VLMs' performance in medical report generation and VQA. We also highlight current challenges and propose future directions, including enhancing clinical validity and addressing patient privacy concerns. Overall, our review summarizes recent progress in developing VLMs to harness multimodal medical data for improved healthcare applications.
Authors: Thang M. Pham, Peijie Chen, Tin Nguyen, Seunghyun Yoon, Trung Bui, Anh Totti Nguyen
Abstract: CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder. Therefore, they perform poorly on new classes or the classes whose names rarely appear on the Internet (e.g., scientific names of birds). For fine-grained classification, we propose PEEB - an explainable and editable classifier to (1) express the class name into a set of text descriptors that describe the visual parts of that class; and (2) match the embeddings of the detected parts to their textual descriptors in each class to compute a logit score for classification. In a zero-shot setting where the class names are unknown, PEEB outperforms CLIP by a huge margin (~10x in top-1 accuracy). Compared to part-based classifiers, PEEB is not only the state-of-the-art (SOTA) on the supervised-learning setting (88.80% and 92.20% accuracy on CUB-200 and Dogs-120, respectively) but also the first to enable users to edit the text descriptors to form a new classifier without any re-training. Compared to concept bottleneck models, PEEB is also the SOTA in both zero-shot and supervised-learning settings.
Authors: Samuel Schmidgall, Ji Woong Kim, Jeffrey Jopling, Axel Krieger
Abstract: The absence of openly accessible data and specialized foundation models is a major barrier for computational research in surgery. Toward this, (i) we open-source the largest dataset of general surgery videos to-date, consisting of 680 hours of surgical videos, including data from robotic and laparoscopic techniques across 28 procedures; (ii) we propose a technique for video pre-training a general surgery vision transformer (GSViT) on surgical videos based on forward video prediction that can run in real-time for surgical applications, toward which we open-source the code and weights of GSViT; (iii) we also release code and weights for procedure-specific fine-tuned versions of GSViT across 10 procedures; (iv) we demonstrate the performance of GSViT on the Cholec80 phase annotation task, displaying improved performance over state-of-the-art single frame predictors.
Authors: Yang He, Lingao Xiao, Joey Tianyi Zhou, Ivor Tsang
Abstract: While dataset condensation effectively enhances training efficiency, its application in on-device scenarios brings unique challenges. 1) Due to the fluctuating computational resources of these devices, there's a demand for a flexible dataset size that diverges from a predefined size. 2) The limited computational power on devices often prevents additional condensation operations. These two challenges connect to the "subset degradation problem" in traditional dataset condensation: a subset from a larger condensed dataset is often unrepresentative compared to directly condensing the whole dataset to that smaller size. In this paper, we propose Multisize Dataset Condensation (MDC) by compressing N condensation processes into a single condensation process to obtain datasets with multiple sizes. Specifically, we introduce an "adaptive subset loss" on top of the basic condensation loss to mitigate the "subset degradation problem". Our MDC method offers several benefits: 1) No additional condensation process is required; 2) reduced storage requirement by reusing condensed images. Experiments validate our findings on networks including ConvNet, ResNet and DenseNet, and datasets including SVHN, CIFAR-10, CIFAR-100 and ImageNet. For example, we achieved 5.22%-6.40% average accuracy gains on condensing CIFAR-10 to ten images per class. Code is available at: https://github.com/he-y/Multisize-Dataset-Condensation.
URLs: https://github.com/he-y/Multisize-Dataset-Condensation.
Authors: Mingze Wang, Lili Su, Cilin Yan, Sheng Xu, Pengcheng Yuan, Xiaolong Jiang, Baochang Zhang
Abstract: The intelligent interpretation of buildings plays a significant role in urban planning and management, macroeconomic analysis, population dynamics, etc. Remote sensing image building interpretation primarily encompasses building extraction and change detection. However, current methodologies often treat these two tasks as separate entities, thereby failing to leverage shared knowledge. Moreover, the complexity and diversity of remote sensing image scenes pose additional challenges, as most algorithms are designed to model individual small datasets, thus lacking cross-scene generalization. In this paper, we propose a comprehensive remote sensing image building understanding model, termed RSBuilding, developed from the perspective of the foundation model. RSBuilding is designed to enhance cross-scene generalization and task universality. Specifically, we extract image features based on the prior knowledge of the foundation model and devise a multi-level feature sampler to augment scale information. To unify task representation and integrate image spatiotemporal clues, we introduce a cross-attention decoder with task prompts. Addressing the current shortage of datasets that incorporate annotations for both tasks, we have developed a federated training strategy to facilitate smooth model convergence even when supervision for some tasks is missing, thereby bolstering the complementarity of different tasks. Our model was trained on a dataset comprising up to 245,000 images and validated on multiple building extraction and change detection datasets. The experimental results substantiate that RSBuilding can concurrently handle two structurally distinct tasks and exhibits robust zero-shot generalization capabilities.
Authors: Yifan Li, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen
Abstract: In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs). We conduct a systematic empirical analysis of the harmlessness performance of representative MLLMs and reveal that the image input poses the alignment vulnerability of MLLMs. Inspired by this, we propose a novel jailbreak method named HADES, which hides and amplifies the harmfulness of the malicious intent within the text input, using meticulously crafted images. Experimental results show that HADES can effectively jailbreak existing MLLMs, which achieves an average Attack Success Rate (ASR) of 90.26% for LLaVA-1.5 and 71.60% for Gemini Pro Vision. Our code and data will be publicly released.
Authors: Tong Wu, Yu-Jie Yuan, Ling-Xiao Zhang, Jie Yang, Yan-Pei Cao, Ling-Qi Yan, Lin Gao
Abstract: The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and viewpoint-conditioned neural networks, 3D Gaussian Splatting utilizes a set of Gaussian ellipsoids to model the scene so that efficient rendering can be accomplished by rasterizing Gaussian ellipsoids into images. Apart from the fast rendering speed, the explicit representation of 3D Gaussian Splatting facilitates editing tasks like dynamic reconstruction, geometry editing, and physical simulation. Considering the rapid change and growing number of works in this field, we present a literature review of recent 3D Gaussian Splatting methods, which can be roughly classified into 3D reconstruction, 3D editing, and other downstream applications by functionality. Traditional point-based rendering methods and the rendering formulation of 3D Gaussian Splatting are also illustrated for a better understanding of this technique. This survey aims to help beginners get into this field quickly and provide experienced researchers with a comprehensive overview, which can stimulate the future development of the 3D Gaussian Splatting representation.
Authors: Minh Tran, Winston Bounsavy, Khoa Vo, Anh Nguyen, Tri Nguyen, Ngan Le
Abstract: Amodal Instance Segmentation (AIS) presents a challenging task as it involves predicting both visible and occluded parts of objects within images. Existing AIS methods rely on a bidirectional approach, encompassing both the transition from amodal features to visible features (amodal-to-visible) and from visible features to amodal features (visible-to-amodal). Our observation shows that the utilization of amodal features through the amodal-to-visible can confuse the visible features due to the extra information of occluded/hidden segments not presented in visible display. Consequently, this compromised quality of visible features during the subsequent visible-to-amodal transition. To tackle this issue, we introduce ShapeFormer, a decoupled Transformer-based model with a visible-to-amodal transition. It facilitates the explicit relationship between output segmentations and avoids the need for amodal-to-visible transitions. ShapeFormer comprises three key modules: (i) Visible-Occluding Mask Head for predicting visible segmentation with occlusion awareness, (ii) Shape-Prior Amodal Mask Head for predicting amodal and occluded masks, and (iii) Category-Specific Shape Prior Retriever aims to provide shape prior knowledge. Comprehensive experiments and extensive ablation studies across various AIS benchmarks demonstrate the effectiveness of our ShapeFormer. The code is available at: https://github.com/UARK-AICV/ShapeFormer
Authors: Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Gl\"ockler, Alex B\"auerle, Timo Ropinski
Abstract: Recent advances in text-to-image synthesis enabled through a combination of language and vision foundation models have led to a proliferation of the tools available and an increased attention to the field. When conducting text-to-image synthesis, a central goal is to ensure that the content between text and image is aligned. As such, there exist numerous evaluation metrics that aim to mimic human judgement. However, it is often unclear which metric to use for evaluating text-to-image synthesis systems as their evaluation is highly nuanced. In this work, we provide a comprehensive overview of existing text-to-image evaluation metrics. Based on our findings, we propose a new taxonomy for categorizing these metrics. Our taxonomy is grounded in the assumption that there are two main quality criteria, namely compositionality and generality, which ideally map to human preferences. Ultimately, we derive guidelines for practitioners conducting text-to-image evaluation, discuss open challenges of evaluation mechanisms, and surface limitations of current metrics.
