Authors: Aryan Mathur
Abstract: In this paper of a research based project, using Bidirectional Long Short-Term Memory (BiLSTM) networks, we provide a novel Fight Scene Detection (FSD) model which can be used for Movie Highlight Generation Systems (MHGS) based on deep learning and Neural Networks . Movies usually have Fight Scenes to keep the audience amazed. For trailer generation, or any other application of Highlight generation, it is very tidious to first identify all such scenes manually and then compile them to generate a highlight serving the purpose. Our proposed FSD system utilises temporal characteristics of the movie scenes and thus is capable to automatically identify fight scenes. Thereby helping in the effective production of captivating movie highlights. We observe that the proposed solution features 93.5% accuracy and is higher than 2D CNN with Hough Forests which being 92% accurate and is significantly higher than 3D CNN which features an accuracy of 65%.
Authors: Scott Geng, Cheng-Yu Hsieh, Vivek Ramanujan, Matthew Wallingford, Chun-Liang Li, Pang Wei Koh, Ranjay Krishna
Abstract: Generative text-to-image models enable us to synthesize unlimited amounts of images in a controllable manner, spurring many recent efforts to train vision models with synthetic data. However, every synthetic image ultimately originates from the upstream data used to train the generator. What additional value does the intermediate generator provide over directly training on relevant parts of the upstream data? Grounding this question in the setting of image classification, we compare finetuning on task-relevant, targeted synthetic data generated by Stable Diffusion -- a generative model trained on the LAION-2B dataset -- against finetuning on targeted real images retrieved directly from LAION-2B. We show that while synthetic data can benefit some downstream tasks, it is universally matched or outperformed by real data from our simple retrieval baseline. Our analysis suggests that this underperformance is partially due to generator artifacts and inaccurate task-relevant visual details in the synthetic images. Overall, we argue that retrieval is a critical baseline to consider when training with synthetic data -- a baseline that current methods do not yet surpass. We release code, data, and models at https://github.com/scottgeng00/unmet-promise.
Authors: Shaurya Dewan, Rushikesh Zawar, Prakanshul Saxena, Yingshan Chang, Andrew Luo, Yonatan Bisk
Abstract: Text-to-image diffusion models have made significant progress in generating naturalistic images from textual inputs, and demonstrate the capacity to learn and represent complex visual-semantic relationships. While these diffusion models have achieved remarkable success, the underlying mechanisms driving their performance are not yet fully accounted for, with many unanswered questions surrounding what they learn, how they represent visual-semantic relationships, and why they sometimes fail to generalize. Our work presents Diffusion Partial Information Decomposition (DiffusionPID), a novel technique that applies information-theoretic principles to decompose the input text prompt into its elementary components, enabling a detailed examination of how individual tokens and their interactions shape the generated image. We introduce a formal approach to analyze the uniqueness, redundancy, and synergy terms by applying PID to the denoising model at both the image and pixel level. This approach enables us to characterize how individual tokens and their interactions affect the model output. We first present a fine-grained analysis of characteristics utilized by the model to uniquely localize specific concepts, we then apply our approach in bias analysis and show it can recover gender and ethnicity biases. Finally, we use our method to visually characterize word ambiguity and similarity from the model's perspective and illustrate the efficacy of our method for prompt intervention. Our results show that PID is a potent tool for evaluating and diagnosing text-to-image diffusion models.
Authors: Sajid Javed, Arif Mahmood, Iyyakutti Iyappan Ganapathi, Fayaz Ali Dharejo, Naoufel Werghi, Mohammed Bennamoun
Abstract: This paper proposes Comprehensive Pathology Language Image Pre-training (CPLIP), a new unsupervised technique designed to enhance the alignment of images and text in histopathology for tasks such as classification and segmentation. This methodology enriches vision-language models by leveraging extensive data without needing ground truth annotations. CPLIP involves constructing a pathology-specific dictionary, generating textual descriptions for images using language models, and retrieving relevant images for each text snippet via a pre-trained model. The model is then fine-tuned using a many-to-many contrastive learning method to align complex interrelated concepts across both modalities. Evaluated across multiple histopathology tasks, CPLIP shows notable improvements in zero-shot learning scenarios, outperforming existing methods in both interpretability and robustness and setting a higher benchmark for the application of vision-language models in the field. To encourage further research and replication, the code for CPLIP is available on GitHub at https://cplip.github.io/
URLs: https://cplip.github.io/
Authors: Yilin Liu, Jiale Chen, Shanshan Pan, Daniel Cohen-Or, Hao Zhang, Hui Huang
Abstract: We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models which involves a two-step process: it first applies a spatial partitioning, referred to as the ``split``, followed by a ``fit`` operation to derive a single primitive within each partition. Specifically, our partitioning aims to produce the classical Voronoi diagram of the set of ground-truth (GT) B-Rep primitives. In contrast to prior B-Rep constructions which were bottom-up, either via direct primitive fitting or point clustering, our Split-and-Fit approach is top-down and structure-aware, since a Voronoi partition explicitly reveals both the number of and the connections between the primitives. We design a neural network to predict the Voronoi diagram from an input point cloud or distance field via a binary classification. We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data and exhibits superior generalization capabilities. Extensive experiments and evaluation demonstrate that the resulting B-Reps, consisting of parametric surfaces, curves, and vertices, are more plausible than those obtained by existing alternatives, with significant improvements in reconstruction quality. Code will be released on https://github.com/yilinliu77/NVDNet.
