Authors: Deen Dayal Mohan, Bhavin Jawade, Srirangaraj Setlur, Venu Govindaraj
Objective functions that optimize deep neural networks play a vital role in creating an enhanced feature representation of the input data. Although cross-entropy-based loss formulations have been extensively used in a variety of supervised deep-learning applications, these methods tend to be less adequate when there is large intra-class variance and low inter-class variance in input data distribution. Deep Metric Learning seeks to develop methods that aim to measure the similarity between data samples by learning a representation function that maps these data samples into a representative embedding space. It leverages carefully designed sampling strategies and loss functions that aid in optimizing the generation of a discriminative embedding space even for distributions having low inter-class and high intra-class variances. In this chapter, we will provide an overview of recent progress in this area and discuss state-of-the-art Deep Metric Learning approaches.
Authors: Yuxuan Li, Luca Weihs
Pretrained representations from large-scale vision models have boosted the performance of downstream embodied policy learning. We look to understand whether additional self-supervised pretraining on exploration trajectories can build on these general-purpose visual representations to better support embodied planning in realistic environments. We evaluated four common auxiliary losses in embodied AI, two hindsight-based losses, and a standard imitation learning loss, by pretraining the agent's visual compression module and state belief representations with each objective and using CLIP as a representative visual backbone. The learned representations are then frozen for downstream multi-step evaluation on two goal-directed tasks. Surprisingly, we find that imitation learning on these exploration trajectories out-performs all other auxiliary losses even despite the exploration trajectories being dissimilar from the downstream tasks. This suggests that imitation of exploration may be ''all you need'' for building powerful planning representations. Additionally, we find that popular auxiliary losses can benefit from simple modifications to improve their support for downstream planning ability.
Authors: Vladimir Yugay, Yue Li, Theo Gevers, Martin R. Oswald
We present a new dense simultaneous localization and mapping (SLAM) method that uses Gaussian splats as a scene representation. The new representation enables interactive-time reconstruction and photo-realistic rendering of real-world and synthetic scenes. We propose novel strategies for seeding and optimizing Gaussian splats to extend their use from multiview offline scenarios to sequential monocular RGBD input data setups. In addition, we extend Gaussian splats to encode geometry and experiment with tracking against this scene representation. Our method achieves state-of-the-art rendering quality on both real-world and synthetic datasets while being competitive in reconstruction performance and runtime.
Authors: Yuzhe Yang, Haoran Zhang, Judy W Gichoya, Dina Katabi, Marzyeh Ghassemi
As artificial intelligence (AI) rapidly approaches human-level performance in medical imaging, it is crucial that it does not exacerbate or propagate healthcare disparities. Prior research has established AI's capacity to infer demographic data from chest X-rays, leading to a key concern: do models using demographic shortcuts have unfair predictions across subpopulations? In this study, we conduct a thorough investigation into the extent to which medical AI utilizes demographic encodings, focusing on potential fairness discrepancies within both in-distribution training sets and external test sets. Our analysis covers three key medical imaging disciplines: radiology, dermatology, and ophthalmology, and incorporates data from six global chest X-ray datasets. We confirm that medical imaging AI leverages demographic shortcuts in disease classification. While correcting shortcuts algorithmically effectively addresses fairness gaps to create "locally optimal" models within the original data distribution, this optimality is not true in new test settings. Surprisingly, we find that models with less encoding of demographic attributes are often most "globally optimal", exhibiting better fairness during model evaluation in new test environments. Our work establishes best practices for medical imaging models which maintain their performance and fairness in deployments beyond their initial training contexts, underscoring critical considerations for AI clinical deployments across populations and sites.
Authors: Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan
It has been shown that learning audiovisual features can lead to improved speech recognition performance over audio-only features, especially for noisy speech. However, in many common applications, the visual features are partially or entirely missing, e.g.~the speaker might move off screen. Multi-modal models need to be robust: missing video frames should not degrade the performance of an audiovisual model to be worse than that of a single-modality audio-only model. While there have been many attempts at building robust models, there is little consensus on how robustness should be evaluated. To address this, we introduce a framework that allows claims about robustness to be evaluated in a precise and testable way. We also conduct a systematic empirical study of the robustness of common audiovisual speech recognition architectures on a range of acoustic noise conditions and test suites. Finally, we show that an architecture-agnostic solution based on cascades can consistently achieve robustness to missing video, even in settings where existing techniques for robustness like dropout fall short.
Authors: Hamed Qazanfari, Mohammad M. AlyanNezhadi, Zohreh Nozari Khoshdaregi
Content-based image retrieval (CBIR) systems have emerged as crucial tools in the field of computer vision, allowing for image search based on visual content rather than relying solely on metadata. This survey paper presents a comprehensive overview of CBIR, emphasizing its role in object detection and its potential to identify and retrieve visually similar images based on content features. Challenges faced by CBIR systems, including the semantic gap and scalability, are discussed, along with potential solutions. It elaborates on the semantic gap, which arises from the disparity between low-level features and high-level semantic concepts, and explores approaches to bridge this gap. One notable solution is the integration of relevance feedback (RF), empowering users to provide feedback on retrieved images and refine search results iteratively. The survey encompasses long-term and short-term learning approaches that leverage RF for enhanced CBIR accuracy and relevance. These methods focus on weight optimization and the utilization of active learning algorithms to select samples for training classifiers. Furthermore, the paper investigates machine learning techniques and the utilization of deep learning and convolutional neural networks to enhance CBIR performance. This survey paper plays a significant role in advancing the understanding of CBIR and RF techniques. It guides researchers and practitioners in comprehending existing methodologies, challenges, and potential solutions while fostering knowledge dissemination and identifying research gaps. By addressing future research directions, it sets the stage for advancements in CBIR that will enhance retrieval accuracy, usability, and effectiveness in various application domains.
Authors: Shun Liu, Jianan Zhang, Ruocheng Song, Teik Toe Teoh
Object detection and localization are crucial tasks for biomedical image analysis, particularly in the field of hematology where the detection and recognition of blood cells are essential for diagnosis and treatment decisions. While attention-based methods have shown significant progress in object detection in various domains, their application in medical object detection has been limited due to the unique challenges posed by medical imaging datasets. To address this issue, we propose ADA-YOLO, a light-weight yet effective method for medical object detection that integrates attention-based mechanisms with the YOLOv8 architecture. Our proposed method leverages the dynamic feature localisation and parallel regression for computer vision tasks through \textit{adaptive head} module. Empirical experiments were conducted on the Blood Cell Count and Detection (BCCD) dataset to evaluate the effectiveness of ADA-YOLO. The results showed that ADA-YOLO outperforms the YOLOv8 model in mAP (mean average precision) on the BCCD dataset by using more than 3 times less space than YOLOv8. This indicates that our proposed method is effective. Moreover, the light-weight nature of our proposed method makes it suitable for deployment in resource-constrained environments such as mobile devices or edge computing systems. which could ultimately lead to improved diagnosis and treatment outcomes in the field of hematology.
Authors: Zhuofan Xia, Dongchen Han, Yizeng Han, Xuran Pan, Shiji Song, Gao Huang
Generalized Referring Expression Segmentation (GRES) extends the scope of classic RES to referring to multiple objects in one expression or identifying the empty targets absent in the image. GRES poses challenges in modeling the complex spatial relationships of the instances in the image and identifying non-existing referents. Recently, Multimodal Large Language Models (MLLMs) have shown tremendous progress in these complicated vision-language tasks. Connecting Large Language Models (LLMs) and vision models, MLLMs are proficient in understanding contexts with visual inputs. Among them, LISA, as a representative, adopts a special [SEG] token to prompt a segmentation mask decoder, e.g., SAM, to enable MLLMs in the RES task. However, existing solutions to of GRES remain unsatisfactory since current segmentation MLLMs cannot properly handle the cases where users might reference multiple subjects in a singular prompt or provide descriptions incongruent with any image target. In this paper, we propose Generalized Segmentation Vision Assistant (GSVA) to address this gap. Specifically, GSVA reuses the [SEG] token to prompt the segmentation model towards supporting multiple mask references simultaneously and innovatively learns to generate a [REJ] token to reject the null targets explicitly. Experiments validate GSVA's efficacy in resolving the GRES issue, marking a notable enhancement and setting a new record on the GRES benchmark gRefCOCO dataset. GSVA also proves effective across various classic referring expression segmentation and comprehension tasks.
Authors: Yingzhe Peng, Xu Yang, Haoxuan Ma, Shuo Xu, Chi Zhang, Yucheng Han, Hanwang Zhang
This paper studies how to configure powerful In-Context Demonstration (ICD) sequences for a Large Vision-Language Model (LVLM) to solve Vision-Language tasks through In-Context Learning (ICL). After observing that configuring an ICD sequence is a mirror process of composing a sentence, i.e., just as a sentence can be composed word by word via a Language Model, an ICD sequence can also be configured one by one. Consequently, we introduce an ICD Language Model (ICD-LM) specifically designed to generate effective ICD sequences. This involves creating a dataset of hand-crafted ICD sequences for various query samples and using it to train the ICD-LM. Our approach, diverging from traditional methods in NLP that select and order ICDs separately, enables to simultaneously learn how to select and order ICDs, enhancing the effect of the sequences. Moreover, during data construction, we use the LVLM intended for ICL implementation to validate the strength of each ICD sequence, resulting in a model-specific dataset and the ICD-LM trained by this dataset is also model-specific. We validate our methodology through experiments in Visual Question Answering and Image Captioning, confirming the viability of using a Language Model for ICD configuration. Our comprehensive ablation studies further explore the impact of various dataset construction and ICD-LM development settings on the outcomes. The code is given in https://github.com/ForJadeForest/ICD-LM.
Authors: Minhyun Lee, Song Park, Byeongho Heo, Dongyoon Han, Hyunjung Shim
Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires extensive datasets, leading to large storage requirements. This storage challenge poses a critical bottleneck for scaling up vision models. Motivated by the success of discrete representations, SeiT proposes to use Vector-Quantized (VQ) feature vectors (i.e., tokens) as network inputs for vision classification. However, applying traditional data augmentations to tokens faces challenges due to input domain shift. To address this issue, we introduce TokenAdapt and ColorAdapt, simple yet effective token-based augmentation strategies. TokenAdapt realigns token embedding space for compatibility with spatial augmentations, preserving the model's efficiency without requiring fine-tuning. Additionally, ColorAdapt addresses color-based augmentations for tokens inspired by Adaptive Instance Normalization (AdaIN). We evaluate our approach across various scenarios, including storage-efficient ImageNet-1k classification, fine-grained classification, robustness benchmarks, and ADE-20k semantic segmentation. Experimental results demonstrate consistent performance improvement in diverse experiments. Code is available at https://github.com/naver-ai/tokenadapt.
Authors: Rubèn Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, Lei Kang, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
Document Visual Question Answering (DocVQA) is a fast growing branch of document understanding. Despite the fact that documents contain sensitive or copyrighted information, none of the current DocVQA methods offers strong privacy guarantees.
In this work, we explore privacy in the domain of DocVQA for the first time. We highlight privacy issues in state of the art multi-modal LLM models used for DocVQA, and explore possible solutions.
Specifically, we focus on the invoice processing use case as a realistic, widely used scenario for document understanding, and propose a large scale DocVQA dataset comprising invoice documents and associated questions and answers. We employ a federated learning scheme, that reflects the real-life distribution of documents in different businesses, and we explore the use case where the ID of the invoice issuer is the sensitive information to be protected.
We demonstrate that non-private models tend to memorise, behaviour that can lead to exposing private information. We then evaluate baseline training schemes employing federated learning and differential privacy in this multi-modal scenario, where the sensitive information might be exposed through any of the two input modalities: vision (document image) or language (OCR tokens).
Finally, we design an attack exploiting the memorisation effect of the model, and demonstrate its effectiveness in probing different DocVQA models.
Authors: Xiaofeng Zhang, Zishan Xu, Hao Tang, Chaochen Gu, Wei Chen, Shanying Zhu, Xinping Guan
Low-light image enhancement is a crucial visual task, and many unsupervised methods tend to overlook the degradation of visible information in low-light scenes, which adversely affects the fusion of complementary information and hinders the generation of satisfactory results. To address this, our study introduces ``Enlighten-Your-Voice'', a multimodal enhancement framework that innovatively enriches user interaction through voice and textual commands. This approach does not merely signify a technical leap but also represents a paradigm shift in user engagement. Our model is equipped with a Dual Collaborative Attention Module (DCAM) that meticulously caters to distinct content and color discrepancies, thereby facilitating nuanced enhancements. Complementarily, we introduce a Semantic Feature Fusion (SFM) plug-and-play module that synergizes semantic context with low-light enhancement operations, sharpening the algorithm's efficacy. Crucially, ``Enlighten-Your-Voice'' showcases remarkable generalization in unsupervised zero-shot scenarios. The source code can be accessed from https://github.com/zhangbaijin/Enlighten-Your-Voice
Authors: Yige Chen, Ang Chen, Siyuan Chen, Ran Yi
With the help of Score Distillation Sampling(SDS) and the rapid development of various trainable 3D representations, Text-to-Image(T2I) diffusion models have been applied to 3D generation tasks and achieved considerable results. There are also some attempts toward the task of editing 3D objects leveraging this Text-to-3D pipeline. However, most methods currently focus on adding additional geometries, overwriting textures or both. But few of them can perform non-rigid transformation of 3D objects. For those who can perform non-rigid editing, on the other hand, suffer from low-resolution, lack of fidelity and poor flexibility. In order to address these issues, we present: Plasticine3D, a general, high-fidelity, photo-realistic and controllable non-rigid editing pipeline. Firstly, our work divides the editing process into a geometry editing stage and a texture editing stage to achieve more detailed and photo-realistic results ; Secondly, in order to perform non-rigid transformation with controllable results while maintain the fidelity towards original 3D models in the same time, we propose a multi-view-embedding(MVE) optimization strategy to ensure that the diffusion model learns the overall features of the original object and an embedding-fusion(EF) to control the degree of editing by adjusting the value of the fusing rate. We also design a geometry processing step before optimizing on the base geometry to cope with different needs of various editing tasks. Further more, to fully leverage the geometric prior from the original 3D object, we provide an optional replacement of score distillation sampling named score projection sampling(SPS) which enables us to directly perform optimization from the origin 3D mesh in most common median non-rigid editing scenarios. We demonstrate the effectiveness of our method on both the non-rigid 3D editing task and general 3D editing task.
Authors: Young Joo Han, Ha-Jin Yu
Modeling and synthesizing real sRGB noise is crucial for various low-level vision tasks. The distribution of real sRGB noise is highly complex and affected by a multitude of factors, making its accurate modeling extremely challenging. Therefore, recent studies have proposed methods that employ data-driven generative models, such as generative adversarial networks (GAN) and Normalizing Flows. These studies achieve more accurate modeling of sRGB noise compared to traditional noise modeling methods. However, there are performance limitations due to the inherent characteristics of each generative model. To address this issue, we propose NM-FlowGAN, a hybrid approach that exploits the strengths of both GAN and Normalizing Flows. We simultaneously employ a pixel-wise noise modeling network based on Normalizing Flows, and spatial correlation modeling networks based on GAN. In our experiments, our NM-FlowGAN outperforms other baselines on the sRGB noise synthesis task. Moreover, the denoising neural network, trained with synthesized image pairs from our model, also shows superior performance compared to other baselines. Our code is available at: https://github.com/YoungJooHan/NM-FlowGAN
Authors: Qin Guo, Tianwei Lin
Recently, diffusion-based methods, like InstructPix2Pix (IP2P), have achieved effective instruction-based image editing, requiring only natural language instructions from the user. However, these methods often inadvertently alter unintended areas and struggle with multi-instruction editing, resulting in compromised outcomes. To address these issues, we introduce the Focus on Your Instruction (FoI), a method designed to ensure precise and harmonious editing across multiple instructions without extra training or test-time optimization. In the FoI, we primarily emphasize two aspects: (1) precisely extracting regions of interest for each instruction and (2) guiding the denoising process to concentrate within these regions of interest. For the first objective, we identify the implicit grounding capability of IP2P from the cross-attention between instruction and image, then develop an effective mask extraction method. For the second objective, we introduce a cross attention modulation module for rough isolation of target editing regions and unrelated regions. Additionally, we introduce a mask-guided disentangle sampling strategy to further ensure clear region isolation. Experimental results demonstrate that FoI surpasses existing methods in both quantitative and qualitative evaluations, especially excelling in multi-instruction editing task.
Authors: Nikolaos Ioannis Bountos, Arthur Ouaknine, David Rolnick
Forests are an essential part of Earth's ecosystems and natural systems, as well as providing services on which humanity depends, yet they are rapidly changing as a result of land use decisions and climate change. Understanding and mitigating negative effects requires parsing data on forests at global scale from a broad array of sensory modalities, and recently many such problems have been approached using machine learning algorithms for remote sensing. To date, forest-monitoring problems have largely been approached in isolation. Inspired by the rise of foundation models for computer vision and remote sensing, we here present the first unified Forest Monitoring Benchmark (FoMo-Bench). FoMo-Bench consists of 15 diverse datasets encompassing satellite, aerial, and inventory data, covering a variety of geographical regions, and including multispectral, red-green-blue, synthetic aperture radar (SAR) and LiDAR data with various temporal, spatial and spectral resolutions. FoMo-Bench includes multiple types of forest-monitoring tasks, spanning classification, segmentation, and object detection. To further enhance the diversity of tasks and geographies represented in FoMo-Bench, we introduce a novel global dataset, TalloS, combining satellite imagery with ground-based annotations for tree species classification, spanning 1,000+ hierarchical taxonomic levels (species, genus, family). Finally, we propose FoMo-Net, a foundation model baseline designed for forest monitoring with the flexibility to process any combination of commonly used sensors in remote sensing. This work aims to inspire research collaborations between machine learning and forest biology researchers in exploring scalable multi-modal and multi-task models for forest monitoring. All code and data will be made publicly available.
Authors: Xin Guo, Jiangwei Lao, Bo Dang, Yingying Zhang, Lei Yu, Lixiang Ru, Liheng Zhong, Ziyuan Huang, Kang Wu, Dingxiang Hu, Huimei He, Jian Wang, Jingdong Chen, Ming Yang, Yongjun Zhang, Yansheng Li
Prior studies on Remote Sensing Foundation Model (RSFM) reveal immense potential towards a generic model for Earth Observation. Nevertheless, these works primarily focus on a single modality without temporal and geo-context modeling, hampering their capabilities for diverse tasks. In this study, we present SkySense, a generic billion-scale model, pre-trained on a curated multi-modal Remote Sensing Imagery (RSI) dataset with 21.5 million temporal sequences. SkySense incorporates a factorized multi-modal spatiotemporal encoder taking temporal sequences of optical and Synthetic Aperture Radar (SAR) data as input. This encoder is pre-trained by our proposed Multi-Granularity Contrastive Learning to learn representations across different modal and spatial granularities. To further enhance the RSI representations by the geo-context clue, we introduce Geo-Context Prototype Learning to learn region-aware prototypes upon RSI's multi-modal spatiotemporal features. To our best knowledge, SkySense is the largest Multi-Modal RSFM to date, whose modules can be flexibly combined or used individually to accommodate various tasks. It demonstrates remarkable generalization capabilities on a thorough evaluation encompassing 16 datasets over 7 tasks, from single- to multi-modal, static to temporal, and classification to localization. SkySense surpasses 18 recent RSFMs in all test scenarios. Specifically, it outperforms the latest models such as GFM, SatLas and Scale-MAE by a large margin, i.e., 2.76%, 3.67% and 3.61% on average respectively. We will release the pre-trained weights to facilitate future research and Earth Observation applications.
Authors: Wei Tan, Lan Du, Wray Buntine
The effectiveness of active learning largely depends on the sampling efficiency of the acquisition function. Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the reduction in classification error, and more general costs fit in the same framework. We propose Bayesian Estimate of Mean Proper Scores (BEMPS) to estimate the increase in strictly proper scores such as log probability or negative mean square error within this framework. We also prove convergence results for this general class of costs. To facilitate better experimentation with the new acquisition functions, we develop a complementary batch AL algorithm that encourages diversity in the vector of expected changes in scores for unlabeled data. To allow high-performance classifiers, we combine deep ensembles, and dynamic validation set construction on pretrained models, and further speed up the ensemble process with the idea of Monte Carlo Dropout. Extensive experiments on both texts and images show that the use of mean square error and log probability with BEMPS yields robust acquisition functions and well-calibrated classifiers, and consistently outperforms the others tested. The advantages of BEMPS over the others are further supported by a set of qualitative analyses, where we visualise their sampling behaviour using data maps and t-SNE plots.