Authors: Wenqi Zhao
Abstract: In order to improve the robustness of traditional image segmentation models to noise, this paper models the illumination term in intensity inhomogeneity images. Additionally, to enhance the model's robustness to noisy images, we incorporate the binary level set model into the proposed model. Compared to the traditional level set, the binary level set eliminates the need for continuous reinitialization. Moreover, by introducing the variational operator GL, our model demonstrates better capability in segmenting noisy images. Finally, we employ the three-step splitting operator method for solving, and the effectiveness of the proposed model is demonstrated on various images.
Authors: R. Gnana Praveen, Jahangir Alam
Abstract: Though multimodal emotion recognition has achieved significant progress over recent years, the potential of rich synergic relationships across the modalities is not fully exploited. In this paper, we introduce Recursive Joint Cross-Modal Attention (RJCMA) to effectively capture both intra- and inter-modal relationships across audio, visual, and text modalities for dimensional emotion recognition. In particular, we compute the attention weights based on cross-correlation between the joint audio-visual-text feature representations and the feature representations of individual modalities to simultaneously capture intra- and intermodal relationships across the modalities. The attended features of the individual modalities are again fed as input to the fusion model in a recursive mechanism to obtain more refined feature representations. We have also explored Temporal Convolutional Networks (TCNs) to improve the temporal modeling of the feature representations of individual modalities. Extensive experiments are conducted to evaluate the performance of the proposed fusion model on the challenging Affwild2 dataset. By effectively capturing the synergic intra- and inter-modal relationships across audio, visual, and text modalities, the proposed fusion model achieves a Concordance Correlation Coefficient (CCC) of 0.585 (0.542) and 0.674 (0.619) for valence and arousal respectively on the validation set(test set). This shows a significant improvement over the baseline of 0.240 (0.211) and 0.200 (0.191) for valence and arousal, respectively, in the validation set (test set), achieving second place in the valence-arousal challenge of the 6th Affective Behavior Analysis in-the-Wild (ABAW) competition.
Authors: Ahmet Alp Kindiroglu, Ozgur Kara, Ogulcan Ozdemir, Lale Akarun
Abstract: Sign language recognition (SLR) has recently achieved a breakthrough in performance thanks to deep neural networks trained on large annotated sign datasets. Of the many different sign languages, these annotated datasets are only available for a select few. Since acquiring gloss-level labels on sign language videos is difficult, learning by transferring knowledge from existing annotated sources is useful for recognition in under-resourced sign languages. This study provides a publicly available cross-dataset transfer learning benchmark from two existing public Turkish SLR datasets. We use a temporal graph convolution-based sign language recognition approach to evaluate five supervised transfer learning approaches and experiment with closed-set and partial-set cross-dataset transfer learning. Experiments demonstrate that improvement over finetuning based transfer learning is possible with specialized supervised transfer learning methods.
Authors: Congrui Hetang, Haoru Xue, Cindy Le, Tianwei Yue, Wenping Wang, Yihui He
Abstract: We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery. To predict graph geometry, we formulate it as a dense semantic segmentation task, leveraging the inherent strengths of SAM. The image encoder of SAM is fine-tuned to produce probability masks for roads and intersections, from which the graph vertices are extracted via simple non-maximum suppression. To predict graph topology, we designed a lightweight transformer-based graph neural network, which leverages the SAM image embeddings to estimate the edge existence probabilities between vertices. Our approach directly predicts the graph vertices and edges for large regions without expensive and complex post-processing heuristics, and is capable of building complete road network graphs spanning multiple square kilometers in a matter of seconds. With its simple, straightforward, and minimalist design, SAM-Road achieves comparable accuracy with the state-of-the-art method RNGDet++, while being 40 times faster on the City-scale dataset. We thus demonstrate the power of a foundational vision model when applied to a graph learning task. The code is available at https://github.com/htcr/sam_road.
Authors: Carl Lindstr\"om, Georg Hess, Adam Lilja, Maryam Fatemi, Lars Hammarstrand, Christoffer Petersson, Lennart Svensson
Abstract: Neural Radiance Fields (NeRFs) have emerged as promising tools for advancing autonomous driving (AD) research, offering scalable closed-loop simulation and data augmentation capabilities. However, to trust the results achieved in simulation, one needs to ensure that AD systems perceive real and rendered data in the same way. Although the performance of rendering methods is increasing, many scenarios will remain inherently challenging to reconstruct faithfully. To this end, we propose a novel perspective for addressing the real-to-simulated data gap. Rather than solely focusing on improving rendering fidelity, we explore simple yet effective methods to enhance perception model robustness to NeRF artifacts without compromising performance on real data. Moreover, we conduct the first large-scale investigation into the real-to-simulated data gap in an AD setting using a state-of-the-art neural rendering technique. Specifically, we evaluate object detectors and an online mapping model on real and simulated data, and study the effects of different fine-tuning strategies.Our results show notable improvements in model robustness to simulated data, even improving real-world performance in some cases. Last, we delve into the correlation between the real-to-simulated gap and image reconstruction metrics, identifying FID and LPIPS as strong indicators. See https://research.zenseact.com/publications/closing-real2sim-gap for our project page.
URLs: https://research.zenseact.com/publications/closing-real2sim-gap
Authors: Fiona R. Kolbinger, Jiangpeng He, Jinge Ma, Fengqing Zhu
Abstract: Accurate identification and localization of anatomical structures of varying size and appearance in laparoscopic imaging are necessary to leverage the potential of computer vision techniques for surgical decision support. Segmentation performance of such models is traditionally reported using metrics of overlap such as IoU. However, imbalanced and unrealistic representation of classes in the training data and suboptimal selection of reported metrics have the potential to skew nominal segmentation performance and thereby ultimately limit clinical translation. In this work, we systematically analyze the impact of class characteristics (i.e., organ size differences), training and test data composition (i.e., representation of positive and negative examples), and modeling parameters (i.e., foreground-to-background class weight) on eight segmentation metrics: accuracy, precision, recall, IoU, F1 score (Dice Similarity Coefficient), specificity, Hausdorff Distance, and Average Symmetric Surface Distance. Our findings support two adjustments to account for data biases in surgical data science: First, training on datasets that are similar to the clinical real-world scenarios in terms of class distribution, and second, class weight adjustments to optimize segmentation model performance with regard to metrics of particular relevance in the respective clinical setting.
Authors: Pancheng Zhao, Peng Xu, Pengda Qin, Deng-Ping Fan, Zhicheng Zhang, Guoli Jia, Bowen Zhou, Jufeng Yang
Abstract: Camouflaged vision perception is an important vision task with numerous practical applications. Due to the expensive collection and labeling costs, this community struggles with a major bottleneck that the species category of its datasets is limited to a small number of object species. However, the existing camouflaged generation methods require specifying the background manually, thus failing to extend the camouflaged sample diversity in a low-cost manner. In this paper, we propose a Latent Background Knowledge Retrieval-Augmented Diffusion (LAKE-RED) for camouflaged image generation. To our knowledge, our contributions mainly include: (1) For the first time, we propose a camouflaged generation paradigm that does not need to receive any background inputs. (2) Our LAKE-RED is the first knowledge retrieval-augmented method with interpretability for camouflaged generation, in which we propose an idea that knowledge retrieval and reasoning enhancement are separated explicitly, to alleviate the task-specific challenges. Moreover, our method is not restricted to specific foreground targets or backgrounds, offering a potential for extending camouflaged vision perception to more diverse domains. (3) Experimental results demonstrate that our method outperforms the existing approaches, generating more realistic camouflage images.
Authors: Yifei Liu, Qiong Cao, Yandong Wen, Huaiguang Jiang, Changxing Ding
Abstract: This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar speech content, while coordination ensures a harmonious alignment among facial expressions, hand gestures, and body poses. We aim to achieve both with ProbTalk, a unified probabilistic framework designed to jointly model facial, hand, and body movements in speech. ProbTalk builds on the variational autoencoder (VAE) architecture and incorporates three core designs. First, we introduce product quantization (PQ) to the VAE, which enriches the representation of complex holistic motion. Second, we devise a novel non-autoregressive model that embeds 2D positional encoding into the product-quantized representation, thereby preserving essential structure information of the PQ codes. Last, we employ a secondary stage to refine the preliminary prediction, further sharpening the high-frequency details. Coupling these three designs enables ProbTalk to generate natural and diverse holistic co-speech motions, outperforming several state-of-the-art methods in qualitative and quantitative evaluations, particularly in terms of realism. Our code and model will be released for research purposes at https://feifeifeiliu.github.io/probtalk/.