Authors: Xiaoqi Wang, Wenbin He, Xiwei Xuan, Clint Sebastian, Jorge Piazentin Ono, Xin Li, Sima Behpour, Thang Doan, Liang Gou, Han Wei Shen, Liu Ren
Abstract: The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recent vision-based foundation models such as the Segment Anything Model (SAM) have shown superior performance in generating class-agnostic image segments. The main challenge in open-vocabulary image segmentation now lies in accurately classifying these segments into text-defined categories. In this paper, we introduce the Universal Segment Embedding (USE) framework to address this challenge. This framework is comprised of two key components: 1) a data pipeline designed to efficiently curate a large amount of segment-text pairs at various granularities, and 2) a universal segment embedding model that enables precise segment classification into a vast range of text-defined categories. The USE model can not only help open-vocabulary image segmentation but also facilitate other downstream tasks (e.g., querying and ranking). Through comprehensive experimental studies on semantic segmentation and part segmentation benchmarks, we demonstrate that the USE framework outperforms state-of-the-art open-vocabulary segmentation methods.
Authors: Yufan He, Pengfei Guo, Yucheng Tang, Andriy Myronenko, Vishwesh Nath, Ziyue Xu, Dong Yang, Can Zhao, Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, Daguang Xu, Wenqi Li
Abstract: Segmentation foundation models have attracted great interest, however, none of them are adequate enough for the use cases in 3D computed tomography scans (CT) images. Existing works finetune on medical images with 2D foundation models trained on natural images, but interactive segmentation, especially in 2D, is too time-consuming for 3D scans and less useful for large cohort analysis. Models that can perform out-of-the-box automatic segmentation are more desirable. However, the model trained in this way lacks the ability to perform segmentation on unseen objects like novel tumors. Thus for 3D medical image analysis, an ideal segmentation solution might expect two features: accurate out-of-the-box performance covering major organ classes, and effective adaptation or zero-shot ability to novel structures. In this paper, we discuss what features a 3D CT segmentation foundation model should have, and introduce VISTA3D, Versatile Imaging SegmenTation and Annotation model. The model is trained systematically on 11454 volumes encompassing 127 types of human anatomical structures and various lesions and provides accurate out-of-the-box segmentation. The model's design also achieves state-of-the-art zero-shot interactive segmentation in 3D. The novel model design and training recipe represent a promising step toward developing a versatile medical image foundation model. Code and model weights will be released shortly. The early version of online demo can be tried on https://build.nvidia.com/nvidia/vista-3d.
Authors: Avrajit Ghosh, Xitong Zhang, Kenneth K. Sun, Qing Qu, Saiprasad Ravishankar, Rongrong Wang
Abstract: We introduce Optimal Eye Surgeon (OES), a framework for pruning and training deep image generator networks. Typically, untrained deep convolutional networks, which include image sampling operations, serve as effective image priors (Ulyanov et al., 2018). However, they tend to overfit to noise in image restoration tasks due to being overparameterized. OES addresses this by adaptively pruning networks at random initialization to a level of underparameterization. This process effectively captures low-frequency image components even without training, by just masking. When trained to fit noisy images, these pruned subnetworks, which we term Sparse-DIP, resist overfitting to noise. This benefit arises from underparameterization and the regularization effect of masking, constraining them in the manifold of image priors. We demonstrate that subnetworks pruned through OES surpass other leading pruning methods, such as the Lottery Ticket Hypothesis, which is known to be suboptimal for image recovery tasks (Wu et al., 2023). Our extensive experiments demonstrate the transferability of OES-masks and the characteristics of sparse-subnetworks for image generation. Code is available at https://github.com/Avra98/Optimal-Eye-Surgeon.git.