Authors: Jaeho Moon, Juan Luis Gonzalez Bello, Byeongjun Kwon, Munchurl Kim
Self-supervised monocular depth estimation (DE) is an approach to learning depth without costly depth ground truths. However, it often struggles with moving objects that violate the static scene assumption during training. To address this issue, we introduce a coarse-to-fine training strategy leveraging the ground contacting prior based on the observation that most moving objects in outdoor scenes contact the ground. In the coarse training stage, we exclude the objects in dynamic classes from the reprojection loss calculation to avoid inaccurate depth learning. To provide precise supervision on the depth of the objects, we present a novel Ground-contacting-prior Disparity Smoothness Loss (GDS-Loss) that encourages a DE network to align the depth of the objects with their ground-contacting points. Subsequently, in the fine training stage, we refine the DE network to learn the detailed depth of the objects from the reprojection loss, while ensuring accurate DE on the moving object regions by employing our regularization loss with a cost-volume-based weighting factor. Our overall coarse-to-fine training strategy can easily be integrated with existing DE methods without any modifications, significantly enhancing DE performance on challenging Cityscapes and KITTI datasets, especially in the moving object regions.
Authors: Suyi Jiang, Haimin Luo, Haoran Jiang, Ziyu Wang, Jingyi Yu, Lan Xu
Recent months have witnessed rapid progress in 3D generation based on diffusion models. Most advances require fine-tuning existing 2D Stable Diffsuions into multi-view settings or tedious distilling operations and hence fall short of 3D human generation due to the lack of diverse 3D human datasets. We present an alternative scheme named MVHuman to generate human radiance fields from text guidance, with consistent multi-view images directly sampled from pre-trained Stable Diffsuions without any fine-tuning or distilling. Our core is a multi-view sampling strategy to tailor the denoising processes of the pre-trained network for generating consistent multi-view images. It encompasses view-consistent conditioning, replacing the original noises with ``consistency-guided noises'', optimizing latent codes, as well as utilizing cross-view attention layers. With the multi-view images through the sampling process, we adopt geometry refinement and 3D radiance field generation followed by a subsequent neural blending scheme for free-view rendering. Extensive experiments demonstrate the efficacy of our method, as well as its superiority to state-of-the-art 3D human generation methods.
Authors: Pascal Zimmer, Sébastien Andreina, Giorgia Azzurra Marson, Ghassan Karame
Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as RND (Qin et al., NeuRIPS 2021) and Random Image Transformations (Xie et al., ICLR 2018), only for low-confidence inputs is sufficient to prevent them. Our approach is independent of training and supported by theory. We verify the effectiveness of our approach for various existing defenses by conducting extensive experiments on CIFAR-10, CIFAR-100, and ImageNet. Our results confirm that our proposal can indeed enhance these defenses by providing better tradeoffs between robustness and accuracy when compared to state-of-the-art approaches while being completely training-free.
Authors: Zhi Zhang, Qizhe Zhang, Zijun Gao, Renrui Zhang, Ekaterina Shutova, Shiji Zhou, Shanghang Zhang
With the growing size of pre-trained models, full fine-tuning and storing all the parameters for various downstream tasks is costly and infeasible. In this paper, we propose a new parameter-efficient fine-tuning method, Gradient-based Parameter Selection (GPS), demonstrating that only tuning a few selected parameters from the pre-trained model while keeping the remainder of the model frozen can generate similar or better performance compared with the full model fine-tuning method. Different from the existing popular and state-of-the-art parameter-efficient fine-tuning approaches, our method does not introduce any additional parameters and computational costs during both the training and inference stages. Another advantage is the model-agnostic and non-destructive property, which eliminates the need for any other design specific to a particular model. Compared with the full fine-tuning, GPS achieves 3.33% (91.78% vs. 88.45%, FGVC) and 9.61% (73.1% vs. 65.57%, VTAB) improvement of the accuracy with tuning only 0.36% parameters of the pre-trained model on average over 24 image classification tasks; it also demonstrates a significant improvement of 17% and 16.8% in mDice and mIoU, respectively, on medical image segmentation task. Moreover, GPS achieves state-of-the-art performance compared with existing PEFT methods.
Authors: Noël Vouitsis, Zhaoyan Liu, Satya Krishna Gorti, Valentin Villecroze, Jesse C. Cresswell, Guangwei Yu, Gabriel Loaiza-Ganem, Maksims Volkovs
The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs. The most powerful models in this space have been trained using massive datasets of paired inputs and large-scale computational resources, making them prohibitively expensive to train in many practical scenarios. We surmise that existing unimodal encoders pre-trained on large amounts of unimodal data should provide an effective bootstrap to create multimodal models from unimodal ones at much lower costs. We therefore propose FuseMix, a multimodal augmentation scheme that operates on the latent spaces of arbitrary pre-trained unimodal encoders. Using FuseMix for multimodal alignment, we achieve competitive performance -- and in certain cases outperform state-of-the art methods -- in both image-text and audio-text retrieval, with orders of magnitude less compute and data: for example, we outperform CLIP on the Flickr30K text-to-image retrieval task with $\sim \! 600\times$ fewer GPU days and $\sim \! 80\times$ fewer image-text pairs. Additionally, we show how our method can be applied to convert pre-trained text-to-image generative models into audio-to-image ones. Code is available at: https://github.com/layer6ai-labs/fusemix.
Authors: Xu Liu, Tong Zhou, Yuanxin Wang, Yuping Wang, Qinjingwen Cao, Weizhi Du, Yonghuan Yang, Junjun He, Yu Qiao, Yiqing Shen
The advent of foundation models, which are pre-trained on vast datasets, has ushered in a new era of computer vision, characterized by their robustness and remarkable zero-shot generalization capabilities. Mirroring the transformative impact of foundation models like large language models (LLMs) in natural language processing, visual foundation models (VFMs) have become a catalyst for groundbreaking developments in computer vision. This review paper delineates the pivotal trajectories of VFMs, emphasizing their scalability and proficiency in generative tasks such as text-to-image synthesis, as well as their adeptness in discriminative tasks including image segmentation. While generative and discriminative models have historically charted distinct paths, we undertake a comprehensive examination of the recent strides made by VFMs in both domains, elucidating their origins, seminal breakthroughs, and pivotal methodologies. Additionally, we collate and discuss the extensive resources that facilitate the development of VFMs and address the challenges that pave the way for future research endeavors. A crucial direction for forthcoming innovation is the amalgamation of generative and discriminative paradigms. The nascent application of generative models within discriminative contexts signifies the early stages of this confluence. This survey aspires to be a contemporary compendium for scholars and practitioners alike, charting the course of VFMs and illuminating their multifaceted landscape.
Authors: Yanan Wu, Zhixiang Chi, Yang Wang, Konstantinos N. Plataniotis, Songhe Feng
Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight matrix and batch normalization (BN) layer. Previous works normally update the whole network naively without explicitly decoupling the knowledge between label and domain. As a result, it leads to knowledge interference and defective distribution adaptation. In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer. However, the normalization step in BN is intrinsically unstable when the statistics are re-estimated from a few samples. We find that ambiguities can be greatly reduced when only updating the two affine parameters in BN while keeping the source domain statistics. To further enhance the domain knowledge extraction from unlabeled data, we construct an auxiliary branch with label-independent self-supervised learning (SSL) to provide supervision. Moreover, we propose a bi-level optimization based on meta-learning to enforce the alignment of two learning objectives of auxiliary and main branches. The goal is to use the auxiliary branch to adapt the domain and benefit main task for subsequent inference. Our method keeps the same computational cost at inference as the auxiliary branch can be thoroughly discarded after adaptation. Extensive experiments show that our method outperforms the prior works on five WILDS real-world domain shift datasets. Our method can also be integrated with methods with label-dependent optimization to further push the performance boundary. Our code is available at https://github.com/ynanwu/MABN.
Authors: Peizhao Li, Junfeng He, Gang Li, Rachit Bhargava, Shaolei Shen, Nachiappan Valliappan, Youwei Liang, Hongxiang Gu, Venky Ramachandran, Golnaz Farhadi, Yang Li, Kai J Kohlhoff, Vidhya Navalpakkam
Progress in human behavior modeling involves understanding both implicit, early-stage perceptual behavior such as human attention and explicit, later-stage behavior such as subjective ratings/preferences. Yet, most prior research has focused on modeling implicit and explicit human behavior in isolation. Can we build a unified model of human attention and preference behavior that reliably works across diverse types of visual content? Such a model would enable predicting subjective feedback such as overall satisfaction or aesthetic quality ratings, along with the underlying human attention or interaction heatmaps and viewing order, enabling designers and content-creation models to optimize their creation for human-centric improvements. In this paper, we propose UniAR -- a unified model that predicts both implicit and explicit human behavior across different types of visual content. UniAR leverages a multimodal transformer, featuring distinct prediction heads for each facet, and predicts attention heatmap, scanpath or viewing order, and subjective rating/preference. We train UniAR on diverse public datasets spanning natural images, web pages and graphic designs, and achieve leading performance on multiple benchmarks across different image domains and various behavior modeling tasks. Potential applications include providing instant feedback on the effectiveness of UIs/digital designs/images, and serving as a reward model to further optimize design/image creation.
Authors: Erez Yosef, Raja Giryes
Image reconstruction in low-light conditions is a challenging problem. Many solutions have been proposed for it, where the main approach is trying to learn a good prior of natural images along with modeling the true statistics of the noise in the scene. In the presence of very low lighting conditions, such approaches are usually not enough, and additional information is required, e.g., in the form of using multiple captures. In this work, we suggest as an alternative to add a description of the scene as prior, which can be easily done by the photographer who is capturing the scene. Using a text-conditioned diffusion model, we show that adding image caption information improves significantly the image reconstruction in low-light conditions on both synthetic and real-world images.
Authors: David C. Jeong, Hongji Liu, Saunder Salazar, Jessie Jiang, Christopher A. Kitts
While recent two-stage many-to-one deep learning models have demonstrated great success in 3D human pose estimation, such models are inefficient ways to detect 3D key points in a sequential video relative to one-shot and many-to-many models. Another key drawback of two-stage and many-to-one models is that errors in the first stage will be passed onto the second stage. In this paper, we introduce SoloPose, a novel one-shot, many-to-many spatio-temporal transformer model for kinematic 3D human pose estimation of video. SoloPose is further fortified by HeatPose, a 3D heatmap based on Gaussian Mixture Model distributions that factors target key points as well as kinematically adjacent key points. Finally, we address data diversity constraints with the 3D AugMotion Toolkit, a methodology to augment existing 3D human pose datasets, specifically by projecting four top public 3D human pose datasets (Humans3.6M, MADS, AIST Dance++, MPI INF 3DHP) into a novel dataset (Humans7.1M) with a universal coordinate system. Extensive experiments are conducted on Human3.6M as well as the augmented Humans7.1M dataset, and SoloPose demonstrates superior results relative to the state-of-the-art approaches.
Authors: Stefanos Ginargiros, Nikolaos Passalis, Anastasios Tefas
Deep Learning (DL) has brought significant advances to robotics vision tasks. However, most existing DL methods have a major shortcoming, they rely on a static inference paradigm inherent in traditional computer vision pipelines. On the other hand, recent studies have found that active perception improves the perception abilities of various models by going beyond these static paradigms. Despite the significant potential of active perception, it poses several challenges, primarily involving significant changes in training pipelines for deep learning models. To overcome these limitations, in this work, we propose a generic supervised active perception pipeline for object detection that can be trained using existing off-the-shelf object detectors, while also leveraging advances in simulation environments. To this end, the proposed method employs an additional neural network architecture that estimates better viewpoints in cases where the object detector confidence is insufficient. The proposed method was evaluated on synthetic datasets, constructed within the Webots robotics simulator, showcasing its effectiveness in two object detection cases.
Authors: Arefeh Rezaei, Mohammad Javad Ahmadi, Amir Molaei, Hamid. D. Taghirad
assessment using video data and to showcase the effectiveness of the proposed approach in evaluating surgeon proficiency, its potential for targeted training interventions, and quality assurance in surgical departments. The pipeline incorporates a representation flow convolutional neural network and a novel tree-based Gaussian process classifier, which is robust to noise, while being computationally efficient. Additionally, new kernels are introduced to enhance accuracy. The performance of the pipeline is evaluated using the JIGSAWS dataset. Comparative analysis with existing literature reveals significant improvement in accuracy and betterment in computation cost. The proposed pipeline contributes to computational efficiency and accuracy improvement in surgical skill assessment using video data. Results of our study based on comments of our colleague surgeons show that the proposed method has the potential to facilitate skill improvement among surgery fellows and enhance patient safety through targeted training interventions and quality assurance in surgical departments.
Authors: Weijie Wei, Fatemeh Karimi Nejadasl, Theo Gevers, Martin R. Oswald
The scarcity of annotated data in outdoor point cloud segmentation poses a significant obstacle in harnessing the modeling capabilities of advanced networks like transformers. Consequently, scholars have been actively investigating efficacious self-supervised pre-training strategies, e.g. contrasting learning and reconstruction-based pretext tasks. Nevertheless, temporal information, which is inherent in the LiDAR point cloud sequence, is consistently disregarded. To better utilize this property, we propose an effective pre-training strategy, namely Temporal Masked AutoEncoders (T-MAE), which takes as input temporally adjacent frames and learns temporal dependency. A SiamWCA backbone, containing a Siamese encoder and a window-based cross-attention (WCA) module, is established for the two-frame input. Taking into account that the motion of an ego-vehicle alters the illumination angles of the same instance, temporal modeling also serves as a robust and natural data augmentation, enhancing the comprehension of target objects. Moreover, instead of utilizing consecutive frames, it is more cost-effective and powerful by using distant historical frames. SiamWCA is a powerful architecture but heavily relies on annotated data. With our T-MAE pre-training strategy, we achieve the best performance on the Waymo dataset among self-supervised learning methods. Comprehensive experiments are conducted to validate all components of our proposal. Upon acceptance, the source code will be made accessible.
Authors: Le Peng, Hengyue Liang, Gaoxiang Luo, Taihui Li, Ju Sun
Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained models may be suboptimal. This insight has partly motivated the recent differential TL strategies, such as TransFusion (TF) and layer-wise finetuning (LWFT), which treat the layers in the pretrained models differentially. In this paper, we add one more strategy into this family, called TruncatedTL, which reuses and finetunes appropriate bottom layers and directly discards the remaining layers. This yields not only superior MIC performance but also compact models for efficient inference, compared to other differential TL methods. Our code is available at: https://github.com/sun-umn/TTL
Authors: Lei Wang, Ke Sun, Piotr Koniusz
We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor. Tensor descriptors require a robust similarity measure due to low numbers of aggregated vectors and the burstiness phenomenon, when a given feature appears more/less frequently than statistically expected. The Heat Diffusion Process (HDP) on a graph Laplacian is closely related to the Eigenvalue Power Normalization (EPN) of the covariance/autocorrelation matrix, whose inverse forms a loopy graph Laplacian. We show that the HDP and the EPN play the same role, i.e., to boost or dampen the magnitude of the eigenspectrum thus preventing the burstiness. We equip higher-order tensors with EPN which acts as a spectral detector of higher-order occurrences to prevent burstiness. We also prove that for a tensor of order r built from d dimensional feature descriptors, such a detector gives the likelihood if at least one higher-order occurrence is 'projected' into one of binom(d,r) subspaces represented by the tensor; thus forming a tensor power normalization metric endowed with binom(d,r) such 'detectors'. For experimental contributions, we apply several second- and higher-order pooling variants to action recognition, provide previously not presented comparisons of such pooling variants, and show state-of-the-art results on HMDB-51, YUP++ and MPII Cooking Activities.
Authors: Bichen Wu, Ruizhe Cheng, Peizhao Zhang, Tianren Gao, Peter Vajda, Joseph E. Gonzalez
Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts than supervised "gold" labels. Previous works, such as CLIP, use InfoNCE loss to train a model to predict the pairing between images and text captions. CLIP, however, is data hungry and requires more than 400M image-text pairs for training. The inefficiency can be partially attributed to the fact that the image-text pairs are noisy. To address this, we propose OTTER (Optimal TransporT distillation for Efficient zero-shot Recognition), which uses online entropic optimal transport to find a soft image-text match as labels for contrastive learning. Based on pretrained image and text encoders, models trained with OTTER achieve strong performance with only 3M image text pairs. Compared with InfoNCE loss, label smoothing, and knowledge distillation, OTTER consistently outperforms these baselines in zero shot evaluation on Google Open Images (19,958 classes) and multi-labeled ImageNet 10K (10032 classes) from Tencent ML-Images. Over 42 evaluations on 7 different dataset/architecture settings x 6 metrics, OTTER outperforms (32) or ties (2) all baselines in 34 of them.
Authors: Yanhui Guo, Fangzhou Luo, Shaoyuan Xu
For image restoration, methods leveraging priors from generative models have been proposed and demonstrated a promising capacity to robustly restore photorealistic and high-quality results. However, these methods are susceptible to semantic ambiguity, particularly with images that have obviously correct semantics such as facial images. In this paper, we propose a semantic-aware latent space exploration method for image restoration (SAIR). By explicitly modeling semantics information from a given reference image, SAIR is able to reliably restore severely degraded images not only to high-resolution and highly realistic looks but also to correct semantics. Quantitative and qualitative experiments collectively demonstrate the superior performance of the proposed SAIR. Our code is available at https://github.com/Liamkuo/SAIR.
Authors: Sunit Shantanu Digamber Fulari
This paper reveals about global navigation satellite system GNSS in the indian subcontinent known as the navigation in the indian subcontinent(NavIC) We have tried to model a new technique in GNSS known as the optical flow tracking global navigation system (OF GNSS). This method using differential equations is very accurate for very small distances on the surface of the earth in the 1500km range of the Indian subcontinent satellite coverage. When we talk of accuracy of the GPS system it should be very accurate on the surface of the earth when used to show changes in coordinate of the moving body with respect to the ground by the satellite which is situated on the earths orbit. Optical flow is a method which uses movements with respect to x and y axis for infinitesimal changes in its coordinates and then uses this algorithm to use it in global positioning system to find accurate position of the body with respect to the satellite coordinates with respect to ground positioning. The modern method of differential frames is also very accurate as it involves infinitesimal frames which are modelled together from the satellite to find changes in the coordinates on the earths surface, so we have designed a new algorithm in this paper on the Optical flow GNSS system which is an alternative and can improve the study done in the design of these algorithms in this field of applications.
Authors: Sanghyun Jo, In-Jae Yu, Kyungsu Kim
Although weakly supervised semantic segmentation using only image-level labels (WSSS-IL) is potentially useful, its low performance and implementation complexity still limit its application. The main causes are (a) non-detection and (b) false-detection phenomena: (a) The class activation maps refined from existing WSSS-IL methods still only represent partial regions for large-scale objects, and (b) for small-scale objects, over-activation causes them to deviate from the object edges. We propose RecurSeed, which alternately reduces non- and false detections through recursive iterations, thereby implicitly finding an optimal junction that minimizes both errors. We also propose a novel data augmentation (DA) approach called EdgePredictMix, which further expresses an object's edge by utilizing the probability difference information between adjacent pixels in combining the segmentation results, thereby compensating for the shortcomings when applying the existing DA methods to WSSS. We achieved new state-of-the-art performances on both the PASCAL VOC 2012 and MS COCO 2014 benchmarks (VOC val: 74.4%, COCO val: 46.4%). The code is available at https://github.com/shjo-april/RecurSeed_and_EdgePredictMix.
Authors: Pan Xie, Qipeng Zhang, Taiyi Peng, Hao Tang, Yao Du, Zexian Li
The Sign Language Production (SLP) project aims to automatically translate spoken languages into sign sequences. Our approach focuses on the transformation of sign gloss sequences into their corresponding sign pose sequences (G2P). In this paper, we present a novel solution for this task by converting the continuous pose space generation problem into a discrete sequence generation problem. We introduce the Pose-VQVAE framework, which combines Variational Autoencoders (VAEs) with vector quantization to produce a discrete latent representation for continuous pose sequences. Additionally, we propose the G2P-DDM model, a discrete denoising diffusion architecture for length-varied discrete sequence data, to model the latent prior. To further enhance the quality of pose sequence generation in the discrete space, we present the CodeUnet model to leverage spatial-temporal information. Lastly, we develop a heuristic sequential clustering method to predict variable lengths of pose sequences for corresponding gloss sequences. Our results show that our model outperforms state-of-the-art G2P models on the public SLP evaluation benchmark. For more generated results, please visit our project page: \textcolor{blue}{\url{https://slpdiffusier.github.io/g2p-ddm}}
Authors: Xu Zheng, Yunhao Luo, Chong Fu, Kangcheng Liu, Lin Wang
The popular methods for semi-supervised semantic segmentation mostly adopt a unitary network model using convolutional neural networks (CNNs) and enforce consistency of the model's predictions over perturbations applied to the inputs or model. However, such a learning paradigm suffers from two critical limitations: a) learning the discriminative features for the unlabeled data; b) learning both global and local information from the whole image. In this paper, we propose a novel Semi-supervised Learning (SSL) approach, called Transformer-CNN Cohort (TCC), that consists of two students with one based on the vision transformer (ViT) and the other based on the CNN. Our method subtly incorporates the multi-level consistency regularization on the predictions and the heterogeneous feature spaces via pseudo-labeling for the unlabeled data. First, as the inputs of the ViT student are image patches, the feature maps extracted encode crucial class-wise statistics. To this end, we propose class-aware feature consistency distillation (CFCD) that first leverages the outputs of each student as the pseudo labels and generates class-aware feature (CF) maps for knowledge transfer between the two students. Second, as the ViT student has more uniform representations for all layers, we propose consistency-aware cross distillation (CCD) to transfer knowledge between the pixel-wise predictions from the cohort. We validate the TCC framework on Cityscapes and Pascal VOC 2012 datasets, which outperforms existing SSL methods by a large margin.