Authors: Qiankun Liu, Yuqi Jiang, Zhentao Tan, Dongdong Chen, Ying Fu, Qi Chu, Gang Hua, Nenghai Yu
Abstract: Transformer based methods have achieved great success in image inpainting recently. However, we find that these solutions regard each pixel as a token, thus suffering from an information loss issue from two aspects: 1) They downsample the input image into much lower resolutions for efficiency consideration. 2) They quantize $256^3$ RGB values to a small number (such as 512) of quantized color values. The indices of quantized pixels are used as tokens for the inputs and prediction targets of the transformer. To mitigate these issues, we propose a new transformer based framework called "PUT". Specifically, to avoid input downsampling while maintaining computation efficiency, we design a patch-based auto-encoder P-VQVAE. The encoder converts the masked image into non-overlapped patch tokens and the decoder recovers the masked regions from the inpainted tokens while keeping the unmasked regions unchanged. To eliminate the information loss caused by input quantization, an Un-quantized Transformer is applied. It directly takes features from the P-VQVAE encoder as input without any quantization and only regards the quantized tokens as prediction targets. Furthermore, to make the inpainting process more controllable, we introduce semantic and structural conditions as extra guidance. Extensive experiments show that our method greatly outperforms existing transformer based methods on image fidelity and achieves much higher diversity and better fidelity than state-of-the-art pluralistic inpainting methods on complex large-scale datasets (e.g., ImageNet). Codes are available at https://github.com/liuqk3/PUT.
Authors: Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou
Abstract: In recent years, Vision Transformer-based approaches for low-level vision tasks have achieved widespread success. Unlike CNN-based models, Transformers are more adept at capturing long-range dependencies, enabling the reconstruction of images utilizing non-local information. In the domain of super-resolution, Swin-transformer-based models have become mainstream due to their capability of global spatial information modeling and their shifting-window attention mechanism that facilitates the interchange of information between different windows. Many researchers have enhanced model performance by expanding the receptive fields or designing meticulous networks, yielding commendable results. However, we observed that it is a general phenomenon for the feature map intensity to be abruptly suppressed to small values towards the network's end. This implies an information bottleneck and a diminishment of spatial information, implicitly limiting the model's potential. To address this, we propose the Dense-residual-connected Transformer (DRCT), aimed at mitigating the loss of spatial information and stabilizing the information flow through dense-residual connections between layers, thereby unleashing the model's potential and saving the model away from information bottleneck. Experiment results indicate that our approach surpasses state-of-the-art methods on benchmark datasets and performs commendably at the NTIRE-2024 Image Super-Resolution (x4) Challenge. Our source code is available at https://github.com/ming053l/DRCT
Authors: Zhihao Chen, Yiyuan Ge
Abstract: The goal of occluded person re-identification (ReID) is to retrieve specific pedestrians in occluded situations. However, occluded person ReID still suffers from background clutter and low-quality local feature representations, which limits model performance. In our research, we introduce a new framework called PAB-ReID, which is a novel ReID model incorporating part-attention mechanisms to tackle the aforementioned issues effectively. Firstly, we introduce the human parsing label to guide the generation of more accurate human part attention maps. In addition, we propose a fine-grained feature focuser for generating fine-grained human local feature representations while suppressing background interference. Moreover, We also design a part triplet loss to supervise the learning of human local features, which optimizes intra/inter-class distance. We conducted extensive experiments on specialized occlusion and regular ReID datasets, showcasing that our approach outperforms the existing state-of-the-art methods.
Authors: Simon Weber, Bar{\i}\c{s} Z\"ong\"ur, Nikita Araslanov, Daniel Cremers
Abstract: Hierarchy is a natural representation of semantic taxonomies, including the ones routinely used in image segmentation. Indeed, recent work on semantic segmentation reports improved accuracy from supervised training leveraging hierarchical label structures. Encouraged by these results, we revisit the fundamental assumptions behind that work. We postulate and then empirically verify that the reasons for the observed improvement in segmentation accuracy may be entirely unrelated to the use of the semantic hierarchy. To demonstrate this, we design a range of cross-domain experiments with a representative hierarchical approach. We find that on the new testing domains, a flat (non-hierarchical) segmentation network, in which the parents are inferred from the children, has superior segmentation accuracy to the hierarchical approach across the board. Complementing these findings and inspired by the intrinsic properties of hyperbolic spaces, we study a more principled approach to hierarchical segmentation using the Poincar\'e ball model. The hyperbolic representation largely outperforms the previous (Euclidean) hierarchical approach as well and is on par with our flat Euclidean baseline in terms of segmentation accuracy. However, it additionally exhibits surprisingly strong calibration quality of the parent nodes in the semantic hierarchy, especially on the more challenging domains. Our combined analysis suggests that the established practice of hierarchical segmentation may be limited to in-domain settings, whereas flat classifiers generalize substantially better, especially if they are modeled in the hyperbolic space.
Authors: Butian Xiong, Nanjun Zheng, Junhua Liu, Zhen Li
Abstract: We introduce a novel, multimodal large-scale scene reconstruction benchmark that utilizes newly developed 3D representation approaches: Gaussian Splatting and Neural Radiance Fields (NeRF). Our expansive U-Scene dataset surpasses any previously existing real large-scale outdoor LiDAR and image dataset in both area and point count. GauU-Scene encompasses over 6.5 square kilometers and features a comprehensive RGB dataset coupled with LiDAR ground truth. Additionally, we are the first to propose a LiDAR and image alignment method for a drone-based dataset. Our assessment of GauU-Scene includes a detailed analysis across various novel viewpoints, employing image-based metrics such as SSIM, LPIPS, and PSNR on NeRF and Gaussian Splatting based methods. This analysis reveals contradictory results when applying geometric-based metrics like Chamfer distance. The experimental results on our multimodal dataset highlight the unreliability of current image-based metrics and reveal significant drawbacks in geometric reconstruction using the current Gaussian Splatting-based method, further illustrating the necessity of our dataset for assessing geometry reconstruction tasks. We also provide detailed supplementary information on data collection protocols and make the dataset available on the following anonymous project page
Authors: Ziyang Wang, Jian-Qing Zheng, Chao Ma, Tao Guo
Abstract: Image registration, a critical process in medical imaging, involves aligning different sets of medical imaging data into a single unified coordinate system. Deep learning networks, such as the Convolutional Neural Network (CNN)-based VoxelMorph, Vision Transformer (ViT)-based TransMorph, and State Space Model (SSM)-based MambaMorph, have demonstrated effective performance in this domain. The recent Visual State Space Model (VMamba), which incorporates a cross-scan module with SSM, has exhibited promising improvements in modeling global-range dependencies with efficient computational cost in computer vision tasks. This paper hereby introduces an exploration of VMamba with image registration, named VMambaMorph. This novel hybrid VMamba-CNN network is designed specifically for 3D image registration. Utilizing a U-shaped network architecture, VMambaMorph computes the deformation field based on target and source volumes. The VMamba-based block with 2D cross-scan module is redesigned for 3D volumetric feature processing. To overcome the complex motion and structure on multi-modality images, we further propose a fine-tune recursive registration framework. We validate VMambaMorph using a public benchmark brain MR-CT registration dataset, comparing its performance against current state-of-the-art methods. The results indicate that VMambaMorph achieves competitive registration quality. The code for VMambaMorph with all baseline methods is available on GitHub.
Authors: Giang Nguyen, Mohammad Reza Taesiri, Sunnie S. Y. Kim, Anh Nguyen
Abstract: Via thousands of papers in Explainable AI (XAI), attention maps \cite{vaswani2017attention} and feature attribution maps \cite{bansal2020sam} have been established as a common means for finding how important each input feature is to an AI's decisions. It is an interesting, unexplored question whether allowing users to edit the feature importance at test time would improve a human-AI team's accuracy on downstream tasks. In this paper, we address this question by leveraging CHM-Corr, a state-of-the-art, ante-hoc explainable classifier \cite{taesiri2022visual} that first predicts patch-wise correspondences between the input and training-set images, and then base on them to make classification decisions. We build CHM-Corr++, an interactive interface for CHM-Corr, enabling users to edit the feature attribution map provided by CHM-Corr and observe updated model decisions. Via CHM-Corr++, users can gain insights into if, when, and how the model changes its outputs, improving their understanding beyond static explanations. However, our user study with 18 users who performed 1,400 decisions finds no statistical significance that our interactive approach improves user accuracy on CUB-200 bird image classification over static explanations. This challenges the hypothesis that interactivity can boost human-AI team accuracy~\cite{sokol2020one,sun2022exploring,shen2024towards,singh2024rethinking,mindlin2024beyond,lakkaraju2022rethinking,cheng2019explaining,liu2021understanding} and raises needs for future research. We open-source CHM-Corr++, an interactive tool for editing image classifier attention (see an interactive demo \href{http://137.184.82.109:7080/}{here}). % , and it lays the groundwork for future research to enable effective human-AI interaction in computer vision. We release code and data on \href{https://github.com/anguyen8/chm-corr-interactive}{github}.