Authors: Yilin Wang, Joong Gon Yim, Neil Birkbeck, Balu Adsumilli
Abstract: The popularity of Short form videos (SFV) has grown dramatically in the past few years, and has become a phenomenal video category with billions of viewers. Meanwhile, High Dynamic Range (HDR) as an advanced feature also becomes more and more popular on video sharing platforms. As a hot topic with huge impact, SFV and HDR bring new questions to video quality research: 1) is SFV+HDR quality assessment significantly different from traditional User Generated Content (UGC) quality assessment? 2) do objective quality metrics designed for traditional UGC still work well for SFV+HDR? To answer the above questions, we created the first large scale SFV+HDR dataset with reliable subjective quality scores, covering 10 popular content categories. Further, we also introduce a general sampling framework to maximize the representativeness of the dataset. We provided a comprehensive analysis of subjective quality scores for Short form SDR and HDR videos, and discuss the reliability of state-of-the-art UGC quality metrics and potential improvements.
Authors: Heming Yao, Phil Hanslovsky, Jan-Christian Huetter, Burkhard Hoeckendorf, David Richmond
Abstract: Optical Pooled Screening (OPS) is a powerful tool combining high-content microscopy with genetic engineering to investigate gene function in disease. The characterization of high-content images remains an active area of research and is currently undergoing rapid innovation through the application of self-supervised learning and vision transformers. In this study, we propose a set-level consistency learning algorithm, Set-DINO, that combines self-supervised learning with weak supervision to improve learned representations of perturbation effects in single-cell images. Our method leverages the replicate structure of OPS experiments (i.e., cells undergoing the same genetic perturbation, both within and across batches) as a form of weak supervision. We conduct extensive experiments on a large-scale OPS dataset with more than 5000 genetic perturbations, and demonstrate that Set-DINO helps mitigate the impact of confounders and encodes more biologically meaningful information. In particular, Set-DINO recalls known biological relationships with higher accuracy compared to commonly used methods for morphological profiling, suggesting that it can generate more reliable insights from drug target discovery campaigns leveraging OPS.
Authors: Zijian Zhang, Wei Liu
Abstract: In this paper, we present our solution for SMART-101 Challenge of CVPR Multi-modal Algorithmic Reasoning Task 2024. Unlike traditional visual questions and answer tasks, this challenge evaluates abstraction, deduction and generalization ability of neural network in solving visuo-linguistic puzzles designed for specially children in the 6-8 age group. Our model is based on two pre-trained models, dedicated to extract features from text and image respectively. To integrate the features from different modalities, we employed a fusion layer with attention mechanism. We explored different text and image pre-trained models, and fine-tune the integrated classifier on the SMART-101 dataset. Experiment results show that under the data splitting style of puzzle split, our proposed integrated classifier achieves superior performance, verifying the effectiveness of multi-modal pre-trained representations.
Authors: Pengyang Ling, Jiazi Bu, Pan Zhang, Xiaoyi Dong, Yuhang Zang, Tong Wu, Huaian Chen, Jiaqi Wang, Yi Jin
Abstract: Motion-based controllable text-to-video generation involves motions to control the video generation. Previous methods typically require the training of models to encode motion cues or the fine-tuning of video diffusion models. However, these approaches often result in suboptimal motion generation when applied outside the trained domain. In this work, we propose MotionClone, a training-free framework that enables motion cloning from a reference video to control text-to-video generation. We employ temporal attention in video inversion to represent the motions in the reference video and introduce primary temporal-attention guidance to mitigate the influence of noisy or very subtle motions within the attention weights. Furthermore, to assist the generation model in synthesizing reasonable spatial relationships and enhance its prompt-following capability, we propose a location-aware semantic guidance mechanism that leverages the coarse location of the foreground from the reference video and original classifier-free guidance features to guide the video generation. Extensive experiments demonstrate that MotionClone exhibits proficiency in both global camera motion and local object motion, with notable superiority in terms of motion fidelity, textual alignment, and temporal consistency.