Authors: Chunzhuo Wang, T. Sunil Kumar, Walter De Raedt, Guido Camps, Hans Hallez, Bart Vanrumste
Unhealthy dietary habits are considered as the primary cause of various chronic diseases, including obesity and diabetes. The automatic food intake monitoring system has the potential to improve the quality of life (QoL) of people with diet-related diseases through dietary assessment. In this work, we propose a novel contactless radar-based approach for food intake monitoring. Specifically, a Frequency Modulated Continuous Wave (FMCW) radar sensor is employed to recognize fine-grained eating and drinking gestures. The fine-grained eating/drinking gesture contains a series of movements from raising the hand to the mouth until putting away the hand from the mouth. A 3D temporal convolutional network with self-attention (3D-TCN-Att) is developed to detect and segment eating and drinking gestures in meal sessions by processing the Range-Doppler Cube (RD Cube). Unlike previous radar-based research, this work collects data in continuous meal sessions (more realistic scenarios). We create a public dataset comprising 70 meal sessions (4,132 eating gestures and 893 drinking gestures) from 70 participants with a total duration of 1,155 minutes. Four eating styles (fork & knife, chopsticks, spoon, hand) are included in this dataset. To validate the performance of the proposed approach, seven-fold cross-validation method is applied. The 3D-TCN-Att model achieves a segmental F1-score of 0.896 and 0.868 for eating and drinking gestures, respectively. The results of the proposed approach indicate the feasibility of using radar for fine-grained eating and drinking gesture detection and segmentation in meal sessions.
Authors: Yu-Hsi Chen, Chien-Yao Wang, Cheng-Yun Yang, Hung-Shuo Chang, Youn-Long Lin, Yung-Yu Chuang, Hong-Yuan Mark Liao
We propose a post-processor, called NeighborTrack, that leverages neighbor information of the tracking target to validate and improve single-object tracking (SOT) results. It requires no additional data or retraining. Instead, it uses the confidence score predicted by the backbone SOT network to automatically derive neighbor information and then uses this information to improve the tracking results. When tracking an occluded target, its appearance features are untrustworthy. However, a general siamese network often cannot tell whether the tracked object is occluded by reading the confidence score alone, because it could be misled by neighbors with high confidence scores. Our proposed NeighborTrack takes advantage of unoccluded neighbors' information to reconfirm the tracking target and reduces false tracking when the target is occluded. It not only reduces the impact caused by occlusion, but also fixes tracking problems caused by object appearance changes. NeighborTrack is agnostic to SOT networks and post-processing methods. For the VOT challenge dataset commonly used in short-term object tracking, we improve three famous SOT networks, Ocean, TransT, and OSTrack, by an average of ${1.92\%}$ EAO and ${2.11\%}$ robustness. For the mid- and long-term tracking experiments based on OSTrack, we achieve state-of-the-art ${72.25\%}$ AUC on LaSOT and ${75.7\%}$ AO on GOT-10K. Code duplication can be found in https://github.com/franktpmvu/NeighborTrack.
Authors: Nisha Huang, Yuxin Zhang, Fan Tang, Chongyang Ma, Haibin Huang, Yong Zhang, Weiming Dong, Changsheng Xu
Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user. Unlike the previous image-to-image transfer approaches, text-guided stylization progress provides users with a more precise and intuitive way to express the desired style. However, the huge discrepancy between cross-modal inputs/outputs makes it challenging to conduct text-driven image stylization in a typical feed-forward CNN pipeline. In this paper, we present DiffStyler, a dual diffusion processing architecture to control the balance between the content and style of the diffused results. The cross-modal style information can be easily integrated as guidance during the diffusion process step-by-step. Furthermore, we propose a content image-based learnable noise on which the reverse denoising process is based, enabling the stylization results to better preserve the structure information of the content image. We validate the proposed DiffStyler beyond the baseline methods through extensive qualitative and quantitative experiments. Code is available at \url{https://github.com/haha-lisa/Diffstyler}.
Authors: Swetha Nadella, Pramiti Barua, Jeremy C. Hagler, David J. Lamb, Qing Tian
In this paper, we investigate the two most popular families of deep neural architectures (i.e., ResNets and InceptionNets) for the autonomous driving task of steering angle prediction. To ensure a comprehensive comparison, we conducted experiments on the Kaggle SAP dataset and custom dataset and carefully examined a range of different model sizes within both the ResNet and InceptionNet families. Our derived models can achieve state-of-the-art results in terms of steering angle MSE. In addition to this analysis, we introduced the attention mechanism to enhance steering angle prediction. This attention mechanism facilitated an in-depth exploration of the model's selective focus on essential elements within the input data. Furthermore, recognizing the importance of security and robustness in autonomous driving assessed the resilience of our models to adversarial attacks.
Authors: Zenglin Shi, Ying Sun, Joo Hwee Lim, Mengmi Zhang
This paper considers learning a sequence of tasks continually with the objectives of generalizing over unseen data regardless of its distribution, accumulating knowledge and transferring knowledge across tasks. To the best of our knowledge, no existing technique can accomplish all of these objectives simultaneously. This paper proposes such a technique by investigating the role of robust generalization in Continual Learning (CL). Recent findings show that models trained to exhibit robust generalization not only generalize better, but also demonstrate improved transferability and tend to find flatter local minima. This motivates us to achieve robust generalization in each task in CL, facilitating learning a new task and reducing the risk of forgetting previously learned tasks. To achieve this, we propose a new online shape-texture self-distillation (STSD) method that learns both shape and texture representations for each task, improving robust generalization. Extensive experiments demonstrate that our approach can be easily combined with existing CL methods to improve generalization, encourage knowledge transfer, and reduce forgetting. We also show that our approach finds flatter local minima, further highlighting the importance of improving robust generalization in CL. Our proposed technique is a significant step forward in achieving the aforementioned CL objectives simultaneously.
Authors: Devon Ulrich, Ruth Fong
Many visualization techniques have been created to explain the behavior of computer vision models, but they largely consist of static diagrams that convey limited information. Interactive visualizations allow users to more easily interpret a model's behavior, but most are not easily reusable for new models. We introduce Visual Feature Search, a novel interactive visualization that is adaptable to any CNN and can easily be incorporated into a researcher's workflow. Our tool allows a user to highlight an image region and search for images from a given dataset with the most similar model features. We demonstrate how our tool elucidates different aspects of model behavior by performing experiments on a range of applications, such as in medical imaging and wildlife classification.
Authors: Nan Jiang, Tengyu Liu, Zhexuan Cao, Jieming Cui, Zhiyuan zhang, Yixin Chen, He Wang, Yixin Zhu, Siyuan Huang
Fine-grained capturing of 3D HOI boosts human activity understanding and facilitates downstream visual tasks, including action recognition, holistic scene reconstruction, and human motion synthesis. Despite its significance, existing works mostly assume that humans interact with rigid objects using only a few body parts, limiting their scope. In this paper, we address the challenging problem of f-AHOI, wherein the whole human bodies interact with articulated objects, whose parts are connected by movable joints. We present CHAIRS, a large-scale motion-captured f-AHOI dataset, consisting of 16.2 hours of versatile interactions between 46 participants and 81 articulated and rigid sittable objects. CHAIRS provides 3D meshes of both humans and articulated objects during the entire interactive process, as well as realistic and physically plausible full-body interactions. We show the value of CHAIRS with object pose estimation. By learning the geometrical relationships in HOI, we devise the very first model that leverage human pose estimation to tackle the estimation of articulated object poses and shapes during whole-body interactions. Given an image and an estimated human pose, our model first reconstructs the pose and shape of the object, then optimizes the reconstruction according to a learned interaction prior. Under both evaluation settings (e.g., with or without the knowledge of objects' geometries/structures), our model significantly outperforms baselines. We hope CHAIRS will promote the community towards finer-grained interaction understanding. We will make the data/code publicly available.
Authors: Yunpyo An, Suyeong Park, Kwang In Kim
Re-training a deep learning model each time a single data point receives a new label is impractical due to the inherent complexity of the training process. Consequently, existing active learning (AL) algorithms tend to adopt a batch-based approach where, during each AL iteration, a set of data points is collectively chosen for annotation. However, this strategy frequently leads to redundant sampling, ultimately eroding the efficacy of the labeling procedure. In this paper, we introduce a new AL algorithm that harnesses the power of a Gaussian process surrogate in conjunction with the neural network principal learner. Our proposed model adeptly updates the surrogate learner for every new data instance, enabling it to emulate and capitalize on the continuous learning dynamics of the neural network without necessitating a complete retraining of the principal model for each individual label. Experiments on four benchmark datasets demonstrate that this approach yields significant enhancements, either rivaling or aligning with the performance of state-of-the-art techniques.
Authors: Tianpeng Deng, Yanqi Huang, Guoqiang Han, Zhenwei Shi, Jiatai Lin, Qi Dou, Zaiyi Liu, Xiao-jing Guo, C. L. Philip Chen, Chu Han
Histopathological tissue classification is a fundamental task in computational pathology. Deep learning-based models have achieved superior performance but centralized training with data centralization suffers from the privacy leakage problem. Federated learning (FL) can safeguard privacy by keeping training samples locally, but existing FL-based frameworks require a large number of well-annotated training samples and numerous rounds of communication which hinder their practicability in the real-world clinical scenario. In this paper, we propose a universal and lightweight federated learning framework, named Federated Deep-Broad Learning (FedDBL), to achieve superior classification performance with limited training samples and only one-round communication. By simply associating a pre-trained deep learning feature extractor, a fast and lightweight broad learning inference system and a classical federated aggregation approach, FedDBL can dramatically reduce data dependency and improve communication efficiency. Five-fold cross-validation demonstrates that FedDBL greatly outperforms the competitors with only one-round communication and limited training samples, while it even achieves comparable performance with the ones under multiple-round communications. Furthermore, due to the lightweight design and one-round communication, FedDBL reduces the communication burden from 4.6GB to only 276.5KB per client using the ResNet-50 backbone at 50-round training. Since no data or deep model sharing across different clients, the privacy issue is well-solved and the model security is guaranteed with no model inversion attack risk. Code is available at https://github.com/tianpeng-deng/FedDBL.
Authors: Mingjie Sun, J. Zico Kolter
Backdoor inversion, a central step in many backdoor defenses, is a reverse-engineering process to recover the hidden backdoor trigger inserted into a machine learning model. Existing approaches tackle this problem by searching for a backdoor pattern that is able to flip a set of clean images into the target class, while the exact size needed of this support set is rarely investigated. In this work, we present a new approach for backdoor inversion, which is able to recover the hidden backdoor with as few as a single image. Insipired by recent advances in adversarial robustness, our method SmoothInv starts from a single clean image, and then performs projected gradient descent towards the target class on a robust smoothed version of the original backdoored classifier. We find that backdoor patterns emerge naturally from such optimization process. Compared to existing backdoor inversion methods, SmoothInv introduces minimum optimization variables and does not require complex regularization schemes. We perform a comprehensive quantitative and qualitative study on backdoored classifiers obtained from existing backdoor attacks. We demonstrate that SmoothInv consistently recovers successful backdoors from single images: for backdoored ImageNet classifiers, our reconstructed backdoors have close to 100% attack success rates. We also show that they maintain high fidelity to the underlying true backdoors. Last, we propose and analyze two countermeasures to our approach and show that SmoothInv remains robust in the face of an adaptive attacker. Our code is available at https://github.com/locuslab/smoothinv.
Authors: Chenyang Liu, Jiajun Yang, Zipeng Qi, Zhengxia Zou, Zhenwei Shi
Remote sensing (RS) images contain numerous objects of different scales, which poses significant challenges for the RS image change captioning (RSICC) task to identify visual changes of interest in complex scenes and describe them via language. However, current methods still have some weaknesses in sufficiently extracting and utilizing multi-scale information. In this paper, we propose a progressive scale-aware network (PSNet) to address the problem. PSNet is a pure Transformer-based model. To sufficiently extract multi-scale visual features, multiple progressive difference perception (PDP) layers are stacked to progressively exploit the differencing features of bitemporal features. To sufficiently utilize the extracted multi-scale features for captioning, we propose a scale-aware reinforcement (SR) module and combine it with the Transformer decoding layer to progressively utilize the features from different PDP layers. Experiments show that the PDP layer and SR module are effective and our PSNet outperforms previous methods. Our code is public at https://github.com/Chen-Yang-Liu/PSNet
Authors: Yuki Tatsunami, Masato Taki
Multi-head-self-attention (MHSA)-equipped models have achieved notable performance in computer vision. Their computational complexity is proportional to quadratic numbers of pixels in input feature maps, resulting in slow processing, especially when dealing with high-resolution images. New types of token-mixer are proposed as an alternative to MHSA to circumvent this problem: an FFT-based token-mixer involves global operations similar to MHSA but with lower computational complexity. However, despite its attractive properties, the FFT-based token-mixer has not been carefully examined in terms of its compatibility with the rapidly evolving MetaFormer architecture. Here, we propose a novel token-mixer called Dynamic Filter and novel image recognition models, DFFormer and CDFFormer, to close the gaps above. The results of image classification and downstream tasks, analysis, and visualization show that our models are helpful. Notably, their throughput and memory efficiency when dealing with high-resolution image recognition is remarkable. Our results indicate that Dynamic Filter is one of the token-mixer options that should be seriously considered. The code is available at https://github.com/okojoalg/dfformer
Authors: Ji Zhang, Lianli Gao, Xu Luo, Hengtao Shen, Jingkuan Song
Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on developing advanced algorithms to achieve the goal, while neglecting the inherent problems of the given support samples. In fact, with only a handful of samples available, the adverse effect of either the image noise (a.k.a. X-noise) or the label noise (a.k.a. Y-noise) from support samples can be severely amplified. To address this challenge, in this work we propose DEnoised Task Adaptation (DETA), a first, unified image- and label-denoising framework orthogonal to existing task adaptation approaches. Without extra supervision, DETA filters out task-irrelevant, noisy representations by taking advantage of both global visual information and local region details of support samples. On the challenging Meta-Dataset, DETA consistently improves the performance of a broad spectrum of baseline methods applied on various pre-trained models. Notably, by tackling the overlooked image noise in Meta-Dataset, DETA establishes new state-of-the-art results. Code is released at https://github.com/JimZAI/DETA.
Authors: Bencheng Liao, Shaoyu Chen, Bo Jiang, Tianheng Cheng, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang
Online lane graph construction is a promising but challenging task in autonomous driving. Previous methods usually model the lane graph at the pixel or piece level, and recover the lane graph by pixel-wise or piece-wise connection, which breaks down the continuity of the lane. Human drivers focus on and drive along the continuous and complete paths instead of considering lane pieces. Autonomous vehicles also require path-specific guidance from lane graph for trajectory planning. We argue that the path, which indicates the traffic flow, is the primitive of the lane graph. Motivated by this, we propose to model the lane graph in a novel path-wise manner, which well preserves the continuity of the lane and encodes traffic information for planning. We present a path-based online lane graph construction method, termed LaneGAP, which end-to-end learns the path and recovers the lane graph via a Path2Graph algorithm. We qualitatively and quantitatively demonstrate the superiority of LaneGAP over conventional pixel-based and piece-based methods on challenging nuScenes and Argoverse2 datasets. Abundant visualizations show LaneGAP can cope with diverse traffic conditions. Code and models will be released at \url{https://github.com/hustvl/LaneGAP} for facilitating future research.
Authors: Chen Song, Chandrajit Bajaj, Qixing Huang
We present DeblurSR, a novel motion deblurring approach that converts a blurry image into a sharp video. DeblurSR utilizes event data to compensate for motion ambiguities and exploits the spiking representation to parameterize the sharp output video as a mapping from time to intensity. Our key contribution, the Spiking Representation (SR), is inspired by the neuromorphic principles determining how biological neurons communicate with each other in living organisms. We discuss why the spikes can represent sharp edges and how the spiking parameters are interpreted from the neuromorphic perspective. DeblurSR has higher output quality and requires fewer computing resources than state-of-the-art event-based motion deblurring methods. We additionally show that our approach easily extends to video super-resolution when combined with recent advances in implicit neural representation. The implementation and animated visualization of DeblurSR are available at https://github.com/chensong1995/DeblurSR.
Authors: Roy Miles, Krystian Mikolajczyk
In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past examples, enabling relational gradients for the student. We then show that the normalisation of representations is tightly coupled with the training dynamics of this projector, which can have a large impact on the students performance. Finally, we show that a simple soft maximum function can be used to address any significant capacity gap problems. Experimental results on various benchmark datasets demonstrate that using these insights can lead to superior or comparable performance to state-of-the-art knowledge distillation techniques, despite being much more computationally efficient. In particular, we obtain these results across image classification (CIFAR100 and ImageNet), object detection (COCO2017), and on more difficult distillation objectives, such as training data efficient transformers, whereby we attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet. Code and models are publicly available.
Authors: Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Pinxue Guo, Kaixun Jiang, Wenqiang Zhang, Lizhe Qi
Adversarial Robustness Distillation (ARD) is a promising task to solve the issue of limited adversarial robustness of small capacity models while optimizing the expensive computational costs of Adversarial Training (AT). Despite the good robust performance, the existing ARD methods are still impractical to deploy in natural high-security scenes due to these methods rely entirely on original or publicly available data with a similar distribution. In fact, these data are almost always private, specific, and distinctive for scenes that require high robustness. To tackle these issues, we propose a challenging but significant task called Data-Free Adversarial Robustness Distillation (DFARD), which aims to train small, easily deployable, robust models without relying on data. We demonstrate that the challenge lies in the lower upper bound of knowledge transfer information, making it crucial to mining and transferring knowledge more efficiently. Inspired by human education, we design a plug-and-play Interactive Temperature Adjustment (ITA) strategy to improve the efficiency of knowledge transfer and propose an Adaptive Generator Balance (AGB) module to retain more data information. Our method uses adaptive hyperparameters to avoid a large number of parameter tuning, which significantly outperforms the combination of existing techniques. Meanwhile, our method achieves stable and reliable performance on multiple benchmarks.
Authors: SeokYeong Lee, JunYong Choi, Seungryong Kim, Ig-Jae Kim, Junghyun Cho
In this paper, we introduce a new challenge for synthesizing novel view images in practical environments with limited input multi-view images and varying lighting conditions. Neural radiance fields (NeRF), one of the pioneering works for this task, demand an extensive set of multi-view images taken under constrained illumination, which is often unattainable in real-world settings. While some previous works have managed to synthesize novel views given images with different illumination, their performance still relies on a substantial number of input multi-view images. To address this problem, we suggest ExtremeNeRF, which utilizes multi-view albedo consistency, supported by geometric alignment. Specifically, we extract intrinsic image components that should be illumination-invariant across different views, enabling direct appearance comparison between the input and novel view under unconstrained illumination. We offer thorough experimental results for task evaluation, employing the newly created NeRF Extreme benchmark-the first in-the-wild benchmark for novel view synthesis under multiple viewing directions and varying illuminations.
Authors: Hansheng Chen, Wei Tian, Pichao Wang, Fan Wang, Lu Xiong, Hao Li
Locating 3D objects from a single RGB image via Perspective-n-Point (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, allowing for partial learning of 2D-3D point correspondences by backpropagating the gradients of pose loss. Yet, learning the entire correspondences from scratch is highly challenging, particularly for ambiguous pose solutions, where the globally optimal pose is theoretically non-differentiable w.r.t. the points. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose with differentiable probability density on the SE(3) manifold. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle generalizes previous approaches, and resembles the attention mechanism. EPro-PnP can enhance existing correspondence networks, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation benchmark. Furthermore, EPro-PnP helps to explore new possibilities of network design, as we demonstrate a novel deformable correspondence network with the state-of-the-art pose accuracy on the nuScenes 3D object detection benchmark. Our code is available at https://github.com/tjiiv-cprg/EPro-PnP-v2.
Authors: Zikui Cai, Zhongpai Gao, Benjamin Planche, Meng Zheng, Terrence Chen, M. Salman Asif, Ziyan Wu
With the rise of cameras and smart sensors, humanity generates an exponential amount of data. This valuable information, including underrepresented cases like AI in medical settings, can fuel new deep-learning tools. However, data scientists must prioritize ensuring privacy for individuals in these untapped datasets, especially for images or videos with faces, which are prime targets for identification methods. Proposed solutions to de-identify such images often compromise non-identifying facial attributes relevant to downstream tasks. In this paper, we introduce Disguise, a novel algorithm that seamlessly de-identifies facial images while ensuring the usability of the modified data. Unlike previous approaches, our solution is firmly grounded in the domains of differential privacy and ensemble-learning research. Our method involves extracting and substituting depicted identities with synthetic ones, generated using variational mechanisms to maximize obfuscation and non-invertibility. Additionally, we leverage supervision from a mixture-of-experts to disentangle and preserve other utility attributes. We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.