URLs: http://137.184.82.109:7080/, https://github.com/anguyen8/chm-corr-interactive
Authors: Giuseppe Macario
Abstract: This work proposes a WebXR-based cross-platform conceptual architecture, leveraging the A-Frame and Networked-Aframe frameworks, in order to facilitate the development of an open, accessible, and interoperable metaverse. By introducing the concept of spatial web app, this research contributes to the discourse on the metaverse, offering an architecture that democratizes access to virtual environments and extended reality through the web, and aligns with Tim Berners-Lee's original vision of the World Wide Web as an open platform in the digital realm.
Authors: Seunghoi Kim, Chen Jin, Tom Diethe, Matteo Figini, Henry F. J. Tregidgo, Asher Mullokandov, Philip Teare, Daniel C. Alexander
Abstract: Recent developments in diffusion models have advanced conditioned image generation, yet they struggle with reconstructing out-of-distribution (OOD) images, such as unseen tumors in medical images, causing ``image hallucination'' and risking misdiagnosis. We hypothesize such hallucinations result from local OOD regions in the conditional images. We verify that partitioning the OOD region and conducting separate image generations alleviates hallucinations in several applications. From this, we propose a training-free diffusion framework that reduces hallucination with multiple Local Diffusion processes. Our approach involves OOD estimation followed by two modules: a ``branching'' module generates locally both within and outside OOD regions, and a ``fusion'' module integrates these predictions into one. Our evaluation shows our method mitigates hallucination over baseline models quantitatively and qualitatively, reducing misdiagnosis by 40% and 25% in the real-world medical and natural image datasets, respectively. It also demonstrates compatibility with various pre-trained diffusion models.
Authors: Zhicheng Lu, Xiang Guo, Le Hui, Tianrui Chen, Min Yang, Xiao Tang, Feng Zhu, Yuchao Dai
Abstract: In this paper, we propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Existing neural radiance fields (NeRF) based solutions learn the deformation in an implicit manner, which cannot incorporate 3D scene geometry. Therefore, the learned deformation is not necessarily geometrically coherent, which results in unsatisfactory dynamic view synthesis and 3D dynamic reconstruction. Recently, 3D Gaussian Splatting provides a new representation of the 3D scene, building upon which the 3D geometry could be exploited in learning the complex 3D deformation. Specifically, the scenes are represented as a collection of 3D Gaussian, where each 3D Gaussian is optimized to move and rotate over time to model the deformation. To enforce the 3D scene geometry constraint during deformation, we explicitly extract 3D geometry features and integrate them in learning the 3D deformation. In this way, our solution achieves 3D geometry-aware deformation modeling, which enables improved dynamic view synthesis and 3D dynamic reconstruction. Extensive experimental results on both synthetic and real datasets prove the superiority of our solution, which achieves new state-of-the-art performance. The project is available at https://npucvr.github.io/GaGS/
Authors: Haoyang He, Yuhu Bai, Jiangning Zhang, Qingdong He, Hongxu Chen, Zhenye Gan, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Lei Xie
Abstract: Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity. Mamba-based models, with their superior long-range modeling and linear efficiency, have garnered substantial attention. This study pioneers the application of Mamba to multi-class unsupervised anomaly detection, presenting MambaAD, which consists of a pre-trained encoder and a Mamba decoder featuring (Locality-Enhanced State Space) LSS modules at multi-scales. The proposed LSS module, integrating parallel cascaded (Hybrid State Space) HSS blocks and multi-kernel convolutions operations, effectively captures both long-range and local information. The HSS block, utilizing (Hybrid Scanning) HS encoders, encodes feature maps into five scanning methods and eight directions, thereby strengthening global connections through the (State Space Model) SSM. The use of Hilbert scanning and eight directions significantly improves feature sequence modeling. Comprehensive experiments on six diverse anomaly detection datasets and seven metrics demonstrate state-of-the-art performance, substantiating the method's effectiveness.
Authors: Jiahao Wang, Wenqi Shao, Mengzhao Chen, Chengyue Wu, Yong Liu, Kaipeng Zhang, Songyang Zhang, Kai Chen, Ping Luo
Abstract: This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a casual mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training. We suggest to reposition the class token behind the image tokens with a post-sequence class token technique to overcome this challenge, enabling causal self-attention to efficiently capture the entire image's information. Additionally, we develop a soft mask strategy that gradually introduces a casual mask to the self-attention at the onset of training to facilitate the optimization behavior. The tailored model, dubbed as image LLaMA (iLLaMA), is akin to LLaMA in architecture and enables direct supervised learning. Its causal self-attention boosts computational efficiency and learns complex representation by elevating attention map ranks. iLLaMA rivals the performance with its encoder-only counterparts, achieving 75.1% ImageNet top-1 accuracy with only 5.7M parameters. Scaling the model to ~310M and pre-training on ImageNet-21K further enhances the accuracy to 86.0%. Extensive experiments demonstrate iLLaMA's reliable properties: calibration, shape-texture bias, quantization compatibility, ADE20K segmentation and CIFAR transfer learning. We hope our study can kindle fresh views to visual model design in the wave of LLMs. Pre-trained models and codes are available here.
Authors: Chunxu Liu, Guozhen Zhang, Rui Zhao, Limin Wang
Abstract: Large motion poses a critical challenge in Video Frame Interpolation (VFI) task. Existing methods are often constrained by limited receptive fields, resulting in sub-optimal performance when handling scenarios with large motion. In this paper, we introduce a new pipeline for VFI, which can effectively integrate global-level information to alleviate issues associated with large motion. Specifically, we first estimate a pair of initial intermediate flows using a high-resolution feature map for extracting local details. Then, we incorporate a sparse global matching branch to compensate for flow estimation, which consists of identifying flaws in initial flows and generating sparse flow compensation with a global receptive field. Finally, we adaptively merge the initial flow estimation with global flow compensation, yielding a more accurate intermediate flow. To evaluate the effectiveness of our method in handling large motion, we carefully curate a more challenging subset from commonly used benchmarks. Our method demonstrates the state-of-the-art performance on these VFI subsets with large motion.
Authors: Jiale Xu, Weihao Cheng, Yiming Gao, Xintao Wang, Shenghua Gao, Ying Shan
Abstract: We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability. By synergizing the strengths of an off-the-shelf multiview diffusion model and a sparse-view reconstruction model based on the LRM architecture, InstantMesh is able to create diverse 3D assets within 10 seconds. To enhance the training efficiency and exploit more geometric supervisions, e.g, depths and normals, we integrate a differentiable iso-surface extraction module into our framework and directly optimize on the mesh representation. Experimental results on public datasets demonstrate that InstantMesh significantly outperforms other latest image-to-3D baselines, both qualitatively and quantitatively. We release all the code, weights, and demo of InstantMesh, with the intention that it can make substantial contributions to the community of 3D generative AI and empower both researchers and content creators.
Authors: Akash Ghosh, Arkadeep Acharya, Sriparna Saha, Vinija Jain, Aman Chadha
Abstract: The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this constraint, researchers have endeavored to integrate visual capabilities with LLMs, resulting in the emergence of Vision-Language Models (VLMs). These advanced models are instrumental in tackling more intricate tasks such as image captioning and visual question answering. In our comprehensive survey paper, we delve into the key advancements within the realm of VLMs. Our classification organizes VLMs into three distinct categories: models dedicated to vision-language understanding, models that process multimodal inputs to generate unimodal (textual) outputs and models that both accept and produce multimodal inputs and outputs.This classification is based on their respective capabilities and functionalities in processing and generating various modalities of data.We meticulously dissect each model, offering an extensive analysis of its foundational architecture, training data sources, as well as its strengths and limitations wherever possible, providing readers with a comprehensive understanding of its essential components. We also analyzed the performance of VLMs in various benchmark datasets. By doing so, we aim to offer a nuanced understanding of the diverse landscape of VLMs. Additionally, we underscore potential avenues for future research in this dynamic domain, anticipating further breakthroughs and advancements.
Authors: Yang Chen, Jingcai Guo, Tian He, Ling Wang
Abstract: Skeleton-based zero-shot action recognition aims to recognize unknown human actions based on the learned priors of the known skeleton-based actions and a semantic descriptor space shared by both known and unknown categories. However, previous works focus on establishing the bridges between the known skeleton representation space and semantic descriptions space at the coarse-grained level for recognizing unknown action categories, ignoring the fine-grained alignment of these two spaces, resulting in suboptimal performance in distinguishing high-similarity action categories. To address these challenges, we propose a novel method via Side information and dual-prompts learning for skeleton-based zero-shot action recognition (STAR) at the fine-grained level. Specifically, 1) we decompose the skeleton into several parts based on its topology structure and introduce the side information concerning multi-part descriptions of human body movements for alignment between the skeleton and the semantic space at the fine-grained level; 2) we design the visual-attribute and semantic-part prompts to improve the intra-class compactness within the skeleton space and inter-class separability within the semantic space, respectively, to distinguish the high-similarity actions. Extensive experiments show that our method achieves state-of-the-art performance in ZSL and GZSL settings on NTU RGB+D, NTU RGB+D 120, and PKU-MMD datasets.