Authors: Thanh-Huy Nguyen, Thi Kim Ngan Ngo, Mai Anh Vu, Ting-Yuan Tu
Abstract: The ability of three-dimensional (3D) spheroid modeling to study the invasive behavior of breast cancer cells has drawn increased attention. The deep learning-based image processing framework is very effective at speeding up the cell morphological analysis process. Out-of-focus photos taken while capturing 3D cells under several z-slices, however, could negatively impact the deep learning model. In this work, we created a new algorithm to handle blurry images while preserving the stacked image quality. Furthermore, we proposed a unique training architecture that leverages consistency training to help reduce the bias of the model when dense-slice stacking is applied. Additionally, the model's stability is increased under the sparse-slice stacking effect by utilizing the self-training approach. The new blurring stacking technique and training flow are combined with the suggested architecture and self-training mechanism to provide an innovative yet easy-to-use framework. Our methods produced noteworthy experimental outcomes in terms of both quantitative and qualitative aspects.
Authors: Qingfeng Liu, Mostafa El-Khamy, Kee-Bong Song
Abstract: The third Pixel-level Video Understanding in the Wild (PVUW CVPR 2024) challenge aims to advance the state of art in video understanding through benchmarking Video Panoptic Segmentation (VPS) and Video Semantic Segmentation (VSS) on challenging videos and scenes introduced in the large-scale Video Panoptic Segmentation in the Wild (VIPSeg) test set and the large-scale Video Scene Parsing in the Wild (VSPW) test set, respectively. This paper details our research work that achieved the 1st place winner in the PVUW'24 VPS challenge, establishing state of art results in all metrics, including the Video Panoptic Quality (VPQ) and Segmentation and Tracking Quality (STQ). With minor fine-tuning our approach also achieved the 3rd place in the PVUW'24 VSS challenge ranked by the mIoU (mean intersection over union) metric and the first place ranked by the VC16 (16-frame video consistency) metric. Our winning solution stands on the shoulders of giant foundational vision transformer model (DINOv2 ViT-g) and proven multi-stage Decoupled Video Instance Segmentation (DVIS) frameworks for video understanding.
Authors: Thomas Dag\`es, Michael Lindenbaum, Alfred M. Bruckstein
Abstract: Standard convolutions are prevalent in image processing and deep learning, but their fixed kernel design limits adaptability. Several deformation strategies of the reference kernel grid have been proposed. Yet, they lack a unified theoretical framework. By returning to a metric perspective for images, now seen as two-dimensional manifolds equipped with notions of local and geodesic distances, either symmetric (Riemannian metrics) or not (Finsler metrics), we provide a unifying principle: the kernel positions are samples of unit balls of implicit metrics. With this new perspective, we also propose metric convolutions, a novel approach that samples unit balls from explicit signal-dependent metrics, providing interpretable operators with geometric regularisation. This framework, compatible with gradient-based optimisation, can directly replace existing convolutions applied to either input images or deep features of neural networks. Metric convolutions typically require fewer parameters and provide better generalisation. Our approach shows competitive performance in standard denoising and classification tasks.
Authors: Zhenyu Wang, Jianxi Huang, Zhida Sun, Daniel Cohen-Or, Min Lu
Abstract: This work presents a novel progressive image vectorization technique aimed at generating layered vectors that represent the original image from coarse to fine detail levels. Our approach introduces semantic simplification, which combines Score Distillation Sampling and semantic segmentation to iteratively simplify the input image. Subsequently, our method optimizes the vector layers for each of the progressively simplified images. Our method provides robust optimization, which avoids local minima and enables adjustable detail levels in the final output. The layered, compact vector representation enhances usability for further editing and modification. Comparative analysis with conventional vectorization methods demonstrates our technique's superiority in producing vectors with high visual fidelity, and more importantly, maintaining vector compactness and manageability. The project homepage is https://szuviz.github.io/layered_vectorization/.
Authors: Hao Zhang, Shuaijie Zhang, Renbin Zou
Abstract: Data augmentation refers to the process of applying a series of transformations or expansions to original data to generate new samples, thereby increasing the diversity and quantity of the data, effectively improving the performance and robustness of models. As a common data augmentation method, Mosaic data augmentation technique stitches multiple images together to increase the diversity and complexity of training data, thereby reducing the risk of overfitting. Although Mosaic data augmentation achieves excellent results in general detection tasks by stitching images together, it still has certain limitations for specific detection tasks. This paper addresses the challenge of detecting a large number of densely distributed small objects in aerial images by proposing the Select-Mosaic data augmentation method, which is improved with a fine-grained region selection strategy. The improved Select-Mosaic method demonstrates superior performance in handling dense small object detection tasks, significantly enhancing the accuracy and stability of detection models. Code is available at https://github.com/malagoutou/Select-Mosaic.