Authors: Yuting Gao, Jinfeng Liu, Zihan Xu, Tong Wu Enwei Zhang, Wei Liu, Jie Yang, Ke Li, Xing Sun
During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a challenging task, and noise exists in the commonly used datasets. To address this issue, we propose SoftCLIP, a novel approach that relaxes the strict one-to-one constraint and achieves a soft cross-modal alignment by introducing a softened target, which is generated from the fine-grained intra-modal self-similarity. The intra-modal guidance is indicative to enable two pairs have some local similarities and model many-to-many relationships between the two modalities. Besides, since the positive still dominates in the softened target distribution, we disentangle the negatives in the distribution to further boost the relation alignment with the negatives in the cross-modal learning. Extensive experiments demonstrate the effectiveness of SoftCLIP. In particular, on ImageNet zero-shot classification task, using CC3M/CC12M as pre-training dataset, SoftCLIP brings a top-1 accuracy improvement of 6.8%/7.2% over the CLIP baseline.
Authors: Renhong Zhang, Tianheng Cheng, Shusheng Yang, Haoyi Jiang, Shuai Zhang, Jiancheng Lyu, Xin Li, Xiaowen Ying, Dashan Gao, Wenyu Liu, Xinggang Wang
Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame pixel-level instance perception and (2) complicated heuristics for tracking objects. To address those issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices. Firstly, MobileInst adopts a mobile vision transformer to extract multi-level semantic features and presents an efficient query-based dual-transformer instance decoder for mask kernels and a semantic-enhanced mask decoder to generate instance segmentation per frame. Secondly, MobileInst exploits simple yet effective kernel reuse and kernel association to track objects for video instance segmentation. Further, we propose temporal query passing to enhance the tracking ability for kernels. We conduct experiments on COCO and YouTube-VIS datasets to demonstrate the superiority of MobileInst and evaluate the inference latency on one single CPU core of Snapdragon 778G Mobile Platform, without other methods of acceleration. On the COCO dataset, MobileInst achieves 31.2 mask AP and 433 ms on the mobile CPU, which reduces the latency by 50% compared to the previous SOTA. For video instance segmentation, MobileInst achieves 35.0 AP on YouTube-VIS 2019 and 30.1 AP on YouTube-VIS 2021. Code will be available to facilitate real-world applications and future research.
Authors: Lecheng Zheng, Dawei Zhou, Hanghang Tong, Jiejun Xu, Yada Zhu, Jingrui He
There have been tremendous efforts over the past decades dedicated to the generation of realistic graphs in a variety of domains, ranging from social networks to computer networks, from gene regulatory networks to online transaction networks. Despite the remarkable success, the vast majority of these works are unsupervised in nature and are typically trained to minimize the expected graph reconstruction loss, which would result in the representation disparity issue in the generated graphs, i.e., the protected groups (often minorities) contribute less to the objective and thus suffer from systematically higher errors. In this paper, we aim to tailor graph generation to downstream mining tasks by leveraging label information and user-preferred parity constraints. In particular, we start from the investigation of representation disparity in the context of graph generative models. To mitigate the disparity, we propose a fairness-aware graph generative model named FairGen. Our model jointly trains a label-informed graph generation module and a fair representation learning module by progressively learning the behaviors of the protected and unprotected groups, from the `easy' concepts to the `hard' ones. In addition, we propose a generic context sampling strategy for graph generative models, which is proven to be capable of fairly capturing the contextual information of each group with a high probability. Experimental results on seven real-world data sets, including web-based graphs, demonstrate that FairGen (1) obtains performance on par with state-of-the-art graph generative models across nine network properties, (2) mitigates the representation disparity issues in the generated graphs, and (3) substantially boosts the model performance by up to 17% in downstream tasks via data augmentation.
Authors: Jiahao Nie, Zhiwei He, Yuxiang Yang, Xudong Lv, Mingyu Gao, Jing Zhang
Siamese trackers based on 3D region proposal network (RPN) have shown remarkable success with deep Hough voting. However, using a single seed point feature as the cue for voting fails to produce high-quality 3D proposals. Additionally, the equal treatment of seed points in the voting process, regardless of their significance, exacerbates this limitation. To address these challenges, we propose a novel transformer-based voting scheme to generate better proposals. Specifically, a global-local transformer (GLT) module is devised to integrate object- and patch-aware geometric priors into seed point features, resulting in robust and accurate cues for offset learning of seed points. To train the GLT module, we introduce an importance prediction branch that learns the potential importance weights of seed points as a training constraint. Incorporating this transformer-based voting scheme into 3D RPN, a novel Siamese method dubbed GLT-T is developed for 3D single object tracking on point clouds. Moreover, we identify that the highest-scored proposal in the Siamese paradigm may not be the most accurate proposal, which limits tracking performance. Towards this concern, we approach the binary score prediction task as a ranking problem, and design a target-aware ranking loss and a localization-aware ranking loss to produce accurate ranking of proposals. With the ranking losses, we further present GLT-T++, an enhanced version of GLT-T. Extensive experiments on multiple benchmarks demonstrate that our GLT-T and GLT-T++ outperform state-of-the-art methods in terms of tracking accuracy while maintaining a real-time inference speed. The source code will be made available at https://github.com/haooozi/GLT-T.
Authors: Tianqi Wang, Sukmin Kim, Wenxuan Ji, Enze Xie, Chongjian Ge, Junsong Chen, Zhenguo Li, Ping Luo
Safety is the primary priority of autonomous driving. Nevertheless, no published dataset currently supports the direct and explainable safety evaluation for autonomous driving. In this work, we propose DeepAccident, a large-scale dataset generated via a realistic simulator containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset with 40k annotated samples. In addition, we propose a new task, end-to-end motion and accident prediction, which can be used to directly evaluate the accident prediction ability for different autonomous driving algorithms. Furthermore, for each scenario, we set four vehicles along with one infrastructure to record data, thus providing diverse viewpoints for accident scenarios and enabling V2X (vehicle-to-everything) research on perception and prediction tasks. Finally, we present a baseline V2X model named V2XFormer that demonstrates superior performance for motion and accident prediction and 3D object detection compared to the single-vehicle model.
Authors: Hao Feng, Shaokai Liu, Jiajun Deng, Wengang Zhou, Houqiang Li
In recent years, tremendous efforts have been made on document image rectification, but existing advanced algorithms are limited to processing restricted document images, i.e., the input images must incorporate a complete document. Once the captured image merely involves a local text region, its rectification quality is degraded and unsatisfactory. Our previously proposed DocTr, a transformer-assisted network for document image rectification, also suffers from this limitation. In this work, we present DocTr++, a novel unified framework for document image rectification, without any restrictions on the input distorted images. Our major technical improvements can be concluded in three aspects. Firstly, we upgrade the original architecture by adopting a hierarchical encoder-decoder structure for multi-scale representation extraction and parsing. Secondly, we reformulate the pixel-wise mapping relationship between the unrestricted distorted document images and the distortion-free counterparts. The obtained data is used to train our DocTr++ for unrestricted document image rectification. Thirdly, we contribute a real-world test set and metrics applicable for evaluating the rectification quality. To our best knowledge, this is the first learning-based method for the rectification of unrestricted document images. Extensive experiments are conducted, and the results demonstrate the effectiveness and superiority of our method. We hope our DocTr++ will serve as a strong baseline for generic document image rectification, prompting the further advancement and application of learning-based algorithms. The source code and the proposed dataset are publicly available at https://github.com/fh2019ustc/DocTr-Plus.
Authors: Amy Lin, Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani
We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images). This task is a vital pre-processing stage for nearly all contemporary (neural) reconstruction algorithms but remains challenging given sparse views, especially for objects with visual symmetries and texture-less surfaces. We build on the recent RelPose framework which learns a network that infers distributions over relative rotations over image pairs. We extend this approach in two key ways; first, we use attentional transformer layers to process multiple images jointly, since additional views of an object may resolve ambiguous symmetries in any given image pair (such as the handle of a mug that becomes visible in a third view). Second, we augment this network to also report camera translations by defining an appropriate coordinate system that decouples the ambiguity in rotation estimation from translation prediction. Our final system results in large improvements in 6D pose prediction over prior art on both seen and unseen object categories and also enables pose estimation and 3D reconstruction for in-the-wild objects.
Authors: Minheng Chen, Zhirun Zhang, Shuheng Gu, Youyong Kong
We present a novel deep learning-based framework: Embedded Feature Similarity Optimization with Specific Parameter Initialization (SOPI) for 2D/3D medical image registration which is a most challenging problem due to the difficulty such as dimensional mismatch, heavy computation load and lack of golden evaluation standard. The framework we design includes a parameter specification module to efficiently choose initialization pose parameter and a fine-registration module to align images. The proposed framework takes extracting multi-scale features into consideration using a novel composite connection encoder with special training techniques. We compare the method with both learning-based methods and optimization-based methods on a in-house CT/X-ray dataset as well as simulated data to further evaluate performance. Our experiments demonstrate that the method in this paper has improved the registration performance, and thereby outperforms the existing methods in terms of accuracy and running time. We also show the potential of the proposed method as an initial pose estimator. The code is available at https://github.com/m1nhengChen/SOPI
Authors: Zhengqing Yuan, Xinyi Wang, Kun Wang, Lichao Sun, Yanyang Ye
In recent years, advancements in large language models have been remarkable, with models such as ChatGPT demonstrating exceptional proficiency in diverse linguistic tasks. The pre-training of large models with billions of parameters, poses a formidable challenge, primarily due to the scarcity of datasets of a commensurate scale for effective training. Nevertheless, innovative strategies have emerged, including methods to fine-tune these pre-trained models using fewer parameters set, as evidenced by models like MiniGPT-4 and LLaVA. Despite their potential in various domains, these models remain limited in their understanding of artistic imagery. They have yet to fully grasp the intricate nuances of art images or to provide an objective articulation of the emotions they evoke, in a manner akin to human perception. This work introduces ArtGPT-4, a pioneering large vision-language model tailored to address the deficiencies of contemporary models in artistic comprehension. ArtGPT-4 underwent training on image-text pairs utilizing a Tesla A100 device in a mere 2 hours, with a dataset comprising approximately 0.52M entries. Impressively, the model can render images with an artistic-understanding and convey the emotions they inspire, mirroring human interpretation. Additionally, this work presents a unique dataset designed to evaluate the efficacy of vision-language models. In subsequent evaluations, ArtGPT-4 not only achieved state-of-the-art performance on the ArtEmis and ArtEmis-v2.0 datasets but also exceeded the established benchmarks introduced in This study, lagging behind professional artists' descriptions by a negligible 0.15 points on a 6-point scale. The code and the pre-trained model are accessible in https://huggingface.co/Tyrannosaurus/ArtGPT-4.
Authors: Bohan Zeng, Shanglin Li, Xuhui Liu, Sicheng Gao, Xiaolong Jiang, Xu Tang, Yao Hu, Jianzhuang Liu, Baochang Zhang
Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models. Although diffusion models have shown promise in analyzing functional magnetic resonance imaging (fMRI) data, including reconstructing high-quality images consistent with original visual stimuli, their accuracy in extracting semantic and silhouette information from brain signals remains limited. In this regard, we propose a novel approach, referred to as Controllable Mind Visual Diffusion Model (CMVDM). CMVDM extracts semantic and silhouette information from fMRI data using attribute alignment and assistant networks. Additionally, a residual block is incorporated to capture information beyond semantic and silhouette features. We then leverage a control model to fully exploit the extracted information for image synthesis, resulting in generated images that closely resemble the visual stimuli in terms of semantics and silhouette. Through extensive experimentation, we demonstrate that CMVDM outperforms existing state-of-the-art methods both qualitatively and quantitatively.
Authors: Zihao Yu, Haoyang Li, Fangcheng Fu, Xupeng Miao, Bin Cui
Due to the recent success of diffusion models, text-to-image generation is becoming increasingly popular and achieves a wide range of applications. Among them, text-to-image editing, or continuous text-to-image generation, attracts lots of attention and can potentially improve the quality of generated images. It's common to see that users may want to slightly edit the generated image by making minor modifications to their input textual descriptions for several rounds of diffusion inference. However, such an image editing process suffers from the low inference efficiency of many existing diffusion models even using GPU accelerators. To solve this problem, we introduce Fast Image Semantically Edit (FISEdit), a cached-enabled sparse diffusion model inference engine for efficient text-to-image editing. The key intuition behind our approach is to utilize the semantic mapping between the minor modifications on the input text and the affected regions on the output image. For each text editing step, FISEdit can automatically identify the affected image regions and utilize the cached unchanged regions' feature map to accelerate the inference process. Extensive empirical results show that FISEdit can be $3.4\times$ and $4.4\times$ faster than existing methods on NVIDIA TITAN RTX and A100 GPUs respectively, and even generates more satisfactory images.
Authors: Songxue Gao, Chuanqi Jiao, Ruidong Chen, Weijie Wang, Weizhi Nie
Point cloud completion aims to recover raw point clouds captured by scanners from partial observations caused by occlusion and limited view angles. This makes it hard to recover details because the global feature is unlikely to capture the full details of all missing parts. In this paper, we propose a novel approach to point cloud completion task called Point-PC, which uses a memory network to retrieve shape priors and designs a causal inference model to filter missing shape information as supplemental geometric information to aid point cloud completion. Specifically, we propose a memory operating mechanism where the complete shape features and the corresponding shapes are stored in the form of ``key-value'' pairs. To retrieve similar shapes from the partial input, we also apply a contrastive learning-based pre-training scheme to transfer the features of incomplete shapes into the domain of complete shape features. Experimental results on the ShapeNet-55, PCN, and KITTI datasets demonstrate that Point-PC outperforms the state-of-the-art methods.
Authors: Chase Walker, Sumit Jha, Kenny Chen, Rickard Ewetz
Attribution algorithms are frequently employed to explain the decisions of neural network models. Integrated Gradients (IG) is an influential attribution method due to its strong axiomatic foundation. The algorithm is based on integrating the gradients along a path from a reference image to the input image. Unfortunately, it can be observed that gradients computed from regions where the output logit changes minimally along the path provide poor explanations for the model decision, which is called the saturation effect problem. In this paper, we propose an attribution algorithm called integrated decision gradients (IDG). The algorithm focuses on integrating gradients from the region of the path where the model makes its decision, i.e., the portion of the path where the output logit rapidly transitions from zero to its final value. This is practically realized by scaling each gradient by the derivative of the output logit with respect to the path. The algorithm thereby provides a principled solution to the saturation problem. Additionally, we minimize the errors within the Riemann sum approximation of the path integral by utilizing non-uniform subdivisions determined by adaptive sampling. In the evaluation on ImageNet, it is demonstrated that IDG outperforms IG, Left-IG, Guided IG, and adversarial gradient integration both qualitatively and quantitatively using standard insertion and deletion metrics across three common models.
Authors: Juan A Rodriguez, David Vazquez, Issam Laradji, Marco Pedersoli, Pau Rodriguez
The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art. Recent techniques have shown impressive potential in creating complex visual compositions while delivering impressive realism and quality. However, state-of-the-art methods have been focusing on the narrow domain of natural images, while other distributions remain unexplored. In this paper, we introduce the problem of text-to-figure generation, that is creating scientific figures of papers from text descriptions. We present FigGen, a diffusion-based approach for text-to-figure as well as the main challenges of the proposed task. Code and models are available at https://github.com/joanrod/figure-diffusion
Authors: Mustapha Bounoua, Giulio Franzese, Pietro Michiardi
Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer from a coherence-quality tradeoff, where models with good generation quality lack generative coherence across modalities, and vice versa. We discuss the limitations underlying the unsatisfactory performance of existing methods, to motivate the need for a different approach. We propose a novel method that uses a set of independently trained, uni-modal, deterministic autoencoders. Individual latent variables are concatenated into a common latent space, which is fed to a masked diffusion model to enable generative modeling. We also introduce a new multi-time training method to learn the conditional score network for multi-modal diffusion. Our methodology substantially outperforms competitors in both generation quality and coherence, as shown through an extensive experimental campaign.
Authors: Spyros Kondylatos, Ioannis Prapas, Gustau Camps-Valls, Ioannis Papoutsis
We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire modeling in the Mediterranean. Mesogeos integrates variables representing wildfire drivers (meteorology, vegetation, human activity) and historical records of wildfire ignitions and burned areas for 17 years (2006-2022). It is designed as a cloud-friendly spatio-temporal dataset, namely a datacube, harmonizing all variables in a grid of 1km x 1km x 1-day resolution. The datacube structure offers opportunities to assess machine learning (ML) usage in various wildfire modeling tasks. We extract two ML-ready datasets that establish distinct tracks to demonstrate this potential: (1) short-term wildfire danger forecasting and (2) final burned area estimation given the point of ignition. We define appropriate metrics and baselines to evaluate the performance of models in each track. By publishing the datacube, along with the code to create the ML datasets and models, we encourage the community to foster the implementation of additional tracks for mitigating the increasing threat of wildfires in the Mediterranean.
Authors: Mengke Li, Zhikai Hu, Yang Lu, Weichao Lan, Yiu-ming Cheung, Hui Huang
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://github.com/Keke921/H2T.
Authors: Paul Couairon, Clément Rambour, Jean-Emmanuel Haugeard, Nicolas Thome
Recently, diffusion-based generative models have achieved remarkable success for image generation and edition. However, their use for video editing still faces important limitations. This paper introduces VidEdit, a novel method for zero-shot text-based video editing ensuring strong temporal and spatial consistency. Firstly, we propose to combine atlas-based and pre-trained text-to-image diffusion models to provide a training-free and efficient editing method, which by design fulfills temporal smoothness. Secondly, we leverage off-the-shelf panoptic segmenters along with edge detectors and adapt their use for conditioned diffusion-based atlas editing. This ensures a fine spatial control on targeted regions while strictly preserving the structure of the original video. Quantitative and qualitative experiments show that VidEdit outperforms state-of-the-art methods on DAVIS dataset, regarding semantic faithfulness, image preservation, and temporal consistency metrics. With this framework, processing a single video only takes approximately one minute, and it can generate multiple compatible edits based on a unique text prompt. Project web-page at https://videdit.github.io
Authors: Wentao Liu, Tong Tian, Lemeng Wang, Weijin Xu, Lei Li, Haoyuan Li, Wenyi Zhao, Siyu Tian, Xipeng Pan, Huihua Yang, Feng Gao, Yiming Deng, Ruisheng Su
Digital subtraction angiography (DSA) is universally acknowledged as the gold standard for examining lesion angioarchitecture, elucidating arterial blood supply dynamics, and guiding endovascular interventions. The automatic segmentation of intracranial arteries (IA) in DSA, which is pivotal for quantifying vascular morphology, plays an essential role in computer-assisted stroke research and clinical practices. Nevertheless, research in this specific domain remains constrained, primarily owing to the unavailability of publicly datasets for IA segmentation within the research community. Currently, the predominant focus of methodologies lies in the segmentation of single-frame DSA using in-house datasets. These methods, limited by the partial inclusion of contrast in single-frame DSA, encounters challenges in rendering a precise representation of vascular structures. In this paper, we introduces DIAS, a dataset specifically developed for IA segmentation in DSA sequences. A comprehensive benchmark has been established for evaluating DIAS, covering fully, weakly, and semi-supervised segmentation methods. Specifically, we propose a vessel sequence segmentation network that captures the spatiotemporal representation of intravascular contrast for segmenting vessels in DSA sequences. For weakly-supervised learning, we propose a novel scribble learning-based image segmentation framework, incorporating both scribble supervision and consistency regularization. Furthermore, we introduce a random patch-based self-training framework that harnesses unlabeled DSA sequences to improve segmentation performance. Our extensive experiments on the DIAS dataset demonstrate the effectiveness of these methods as potential baselines for future research and clinical applications.
Authors: Benedikt Blumenstiel, Johannes Jakubik, Hilde Kühne, Michael Vössing
While semantic segmentation has seen tremendous improvements in the past, there are still significant labeling efforts necessary and the problem of limited generalization to classes that have not been present during training. To address this problem, zero-shot semantic segmentation makes use of large self-supervised vision-language models, allowing zero-shot transfer to unseen classes. In this work, we build a benchmark for Multi-domain Evaluation of Semantic Segmentation (MESS), which allows a holistic analysis of performance across a wide range of domain-specific datasets such as medicine, engineering, earth monitoring, biology, and agriculture. To do this, we reviewed 120 datasets, developed a taxonomy, and classified the datasets according to the developed taxonomy. We select a representative subset consisting of 22 datasets and propose it as the MESS benchmark. We evaluate eight recently published models on the proposed MESS benchmark and analyze characteristics for the performance of zero-shot transfer models. The toolkit is available at https://github.com/blumenstiel/MESS.