Authors: Kai Luo, Yakun Ju, Lin Qi, Kaixuan Wang, Junyu Dong
Abstract: Predicting accurate normal maps of objects from two-dimensional images in regions of complex structure and spatial material variations is challenging using photometric stereo methods due to the influence of surface reflection properties caused by variations in object geometry and surface materials. To address this issue, we propose a photometric stereo network called a RMAFF-PSN that uses residual multiscale attentional feature fusion to handle the ``difficult'' regions of the object. Unlike previous approaches that only use stacked convolutional layers to extract deep features from the input image, our method integrates feature information from different resolution stages and scales of the image. This approach preserves more physical information, such as texture and geometry of the object in complex regions, through shallow-deep stage feature extraction, double branching enhancement, and attention optimization. To test the network structure under real-world conditions, we propose a new real dataset called Simple PS data, which contains multiple objects with varying structures and materials. Experimental results on a publicly available benchmark dataset demonstrate that our method outperforms most existing calibrated photometric stereo methods for the same number of input images, especially in the case of highly non-convex object structures. Our method also obtains good results under sparse lighting conditions.
Authors: Jie Wang, Jun Ai, Minyan Lu, Haoran Su, Dan Yu, Yutao Zhang, Junda Zhu, Jingyu Liu
Abstract: In recent years, there has been significant attention given to the robustness assessment of neural networks. Robustness plays a critical role in ensuring reliable operation of artificial intelligence (AI) systems in complex and uncertain environments. Deep learning's robustness problem is particularly significant, highlighted by the discovery of adversarial attacks on image classification models. Researchers have dedicated efforts to evaluate robustness in diverse perturbation conditions for image recognition tasks. Robustness assessment encompasses two main techniques: robustness verification/ certification for deliberate adversarial attacks and robustness testing for random data corruptions. In this survey, we present a detailed examination of both adversarial robustness (AR) and corruption robustness (CR) in neural network assessment. Analyzing current research papers and standards, we provide an extensive overview of robustness assessment in image recognition. Three essential aspects are analyzed: concepts, metrics, and assessment methods. We investigate the perturbation metrics and range representations used to measure the degree of perturbations on images, as well as the robustness metrics specifically for the robustness conditions of classification models. The strengths and limitations of the existing methods are also discussed, and some potential directions for future research are provided.
Authors: Yuelong Li, Tengfei Xiao, Lei Geng, Jianming Wang
Abstract: Pose diversity is an inherent representative characteristic of 2D images. Due to the 3D to 2D projection mechanism, there is evident content discrepancy among distinct pose images. This is the main obstacle bothering pose transformation related researches. To deal with this challenge, we propose a fine-grained incremental evolution centered pose generation framework, rather than traditional direct one-to-one in a rush. Since proposed approach actually bypasses the theoretical difficulty of directly modeling dramatic non-linear variation, the incurred content distortion and blurring could be effectively constrained, at the same time the various individual pose details, especially clothes texture, could be precisely maintained. In order to systematically guide the evolution course, both global and incremental evolution constraints are elaborately designed and merged into the overall framework. And a novel triple-path knowledge fusion structure is worked out to take full advantage of all available valuable knowledge to conduct high-quality pose synthesis. In addition, our framework could generate a series of valuable byproducts, namely the various intermediate poses. Extensive experiments have been conducted to verify the effectiveness of the proposed approach. Code is available at https://github.com/Xiaofei-CN/Incremental-Evolution-Pose-Generation.
URLs: https://github.com/Xiaofei-CN/Incremental-Evolution-Pose-Generation.
Authors: Jingrui Ye, Zongkai Zhang, Yujiao Jiang, Qingmin Liao, Wenming Yang, Zongqing Lu
Abstract: Rendering dynamic 3D human from monocular videos is crucial for various applications such as virtual reality and digital entertainment. Most methods assume the people is in an unobstructed scene, while various objects may cause the occlusion of body parts in real-life scenarios. Previous method utilizing NeRF for surface rendering to recover the occluded areas, but it requiring more than one day to train and several seconds to render, failing to meet the requirements of real-time interactive applications. To address these issues, we propose OccGaussian based on 3D Gaussian Splatting, which can be trained within 6 minutes and produces high-quality human renderings up to 160 FPS with occluded input. OccGaussian initializes 3D Gaussian distributions in the canonical space, and we perform occlusion feature query at occluded regions, the aggregated pixel-align feature is extracted to compensate for the missing information. Then we use Gaussian Feature MLP to further process the feature along with the occlusion-aware loss functions to better perceive the occluded area. Extensive experiments both in simulated and real-world occlusions, demonstrate that our method achieves comparable or even superior performance compared to the state-of-the-art method. And we improving training and inference speeds by 250x and 800x, respectively. Our code will be available for research purposes.
Authors: Robik Shrestha, Kushal Kafle, Christopher Kanan
Abstract: A critical problem in deep learning is that systems learn inappropriate biases, resulting in their inability to perform well on minority groups. This has led to the creation of multiple algorithms that endeavor to mitigate bias. However, it is not clear how effective these methods are. This is because study protocols differ among papers, systems are tested on datasets that fail to test many forms of bias, and systems have access to hidden knowledge or are tuned specifically to the test set. To address this, we introduce an improved evaluation protocol, sensible metrics, and a new dataset, which enables us to ask and answer critical questions about bias mitigation algorithms. We evaluate seven state-of-the-art algorithms using the same network architecture and hyperparameter selection policy across three benchmark datasets. We introduce a new dataset called Biased MNIST that enables assessment of robustness to multiple bias sources. We use Biased MNIST and a visual question answering (VQA) benchmark to assess robustness to hidden biases. Rather than only tuning to the test set distribution, we study robustness across different tuning distributions, which is critical because for many applications the test distribution may not be known during development. We find that algorithms exploit hidden biases, are unable to scale to multiple forms of bias, and are highly sensitive to the choice of tuning set. Based on our findings, we implore the community to adopt more rigorous assessment of future bias mitigation methods. All data, code, and results are publicly available at: https://github.com/erobic/bias-mitigators.
Authors: Jay Aodh Mackenzie, Megan Jeanne Miller, Nicholas Hill, Mette Olufsen
Abstract: Numerical simulations of real-world phenomenon are implemented with at least two parts: the computational scheme and the computational domain. In the context of hemodynamics, the computational domain of a simulation represents the blood vessel network through which blood flows. Such blood vessel networks can contain millions of individual vessels that are joined together to form a in series and parallel to form the network. It is computationally unfeasible to explicitly simulate blood flow in all blood vessels. Here, from imaged data of a single porcine left coronary arterial tree, we develop a data-pipeline to obtain computational domains for hemodynmaic simulations from a graph representing the coronary vascular tree. Further, we develop a method to ascertain which subregions of the left ventricle are most likely to be perfused via a given artery using a comparison with the American Heart Association division of the left ventricle as a sense check.
Authors: Yan Wang, Yusen Li, Gang Wang, Xiaoguang Liu
Abstract: ConvNets can compete with transformers in high-level tasks by exploiting larger receptive fields. To unleash the potential of ConvNet in super-resolution, we propose a multi-scale attention network (MAN), by coupling classical multi-scale mechanism with emerging large kernel attention. In particular, we proposed multi-scale large kernel attention (MLKA) and gated spatial attention unit (GSAU). Through our MLKA, we modify large kernel attention with multi-scale and gate schemes to obtain the abundant attention map at various granularity levels, thereby aggregating global and local information and avoiding potential blocking artifacts. In GSAU, we integrate gate mechanism and spatial attention to remove the unnecessary linear layer and aggregate informative spatial context. To confirm the effectiveness of our designs, we evaluate MAN with multiple complexities by simply stacking different numbers of MLKA and GSAU. Experimental results illustrate that our MAN can perform on par with SwinIR and achieve varied trade-offs between state-of-the-art performance and computations.