Authors: Minho Park, Sunghyun Park, Jooyeol Yun, Jaegul Choo
Abstract: Recent advancements in text-to-image generation have inspired researchers to generate datasets tailored for perception models using generative models, which prove particularly valuable in scenarios where real-world data is limited. In this study, our goal is to address the challenges when fine-tuning vision-language models (e.g., CLIP) on generated datasets. Specifically, we aim to fine-tune vision-language models to a specific classification model without access to any real images, also known as name-only transfer. However, despite the high fidelity of generated images, we observed a significant performance degradation when fine-tuning the model using the generated datasets due to the domain gap between real and generated images. To overcome the domain gap, we provide two regularization methods for training and post-training, respectively. First, we leverage the domain-agnostic knowledge from the original pre-trained vision-language model by conducting the weight-space ensemble of the fine-tuned model on the generated dataset with the original pre-trained model at the post-training. Secondly, we reveal that fine-tuned models with high feature diversity score high performance in the real domain, which indicates that increasing feature diversity prevents learning the generated domain-specific knowledge. Thus, we encourage feature diversity by providing additional regularization at training time. Extensive experiments on various classification datasets and various text-to-image generation models demonstrated that our analysis and regularization techniques effectively mitigate the domain gap, which has long been overlooked, and enable us to achieve state-of-the-art performance by training with generated images. Code is available at https://github.com/pmh9960/regft-for-gen
Authors: Shivansh Chandra Tripathi, Rahul Garg
Abstract: The development of existing facial coding systems, such as the Facial Action Coding System (FACS), relied on manual examination of facial expression videos for defining Action Units (AUs). To overcome the labor-intensive nature of this process, we propose the unsupervised learning of an automated facial coding system by leveraging computer-vision-based facial keypoint tracking. In this novel facial coding system called the Data-driven Facial Expression Coding System (DFECS), the AUs are estimated by applying dimensionality reduction to facial keypoint movements from a neutral frame through a proposed Full Face Model (FFM). FFM employs a two-level decomposition using advanced dimensionality reduction techniques such as dictionary learning (DL) and non-negative matrix factorization (NMF). These techniques enhance the interpretability of AUs by introducing constraints such as sparsity and positivity to the encoding matrix. Results show that DFECS AUs estimated from the DISFA dataset can account for an average variance of up to 91.29 percent in test datasets (CK+ and BP4D-Spontaneous) and also surpass the variance explained by keypoint-based equivalents of FACS AUs in these datasets. Additionally, 87.5 percent of DFECS AUs are interpretable, i.e., align with the direction of facial muscle movements. In summary, advancements in automated facial coding systems can accelerate facial expression analysis across diverse fields such as security, healthcare, and entertainment. These advancements offer numerous benefits, including enhanced detection of abnormal behavior, improved pain analysis in healthcare settings, and enriched emotion-driven interactions. To facilitate further research, the code repository of DFECS has been made publicly accessible.
Authors: Jingchao Peng, Thomas Bashford-Rogers, Francesco Banterle, Haitao Zhao, Kurt Debattista
Abstract: Capturing real world lighting is a long standing challenge in imaging and most practical methods acquire High Dynamic Range (HDR) images by either fusing multiple exposures, or boosting the dynamic range of Standard Dynamic Range (SDR) images. Multiple exposure capture is problematic as it requires longer capture times which can often lead to ghosting problems. The main alternative, inverse tone mapping is an ill-defined problem that is especially challenging as single captured exposures usually contain clipped and quantized values, and are therefore missing substantial amounts of content. To alleviate this, we propose a new approach, High Dynamic Range Thermal (HDRT), for HDR acquisition using a separate, commonly available, thermal infrared (IR) sensor. We propose a novel deep neural method (HDRTNet) which combines IR and SDR content to generate HDR images. HDRTNet learns to exploit IR features linked to the RGB image and the IR-specific parameters are subsequently used in a dual branch method that fuses features at shallow layers. This produces an HDR image that is significantly superior to that generated using naive fusion approaches. To validate our method, we have created the first HDR and thermal dataset, and performed extensive experiments comparing HDRTNet with the state-of-the-art. We show substantial quantitative and qualitative quality improvements on both over- and under-exposed images, showing that our approach is robust to capturing in multiple different lighting conditions.