Authors: Qi Bi, Shaodi You, Theo Gevers
Domain-generalized urban-scene semantic segmentation (USSS) aims to learn generalized semantic predictions across diverse urban-scene styles. Unlike domain gap challenges, USSS is unique in that the semantic categories are often similar in different urban scenes, while the styles can vary significantly due to changes in urban landscapes, weather conditions, lighting, and other factors. Existing approaches typically rely on convolutional neural networks (CNNs) to learn the content of urban scenes.
In this paper, we propose a Content-enhanced Mask TransFormer (CMFormer) for domain-generalized USSS. The main idea is to enhance the focus of the fundamental component, the mask attention mechanism, in Transformer segmentation models on content information. To achieve this, we introduce a novel content-enhanced mask attention mechanism. It learns mask queries from both the image feature and its down-sampled counterpart, as lower-resolution image features usually contain more robust content information and are less sensitive to style variations. These features are fused into a Transformer decoder and integrated into a multi-resolution content-enhanced mask attention learning scheme.
Extensive experiments conducted on various domain-generalized urban-scene segmentation datasets demonstrate that the proposed CMFormer significantly outperforms existing CNN-based methods for domain-generalized semantic segmentation, achieving improvements of up to 14.00\% in terms of mIoU (mean intersection over union). The source code is publicly available at \url{https://github.com/BiQiWHU/CMFormer}.
Authors: Delong Chen, Jianfeng Liu, Wenliang Dai, Baoyuan Wang
Recent research has demonstrated that the multi-task fine-tuning of multi-modal Large Language Models (LLMs) using an assortment of annotated downstream vision-language datasets significantly enhances their performance. Yet, during this process, a side effect, which we termed as the "multi-modal alignment tax", surfaces. This side effect negatively impacts the model's ability to format responses appropriately -- for instance, its "politeness" -- due to the overly succinct and unformatted nature of raw annotations, resulting in reduced human preference. In this paper, we introduce Polite Flamingo, a multi-modal response rewriter that transforms raw annotations into a more appealing, "polite" format. Polite Flamingo is trained to reconstruct high-quality responses from their automatically distorted counterparts and is subsequently applied to a vast array of vision-language datasets for response rewriting. After rigorous filtering, we generate the PF-1M dataset and further validate its value by fine-tuning a multi-modal LLM with it. Combined with novel methodologies including U-shaped multi-stage tuning and multi-turn augmentation, the resulting model, Clever Flamingo, demonstrates its advantages in both multi-modal understanding and response politeness according to automated and human evaluations.
Authors: Shengyi Gao, Zhe Chen, Guo Chen, Wenhai Wang, Tong Lu
The combination of audio and vision has long been a topic of interest in the multi-modal community. Recently, a new audio-visual segmentation (AVS) task has been introduced, aiming to locate and segment the sounding objects in a given video. This task demands audio-driven pixel-level scene understanding for the first time, posing significant challenges. In this paper, we propose AVSegFormer, a novel framework for AVS tasks that leverages the transformer architecture. Specifically, we introduce audio queries and learnable queries into the transformer decoder, enabling the network to selectively attend to interested visual features. Besides, we present an audio-visual mixer, which can dynamically adjust visual features by amplifying relevant and suppressing irrelevant spatial channels. Additionally, we devise an intermediate mask loss to enhance the supervision of the decoder, encouraging the network to produce more accurate intermediate predictions. Extensive experiments demonstrate that AVSegFormer achieves state-of-the-art results on the AVS benchmark. The code is available at https://github.com/vvvb-github/AVSegFormer.
Authors: Zahid Hasan, Abu Zaher Md Faridee, Masud Ahmed, Sanjay Purushotham, Heesung Kwon, Hyungtae Lee, Nirmalya Roy
Novel Categories Discovery (NCD) aims to cluster novel data based on the class semantics of known classes using the open-world partial class space annotated dataset. As an alternative to the traditional pseudo-labeling-based approaches, we leverage the connection between the data sampling and the provided multinoulli (categorical) distribution of novel classes. We introduce constraints on individual and collective statistics of predicted novel class probabilities to implicitly achieve semantic-based clustering. More specifically, we align the class neuron activation distributions under Monte-Carlo sampling of novel classes in large batches by matching their empirical first-order (mean) and second-order (covariance) statistics with the multinoulli distribution of the labels while applying instance information constraints and prediction consistency under label-preserving augmentations. We then explore a directional statistics-based probability formation that learns the mixture of Von Mises-Fisher distribution of class labels in a unit hypersphere. We demonstrate the discriminative ability of our approach to realize semantic clustering of novel samples in image, video, and time-series modalities. We perform extensive ablation studies regarding data, networks, and framework components to provide better insights. Our approach maintains 94%, 93%, 85%, and 93% (approx.) classification accuracy in labeled data while achieving 90%, 84%, 72%, and 75% (approx.) clustering accuracy for novel categories in Cifar10, UCF101, MPSC-ARL, and SHAR datasets that match state-of-the-art approaches without any external clustering.
Authors: Liqi Xue, Tianyi Xu, Yongbao Song, Yan Liu, Lei Zhang, Xiantong Zhen, Jun Xu
The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format. Therefore, converting SDR images to HDR ones by inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. However, existing ITM methods are usually developed with complex network architectures requiring huge computational costs. In this paper, we propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM. Specifically, we propose a new Improved Residual Block (IRB) to extract and fuse multi-layer features for fine-grained HDR image reconstruction. Experiments on three benchmark datasets demonstrate that our IRNet achieves state-of-the-art performance on both the ITM and joint SR-ITM tasks. The code, models and data will be publicly available at https://github.com/ThisisVikki/ITM-baseline.
Authors: Lukas Haas, Michal Skreta, Silas Alberti, Chelsea Finn
Planet-scale image geolocalization remains a challenging problem due to the diversity of images originating from anywhere in the world. Although approaches based on vision transformers have made significant progress in geolocalization accuracy, success in prior literature is constrained to narrow distributions of images of landmarks, and performance has not generalized to unseen places. We present a new geolocalization system that combines semantic geocell creation, multi-task contrastive pretraining, and a novel loss function. Additionally, our work is the first to perform retrieval over location clusters for guess refinements. We train two models for evaluations on street-level data and general-purpose image geolocalization; the first model, PIGEON, is trained on data from the game of Geoguessr and is capable of placing over 40% of its guesses within 25 kilometers of the target location globally. We also develop a bot and deploy PIGEON in a blind experiment against humans, ranking in the top 0.01% of players. We further challenge one of the world's foremost professional Geoguessr players to a series of six matches with millions of viewers, winning all six games. Our second model, PIGEOTTO, differs in that it is trained on a dataset of images from Flickr and Wikipedia, achieving state-of-the-art results on a wide range of image geolocalization benchmarks, outperforming the previous SOTA by up to 7.7 percentage points on the city accuracy level and up to 38.8 percentage points on the country level. Our findings suggest that PIGEOTTO is the first image geolocalization model that effectively generalizes to unseen places and that our approach can pave the way for highly accurate, planet-scale image geolocalization systems. Our code is available on GitHub.
Authors: Chen Sun, Calvin Luo, Xingyi Zhou, Anurag Arnab, Cordelia Schmid
We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result would refute the common belief that explicit visual abstraction (e.g. object detection) is essential for compositional generalization on visual reasoning, and confirm the feasibility of a neural network "generalist" to solve visual recognition and reasoning tasks. We propose a simple and general self-supervised framework which "compresses" each video frame into a small set of tokens with a transformer network, and reconstructs the remaining frames based on the compressed temporal context. To minimize the reconstruction loss, the network must learn a compact representation for each image, as well as capture temporal dynamics and object permanence from temporal context. We perform evaluation on two visual reasoning benchmarks, CATER and ACRE. We observe that pretraining is essential to achieve compositional generalization for end-to-end visual reasoning. Our proposed framework outperforms traditional supervised pretraining, including image classification and explicit object detection, by large margins.
Authors: Wei Jiang, Jiayu Yang, Yongqi Zhai, Feng Gao, Ronggang Wang
Recently, learned image compression has achieved impressive performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in enhancing rate-distortion performance. However, existing global context modules rely on computationally intensive quadratic complexity computations to capture global correlations. This quadratic complexity imposes limitations on the potential of high-resolution image coding. Moreover, effectively capturing local, global, and channel-wise contexts with acceptable even linear complexity within a single entropy model remains a challenge. To address these limitations, we propose the Linear Complexity Attention-based Multi-Reference Entropy Model (MEM++). MEM++ effectively captures the diverse range of correlations inherent in the latent representation. Specifically, the latent representation is first divided into multiple slices. When compressing a particular slice, the previously compressed slices serve as its channel-wise contexts. To capture local contexts without sacrificing performance, we introduce a novel checkerboard attention module. Additionally, to capture global contexts, we propose the linear complexity attention-based global correlations capturing by leveraging the decomposition of the softmax operation. The attention map of the previously decoded slice is implicitly computed and employed to predict global correlations in the current slice. Based on MEM++, we propose image compression model MLIC++. Extensive experimental evaluations demonstrate that our MLIC++ achieves state-of-the-art performance, reducing BD-rate by 13.39% on the Kodak dataset compared to VTM-17.0 in PSNR. Furthermore, MLIC++ exhibits linear GPU memory consumption with resolution, making it highly suitable for high-resolution image coding. Code and pre-trained models are available at https://github.com/JiangWeibeta/MLIC.
Authors: Elad Richardson, Kfir Goldberg, Yuval Alaluf, Daniel Cohen-Or
Recent text-to-image generative models have enabled us to transform our words into vibrant, captivating imagery. The surge of personalization techniques that has followed has also allowed us to imagine unique concepts in new scenes. However, an intriguing question remains: How can we generate a new, imaginary concept that has never been seen before? In this paper, we present the task of creative text-to-image generation, where we seek to generate new members of a broad category (e.g., generating a pet that differs from all existing pets). We leverage the under-studied Diffusion Prior models and show that the creative generation problem can be formulated as an optimization process over the output space of the diffusion prior, resulting in a set of "prior constraints". To keep our generated concept from converging into existing members, we incorporate a question-answering Vision-Language Model (VLM) that adaptively adds new constraints to the optimization problem, encouraging the model to discover increasingly more unique creations. Finally, we show that our prior constraints can also serve as a strong mixing mechanism allowing us to create hybrids between generated concepts, introducing even more flexibility into the creative process.
Authors: Seokhyeon Ha, Sunbeom Jung, Jungwoo Lee
Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities. Mitigating feature distortion during adaptation to new target domains is crucial. Recent studies have shown promising results in handling feature distortion by aligning the head layer on in-distribution datasets before performing fine-tuning. Nonetheless, a significant limitation arises from the treatment of batch normalization layers during fine-tuning, leading to suboptimal performance. In this paper, we propose Domain-Aware Fine-Tuning (DAFT), a novel approach that incorporates batch normalization conversion and the integration of linear probing and fine-tuning. Our batch normalization conversion method effectively mitigates feature distortion by reducing modifications to the neural network during fine-tuning. Additionally, we introduce the integration of linear probing and fine-tuning to optimize the head layer with gradual adaptation of the feature extractor. By leveraging batch normalization layers and integrating linear probing and fine-tuning, our DAFT significantly mitigates feature distortion and achieves improved model performance on both in-distribution and out-of-distribution datasets. Extensive experiments demonstrate that our method outperforms other baseline methods, demonstrating its effectiveness in not only improving performance but also mitigating feature distortion.
Authors: Maximilian Dreyer, Frederik Pahde, Christopher J. Anders, Wojciech Samek, Sebastian Lapuschkin
Deep Neural Networks are prone to learning spurious correlations embedded in the training data, leading to potentially biased predictions. This poses risks when deploying these models for high-stake decision-making, such as in medical applications. Current methods for post-hoc model correction either require input-level annotations which are only possible for spatially localized biases, or augment the latent feature space, thereby hoping to enforce the right reasons. We present a novel method for model correction on the concept level that explicitly reduces model sensitivity towards biases via gradient penalization. When modeling biases via Concept Activation Vectors, we highlight the importance of choosing robust directions, as traditional regression-based approaches such as Support Vector Machines tend to result in diverging directions. We effectively mitigate biases in controlled and real-world settings on the ISIC, Bone Age, ImageNet and CelebA datasets using VGG, ResNet and EfficientNet architectures. Code is available on https://github.com/frederikpahde/rrclarc.
Authors: Xiaohui Jiang, Shuailin Li, Yingfei Liu, Shihao Wang, Fan Jia, Tiancai Wang, Lijin Han, Xiangyu Zhang
Recently 3D object detection from surround-view images has made notable advancements with its low deployment cost. However, most works have primarily focused on close perception range while leaving long-range detection less explored. Expanding existing methods directly to cover long distances poses challenges such as heavy computation costs and unstable convergence. To address these limitations, this paper proposes a novel sparse query-based framework, dubbed Far3D. By utilizing high-quality 2D object priors, we generate 3D adaptive queries that complement the 3D global queries. To efficiently capture discriminative features across different views and scales for long-range objects, we introduce a perspective-aware aggregation module. Additionally, we propose a range-modulated 3D denoising approach to address query error propagation and mitigate convergence issues in long-range tasks. Significantly, Far3D demonstrates SoTA performance on the challenging Argoverse 2 dataset, covering a wide range of 150 meters, surpassing several LiDAR-based approaches. Meanwhile, Far3D exhibits superior performance compared to previous methods on the nuScenes dataset. The code is available at https://github.com/megvii-research/Far3D.
Authors: Wenbo Hu, Yifan Xu, Yi Li, Weiyue Li, Zeyuan Chen, Zhuowen Tu
Vision Language Models (VLMs), which extend Large Language Models (LLM) by incorporating visual understanding capability, have demonstrated significant advancements in addressing open-ended visual question-answering (VQA) tasks. However, these models cannot accurately interpret images infused with text, a common occurrence in real-world scenarios. Standard procedures for extracting information from images often involve learning a fixed set of query embeddings. These embeddings are designed to encapsulate image contexts and are later used as soft prompt inputs in LLMs. Yet, this process is limited to the token count, potentially curtailing the recognition of scenes with text-rich context. To improve upon them, the present study introduces BLIVA: an augmented version of InstructBLIP with Visual Assistant. BLIVA incorporates the query embeddings from InstructBLIP and also directly projects encoded patch embeddings into the LLM, a technique inspired by LLaVA. This approach assists the model to capture intricate details potentially missed during the query decoding process. Empirical evidence demonstrates that our model, BLIVA, significantly enhances performance in processing text-rich VQA benchmarks (up to 17.76% in OCR-VQA benchmark) and in undertaking general (not particularly text-rich) VQA benchmarks (up to 7.9% in Visual Spatial Reasoning benchmark), and achieved 17.72% overall improvement in a comprehensive multimodal LLM benchmark (MME), comparing to our baseline InstructBLIP. BLIVA demonstrates significant capability in decoding real-world images, irrespective of text presence. To demonstrate the broad industry applications enabled by BLIVA, we evaluate the model using a new dataset comprising YouTube thumbnails paired with question-answer sets across 11 diverse categories. Our code and models are freely accessible at https://github.com/mlpc-ucsd/BLIVA.
Authors: Sadeep Jayasumana, Daniel Glasner, Srikumar Ramalingam, Andreas Veit, Ayan Chakrabarti, Sanjiv Kumar
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However, this quality comes at significant computational cost: nearly all of these models are iterative and require running sampling multiple times with large models. This iterative process is needed to ensure that different regions of the image are not only aligned with the text prompt, but also compatible with each other. In this work, we propose a light-weight approach to achieving this compatibility between different regions of an image, using a Markov Random Field (MRF) model. We demonstrate the effectiveness of this method on top of the latent token-based Muse text-to-image model. The MRF richly encodes the compatibility among image tokens at different spatial locations to improve quality and significantly reduce the required number of Muse sampling steps. Inference with the MRF is significantly cheaper, and its parameters can be quickly learned through back-propagation by modeling MRF inference as a differentiable neural-network layer. Our full model, MarkovGen, uses this proposed MRF model to both speed up Muse by 1.5X and produce higher quality images by decreasing undesirable image artifacts.
Authors: Zhiheng Li, Yu Lin, Yubo Cui, Shuo Li, Zheng Fang
3D single object tracking with LiDAR points is an important task in the computer vision field. Previous methods usually adopt the matching-based or motion-centric paradigms to estimate the current target status. However, the former is sensitive to the similar distractors and the sparseness of point cloud due to relying on appearance matching, while the latter usually focuses on short-term motion clues (eg. two frames) and ignores the long-term motion pattern of target. To address these issues, we propose a mixed paradigm with two stages, named MTM-Tracker, which combines motion modeling with feature matching into a single network. Specifically, in the first stage, we exploit the continuous historical boxes as motion prior and propose an encoder-decoder structure to locate target coarsely. Then, in the second stage, we introduce a feature interaction module to extract motion-aware features from consecutive point clouds and match them to refine target movement as well as regress other target states. Extensive experiments validate that our paradigm achieves competitive performance on large-scale datasets (70.9% in KITTI and 51.70% in NuScenes). The code will be open soon at https://github.com/LeoZhiheng/MTM-Tracker.git.
Authors: Jie Hong, Zeeshan Hayder, Junlin Han, Pengfei Fang, Mehrtash Harandi, Lars Petersson
Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training. An analysis of the audio-visual data reveals a large degree of hyperbolicity, indicating the potential benefit of using a hyperbolic transformation to achieve curvature-aware geometric learning, with the aim of exploring more complex hierarchical data structures for this task. The proposed approach employs a novel loss function that incorporates cross-modality alignment between video and audio features in the hyperbolic space. Additionally, we explore the use of multiple adaptive curvatures for hyperbolic projections. The experimental results on this very challenging task demonstrate that our proposed hyperbolic approach for zero-shot learning outperforms the SOTA method on three datasets: VGGSound-GZSL, UCF-GZSL, and ActivityNet-GZSL achieving a harmonic mean (HM) improvement of around 3.0%, 7.0%, and 5.3%, respectively.
Authors: Yiyang Yao, Peng Liu, Tiancheng Zhao, Qianqian Zhang, Jiajia Liao, Chunxin Fang, Kyusong Lee, Qing Wang
Object detection (OD) in computer vision has made significant progress in recent years, transitioning from closed-set labels to open-vocabulary detection (OVD) based on large-scale vision-language pre-training (VLP). However, current evaluation methods and datasets are limited to testing generalization over object types and referral expressions, which do not provide a systematic, fine-grained, and accurate benchmark of OVD models' abilities. In this paper, we propose a new benchmark named OVDEval, which includes 9 sub-tasks and introduces evaluations on commonsense knowledge, attribute understanding, position understanding, object relation comprehension, and more. The dataset is meticulously created to provide hard negatives that challenge models' true understanding of visual and linguistic input. Additionally, we identify a problem with the popular Average Precision (AP) metric when benchmarking models on these fine-grained label datasets and propose a new metric called Non-Maximum Suppression Average Precision (NMS-AP) to address this issue. Extensive experimental results show that existing top OVD models all fail on the new tasks except for simple object types, demonstrating the value of the proposed dataset in pinpointing the weakness of current OVD models and guiding future research. Furthermore, the proposed NMS-AP metric is verified by experiments to provide a much more truthful evaluation of OVD models, whereas traditional AP metrics yield deceptive results. Data is available at \url{https://github.com/om-ai-lab/OVDEval}
Authors: Zelin Peng, Zhengqin Xu, Zhilin Zeng, Xiaokang Yang, Wei Shen
Segment Anything Model (SAM) has received remarkable attention as it offers a powerful and versatile solution for object segmentation in images. However, fine-tuning SAM for downstream segmentation tasks under different scenarios remains a challenge, as the varied characteristics of different scenarios naturally requires diverse model parameter spaces. Most existing fine-tuning methods attempt to bridge the gaps among different scenarios by introducing a set of new parameters to modify SAM's original parameter space. Unlike these works, in this paper, we propose fine-tuning SAM efficiently by parameter space reconstruction (SAM-PARSER), which introduce nearly zero trainable parameters during fine-tuning. In SAM-PARSER, we assume that SAM's original parameter space is relatively complete, so that its bases are able to reconstruct the parameter space of a new scenario. We obtain the bases by matrix decomposition, and fine-tuning the coefficients to reconstruct the parameter space tailored to the new scenario by an optimal linear combination of the bases. Experimental results show that SAM-PARSER exhibits superior segmentation performance across various scenarios, while reducing the number of trainable parameters by $\approx 290$ times compared with current parameter-efficient fine-tuning methods.
Authors: Gehui Li, Jinyuan Liu, Long Ma, Zhiying Jiang, Xin Fan, Risheng Liu
Photographs taken with less-than-ideal exposure settings often display poor visual quality. Since the correction procedures vary significantly, it is difficult for a single neural network to handle all exposure problems. Moreover, the inherent limitations of convolutions, hinder the models ability to restore faithful color or details on extremely over-/under- exposed regions. To overcome these limitations, we propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction. In specific, the complementary macro-micro attention designs enhance locality while allowing global interactions. The hierarchical structure enables the network to correct exposure errors of different scales layer by layer. Furthermore, we propose a contrast constraint and couple it seamlessly in the loss function, where the corrected image is pulled towards the positive sample and pushed away from the dynamically generated negative samples. Thus the remaining color distortion and loss of detail can be removed. We also extend our method as an image enhancer for low-light face recognition and low-light semantic segmentation. Experiments demonstrate that our approach obtains more attractive results than state-of-the-art methods quantitatively and qualitatively.