Authors: Pattarawat Chormai, Jan Herrmann, Klaus-Robert M\"uller, Gr\'egoire Montavon
Abstract: Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of a heatmap identifying input features (e.g. pixels) that are relevant to the model's decision. These explanations, however, entangle the potentially multiple factors that enter into the overall complex decision strategy. We propose to disentangle explanations by extracting at some intermediate layer of a neural network, subspaces that capture the multiple and distinct activation patterns (e.g. visual concepts) that are relevant to the prediction. To automatically extract these subspaces, we propose two new analyses, extending principles found in PCA or ICA to explanations. These novel analyses, which we call principal relevant component analysis (PRCA) and disentangled relevant subspace analysis (DRSA), maximize relevance instead of e.g. variance or kurtosis. This allows for a much stronger focus of the analysis on what the ML model actually uses for predicting, ignoring activations or concepts to which the model is invariant. Our approach is general enough to work alongside common attribution techniques such as Shapley Value, Integrated Gradients, or LRP. Our proposed methods show to be practically useful and compare favorably to the state of the art as demonstrated on benchmarks and three use cases.
Authors: Ke Zou, Yidi Chen, Ling Huang, Xuedong Yuan, Xiaojing Shen, Meng Wang, Rick Siow Mong Goh, Yong Liu, Huazhu Fu
Abstract: Medical image segmentation is critical for disease diagnosis and treatment assessment. However, concerns regarding the reliability of segmentation regions persist among clinicians, mainly attributed to the absence of confidence assessment, robustness, and calibration to accuracy. To address this, we introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks. DEviS not only enhances the calibration and robustness of baseline segmentation accuracy but also provides high-efficiency uncertainty estimation for reliable predictions. By leveraging subjective logic theory, we explicitly model probability and uncertainty for the problem of medical image segmentation. Here, the Dirichlet distribution parameterizes the distribution of probabilities for different classes of the segmentation results. To generate calibrated predictions and uncertainty, we develop a trainable calibrated uncertainty penalty. Furthermore, DEviS incorporates an uncertainty-aware filtering module, which utilizes the metric of uncertainty-calibrated error to filter reliable data within the dataset. We conducted validation studies to assess both the accuracy and robustness of DEviS segmentation, along with evaluating the efficiency and reliability of uncertainty estimation. These evaluations were performed using publicly available datasets including ISIC2018, LiTS2017, and BraTS2019. Additionally, two potential clinical trials are being conducted at Johns Hopkins OCT, Duke-OCT-DME, and FIVES datasets to demonstrate their efficacy in filtering high-quality or out-of-distribution data. Our code has been released in https://github.com/Cocofeat/DEviS.
Authors: Yang Yu, Danruo Deng, Furui Liu, Yueming Jin, Qi Dou, Guangyong Chen, Pheng-Ann Heng
Abstract: Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers). Most previous works focused on outlier detection via binary classifiers, which suffer from insufficient scalability and inability to distinguish different types of uncertainty. In this paper, we propose a novel framework, Adaptive Negative Evidential Deep Learning (ANEDL) to tackle these limitations. Concretely, we first introduce evidential deep learning (EDL) as an outlier detector to quantify different types of uncertainty, and design different uncertainty metrics for self-training and inference. Furthermore, we propose a novel adaptive negative optimization strategy, making EDL more tailored to the unlabeled dataset containing both inliers and outliers. As demonstrated empirically, our proposed method outperforms existing state-of-the-art methods across four datasets.
Authors: Chuang Niu, Qing Lyu, Christopher D. Carothers, Parisa Kaviani, Josh Tan, Pingkun Yan, Mannudeep K. Kalra, Christopher T. Whitlow, Ge Wang
Abstract: Modern medical records include a vast amount of multimodal free text clinical data and imaging data from radiology, cardiology, and digital pathology. Fully mining such big data requires multitasking; otherwise, occult but important aspects may be overlooked, adversely affecting clinical management and population healthcare. Despite remarkable successes of AI in individual tasks with single-modal data, the progress in developing generalist medical AI remains relatively slow to combine multimodal data for multitasks because of the dual challenges of data curation and model architecture. The data challenge involves querying and curating multimodal structured and unstructured text, alphanumeric, and especially 3D tomographic scans on an individual patient level for real-time decisions and on a scale to estimate population health statistics. The model challenge demands a scalable and adaptable network architecture to integrate multimodal datasets for diverse clinical tasks. Here we propose the first-of-its-kind medical multimodal-multitask foundation model (M3FM) with application in lung cancer screening and related tasks. After we curated a comprehensive multimodal multitask dataset consisting of 49 clinical data types including 163,725 chest CT series and 17 medical tasks involved in LCS, we develop a multimodal question-answering framework as a unified training and inference strategy to synergize multimodal information and perform multiple tasks via free-text prompting. M3FM consistently outperforms the state-of-the-art single-modal task-specific models, identifies multimodal data elements informative for clinical tasks and flexibly adapts to new tasks with a small out-of-distribution dataset. As a specialty-oriented generalist medical AI model, M3FM paves the way for similar breakthroughs in other areas of medicine, closing the gap between specialists and the generalist.
Authors: Xingyu Fu, Ben Zhou, Sihao Chen, Mark Yatskar, Dan Roth
Abstract: Recent advances in multimodal large language models (LLMs) have shown extreme effectiveness in visual question answering (VQA). However, the design nature of these end-to-end models prevents them from being interpretable to humans, undermining trust and applicability in critical domains. While post-hoc rationales offer certain insight into understanding model behavior, these explanations are not guaranteed to be faithful to the model. In this paper, we address these shortcomings by introducing an interpretable by design model that factors model decisions into intermediate human-legible explanations, and allows people to easily understand why a model fails or succeeds. We propose the Dynamic Clue Bottleneck Model ( (DCLUB), a method that is designed towards an inherently interpretable VQA system. DCLUB provides an explainable intermediate space before the VQA decision and is faithful from the beginning, while maintaining comparable performance to black-box systems. Given a question, DCLUB first returns a set of visual clues: natural language statements of visually salient evidence from the image, and then generates the output based solely on the visual clues. To supervise and evaluate the generation of VQA explanations within DCLUB, we collect a dataset of 1.7k reasoning-focused questions with visual clues. Evaluations show that our inherently interpretable system can improve 4.64% over a comparable black-box system in reasoning-focused questions while preserving 99.43% of performance on VQA-v2.
Authors: Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Yarin Gal, Nicolas Papernot, Ross Anderson
Abstract: Stable Diffusion revolutionised image creation from descriptive text. GPT-2, GPT-3(.5) and GPT-4 demonstrated astonishing performance across a variety of language tasks. ChatGPT introduced such language models to the general public. It is now clear that large language models (LLMs) are here to stay, and will bring about drastic change in the whole ecosystem of online text and images. In this paper we consider what the future might hold. What will happen to GPT-{n} once LLMs contribute much of the language found online? We find that use of model-generated content in training causes irreversible defects in the resulting models, where tails of the original content distribution disappear. We refer to this effect as Model Collapse and show that it can occur in Variational Autoencoders, Gaussian Mixture Models and LLMs. We build theoretical intuition behind the phenomenon and portray its ubiquity amongst all learned generative models. We demonstrate that it has to be taken seriously if we are to sustain the benefits of training from large-scale data scraped from the web. Indeed, the value of data collected about genuine human interactions with systems will be increasingly valuable in the presence of content generated by LLMs in data crawled from the Internet.
Authors: Haomin Zhuang, Mingxian Yu, Hao Wang, Yang Hua, Jian Li, Xu Yuan
Abstract: Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices. However, the decentralized learning paradigm and heterogeneity of FL further extend the attack surface for backdoor attacks. Existing FL attack and defense methodologies typically focus on the whole model. None of them recognizes the existence of backdoor-critical (BC) layers-a small subset of layers that dominate the model vulnerabilities. Attacking the BC layers achieves equivalent effects as attacking the whole model but at a far smaller chance of being detected by state-of-the-art (SOTA) defenses. This paper proposes a general in-situ approach that identifies and verifies BC layers from the perspective of attackers. Based on the identified BC layers, we carefully craft a new backdoor attack methodology that adaptively seeks a fundamental balance between attacking effects and stealthiness under various defense strategies. Extensive experiments show that our BC layer-aware backdoor attacks can successfully backdoor FL under seven SOTA defenses with only 10% malicious clients and outperform the latest backdoor attack methods.
Authors: Eve Le Guillou, Michael Will, Pierre Guillou, Jonas Lukasczyk, Pierre Fortin, Christoph Garth, Julien Tierny
Abstract: This system paper documents the technical foundations for the extension of the Topology ToolKit (TTK) to distributed-memory parallelism with the Message Passing Interface (MPI). While several recent papers introduced topology-based approaches for distributed-memory environments, these were reporting experiments obtained with tailored, mono-algorithm implementations. In contrast, we describe in this paper a versatile approach (supporting both triangulated domains and regular grids) for the support of topological analysis pipelines, i.e. a sequence of topological algorithms interacting together. While developing this extension, we faced several algorithmic and software engineering challenges, which we document in this paper. We describe an MPI extension of TTK's data structure for triangulation representation and traversal, a central component to the global performance and generality of TTK's topological implementations. We also introduce an intermediate interface between TTK and MPI, both at the global pipeline level, and at the fine-grain algorithmic level. We provide a taxonomy for the distributed-memory topological algorithms supported by TTK, depending on their communication needs and provide examples of hybrid MPI+thread parallelizations. Performance analyses show that parallel efficiencies range from 20% to 80% (depending on the algorithms), and that the MPI-specific preconditioning introduced by our framework induces a negligible computation time overhead. We illustrate the new distributed-memory capabilities of TTK with an example of advanced analysis pipeline, combining multiple algorithms, run on the largest publicly available dataset we have found (120 billion vertices) on a cluster with 64 nodes (for a total of 1536 cores). Finally, we provide a roadmap for the completion of TTK's MPI extension, along with generic recommendations for each algorithm communication category.