Authors: Susu Sun, Stefano Woerner, Andreas Maier, Lisa M. Koch, Christian F. Baumgartner
Abstract: Interpretability is crucial for machine learning algorithms in high-stakes medical applications. However, high-performing neural networks typically cannot explain their predictions. Post-hoc explanation methods provide a way to understand neural networks but have been shown to suffer from conceptual problems. Moreover, current research largely focuses on providing local explanations for individual samples rather than global explanations for the model itself. In this paper, we propose Attri-Net, an inherently interpretable model for multi-label classification that provides local and global explanations. Attri-Net first counterfactually generates class-specific attribution maps to highlight the disease evidence, then performs classification with logistic regression classifiers based solely on the attribution maps. Local explanations for each prediction can be obtained by interpreting the attribution maps weighted by the classifiers' weights. Global explanation of whole model can be obtained by jointly considering learned average representations of the attribution maps for each class (called the class centers) and the weights of the linear classifiers. To ensure the model is ``right for the right reason", we further introduce a mechanism to guide the model's explanations to align with human knowledge. Our comprehensive evaluations show that Attri-Net can generate high-quality explanations consistent with clinical knowledge while not sacrificing classification performance.
Authors: Zanlin Ni, Yulin Wang, Renping Zhou, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Shiji Song, Yuan Yao, Gao Huang
Abstract: The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has prompted the pursuit of more efficient alternatives. As a representative work, non-autoregressive Transformers (NATs) have been recognized for their rapid generation. However, a major drawback of these models is their inferior performance compared to diffusion models. In this paper, we aim to re-evaluate the full potential of NATs by revisiting the design of their training and inference strategies. Specifically, we identify the complexities in properly configuring these strategies and indicate the possible sub-optimality in existing heuristic-driven designs. Recognizing this, we propose to go beyond existing methods by directly solving the optimal strategies in an automatic framework. The resulting method, named AutoNAT, advances the performance boundaries of NATs notably, and is able to perform comparably with the latest diffusion models at a significantly reduced inference cost. The effectiveness of AutoNAT is validated on four benchmark datasets, i.e., ImageNet-256 & 512, MS-COCO, and CC3M. Our code is available at https://github.com/LeapLabTHU/ImprovedNAT.
Authors: Xiaoli Wei, Zhaoqing Wang, Yandong Guo, Chunxia Zhang, Tongliang Liu, Mingming Gong
Abstract: Interactive video object segmentation is a crucial video task, having various applications from video editing to data annotating. However, current approaches struggle to accurately segment objects across diverse domains. Recently, Segment Anything Model (SAM) introduces interactive visual prompts and demonstrates impressive performance across different domains. In this paper, we propose a training-free prompt tracking framework for interactive video object segmentation (I-PT), leveraging the powerful generalization of SAM. Although point tracking efficiently captures the pixel-wise information of objects in a video, points tend to be unstable when tracked over a long period, resulting in incorrect segmentation. Towards fast and robust interaction, we jointly adopt sparse points and boxes tracking, filtering out unstable points and capturing object-wise information. To better integrate reference information from multiple interactions, we introduce a cross-round space-time module (CRSTM), which adaptively aggregates mask features from previous rounds and frames, enhancing the segmentation stability. Our framework has demonstrated robust zero-shot video segmentation results on popular VOS datasets with interaction types, including DAVIS 2017, YouTube-VOS 2018, and MOSE 2023, maintaining a good tradeoff between performance and interaction time.
Authors: Hao Fang, Jiawei Kong, Wenbo Yu, Bin Chen, Jiawei Li, Shutao Xia, Ke Xu
Abstract: Vision-Language Pre-training (VLP) models trained on large-scale image-text pairs have demonstrated unprecedented capability in many practical applications. However, previous studies have revealed that VLP models are vulnerable to adversarial samples crafted by a malicious adversary. While existing attacks have achieved great success in improving attack effect and transferability, they all focus on instance-specific attacks that generate perturbations for each input sample. In this paper, we show that VLP models can be vulnerable to a new class of universal adversarial perturbation (UAP) for all input samples. Although initially transplanting existing UAP algorithms to perform attacks showed effectiveness in attacking discriminative models, the results were unsatisfactory when applied to VLP models. To this end, we revisit the multimodal alignments in VLP model training and propose the Contrastive-training Perturbation Generator with Cross-modal conditions (C-PGC). Specifically, we first design a generator that incorporates cross-modal information as conditioning input to guide the training. To further exploit cross-modal interactions, we propose to formulate the training objective as a multimodal contrastive learning paradigm based on our constructed positive and negative image-text pairs. By training the conditional generator with the designed loss, we successfully force the adversarial samples to move away from its original area in the VLP model's feature space, and thus essentially enhance the attacks. Extensive experiments show that our method achieves remarkable attack performance across various VLP models and Vision-and-Language (V+L) tasks. Moreover, C-PGC exhibits outstanding black-box transferability and achieves impressive results in fooling prevalent large VLP models including LLaVA and Qwen-VL.