Authors: Henik Riedel, Robert Steven Lorenzen, Clemens Hübler
Rising maintenance costs of ageing infrastructure necessitate innovative monitoring techniques. This paper presents a new approach for detecting axles, enabling real-time application of Bridge Weigh-In-Motion (BWIM) systems without dedicated axle detectors. The proposed Virtual Axle Detector with Enhanced Receptive Field (VADER) is independent of bridge type and sensor placement while only using raw acceleration data as input. By using raw data instead of spectograms as input, the receptive field can be enhanced without increasing the number of parameters. We also introduce a novel receptive field (RF) rule for an object-size driven design of Convolutional Neural Network (CNN) architectures. We were able to show, that the RF rule has the potential to bridge the gap between physical boundary conditions and deep learning model development. Based on the RF rule, our results suggest that models using raw data could achieve better performance than those using spectrograms, offering a compelling reason to consider raw data as input. The proposed VADER achieves to detect 99.9 % of axles with a spatial error of 4.13 cm using only acceleration measurements, while cutting computational and memory costs by 99 % compared to the state-of-the-art using spectograms.
Authors: Siwei Li, Mingxuan Liu, Yating Zhang, Shu Chen, Haoxiang Li, Zifei Dou, Hong Chen
Image deblurring is a critical task in the field of image restoration, aiming to eliminate blurring artifacts. However, the challenge of addressing non-uniform blurring leads to an ill-posed problem, which limits the generalization performance of existing deblurring models. To solve the problem, we propose a framework SAM-Deblur, integrating prior knowledge from the Segment Anything Model (SAM) into the deblurring task for the first time. In particular, SAM-Deblur is divided into three stages. First, we preprocess the blurred images, obtain segment masks via SAM, and propose a mask dropout method for training to enhance model robustness. Then, to fully leverage the structural priors generated by SAM, we propose a Mask Average Pooling (MAP) unit specifically designed to average SAM-generated segmented areas, serving as a plug-and-play component which can be seamlessly integrated into existing deblurring networks. Finally, we feed the fused features generated by the MAP Unit into the deblurring model to obtain a sharp image. Experimental results on the RealBlurJ, ReloBlur, and REDS datasets reveal that incorporating our methods improves GoPro-trained NAFNet's PSNR by 0.05, 0.96, and 7.03, respectively. Project page is available at GitHub \href{https://hplqaq.github.io/projects/sam-deblur}{HPLQAQ/SAM-Deblur}.
Authors: Zhengxiang Shi, Aldo Lipani
Prompt tuning (PT), where a small amount of trainable soft (continuous) prompt vectors is affixed to the input of language models (LM), has shown promising results across various tasks and models for parameter-efficient fine-tuning (PEFT). PT stands out from other PEFT approaches because it maintains competitive performance with fewer trainable parameters and does not drastically scale up its parameters as the model size expands. However, PT introduces additional soft prompt tokens, leading to longer input sequences, which significantly impacts training and inference time and memory usage due to the Transformer's quadratic complexity. Particularly concerning for Large Language Models (LLMs) that face heavy daily querying. To address this issue, we propose Decomposed Prompt Tuning (DePT), which decomposes the soft prompt into a shorter soft prompt and a pair of low-rank matrices that are then optimised with two different learning rates. This allows DePT to achieve better performance while saving over 20% memory and time costs compared to vanilla PT and its variants, without changing trainable parameter sizes. Through extensive experiments on 23 natural language processing (NLP) and vision-language (VL) tasks, we demonstrate that DePT outperforms state-of-the-art PEFT approaches, including the full fine-tuning baseline in some scenarios. Additionally, we empirically show that DEPT grows more efficient as the model size increases. Our further study reveals that DePT integrates seamlessly with parameter-efficient transfer learning in the few-shot learning setting and highlights its adaptability to various model architectures and sizes.
Authors: Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu
Contrastive learning has emerged as a prevailing paradigm for high-level vision tasks, which, by introducing properly negative samples, has also been exploited for low-level vision tasks to achieve a compact optimization space to account for their ill-posed nature. However, existing methods rely on manually predefined and task-oriented negatives, which often exhibit pronounced task-specific biases. To address this challenge, our paper introduces an innovative method termed 'learning from history', which dynamically generates negative samples from the target model itself. Our approach, named Model Contrastive paradigm for Image Restoration (MCIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks. We propose the Self-Prior guided Negative loss (SPN) to enable it. This approach significantly enhances existing models when retrained with the proposed model contrastive paradigm. The results show significant improvements in image restoration across various tasks and architectures. For example, models retrained with SPN outperform the original FFANet and DehazeFormer by 3.41 dB and 0.57 dB on the RESIDE indoor dataset for image dehazing. Similarly, they achieve notable improvements of 0.47 dB on SPA-Data over IDT for image deraining and 0.12 dB on Manga109 for a 4x scale super-resolution over lightweight SwinIR, respectively. Code and retrained models are available at https://github.com/Aitical/MCIR.
Authors: Yixing Lu, Zhaoxin Fan, Min Xu
In this paper, we introduce a novel semi-supervised learning framework tailored for medical image segmentation. Central to our approach is the innovative Multi-scale Text-aware ViT-CNN Fusion scheme. This scheme adeptly combines the strengths of both ViTs and CNNs, capitalizing on the unique advantages of both architectures as well as the complementary information in vision-language modalities. Further enriching our framework, we propose the Multi-Axis Consistency framework for generating robust pseudo labels, thereby enhancing the semisupervised learning process. Our extensive experiments on several widelyused datasets unequivocally demonstrate the efficacy of our approach.
Authors: Ruihai Wu, Chenrui Tie, Yushi Du, Yan Zhao, Hao Dong
Shape assembly aims to reassemble parts (or fragments) into a complete object, which is a common task in our daily life. Different from the semantic part assembly (e.g., assembling a chair's semantic parts like legs into a whole chair), geometric part assembly (e.g., assembling bowl fragments into a complete bowl) is an emerging task in computer vision and robotics. Instead of semantic information, this task focuses on geometric information of parts. As the both geometric and pose space of fractured parts are exceptionally large, shape pose disentanglement of part representations is beneficial to geometric shape assembly. In our paper, we propose to leverage SE(3) equivariance for such shape pose disentanglement. Moreover, while previous works in vision and robotics only consider SE(3) equivariance for the representations of single objects, we move a step forward and propose leveraging SE(3) equivariance for representations considering multi-part correlations, which further boosts the performance of the multi-part assembly. Experiments demonstrate the significance of SE(3) equivariance and our proposed method for geometric shape assembly. Project page: https://crtie.github.io/SE-3-part-assembly/
Authors: Namhyuk Ahn, Junsoo Lee, Chunggi Lee, Kunhee Kim, Daesik Kim, Seung-Hun Nam, Kibeom Hong
Recent progresses in large-scale text-to-image models have yielded remarkable accomplishments, finding various applications in art domain. However, expressing unique characteristics of an artwork (e.g. brushwork, colortone, or composition) with text prompts alone may encounter limitations due to the inherent constraints of verbal description. To this end, we introduce DreamStyler, a novel framework designed for artistic image synthesis, proficient in both text-to-image synthesis and style transfer. DreamStyler optimizes a multi-stage textual embedding with a context-aware text prompt, resulting in prominent image quality. In addition, with content and style guidance, DreamStyler exhibits flexibility to accommodate a range of style references. Experimental results demonstrate its superior performance across multiple scenarios, suggesting its promising potential in artistic product creation.
Authors: Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Matthew Groh, Roxana Daneshjou, Labelling Consortium, Alexander A. Navarini, Marc Pouly
Benchmark datasets for digital dermatology unwittingly contain inaccuracies that reduce trust in model performance estimates. We propose a resource-efficient data-cleaning protocol to identify issues that escaped previous curation. The protocol leverages an existing algorithmic cleaning strategy and is followed by a confirmation process terminated by an intuitive stopping criterion. Based on confirmation by multiple dermatologists, we remove irrelevant samples and near duplicates and estimate the percentage of label errors in six dermatology image datasets for model evaluation promoted by the International Skin Imaging Collaboration. Along with this paper, we publish revised file lists for each dataset which should be used for model evaluation. Our work paves the way for more trustworthy performance assessment in digital dermatology.
Authors: Xuan Bac Nguyen, Hugh Churchill, Khoa Luu, Samee U. Khan
Unsupervised visual clustering has garnered significant attention in recent times, aiming to characterize distributions of unlabeled visual images through clustering based on a parameterized appearance approach. Alternatively, clustering algorithms can be viewed as assignment problems, often characterized as NP-hard, yet precisely solvable for small instances on contemporary hardware. Adiabatic quantum computing (AQC) emerges as a promising solution, poised to deliver substantial speedups for a range of NP-hard optimization problems. However, existing clustering formulations face challenges in quantum computing adoption due to scalability issues. In this study, we present the first clustering formulation tailored for resolution using Adiabatic quantum computing. An Ising model is introduced to represent the quantum mechanical system implemented on AQC. The proposed approach demonstrates high competitiveness compared to state-of-the-art optimization-based methods, even when utilizing off-the-shelf integer programming solvers. Lastly, this work showcases the solvability of the proposed clustering problem on current-generation real quantum computers for small examples and analyzes the properties of the obtained solutions
Authors: Chen Jiang, Hong Liu, Xuzheng Yu, Qing Wang, Yuan Cheng, Jia Xu, Zhongyi Liu, Qingpei Guo, Wei Chu, Ming Yang, Yuan Qi
In recent years, the explosion of web videos makes text-video retrieval increasingly essential and popular for video filtering, recommendation, and search. Text-video retrieval aims to rank relevant text/video higher than irrelevant ones. The core of this task is to precisely measure the cross-modal similarity between texts and videos. Recently, contrastive learning methods have shown promising results for text-video retrieval, most of which focus on the construction of positive and negative pairs to learn text and video representations. Nevertheless, they do not pay enough attention to hard negative pairs and lack the ability to model different levels of semantic similarity. To address these two issues, this paper improves contrastive learning using two novel techniques. First, to exploit hard examples for robust discriminative power, we propose a novel Dual-Modal Attention-Enhanced Module (DMAE) to mine hard negative pairs from textual and visual clues. By further introducing a Negative-aware InfoNCE (NegNCE) loss, we are able to adaptively identify all these hard negatives and explicitly highlight their impacts in the training loss. Second, our work argues that triplet samples can better model fine-grained semantic similarity compared to pairwise samples. We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs. The proposed TPM-CL designs an adaptive token masking strategy with cross-modal interaction to model subtle semantic differences. Extensive experiments demonstrate that the proposed approach outperforms existing methods on four widely-used text-video retrieval datasets, including MSR-VTT, MSVD, DiDeMo and ActivityNet.
Authors: Atif Belal, Akhil Meethal, Francisco Perdigon Romero, Marco Pedersoli, Eric Granger
Adapting visual object detectors to operational target domains is a challenging task, commonly achieved using unsupervised domain adaptation (UDA) methods. Recent studies have shown that when the labeled dataset comes from multiple source domains, treating them as separate domains and performing a multi-source domain adaptation (MSDA) improves the accuracy and robustness over blending these source domains and performing a UDA. For adaptation, existing MSDA methods learn domain-invariant and domain-specific parameters (for each source domain). However, unlike single-source UDA methods, learning domain-specific parameters makes them grow significantly in proportion to the number of source domains. This paper proposes a novel MSDA method called Prototype-based Mean Teacher (PMT), which uses class prototypes instead of domain-specific subnets to encode domain-specific information. These prototypes are learned using a contrastive loss, aligning the same categories across domains and separating different categories far apart. Given the use of prototypes, the number of parameters required for our PMT method does not increase significantly with the number of source domains, thus reducing memory issues and possible overfitting. Empirical studies indicate that PMT outperforms state-of-the-art MSDA methods on several challenging object detection datasets. Our code is available at https://github.com/imatif17/Prototype-Mean-Teacher.
Authors: Chirayu D. Athalye, Kunal N. Chaudhury, Bhartendu Kumar
In plug-and-play (PnP) regularization, the proximal operator in algorithms such as ISTA and ADMM is replaced by a powerful denoiser. This formal substitution works surprisingly well in practice. In fact, PnP has been shown to give state-of-the-art results for various imaging applications. The empirical success of PnP has motivated researchers to understand its theoretical underpinnings and, in particular, its convergence. It was shown in prior work that for kernel denoisers such as the nonlocal means, PnP-ISTA provably converges under some strong assumptions on the forward model. The present work is motivated by the following questions: Can we relax the assumptions on the forward model? Can the convergence analysis be extended to PnP-ADMM? Can we estimate the convergence rate? In this letter, we resolve these questions using the contraction mapping theorem: (i) for symmetric denoisers, we show that (under mild conditions) PnP-ISTA and PnP-ADMM exhibit linear convergence; and (ii) for kernel denoisers, we show that PnP-ISTA and PnP-ADMM converge linearly for image inpainting. We validate our theoretical findings using reconstruction experiments.
Authors: Ruiyuan Gao, Kai Chen, Enze Xie, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung, Qiang Xu
Recent advancements in diffusion models have significantly enhanced the data synthesis with 2D control. Yet, precise 3D control in street view generation, crucial for 3D perception tasks, remains elusive. Specifically, utilizing Bird's-Eye View (BEV) as the primary condition often leads to challenges in geometry control (e.g., height), affecting the representation of object shapes, occlusion patterns, and road surface elevations, all of which are essential to perception data synthesis, especially for 3D object detection tasks. In this paper, we introduce MagicDrive, a novel street view generation framework offering diverse 3D geometry controls, including camera poses, road maps, and 3D bounding boxes, together with textual descriptions, achieved through tailored encoding strategies. Besides, our design incorporates a cross-view attention module, ensuring consistency across multiple camera views. With MagicDrive, we achieve high-fidelity street-view synthesis that captures nuanced 3D geometry and various scene descriptions, enhancing tasks like BEV segmentation and 3D object detection.
Authors: Yiwen Tang, Ray Zhang, Zoey Guo, Xianzheng Ma, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li
The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost for downstream tasks, many Parameter-Efficient Fine-Tuning (PEFT) techniques are proposed for language and 2D image pre-trained models. However, the specialized PEFT method for 3D pre-trained models is still under-explored. To this end, we introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters. Specifically, for a pre-trained 3D model, we freeze most of its parameters, and only tune the newly added PEFT modules on downstream tasks, which consist of a Point-prior Prompt and a Geometry-aware Adapter. The Point-prior Prompt adopts a set of learnable prompt tokens, for which we propose to construct a memory bank with domain-specific knowledge, and utilize a parameter-free attention to enhance the prompt tokens. The Geometry-aware Adapter aims to aggregate point cloud features within spatial neighborhoods to capture fine-grained geometric information through local interactions. Extensive experiments indicate that our Point-PEFT can achieve better performance than the full fine-tuning on various downstream tasks, while using only 5% of the trainable parameters, demonstrating the efficiency and effectiveness of our approach. Code is released at https://github.com/Ivan-Tang-3D/PEFT-3D.
Authors: Baixin Xu, Jiangbei Hu, Fei Hou, Kwan-Yee Lin, Wayne Wu, Chen Qian, Ying He
The growing capabilities of neural rendering have increased the demand for new techniques that enable intuitive editing of 3D objects, particularly when they are represented as neural implicit surfaces. In this paper, we present a novel neural algorithm to parameterize neural implicit surfaces to simple parametric domains, such as spheres, cubes, or polycubes, thereby facilitating visualization and various editing tasks. Technically, our method computes a bi-directional deformation between 3D objects and their chosen parametric domains, eliminating the need for any prior information. We adopt a forward mapping of points on the zero level set of the 3D object to a parametric domain, followed by a backward mapping through inverse deformation. To ensure the map is bijective, we employ a cycle loss while optimizing the smoothness of both deformations. Additionally, we leverage a Laplacian regularizer to effectively control angle distortion and offer the flexibility to choose from a range of parametric domains for managing area distortion. Designed for compatibility, our framework integrates seamlessly with existing neural rendering pipelines, taking multi-view images as input to reconstruct 3D geometry and compute the corresponding texture map. We also introduce a simple yet effective technique for intrinsic radiance decomposition, facilitating both view-independent material editing and view-dependent shading editing. Our method allows for the immediate rendering of edited textures through volume rendering, without the need for network re-training. Moreover, our approach supports the co-parameterization of multiple objects and enables texture transfer between them. We demonstrate the effectiveness of our method on images of human heads and man-made objects. We will make the source code publicly available.
Authors: Lei Wang, Piotr Koniusz
Various research studies indicate that action recognition performance highly depends on the types of motions being extracted and how accurate the human actions are represented. In this paper, we investigate different optical flow, and features extracted from these optical flow that capturing both short-term and long-term motion dynamics. We perform power normalization on the magnitude component of optical flow for flow dynamics correction to boost subtle or dampen sudden motions. We show that existing action recognition models which rely on optical flow are able to get performance boosted with our corrected optical flow. To further improve performance, we integrate our corrected flow dynamics into popular models through a simple hallucination step by selecting only the best performing optical flow features, and we show that by 'translating' the CNN feature maps into these optical flow features with different scales of motions leads to the new state-of-the-art performance on several benchmarks including HMDB-51, YUP++, fine-grained action recognition on MPII Cooking Activities, and large-scale Charades.
Authors: Lv Tang, Peng-Tao Jiang, Hao-Ke Xiao, Bo Li
The realm of computer vision has witnessed a paradigm shift with the advent of foundational models, mirroring the transformative influence of large language models in the domain of natural language processing. This paper delves into the exploration of open-world segmentation, presenting a novel approach called Image Prompt Segmentation (IPSeg) that harnesses the power of vision foundational models. IPSeg lies the principle of a training-free paradigm, which capitalizes on image prompt techniques. Specifically, IPSeg utilizes a single image containing a subjective visual concept as a flexible prompt to query vision foundation models like DINOv2 and Stable Diffusion. Our approach extracts robust features for the prompt image and input image, then matches the input representations to the prompt representations via a novel feature interaction module to generate point prompts highlighting target objects in the input image. The generated point prompts are further utilized to guide the Segment Anything Model to segment the target object in the input image. The proposed method stands out by eliminating the need for exhaustive training sessions, thereby offering a more efficient and scalable solution. Experiments on COCO, PASCAL VOC, and other datasets demonstrate IPSeg's efficacy for flexible open-world segmentation using intuitive image prompts. This work pioneers tapping foundation models for open-world understanding through visual concepts conveyed in images.
Authors: Seoha Kim, Jeongmin Bae, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh
Recent advancements in 4D scene reconstruction using neural radiance fields (NeRF) have demonstrated the ability to represent dynamic scenes from multi-view videos. However, they fail to reconstruct the dynamic scenes and struggle to fit even the training views in unsynchronized settings. It happens because they employ a single latent embedding for a frame while the multi-view images at the same frame were actually captured at different moments. To address this limitation, we introduce time offsets for individual unsynchronized videos and jointly optimize the offsets with NeRF. By design, our method is applicable for various baselines and improves them with large margins. Furthermore, finding the offsets naturally works as synchronizing the videos without manual effort. Experiments are conducted on the common Plenoptic Video Dataset and a newly built Unsynchronized Dynamic Blender Dataset to verify the performance of our method. Project page: https://seoha-kim.github.io/sync-nerf
Authors: Weixi Weng, Chun Yuan
Unsupervised domain adaptation object detection (UDAOD) research on Detection Transformer(DETR) mainly focuses on feature alignment and existing methods can be divided into two kinds, each of which has its unresolved issues. One-stage feature alignment methods can easily lead to performance fluctuation and training stagnation. Two-stage feature alignment method based on mean teacher comprises a pretraining stage followed by a self-training stage, each facing problems in obtaining reliable pretrained model and achieving consistent performance gains. Methods mentioned above have not yet explore how to utilize the third related domain such as target-like domain to assist adaptation. To address these issues, we propose a two-stage framework named MTM, i.e. Mean Teacher-DETR with Masked Feature Alignment. In the pretraining stage, we utilize labeled target-like images produced by image style transfer to avoid performance fluctuation. In the self-training stage, we leverage unlabeled target images by pseudo labels based on mean teacher and propose a module called Object Queries Knowledge Transfer (OQKT) to ensure consistent performance gains of the student model. Most importantly, we propose masked feature alignment methods including Masked Domain Query-based Feature Alignment (MDQFA) and Masked Token-wise Feature Alignment (MTWFA) to alleviate domain shift in a more robust way, which not only prevent training stagnation and lead to a robust pretrained model in the pretraining stage, but also enhance the model's target performance in the self-training stage. Experiments on three challenging scenarios and a theoretical analysis verify the effectiveness of MTM.