Authors: Yujin Oh, Sangjoon Park, Hwa Kyung Byun, Yeona Cho, Ik Jae Lee, Jin Sung Kim, Jong Chul Ye
Abstract: Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the recent advancement of large language models (LLMs) that can facilitate the integration of the textural information and images, here we present a novel LLM-driven multimodal AI, namely LLMSeg, that utilizes the clinical text information and is applicable to the challenging task of target volume contouring for radiation therapy, and validate it within the context of breast cancer radiation therapy target volume contouring. Using external validation and data-insufficient environments, which attributes highly conducive to real-world applications, we demonstrate that the proposed model exhibits markedly improved performance compared to conventional unimodal AI models, particularly exhibiting robust generalization performance and data efficiency. To our best knowledge, this is the first LLM-driven multimodal AI model that integrates the clinical text information into target volume delineation for radiation oncology.
Authors: Tianyi Xie, Zeshun Zong, Yuxing Qiu, Xuan Li, Yutao Feng, Yin Yang, Chenfanfu Jiang
Abstract: We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis. Employing a custom Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, "cage meshes," or any other geometry embedding, highlighting the principle of "what you see is what you simulate (WS$^2$)." Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements. Our project page is at: https://xpandora.github.io/PhysGaussian/
Authors: Woohyeok Kim, Geonu Kim, Junyong Lee, Seungyong Lee, Seung-Hwan Baek, Sunghyun Cho
Abstract: RAW images are rarely shared mainly due to its excessive data size compared to their sRGB counterparts obtained by camera ISPs. Learning the forward and inverse processes of camera ISPs has been recently demonstrated, enabling physically-meaningful RAW-level image processing on input sRGB images. However, existing learning-based ISP methods fail to handle the large variations in the ISP processes with respect to camera parameters such as ISO and exposure time, and have limitations when used for various applications. In this paper, we propose ParamISP, a learning-based method for forward and inverse conversion between sRGB and RAW images, that adopts a novel neural-network module to utilize camera parameters, which is dubbed as ParamNet. Given the camera parameters provided in the EXIF data, ParamNet converts them into a feature vector to control the ISP networks. Extensive experiments demonstrate that ParamISP achieve superior RAW and sRGB reconstruction results compared to previous methods and it can be effectively used for a variety of applications such as deblurring dataset synthesis, raw deblurring, HDR reconstruction, and camera-to-camera transfer.
Authors: Tomer Garber, Tom Tirer
Abstract: Training deep neural networks has become a common approach for addressing image restoration problems. An alternative for training a "task-specific" network for each observation model is to use pretrained deep denoisers for imposing only the signal's prior within iterative algorithms, without additional training. Recently, a sampling-based variant of this approach has become popular with the rise of diffusion/score-based generative models. Using denoisers for general purpose restoration requires guiding the iterations to ensure agreement of the signal with the observations. In low-noise settings, guidance that is based on back-projection (BP) has been shown to be a promising strategy (used recently also under the names "pseudoinverse" or "range/null-space" guidance). However, the presence of noise in the observations hinders the gains from this approach. In this paper, we propose a novel guidance technique, based on preconditioning that allows traversing from BP-based guidance to least squares based guidance along the restoration scheme. The proposed approach is robust to noise while still having much simpler implementation than alternative methods (e.g., it does not require SVD or a large number of iterations). We use it within both an optimization scheme and a sampling-based scheme, and demonstrate its advantages over existing methods for image deblurring and super-resolution.
Authors: Wenxuan Yang, Weimin Tan, Yuqi Sun, Bo Yan
Abstract: Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models. This involves strategies that focus on data quality rather than quantity, ensuring the data used for training has high informational value. Data-effective learning plays a profound role in accelerating foundation model training, reducing computational costs, and saving data storage, which is very important as the volume of medical data in recent years has grown beyond many people's expectations. However, due to the lack of standards and comprehensive benchmarks, research on medical data-effective learning is poorly studied. To address this gap, our paper introduces a comprehensive benchmark specifically for evaluating data-effective learning in the medical field. This benchmark includes a dataset with millions of data samples from 31 medical centers (DataDEL), a baseline method for comparison (MedDEL), and a new evaluation metric (NormDEL) to objectively measure data-effective learning performance. Our extensive experimental results show the baseline MedDEL can achieve performance comparable to the original large dataset with only 5% of the data. Establishing such an open data-effective learning benchmark is crucial for the medical foundation model research community because it facilitates efficient data use, promotes collaborative breakthroughs, and fosters the development of cost-effective, scalable, and impactful healthcare solutions.
Authors: Chandan Agrawal, Ashish Papanai, Jerome White
Abstract: This paper describes and evaluates a multistage approach to AI deployment. Each stage involves a more accurate method of inference, yet engaging each comes with an increasing cost. In outlining the architecture, we present a method for quantifying model uncertainty that facilitates confident deferral decisions. The architecture is currently under active deployment to thousands of cotton farmers across India. The broader idea however is applicable to a growing sector of AI deployments in challenging low resources settings.
Authors: Yatong Bai, Mo Zhou, Vishal M. Patel, Somayeh Sojoudi
Abstract: Adversarial robustness often comes at the cost of degraded accuracy, impeding the real-life application of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with already-trained high-performance large models, necessitating the exploration of training-free ensemble approaches. Observing that robust models are more confident in correct predictions than in incorrect ones on clean and adversarial data alike, we speculate amplifying this "benign confidence property" can reconcile accuracy and robustness in an ensemble setting. To achieve so, we propose "MixedNUTS", a training-free method where the output logits of a robust classifier and a standard non-robust classifier are processed by nonlinear transformations with only three parameters, which are optimized through an efficient algorithm. MixedNUTS then converts the transformed logits into probabilities and mixes them as the overall output. On CIFAR-10, CIFAR-100, and ImageNet datasets, experimental results with custom strong adaptive attacks demonstrate MixedNUTS's vastly improved accuracy and near-SOTA robustness -- it boosts CIFAR-100 clean accuracy by 7.86 points, sacrificing merely 0.87 points in robust accuracy.
Authors: Yanbo Wang, Jian Liang, Ran He
Abstract: Gradient inversion attacks aim to reconstruct local training data from intermediate gradients exposed in the federated learning framework. Despite successful attacks, all previous methods, starting from reconstructing a single data point and then relaxing the single-image limit to batch level, are only tested under hard label constraints. Even for single-image reconstruction, we still lack an analysis-based algorithm to recover augmented soft labels. In this work, we change the focus from enlarging batchsize to investigating the hard label constraints, considering a more realistic circumstance where label smoothing and mixup techniques are used in the training process. In particular, we are the first to initiate a novel algorithm to simultaneously recover the ground-truth augmented label and the input feature of the last fully-connected layer from single-input gradients, and provide a necessary condition for any analytical-based label recovery methods. Extensive experiments testify to the label recovery accuracy, as well as the benefits to the following image reconstruction. We believe soft labels in classification tasks are worth further attention in gradient inversion attacks.
Authors: Jessica Quaye, Alicia Parrish, Oana Inel, Charvi Rastogi, Hannah Rose Kirk, Minsuk Kahng, Erin van Liemt, Max Bartolo, Jess Tsang, Justin White, Nathan Clement, Rafael Mosquera, Juan Ciro, Vijay Janapa Reddi, Lora Aroyo
Abstract: With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generation of offensive images. By focusing on ``implicitly adversarial'' prompts (those that trigger T2I models to generate unsafe images for non-obvious reasons), we isolate a set of difficult safety issues that human creativity is well-suited to uncover. To this end, we built the Adversarial Nibbler Challenge, a red-teaming methodology for crowdsourcing a diverse set of implicitly adversarial prompts. We have assembled a suite of state-of-the-art T2I models, employed a simple user interface to identify and annotate harms, and engaged diverse populations to capture long-tail safety issues that may be overlooked in standard testing. The challenge is run in consecutive rounds to enable a sustained discovery and analysis of safety pitfalls in T2I models. In this paper, we present an in-depth account of our methodology, a systematic study of novel attack strategies and discussion of safety failures revealed by challenge participants. We also release a companion visualization tool for easy exploration and derivation of insights from the dataset. The first challenge round resulted in over 10k prompt-image pairs with machine annotations for safety. A subset of 1.5k samples contains rich human annotations of harm types and attack styles. We find that 14% of images that humans consider harmful are mislabeled as ``safe'' by machines. We have identified new attack strategies that highlight the complexity of ensuring T2I model robustness. Our findings emphasize the necessity of continual auditing and adaptation as new vulnerabilities emerge. We are confident that this work will enable proactive, iterative safety assessments and promote responsible development of T2I models.