Authors: Jianzhao Wang, Yanyan Wei, Dehua Hu, Yilin Zhang, Shengeng Tang, Dan Guo, Zhao Zhang
Abstract: This technical report presents our team's solution for the WeatherProof Dataset Challenge: Semantic Segmentation in Adverse Weather at CVPR'24 UG2+. We propose a two-stage deep learning framework for this task. In the first stage, we preprocess the provided dataset by concatenating images into video sequences. Subsequently, we leverage a low-rank video deraining method to generate high-fidelity pseudo ground truths. These pseudo ground truths offer superior alignment compared to the original ground truths, facilitating model convergence during training. In the second stage, we employ the InternImage network to train for the semantic segmentation task using the generated pseudo ground truths. Notably, our meticulously designed framework demonstrates robustness to degraded data captured under adverse weather conditions. In the challenge, our solution achieved a competitive score of 0.43 on the Mean Intersection over Union (mIoU) metric, securing a respectable rank of 4th.
Authors: Shichong Peng, Yanshu Zhang, Ke Li
Abstract: We propose the problem of point-level 3D scene interpolation, which aims to simultaneously reconstruct a 3D scene in two states from multiple views, synthesize smooth point-level interpolations between them, and render the scene from novel viewpoints, all without any supervision between the states. The primary challenge is on achieving a smooth transition between states that may involve significant and non-rigid changes. To address these challenges, we introduce "PAPR in Motion", a novel approach that builds upon the recent Proximity Attention Point Rendering (PAPR) technique, which can deform a point cloud to match a significantly different shape and render a visually coherent scene even after non-rigid deformations. Our approach is specifically designed to maintain the temporal consistency of the geometric structure by introducing various regularization techniques for PAPR. The result is a method that can effectively bridge large scene changes and produce visually coherent and temporally smooth interpolations in both geometry and appearance. Evaluation across diverse motion types demonstrates that "PAPR in Motion" outperforms the leading neural renderer for dynamic scenes. For more results and code, please visit our project website at https://niopeng.github.io/PAPR-in-Motion/ .
Authors: Jianmeng Liu, Yichen Liu, Yuyao Zhang, Zeyuan Meng, Yu-Wing Tai, Chi-Keung Tang
Abstract: Recent conditional 3D completion works have mainly relied on CLIP or BERT to encode textual information, which cannot support complex instruction. Meanwhile, large language models (LLMs) have shown great potential in multi-modal understanding and generation tasks. Inspired by the recent advancements of LLM, we present Volume Patch LLM (VP-LLM), which leverages LLMs to perform conditional 3D completion in a single-forward pass. To integrate a 3D model into the LLM tokenization configuration, the incomplete 3D object is first divided into small patches that can be encoded independently. These encoded patches are then fed into an LLM along with the text prompt, instructing the LLM to capture the relations between these patches as well as injecting semantic meanings into the 3D object. Our results demonstrate a strong ability of LLMs to interpret complex text instructions and understand 3D objects, surpassing state-of-the-art diffusion-based 3D completion models in generation quality.
Authors: Sucheng Ren, Xiaoke Huang, Xianhang Li, Junfei Xiao, Jieru Mei, Zeyu Wang, Alan Yuille, Yuyin Zhou
Abstract: This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework. Specifically, MVG employs an in-context generation strategy that standardizes the handling of inputs and outputs as images. By treating these tasks as an image generation process conditioned on prompt image-label pairs and input images, this approach enables a flexible unification of various tasks, even those spanning different modalities and datasets. To capitalize on both local and global context, we design a hybrid method combining masked image modeling with autoregressive training for conditional image generation. This hybrid approach yields the most robust performance across all involved medical imaging tasks. To rigorously evaluate MVG's capabilities, we curated the first comprehensive generalist medical vision benchmark, comprising 13 datasets and spanning four imaging modalities (CT, MRI, X-ray, and micro-ultrasound). Our results consistently establish MVG's superior performance, outperforming existing vision generalists, such as Painter and LVM. Furthermore, MVG exhibits strong scalability, with its performance demonstrably improving when trained on a more diverse set of tasks, and can be effectively adapted to unseen datasets with only minimal task-specific samples. The code is available at \url{https://github.com/OliverRensu/MVG}.