Authors: Zhaoyang Liu, Zeqiang Lai, Zhangwei Gao, Erfei Cui, Ziheng Li, Xizhou Zhu, Lewei Lu, Qifeng Chen, Yu Qiao, Jifeng Dai, Wenhai Wang
We present ControlLLM, a novel framework that enables large language models (LLMs) to utilize multi-modal tools for solving complex real-world tasks. Despite the remarkable performance of LLMs, they still struggle with tool invocation due to ambiguous user prompts, inaccurate tool selection and parameterization, and inefficient tool scheduling. To overcome these challenges, our framework comprises three key components: (1) a \textit{task decomposer} that breaks down a complex task into clear subtasks with well-defined inputs and outputs; (2) a \textit{Thoughts-on-Graph (ToG) paradigm} that searches the optimal solution path on a pre-built tool graph, which specifies the parameter and dependency relations among different tools; and (3) an \textit{execution engine with a rich toolbox} that interprets the solution path and runs the tools efficiently on different computational devices. We evaluate our framework on diverse tasks involving image, audio, and video processing, demonstrating its superior accuracy, efficiency, and versatility compared to existing methods. The code is at https://github.com/OpenGVLab/ControlLLM.
Authors: Ali Javidani, Mohammad Amin Sadeghi, Babak Nadjar Araabi
Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative dimension by integrating patch-level discrimination into these methodologies. This integration allows for the simultaneous analysis of both local and global visual features, thereby enriching the quality of the representations learned. Initially, the original images undergo spatial augmentation. Subsequently, we employ a distinctive photometric patch-level augmentation, where each patch is individually augmented, independent from other patches within the same view. This approach generates a diverse training dataset with distinct color variations in each segment. The augmented images are then processed through a self-distillation learning framework, utilizing the Vision Transformer (ViT) as its backbone. The proposed method minimizes the representation distances across both image and patch levels to capture details from macro to micro perspectives. To this end, we present a simple yet effective patch-matching algorithm that can find the corresponding patches across the augmented views. Thanks to the efficient structure of the patch-matching algorithm, our method reduces computational complexity compared to similar approaches. Consequently, we achieve an advanced understanding of the model without adding significant computational requirements. We have extensively pre-trained our method on datasets of varied scales, such as Cifar10, ImageNet-100, and ImageNet-1K. It demonstrates superior performance over state-of-the-art self-supervised representation learning methods in image classification and downstream tasks, such as copy detection and image retrieval. The implementation of our method is accessible on GitHub.
Authors: Jiatai Wang, Zhiwei Xu, Xin Wang, Tao Li
Existing multi-stage clustering methods independently learn the salient features from multiple views and then perform the clustering task. Particularly, multi-view clustering (MVC) has attracted a lot of attention in multi-view or multi-modal scenarios. MVC aims at exploring common semantics and pseudo-labels from multiple views and clustering in a self-supervised manner. However, limited by noisy data and inadequate feature learning, such a clustering paradigm generates overconfident pseudo-labels that mis-guide the model to produce inaccurate predictions. Therefore, it is desirable to have a method that can correct this pseudo-label mistraction in multi-stage clustering to avoid the bias accumulation. To alleviate the effect of overconfident pseudo-labels and improve the generalization ability of the model, this paper proposes a novel multi-stage deep MVC framework where multi-view self-distillation (DistilMVC) is introduced to distill dark knowledge of label distribution. Specifically, in the feature subspace at different hierarchies, we explore the common semantics of multiple views through contrastive learning and obtain pseudo-labels by maximizing the mutual information between views. Additionally, a teacher network is responsible for distilling pseudo-labels into dark knowledge, supervising the student network and improving its predictive capabilities to enhance the robustness. Extensive experiments on real-world multi-view datasets show that our method has better clustering performance than state-of-the-art methods.
Authors: Zhuoman Liu, Bo Yang, Yan Luximon, Ajay Kumar, Jinxi Li
In this paper, we study the problem of continuous 3D shape representations. The majority of existing successful methods are coordinate-based implicit neural representations. However, they are inefficient to render novel views or recover explicit surface points. A few works start to formulate 3D shapes as ray-based neural functions, but the learned structures are inferior due to the lack of multi-view geometry consistency. To tackle these challenges, we propose a new framework called RayDF. It consists of three major components: 1) the simple ray-surface distance field, 2) the novel dual-ray visibility classifier, and 3) a multi-view consistency optimization module to drive the learned ray-surface distances to be multi-view geometry consistent. We extensively evaluate our method on three public datasets, demonstrating remarkable performance in 3D surface point reconstruction on both synthetic and challenging real-world 3D scenes, clearly surpassing existing coordinate-based and ray-based baselines. Most notably, our method achieves a 1000x faster speed than coordinate-based methods to render an 800x800 depth image, showing the superiority of our method for 3D shape representation. Our code and data are available at https://github.com/vLAR-group/RayDF
Authors: Ao Zhang, Yuan Yao, Wei Ji, Zhiyuan Liu, Tat-Seng Chua
The development of large language models (LLMs) has greatly advanced the field of multimodal understanding, leading to the emergence of large multimodal models (LMMs). In order to enhance the level of visual comprehension, recent studies have equipped LMMs with region-level understanding capabilities by representing object bounding box coordinates as a series of text sequences (pix2seq). In this paper, we introduce a novel paradigm for object location modeling called pix2emb method, where we ask the LMM to output the location embeddings and then decode them with different decoders. This paradigm allows us to use different location formats (such as bounding boxes and masks) in multimodal conversations. Leveraging the proposed pix2emb method, we train an LMM named NExT-Chat and demonstrate its capability of handling multiple tasks like visual grounding, region captioning, and grounded reasoning. Comprehensive experiments show the effectiveness of our NExT-Chat on various tasks, e.g., NExT-Chat (87.7) vs. Shikra (86.9) on POPE-Random, NExT-Chat (68.9) vs. LISA (67.9) on referring expression segmentation task, and NExT-Chat (79.6) vs. Kosmos-2 (62.3) on region caption task. The code and model are released at https://github.com/NExT-ChatV/NExT-Chat.
Authors: Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin
Layout-to-image synthesis is an emerging technique in conditional image generation. It aims to generate complex scenes, where users require fine control over the layout of the objects in a scene. However, it remains challenging to control the object coherence, including semantic coherence (e.g., the cat looks at the flowers or not) and physical coherence (e.g., the hand and the racket should not be misaligned). In this paper, we propose a novel diffusion model with effective global semantic fusion (GSF) and self-similarity feature enhancement modules to guide the object coherence for this task. For semantic coherence, we argue that the image caption contains rich information for defining the semantic relationship within the objects in the images. Instead of simply employing cross-attention between captions and generated images, which addresses the highly relevant layout restriction and semantic coherence separately and thus leads to unsatisfying results shown in our experiments, we develop GSF to fuse the supervision from the layout restriction and semantic coherence requirement and exploit it to guide the image synthesis process. Moreover, to improve the physical coherence, we develop a Self-similarity Coherence Attention (SCA) module to explicitly integrate local contextual physical coherence into each pixel's generation process. Specifically, we adopt a self-similarity map to encode the coherence restrictions and employ it to extract coherent features from text embedding. Through visualization of our self-similarity map, we explore the essence of SCA, revealing that its effectiveness is not only in capturing reliable physical coherence patterns but also in enhancing complex texture generation. Extensive experiments demonstrate the superiority of our proposed method in both image generation quality and controllability.
Authors: Yamei Chen, Yan Di, Guangyao Zhai, Fabian Manhardt, Chenyangguang Zhang, Ruida Zhang, Federico Tombari, Nassir Navab, Benjamin Busam
Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of capturing this variation. To address this issue, we present SecondPose, a novel approach integrating object-specific geometric features with semantic category priors from DINOv2. Leveraging the advantage of DINOv2 in providing SE(3)-consistent semantic features, we hierarchically extract two types of SE(3)-invariant geometric features to further encapsulate local-to-global object-specific information. These geometric features are then point-aligned with DINOv2 features to establish a consistent object representation under SE(3) transformations, facilitating the mapping from camera space to the pre-defined canonical space, thus further enhancing pose estimation. Extensive experiments on NOCS-REAL275 demonstrate that SecondPose achieves a 12.4% leap forward over the state-of-the-art. Moreover, on a more complex dataset HouseCat6D which provides photometrically challenging objects, SecondPose still surpasses other competitors by a large margin. The code will be released soon.
Authors: Dekai Zhang, Matthew Williams, Francesca Toni
Neural networks (NNs) can learn to rely on spurious signals in the training data, leading to poor generalisation. Recent methods tackle this problem by training NNs with additional ground-truth annotations of such signals. These methods may, however, let spurious signals re-emerge in deep convolutional NNs (CNNs). We propose Targeted Activation Penalty (TAP), a new method tackling the same problem by penalising activations to control the re-emergence of spurious signals in deep CNNs, while also lowering training times and memory usage. In addition, ground-truth annotations can be expensive to obtain. We show that TAP still works well with annotations generated by pre-trained models as effective substitutes of ground-truth annotations. We demonstrate the power of TAP against two state-of-the-art baselines on the MNIST benchmark and on two clinical image datasets, using four different CNN architectures.
Authors: Chao Fan, Jingzhe Ma, Dongyang Jin, Chuanfu Shen, Shiqi Yu
The choice of the representations is essential for deep gait recognition methods. The binary silhouettes and skeletal coordinates are two dominant representations in recent literature, achieving remarkable advances in many scenarios. However, inherent challenges remain, in which silhouettes are not always guaranteed in unconstrained scenes, and structural cues have not been fully utilized from skeletons. In this paper, we introduce a novel skeletal gait representation named skeleton map, together with SkeletonGait, a skeleton-based method to exploit structural information from human skeleton maps. Specifically, the skeleton map represents the coordinates of human joints as a heatmap with Gaussian approximation, exhibiting a silhouette-like image devoid of exact body structure. Beyond achieving state-of-the-art performances over five popular gait datasets, more importantly, SkeletonGait uncovers novel insights about how important structural features are in describing gait and when they play a role. Furthermore, we propose a multi-branch architecture, named SkeletonGait++, to make use of complementary features from both skeletons and silhouettes. Experiments indicate that SkeletonGait++ outperforms existing state-of-the-art methods by a significant margin in various scenarios. For instance, it achieves an impressive rank-1 accuracy of over 85% on the challenging GREW dataset. All the source code is available at https://github.com/ShiqiYu/OpenGait.
Authors: Jixuan Leng, Yijiang Li, Haohan Wang
Domain Generalization (DG), a crucial research area, seeks to train models across multiple domains and test them on unseen ones. In this paper, we introduce a novel approach, namely, Selective Cross-Modality Distillation for Domain Generalization (SCMD). SCMD leverages the capabilities of large vision-language models, specifically the CLIP model, to train a more efficient model, ensuring it acquires robust generalization capabilities across unseen domains. Our primary contribution is a unique selection framework strategically designed to identify hard-to-learn samples for distillation. In parallel, we introduce a novel cross-modality module. This module seamlessly combines the projected features of the student model with the text embeddings from CLIP, ensuring the alignment of similarity distributions. We assess SCMD's performance on various benchmarks, where it empowers a ResNet50 to deliver state-of-the-art performance, surpassing existing domain generalization methods. Furthermore, we provide a theoretical analysis of our selection strategy, offering deeper insight into its effectiveness and potential in the field of DG.
Authors: Xiao Wang, Yaoyu Li, Tian Gan, Zheng Zhang, Jingjing Lv, Liqiang Nie
Recent advancements in video-language understanding have been established on the foundation of image-text models, resulting in promising outcomes due to the shared knowledge between images and videos. However, video-language understanding presents unique challenges due to the inclusion of highly complex semantic details, which result in information redundancy, temporal dependency, and scene complexity. Current techniques have only partially tackled these issues, and our quantitative analysis indicates that some of these methods are complementary. In light of this, we propose a novel framework called RTQ (Refine, Temporal model, and Query), which addresses these challenges simultaneously. The approach involves refining redundant information within frames, modeling temporal relations among frames, and querying task-specific information from the videos. Remarkably, our model demonstrates outstanding performance even in the absence of video-language pre-training, and the results are comparable with or superior to those achieved by state-of-the-art pre-training methods. Code is available at https://github.com/SCZwangxiao/RTQ-MM2023.
Authors: Fangxin Shang, Jie Fu, Yehui Yang, Haifeng Huang, Junwei Liu, Lei Ma
In the field of medical imaging, there are seldom large-scale public datasets with high-quality annotations due to data privacy and annotation cost. To address this issue, we release SynFundus-1M, a high-quality synthetic dataset containing over \textbf{1 million} fundus images w.r.t. 11 disease types. Moreover, we intentionally diversify the readability of the images and accordingly provide 4 types of the quality score for each image. To the best of our knowledge, SynFundus-1M is currently the largest fundus dataset with the most sophisticated annotations. All the images are generated by a Denoising Diffusion Probabilistic Model, named SynFundus-Generator. Trained with over 1.3 million private fundus images, our SynFundus-Generator achieves significant superior performance in generating fundus images compared to some recent related works. Furthermore, we blend some synthetic images from SynFundus-1M with real fundus images, and ophthalmologists can hardly distinguish the synthetic images from real ones. Through extensive experiments, we demonstrate that both convolutional neural networs (CNN) and Vision Transformer (ViT) can benefit from SynFundus-1M by pretraining or training directly. Compared to datasets like ImageNet or EyePACS, models trained on SynFundus-1M not only achieve better performance but also faster convergence on various downstream tasks.
Authors: Feng Wang, Jieru Mei, Alan Yuille
Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention, we surprisingly find that CLIP can adapt to dense prediction tasks by simply introducing a novel Correlative Self-Attention (CSA) mechanism. Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation. Extensive experiments show the advantage of CSA: we obtain a 38.2% average zero-shot mIoU across eight semantic segmentation benchmarks highlighted in this paper, significantly outperforming the existing SoTA's 33.9% and the vanilla CLIP's 14.1%.
Authors: Xiaochen Zhao, Jingxiang Sun, Lizhen Wang, Yebin Liu
While high fidelity and efficiency are central to the creation of digital head avatars, recent methods relying on 2D or 3D generative models often experience limitations such as shape distortion, expression inaccuracy, and identity flickering. Additionally, existing one-shot inversion techniques fail to fully leverage multiple input images for detailed feature extraction. We propose a novel framework, \textbf{Incremental 3D GAN Inversion}, that enhances avatar reconstruction performance using an algorithm designed to increase the fidelity from multiple frames, resulting in improved reconstruction quality proportional to frame count. Our method introduces a unique animatable 3D GAN prior with two crucial modifications for enhanced expression controllability alongside an innovative neural texture encoder that categorizes texture feature spaces based on UV parameterization. Differentiating from traditional techniques, our architecture emphasizes pixel-aligned image-to-image translation, mitigating the need to learn correspondences between observation and canonical spaces. Furthermore, we incorporate ConvGRU-based recurrent networks for temporal data aggregation from multiple frames, boosting geometry and texture detail reconstruction. The proposed paradigm demonstrates state-of-the-art performance on one-shot and few-shot avatar animation tasks.
Authors: Gabriel della Maggiora, Luis Alberto Croquevielle, Nikita Desphande, Harry Horsley, Thomas Heinis, Artur Yakimovich
Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic solutions and their good mathematical properties. Despite their success, an important drawback of diffusion models is their sensitivity to the choice of variance schedule, which controls the dynamics of the diffusion process. Fine-tuning this schedule for specific applications is crucial but time-costly and does not guarantee an optimal result. We propose a novel approach for learning the schedule as part of the training process. Our method supports probabilistic conditioning on data, provides high-quality solutions, and is flexible, proving able to adapt to different applications with minimum overhead. This approach is tested in two unrelated inverse problems: super-resolution microscopy and quantitative phase imaging, yielding comparable or superior results to previous methods and fine-tuned diffusion models. We conclude that fine-tuning the schedule by experimentation should be avoided because it can be learned during training in a stable way that yields better results.
Authors: Zhen Wang, Qiangeng Xu, Feitong Tan, Menglei Chai, Shichen Liu, Rohit Pandey, Sean Fanello, Achuta Kadambi, Yinda Zhang
Denoising diffusion models have demonstrated outstanding results in 2D image generation, yet it remains a challenge to replicate its success in 3D shape generation. In this paper, we propose leveraging multi-view depth, which represents complex 3D shapes in a 2D data format that is easy to denoise. We pair this representation with a diffusion model, MVDD, that is capable of generating high-quality dense point clouds with 20K+ points with fine-grained details. To enforce 3D consistency in multi-view depth, we introduce an epipolar line segment attention that conditions the denoising step for a view on its neighboring views. Additionally, a depth fusion module is incorporated into diffusion steps to further ensure the alignment of depth maps. When augmented with surface reconstruction, MVDD can also produce high-quality 3D meshes. Furthermore, MVDD stands out in other tasks such as depth completion, and can serve as a 3D prior, significantly boosting many downstream tasks, such as GAN inversion. State-of-the-art results from extensive experiments demonstrate MVDD's excellent ability in 3D shape generation, depth completion, and its potential as a 3D prior for downstream tasks.
Authors: Praneeta Immadisetty, Pooja Rajesh, Akshita Gupta, Anala M R, Soumya A, K. N. Subramanya
The commencement of the decade brought along with it a grave pandemic and in response the movement of education forums predominantly into the online world. With a surge in the usage of online video conferencing platforms and tools to better gauge student understanding, there needs to be a mechanism to assess whether instructors can grasp the extent to which students understand the subject and their response to the educational stimuli. The current systems consider only a single cue with a lack of focus in the educational domain. Thus, there is a necessity for the measurement of an all-encompassing holistic overview of the students' reaction to the subject matter. This paper highlights the need for a multimodal approach to affect recognition and its deployment in the online classroom while considering four cues, posture and gesture, facial, eye tracking and verbal recognition. It compares the various machine learning models available for each cue and provides the most suitable approach given the available dataset and parameters of classroom footage. A multimodal approach derived from weighted majority voting is proposed by combining the most fitting models from this analysis of individual cues based on accuracy, ease of procuring data corpus, sensitivity and any major drawbacks.
Authors: Youjia Zhang, Junqing Yu, Zikai Song, Wei Yang
Generating multi-view images from a single input view using image-conditioned diffusion models is a recent advancement and has shown considerable potential. However, issues such as the lack of consistency in synthesized views and over-smoothing in extracted geometry persist. Previous methods integrate multi-view consistency modules or impose additional supervisory to enhance view consistency while compromising on the flexibility of camera positioning and limiting the versatility of view synthesis. In this study, we consider the radiance field optimized during geometry extraction as a more rigid consistency prior, compared to volume and ray aggregation used in previous works. We further identify and rectify a critical bias in the traditional radiance field optimization process through score distillation from a multi-view diffuser. We introduce an Unbiased Score Distillation (USD) that utilizes unconditioned noises from a 2D diffusion model, greatly refining the radiance field fidelity. we leverage the rendered views from the optimized radiance field as the basis and develop a two-step specialization process of a 2D diffusion model, which is adept at conducting object-specific denoising and generating high-quality multi-view images. Finally, we recover faithful geometry and texture directly from the refined multi-view images. Empirical evaluations demonstrate that our optimized geometry and view distillation technique generates comparable results to the state-of-the-art models trained on extensive datasets, all while maintaining freedom in camera positioning. Please see our project page at https://youjiazhang.github.io/USD/.
Authors: Yufei Guo, Yuanpei Chen, Xiaode Liu, Weihang Peng, Yuhan Zhang, Xuhui Huang, Zhe Ma
The Spiking Neural Network (SNN), as one of the biologically inspired neural network infrastructures, has drawn increasing attention recently. It adopts binary spike activations to transmit information, thus the multiplications of activations and weights can be substituted by additions, which brings high energy efficiency. However, in the paper, we theoretically and experimentally prove that the binary spike activation map cannot carry enough information, thus causing information loss and resulting in accuracy decreasing. To handle the problem, we propose a ternary spike neuron to transmit information. The ternary spike neuron can also enjoy the event-driven and multiplication-free operation advantages of the binary spike neuron but will boost the information capacity. Furthermore, we also embed a trainable factor in the ternary spike neuron to learn the suitable spike amplitude, thus our SNN will adopt different spike amplitudes along layers, which can better suit the phenomenon that the membrane potential distributions are different along layers. To retain the efficiency of the vanilla ternary spike, the trainable ternary spike SNN will be converted to a standard one again via a re-parameterization technique in the inference. Extensive experiments with several popular network structures over static and dynamic datasets show that the ternary spike can consistently outperform state-of-the-art methods. Our code is open-sourced at https://github.com/yfguo91/Ternary-Spike.
Authors: Joel Shor, Hiro-o Yamano, Daisuke Tsurumaru, Yotami Intrator, Hiroki Kayama, Joe Ledsam, Atsushi Hamabe, Koji Ando, Mitsuhiko Ota, Haruei Ogino, Hiroshi Nakase, Kaho Kobayashi, Eiji Oki, Roman Goldenberg, Ehud Rivlin, Ichiro Takemasa
$\textbf{Background and aims}$: Artificial Intelligence (AI) Computer-Aided Detection (CADe) is commonly used for polyp detection, but data seen in clinical settings can differ from model training. Few studies evaluate how well CADe detectors perform on colonoscopies from countries not seen during training, and none are able to evaluate performance without collecting expensive and time-intensive labels.