Authors: Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, Huajun Chen
Abstract: This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive metrics for systematic evaluation. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to efficiently detoxify LLMs with limited impact on general performance. Then, we propose a simple yet effective baseline, dubbed Detoxifying with Intraoperative Neural Monitoring (DINM), to diminish the toxicity of LLMs within a few tuning steps via only one instance. We further provide an in-depth analysis of the internal mechanism for various detoxifying approaches, demonstrating that previous methods like SFT and DPO may merely suppress the activations of toxic parameters, while DINM mitigates the toxicity of the toxic parameters to a certain extent, making permanent adjustments. We hope that these insights could shed light on future work of developing detoxifying approaches and the underlying knowledge mechanisms of LLMs. Code and benchmark are available at https://github.com/zjunlp/EasyEdit.
Authors: Huiping Zhuang, Yizhu Chen, Di Fang, Run He, Kai Tong, Hongxin Wei, Ziqian Zeng, Cen Chen
Abstract: Class incremental learning (CIL) trains a network on sequential tasks with separated categories but suffers from catastrophic forgetting, where models quickly lose previously learned knowledge when acquiring new tasks. The generalized CIL (GCIL) aims to address the CIL problem in a more real-world scenario, where incoming data have mixed data categories and unknown sample size distribution, leading to intensified forgetting. Existing attempts for the GCIL either have poor performance, or invade data privacy by saving historical exemplars. To address this, in this paper, we propose an exemplar-free generalized analytic class incremental learning (G-ACIL). The G-ACIL adopts analytic learning (a gradient-free training technique), and delivers an analytical solution (i.e., closed-form) to the GCIL scenario. This solution is derived via decomposing the incoming data into exposed and unexposed classes, allowing an equivalence between the incremental learning and its joint training, i.e., the weight-invariant property. Such an equivalence is theoretically validated through matrix analysis tools, and hence contributes interpretability in GCIL. It is also empirically evidenced by experiments on various datasets and settings of GCIL. The results show that the G-ACIL exhibits leading performance with high robustness compared with existing competitive GCIL methods. Codes will be ready at \url{https://github.com/ZHUANGHP/Analytic-continual-learning}.
URLs: https://github.com/ZHUANGHP/Analytic-continual-learning
Authors: Sreenitha Kasarapu, Sanket Shukla, Rakibul Hassan, Avesta Sasan, Houman Homayoun, Sai Manoj Pudukotai Dinakarrao
Abstract: One of the pivotal security threats for the embedded computing systems is malicious software a.k.a malware. With efficiency and efficacy, Machine Learning (ML) has been widely adopted for malware detection in recent times. Despite being efficient, the existing techniques require a tremendous number of benign and malware samples for training and modeling an efficient malware detector. Furthermore, such constraints limit the detection of emerging malware samples due to the lack of sufficient malware samples required for efficient training. To address such concerns, we introduce a code-aware data generation technique that generates multiple mutated samples of the limitedly seen malware by the devices. Loss minimization ensures that the generated samples closely mimic the limitedly seen malware and mitigate the impractical samples. Such developed malware is further incorporated into the training set to formulate the model that can efficiently detect the emerging malware despite having limited exposure. The experimental results demonstrates that the proposed technique achieves an accuracy of 90% in detecting limitedly seen malware, which is approximately 3x more than the accuracy attained by state-of-the-art techniques.
Authors: Hongruixuan Chen, Jian Song, Chengxi Han, Junshi Xia, Naoto Yokoya
Abstract: Convolutional neural networks (CNN) and Transformers have made impressive progress in the field of remote sensing change detection (CD). However, both architectures have inherent shortcomings. Recently, the Mamba architecture, based on state space models, has shown remarkable performance in a series of natural language processing tasks, which can effectively compensate for the shortcomings of the above two architectures. In this paper, we explore for the first time the potential of the Mamba architecture for remote sensing CD tasks. We tailor the corresponding frameworks, called MambaBCD, MambaSCD, and MambaBDA, for binary change detection (BCD), semantic change detection (SCD), and building damage assessment (BDA), respectively. All three frameworks adopt the cutting-edge Visual Mamba architecture as the encoder, which allows full learning of global spatial contextual information from the input images. For the change decoder, which is available in all three architectures, we propose three spatio-temporal relationship modeling mechanisms, which can be naturally combined with the Mamba architecture and fully utilize its attribute to achieve spatio-temporal interaction of multi-temporal features, thereby obtaining accurate change information. On five benchmark datasets, our proposed frameworks outperform current CNN- and Transformer-based approaches without using any complex training strategies or tricks, fully demonstrating the potential of the Mamba architecture in CD tasks. Specifically, we obtained 83.11%, 88.39% and 94.19% F1 scores on the three BCD datasets SYSU, LEVIR-CD+, and WHU-CD; on the SCD dataset SECOND, we obtained 24.11% SeK; and on the BDA dataset xBD, we obtained 81.41% overall F1 score. Further experiments show that our architecture is quite robust to degraded data. The source code will be available in https://github.com/ChenHongruixuan/MambaCD
Authors: Judy X Yang, Jun Zhou, Jing Wang, Hui Tian, Alan Wee-Chung Liew
Abstract: The fusion of hyperspectral and LiDAR data has been an active research topic. Existing fusion methods have ignored the high-dimensionality and redundancy challenges in hyperspectral images, despite that band selection methods have been intensively studied for hyperspectral image (HSI) processing. This paper addresses this significant gap by introducing a cross-attention mechanism from the transformer architecture for the selection of HSI bands guided by LiDAR data. LiDAR provides high-resolution vertical structural information, which can be useful in distinguishing different types of land cover that may have similar spectral signatures but different structural profiles. In our approach, the LiDAR data are used as the "query" to search and identify the "key" from the HSI to choose the most pertinent bands for LiDAR. This method ensures that the selected HSI bands drastically reduce redundancy and computational requirements while working optimally with the LiDAR data. Extensive experiments have been undertaken on three paired HSI and LiDAR data sets: Houston 2013, Trento and MUUFL. The results highlight the superiority of the cross-attention mechanism, underlining the enhanced classification accuracy of the identified HSI bands when fused with the LiDAR features. The results also show that the use of fewer bands combined with LiDAR surpasses the performance of state-of-the-art fusion models.
Authors: Hugo Caselles-Dupr\'e, Charles Mellerio, Paul H\'erent, Aliz\'ee Lopez-Persem, Benoit B\'eranger, Mathieu Soularue, Pierre Fautrel, Gauthier Vernier, Matthieu Cord
Abstract: The reconstruction of images observed by subjects from fMRI data collected during visual stimuli has made significant strides in the past decade, thanks to the availability of extensive fMRI datasets and advancements in generative models for image generation. However, the application of visual reconstruction has remained limited. Reconstructing visual imagination presents a greater challenge, with potentially revolutionary applications ranging from aiding individuals with disabilities to verifying witness accounts in court. The primary hurdles in this field are the absence of data collection protocols for visual imagery and the lack of datasets on the subject. Traditionally, fMRI-to-image relies on data collected from subjects exposed to visual stimuli, which poses issues for generating visual imagery based on the difference of brain activity between visual stimulation and visual imagery. For the first time, we have compiled a substantial dataset (around 6h of scans) on visual imagery along with a proposed data collection protocol. We then train a modified version of an fMRI-to-image model and demonstrate the feasibility of reconstructing images from two modes of imagination: from memory and from pure imagination. This marks an important step towards creating a technology that allow direct reconstruction of visual imagery.
Authors: Chi Tran, Huong Le Thanh
Abstract: Large Language Models (LLMs) and Multimodal Large language models (MLLMs) have taken the world by storm with impressive abilities in complex reasoning and linguistic comprehension. Meanwhile there are plethora of works related to Vietnamese Large Language Models, the lack of high-quality resources in multimodality limits the progress of Vietnamese MLLMs. In this paper, we pioneer in address this by introducing LaVy, a state-of-the-art Vietnamese MLLM, and we also introduce LaVy-Bench benchmark designated for evaluating MLLMs's understanding on Vietnamese visual language tasks. Our project is public at https://github.com/baochi0212/LaVy