$\textbf{Methods}$: We trained a CADe polyp detector on Israeli colonoscopy videos (5004 videos, 1106 hours) and evaluated on Japanese videos (354 videos, 128 hours) by measuring the True Positive Rate (TPR) versus false alarms per minute (FAPM). We introduce a colonoscopy dissimilarity measure called "MAsked mediCal Embedding Distance" (MACE) to quantify differences between colonoscopies, without labels. We evaluated CADe on all Japan videos and on those with the highest MACE.
$\textbf{Results}$: MACE correctly quantifies that narrow-band imaging (NBI) and chromoendoscopy (CE) frames are less similar to Israel data than Japan whitelight (bootstrapped z-test, |z| > 690, p < $10^{-8}$ for both). Despite differences in the data, CADe performance on Japan colonoscopies was non-inferior to Israel ones without additional training (TPR at 0.5 FAPM: 0.957 and 0.972 for Israel and Japan; TPR at 1.0 FAPM: 0.972 and 0.989 for Israel and Japan; superiority test t > 45.2, p < $10^{-8}$). Despite not being trained on NBI or CE, TPR on those subsets were non-inferior to Japan overall (non-inferiority test t > 47.3, p < $10^{-8}$, $\delta$ = 1.5% for both).
$\textbf{Conclusion}$: Differences that prevent CADe detectors from performing well in non-medical settings do not degrade the performance of our AI CADe polyp detector when applied to data from a new country. MACE can help medical AI models internationalize by identifying the most "dissimilar" data on which to evaluate models.
Authors: Guangfeng Jiang, Jun Liu, Yuzhi Wu, Wenlong Liao, Tao He, Pai Peng
Instance segmentation is a fundamental research in computer vision, especially in autonomous driving. However, manual mask annotation for instance segmentation is quite time-consuming and costly. To address this problem, some prior works attempt to apply weakly supervised manner by exploring 2D or 3D boxes. However, no one has ever successfully segmented 2D and 3D instances simultaneously by only using 2D box annotations, which could further reduce the annotation cost by an order of magnitude. Thus, we propose a novel framework called Multimodal Weakly Supervised Instance Segmentation (MWSIS), which incorporates various fine-grained label generation and correction modules for both 2D and 3D modalities to improve the quality of pseudo labels, along with a new multimodal cross-supervision approach, named Consistency Sparse Cross-modal Supervision (CSCS), to reduce the inconsistency of multimodal predictions by response distillation. Particularly, transferring the 3D backbone to downstream tasks not only improves the performance of the 3D detectors, but also outperforms fully supervised instance segmentation with only 5% fully supervised annotations. On the Waymo dataset, the proposed framework demonstrates significant improvements over the baseline, especially achieving 2.59% mAP and 12.75% mAP increases for 2D and 3D instance segmentation tasks, respectively. The code is available at https://github.com/jiangxb98/mwsis-plugin.
Authors: Qi Tang, Yao Zhao, Meiqin Liu, Jian Jin, Chao Yao
As a critical clue of video super-resolution (VSR), inter-frame alignment significantly impacts overall performance. However, accurate pixel-level alignment is a challenging task due to the intricate motion interweaving in the video. In response to this issue, we introduce a novel paradigm for VSR named Semantic Lens, predicated on semantic priors drawn from degraded videos. Specifically, video is modeled as instances, events, and scenes via a Semantic Extractor. Those semantics assist the Pixel Enhancer in understanding the recovered contents and generating more realistic visual results. The distilled global semantics embody the scene information of each frame, while the instance-specific semantics assemble the spatial-temporal contexts related to each instance. Furthermore, we devise a Semantics-Powered Attention Cross-Embedding (SPACE) block to bridge the pixel-level features with semantic knowledge, composed of a Global Perspective Shifter (GPS) and an Instance-Specific Semantic Embedding Encoder (ISEE). Concretely, the GPS module generates pairs of affine transformation parameters for pixel-level feature modulation conditioned on global semantics. After that, the ISEE module harnesses the attention mechanism to align the adjacent frames in the instance-centric semantic space. In addition, we incorporate a simple yet effective pre-alignment module to alleviate the difficulty of model training. Extensive experiments demonstrate the superiority of our model over existing state-of-the-art VSR methods.
Authors: Haifeng Huang, Zehan Wang, Rongjie Huang, Luping Liu, Xize Cheng, Yang Zhao, Tao Jin, Zhou Zhao
Recent research has evidenced the significant potentials of Large Language Models (LLMs) in handling challenging tasks within 3D scenes. However, current models are constrained to addressing object-centric tasks, where each question-answer pair focuses solely on an individual object. In real-world applications, users may pose queries involving multiple objects or expect for answers that precisely reference various objects. We introduce the use of object identifiers to freely reference objects during a conversation. While this solution appears straightforward, it presents two main challenges: 1) How to establish a reliable one-to-one correspondence between each object and its identifier? 2) How to incorporate complex spatial relationships among dozens of objects into the embedding space of the LLM? To address these challenges, we propose a two-stage alignment method, which involves learning an attribute-aware token and a relation-aware token for each object. These tokens capture the object's attributes and spatial relationships with surrounding objects in the 3D scene. Once the alignment is established, we can fine-tune our model on various downstream tasks using instruction tuning. Experiments conducted on traditional datasets like ScanQA, ScanRefer, and Nr3D/Sr3D showcase the effectiveness of our proposed method. Additionally, we create a 3D scene captioning dataset annotated with rich object identifiers, with the assistant of GPT-4. This dataset aims to further explore the capability of object identifiers in effective object referencing and precise scene understanding.
Authors: Zhuoyao Xin, Christopher Wu, Dong Liu, Chunming Gu, Jia Guo, Jun Hua
Image segmentation, real-value prediction, and cross-modal translation are critical challenges in medical imaging. In this study, we propose a versatile multi-task neural network framework, based on an enhanced Transformer U-Net architecture, capable of simultaneously, selectively, and adaptively addressing these medical image tasks. Validation is performed on a public repository of human brain MR and CT images. We decompose the traditional problem of synthesizing CT images into distinct subtasks, which include skull segmentation, Hounsfield unit (HU) value prediction, and image sequential reconstruction. To enhance the framework's versatility in handling multi-modal data, we expand the model with multiple image channels. Comparisons between synthesized CT images derived from T1-weighted and T2-Flair images were conducted, evaluating the model's capability to integrate multi-modal information from both morphological and pixel value perspectives.
Authors: Wenbin Zou, Hongxia Gao, Tian Ye, Liang Chen, Weipeng Yang, Shasha Huang, Hongsheng Chen, Sixiang Chen
Night photography often struggles with challenges like low light and blurring, stemming from dark environments and prolonged exposures. Current methods either disregard priors and directly fitting end-to-end networks, leading to inconsistent illumination, or rely on unreliable handcrafted priors to constrain the network, thereby bringing the greater error to the final result. We believe in the strength of data-driven high-quality priors and strive to offer a reliable and consistent prior, circumventing the restrictions of manual priors. In this paper, we propose Clearer Night Image Restoration with Vector-Quantized Codebook (VQCNIR) to achieve remarkable and consistent restoration outcomes on real-world and synthetic benchmarks. To ensure the faithful restoration of details and illumination, we propose the incorporation of two essential modules: the Adaptive Illumination Enhancement Module (AIEM) and the Deformable Bi-directional Cross-Attention (DBCA) module. The AIEM leverages the inter-channel correlation of features to dynamically maintain illumination consistency between degraded features and high-quality codebook features. Meanwhile, the DBCA module effectively integrates texture and structural information through bi-directional cross-attention and deformable convolution, resulting in enhanced fine-grained detail and structural fidelity across parallel decoders. Extensive experiments validate the remarkable benefits of VQCNIR in enhancing image quality under low-light conditions, showcasing its state-of-the-art performance on both synthetic and real-world datasets. The code is available at https://github.com/AlexZou14/VQCNIR.
Authors: Hanyang Kong, Dongze Lian, Michael Bi Mi, Xinchao Wang
We introduce DreamDrone, an innovative method for generating unbounded flythrough scenes from textual prompts. Central to our method is a novel feature-correspondence-guidance diffusion process, which utilizes the strong correspondence of intermediate features in the diffusion model. Leveraging this guidance strategy, we further propose an advanced technique for editing the intermediate latent code, enabling the generation of subsequent novel views with geometric consistency. Extensive experiments reveal that DreamDrone significantly surpasses existing methods, delivering highly authentic scene generation with exceptional visual quality. This approach marks a significant step in zero-shot perpetual view generation from textual prompts, enabling the creation of diverse scenes, including natural landscapes like oases and caves, as well as complex urban settings such as Lego-style street views. Our code is publicly available.
Authors: Jingxuan He, Lechao Cheng, Chaowei Fang, Zunlei Feng, Tingting Mu, Mingli Song
Compared to conventional semantic segmentation with pixel-level supervision, Weakly Supervised Semantic Segmentation (WSSS) with image-level labels poses the challenge that it always focuses on the most discriminative regions, resulting in a disparity between fully supervised conditions. A typical manifestation is the diminished precision on the object boundaries, leading to a deteriorated accuracy of WSSS. To alleviate this issue, we propose to adaptively partition the image content into deterministic regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing. For uncertain cues, we employ an activation-based masking strategy and seek to recover the local information with self-distilled knowledge. We further assume that the unmasked confident regions should be robust enough to preserve the global semantics. Building upon this, we introduce a complementary self-enhancement method that constrains the semantic consistency between these confident regions and an augmented image with the same class labels. Extensive experiments conducted on PASCAL VOC 2012 and MS COCO 2014 demonstrate that our proposed single-stage approach for WSSS not only outperforms state-of-the-art benchmarks remarkably but also surpasses multi-stage methodologies that trade complexity for accuracy. The code can be found at \url{https://github.com/Jessie459/feature-self-reinforcement}.
Authors: Han Liang, Jiacheng Bao, Ruichi Zhang, Sihan Ren, Yuecheng Xu, Sibei Yang, Xin Chen, Jingyi Yu, Lan Xu
We have recently seen tremendous progress in realistic text-to-motion generation. Yet, the existing methods often fail or produce implausible motions with unseen text inputs, which limits the applications. In this paper, we present OMG, a novel framework, which enables compelling motion generation from zero-shot open-vocabulary text prompts. Our key idea is to carefully tailor the pretrain-then-finetune paradigm into the text-to-motion generation. At the pre-training stage, our model improves the generation ability by learning the rich out-of-domain inherent motion traits. To this end, we scale up a large unconditional diffusion model up to 1B parameters, so as to utilize the massive unlabeled motion data up to over 20M motion instances. At the subsequent fine-tuning stage, we introduce motion ControlNet, which incorporates text prompts as conditioning information, through a trainable copy of the pre-trained model and the proposed novel Mixture-of-Controllers (MoC) block. MoC block adaptively recognizes various ranges of the sub-motions with a cross-attention mechanism and processes them separately with the text-token-specific experts. Such a design effectively aligns the CLIP token embeddings of text prompts to various ranges of compact and expressive motion features. Extensive experiments demonstrate that our OMG achieves significant improvements over the state-of-the-art methods on zero-shot text-to-motion generation. Project page: https://tr3e.github.io/omg-page.
Authors: Jinghong Li, Wen Gu, Koichi Ota, Shinobu Hasegawa
With the rapid development of the internet in the past decade, it has become increasingly important to extract valuable information from vast resources efficiently, which is crucial for establishing a comprehensive digital ecosystem, particularly in the context of research surveys and comprehension. The foundation of these tasks focuses on accurate extraction and deep mining of data from scientific documents, which are essential for building a robust data infrastructure. However, parsing raw data or extracting data from complex scientific documents have been ongoing challenges. Current data extraction methods for scientific documents typically use rule-based (RB) or machine learning (ML) approaches. However, using rule-based methods can incur high coding costs for articles with intricate typesetting. Conversely, relying solely on machine learning methods necessitates annotation work for complex content types within the scientific document, which can be costly. Additionally, few studies have thoroughly defined and explored the hierarchical layout within scientific documents. The lack of a comprehensive definition of the internal structure and elements of the documents indirectly impacts the accuracy of text classification and object recognition tasks. From the perspective of analyzing the standard layout and typesetting used in the specified publication, we propose a new document layout analysis framework called CTBR(Compartment & Text Blocks Refinement). Firstly, we define scientific documents into hierarchical divisions: base domain, compartment, and text blocks. Next, we conduct an in-depth exploration and classification of the meanings of text blocks. Finally, we utilize the results of text block classification to implement object recognition within scientific documents based on rule-based compartment segmentation.
Authors: Tom Nuno Wolf, Fabian Bongratz, Anne-Marie Rickmann, Sebastian Pölsterl, Christian Wachinger
Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations based on similar examples. To this end, ProtoPNet learns a set of class-representative feature vectors (prototypes) for case-based reasoning. During inference, similarities of latent features to prototypes are linearly classified to form predictions and attribution maps are provided to explain the similarity. In this work, we evaluate whether architectures for case-based reasoning fulfill established axioms required for faithful explanations using the example of ProtoPNet. We show that such architectures allow the extraction of faithful explanations. However, we prove that the attribution maps used to explain the similarities violate the axioms. We propose a new procedure to extract explanations for trained ProtoPNets, named ProtoPFaith. Conceptually, these explanations are Shapley values, calculated on the similarity scores of each prototype. They allow to faithfully answer which prototypes are present in an unseen image and quantify each pixel's contribution to that presence, thereby complying with all axioms. The theoretical violations of ProtoPNet manifest in our experiments on three datasets (CUB-200-2011, Stanford Dogs, RSNA) and five architectures (ConvNet, ResNet, ResNet50, WideResNet50, ResNeXt50). Our experiments show a qualitative difference between the explanations given by ProtoPNet and ProtoPFaith. Additionally, we quantify the explanations with the Area Over the Perturbation Curve, on which ProtoPFaith outperforms ProtoPNet on all experiments by a factor $>10^3$.
Authors: Zhengqiang Zhang, Ruihuang Li, Shi Guo, Yang Cao, Lei Zhang
Online video super-resolution (online-VSR) highly relies on an effective alignment module to aggregate temporal information, while the strict latency requirement makes accurate and efficient alignment very challenging. Though much progress has been achieved, most of the existing online-VSR methods estimate the motion fields of each frame separately to perform alignment, which is computationally redundant and ignores the fact that the motion fields of adjacent frames are correlated. In this work, we propose an efficient Temporal Motion Propagation (TMP) method, which leverages the continuity of motion field to achieve fast pixel-level alignment among consecutive frames. Specifically, we first propagate the offsets from previous frames to the current frame, and then refine them in the neighborhood, which significantly reduces the matching space and speeds up the offset estimation process. Furthermore, to enhance the robustness of alignment, we perform spatial-wise weighting on the warped features, where the positions with more precise offsets are assigned higher importance. Experiments on benchmark datasets demonstrate that the proposed TMP method achieves leading online-VSR accuracy as well as inference speed. The source code of TMP can be found at https://github.com/xtudbxk/TMP.
Authors: Jifan Zhang, Julian Katz-Samuels, Robert Nowak
Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a small fraction of the overall dataset -- most of the data may be viewed as an out-of-distribution or irrelevant class. This leads to extreme class-imbalance, and our theory and methods focus on this core issue. We propose a new strategy for active learning called GALAXY (Graph-based Active Learning At the eXtrEme), which blends ideas from graph-based active learning and deep learning. GALAXY automatically and adaptively selects more class-balanced examples for labeling than most other methods for active learning. Our theory shows that GALAXY performs a refined form of uncertainty sampling that gathers a much more class-balanced dataset than vanilla uncertainty sampling. Experimentally, we demonstrate GALAXY's superiority over existing state-of-art deep active learning algorithms in unbalanced vision classification settings generated from popular datasets.
Authors: Danya Li, Joaquin Gajardo, Michele Volpi, Thijs Defraeye
Crop maps are crucial for agricultural monitoring and food management and can additionally support domain-specific applications, such as setting cold supply chain infrastructure in developing countries. Machine learning (ML) models, combined with freely-available satellite imagery, can be used to produce cost-effective and high spatial-resolution crop maps. However, accessing ground truth data for supervised learning is especially challenging in developing countries due to factors such as smallholding and fragmented geography, which often results in a lack of crop type maps or even reliable cropland maps. Our area of interest for this study lies in Himachal Pradesh, India, where we aim at producing an open-access binary cropland map at 10-meter resolution for the Kullu, Shimla, and Mandi districts. To this end, we developed an ML pipeline that relies on Sentinel-2 satellite images time series. We investigated two pixel-based supervised classifiers, support vector machines (SVM) and random forest (RF), which are used to classify per-pixel time series for binary cropland mapping. The ground truth data used for training, validation and testing was manually annotated from a combination of field survey reference points and visual interpretation of very high resolution (VHR) imagery. We trained and validated the models via spatial cross-validation to account for local spatial autocorrelation and selected the RF model due to overall robustness and lower computational cost. We tested the generalization capability of the chosen model at the pixel level by computing the accuracy, recall, precision, and F1-score on hold-out test sets of each district, achieving an average accuracy for the RF (our best model) of 87%. We used this model to generate a cropland map for three districts of Himachal Pradesh, spanning 14,600 km2, which improves the resolution and quality of existing public maps.
Authors: Jifan Zhang, Shuai Shao, Saurabh Verma, Robert Nowak
Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning algorithms can vary dramatically across datasets and applications. It is difficult to know in advance which active learning strategy will perform well or best in a given application. To address this, we propose the first adaptive algorithm selection strategy for deep active learning. For any unlabeled dataset, our (meta) algorithm TAILOR (Thompson ActIve Learning algORithm selection) iteratively and adaptively chooses among a set of candidate active learning algorithms. TAILOR uses novel reward functions aimed at gathering class-balanced examples. Extensive experiments in multi-class and multi-label applications demonstrate TAILOR's effectiveness in achieving accuracy comparable or better than that of the best of the candidate algorithms. Our implementation of TAILOR is open-sourced at https://github.com/jifanz/TAILOR.
Authors: Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person has a different appearance e.g. pose, face, and clothing, despite using the same text prompt. The appearance inconsistency makes T2I unsuitable for pose transfer. We address this by proposing a multimodal diffusion model that accepts text, pose, and visual prompting. Our model is the first unified method to perform all person image tasks - generation, pose transfer, and mask-less edit. We also pioneer using small dimensional 3D body model parameters directly to demonstrate new capability - simultaneous pose and camera view interpolation while maintaining the person's appearance.
Authors: Jifan Zhang, Yifang Chen, Gregory Canal, Stephen Mussmann, Arnav M. Das, Gantavya Bhatt, Yinglun Zhu, Simon Shaolei Du, Kevin Jamieson, Robert D Nowak
Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer learning, semi-supervised learning and active learning, aim to be label-efficient: achieving high predictive performance from relatively few labeled examples. While obtaining the best label-efficiency in practice often requires combinations of these techniques, existing benchmark and evaluation frameworks do not capture a concerted combination of all such techniques. This paper addresses this deficiency by introducing LabelBench, a new computationally-efficient framework for joint evaluation of multiple label-efficient learning techniques. As an application of LabelBench, we introduce a novel benchmark of state-of-the-art active learning methods in combination with semi-supervised learning for fine-tuning pretrained vision transformers. Our benchmark demonstrates better label-efficiencies than previously reported in active learning. LabelBench's modular codebase is open-sourced for the broader community to contribute label-efficient learning methods and benchmarks. The repository can be found at: https://github.com/EfficientTraining/LabelBench.
Authors: Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
This paper introduces ViscoNet, a novel method that enhances text-to-image human generation models with visual prompting. Unlike existing methods that rely on lengthy text descriptions to control the image structure, ViscoNet allows users to specify the visual appearance of the target object with a reference image. ViscoNet disentangles the object's appearance from the image background and injects it into a pre-trained latent diffusion model (LDM) model via a ControlNet branch. This way, ViscoNet mitigates the style mode collapse problem and enables precise and flexible visual control. We demonstrate the effectiveness of ViscoNet on human image generation, where it can manipulate visual attributes and artistic styles with text and image prompts. We also show that ViscoNet can learn visual conditioning from small and specific object domains while preserving the generative power of the LDM backbone.
Authors: Shyam Nuggehalli, Jifan Zhang, Lalit Jain, Robert Nowak
Class imbalance is a prevalent issue in real world machine learning applications, often leading to poor performance in rare and minority classes. With an abundance of wild unlabeled data, active learning is perhaps the most effective technique in solving the problem at its root -- collecting a more balanced and informative set of labeled examples during annotation. In this work, we propose a novel algorithm that first identifies the class separation threshold and then annotate the most uncertain examples from the minority classes, close to the separation threshold. Through a novel reduction to one-dimensional active learning, our algorithm DIRECT is able to leverage the classic active learning literature to address issues such as batch labeling and tolerance towards label noise. Compared to existing algorithms, our algorithm saves more than 15\% of the annotation budget compared to state-of-art active learning algorithm and more than 90\% of annotation budget compared to random sampling.