Authors: Yunhe Gao, Difei Gu, Mu Zhou, Dimitris Metaxas
Abstract: Although explainability is essential in the clinical diagnosis, most deep learning models still function as black boxes without elucidating their decision-making process. In this study, we investigate the explainable model development that can mimic the decision-making process of human experts by fusing the domain knowledge of explicit diagnostic criteria. We introduce a simple yet effective framework, Explicd, towards Explainable language-informed criteria-based diagnosis. Explicd initiates its process by querying domain knowledge from either large language models (LLMs) or human experts to establish diagnostic criteria across various concept axes (e.g., color, shape, texture, or specific patterns of diseases). By leveraging a pretrained vision-language model, Explicd injects these criteria into the embedding space as knowledge anchors, thereby facilitating the learning of corresponding visual concepts within medical images. The final diagnostic outcome is determined based on the similarity scores between the encoded visual concepts and the textual criteria embeddings. Through extensive evaluation of five medical image classification benchmarks, Explicd has demonstrated its inherent explainability and extends to improve classification performance compared to traditional black-box models.
Authors: Chris Hamblin, Srijani Saha, Talia Konkle, George Alvarez
Abstract: We address the functional role of 'feature inhibition' in vision models; that is, what are the mechanisms by which a neural network ensures images do not express a given feature? We observe that standard interpretability tools in the literature are not immediately suited to the inhibitory case, given the asymmetry introduced by the ReLU activation function. Given this, we propose inhibition be understood through a study of 'maximally tense images' (MTIs), i.e. those images that excite and inhibit a given feature simultaneously. We show how MTIs can be studied with two novel visualization techniques; +/- attribution inversions, which split single images into excitatory and inhibitory components, and the attribution atlas, which provides a global visualization of the various ways images can excite/inhibit a feature. Finally, we explore the difficulties introduced by superposition, as such interfering features induce the same attribution motif as MTIs.
Authors: Philip Wootaek Shin, Jihyun Janice Ahn, Wenpeng Yin, Jack Sampson, Vijaykrishnan Narayanan
Abstract: It has been shown that many generative models inherit and amplify societal biases. To date, there is no uniform/systematic agreed standard to control/adjust for these biases. This study examines the presence and manipulation of societal biases in leading text-to-image models: Stable Diffusion, DALL-E 3, and Adobe Firefly. Through a comprehensive analysis combining base prompts with modifiers and their sequencing, we uncover the nuanced ways these AI technologies encode biases across gender, race, geography, and region/culture. Our findings reveal the challenges and potential of prompt engineering in controlling biases, highlighting the critical need for ethical AI development promoting diversity and inclusivity. This work advances AI ethics by not only revealing the nuanced dynamics of bias in text-to-image generation models but also by offering a novel framework for future research in controlling bias. Our contributions-panning comparative analyses, the strategic use of prompt modifiers, the exploration of prompt sequencing effects, and the introduction of a bias sensitivity taxonomy-lay the groundwork for the development of common metrics and standard analyses for evaluating whether and how future AI models exhibit and respond to requests to adjust for inherent biases.
Authors: Sayan Mandal
Abstract: Glaucoma is a chronic eye disease characterized by optic neuropathy, leading to irreversible vision loss. It progresses gradually, often remaining undiagnosed until advanced stages. Early detection is crucial to monitor atrophy and develop treatment strategies to prevent further vision impairment. Data-centric methods have enabled computer-aided algorithms for precise glaucoma diagnosis. In this study, we use deep learning models to identify complex disease traits and progression criteria, detecting subtle changes indicative of glaucoma. We explore the structure-function relationship in glaucoma progression and predict functional impairment from structural eye deterioration. We analyze statistical and machine learning methods, including deep learning techniques with optical coherence tomography (OCT) scans for accurate progression prediction. Addressing challenges like age variability, data imbalances, and noisy labels, we develop novel semi-supervised time-series algorithms: 1. Weakly-Supervised Time-Series Learning: We create a CNN-LSTM model to encode spatiotemporal features from OCT scans. This approach uses age-related progression and positive-unlabeled data to establish robust pseudo-progression criteria, bypassing gold-standard labels. 2. Semi-Supervised Time-Series Learning: Using labels from Guided Progression Analysis (GPA) in a contrastive learning scheme, the CNN-LSTM architecture learns from potentially mislabeled data to improve prediction accuracy. Our methods outperform conventional and state-of-the-art techniques.
Authors: Pranav Jeevan, Amit Sethi
Abstract: In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors. Despite the widespread use of these pre-trained convolutional neural networks (CNNs), there remains a gap in understanding the performance of various resource-efficient backbones across diverse domains and dataset sizes. Our study systematically evaluates multiple lightweight, pre-trained CNN backbones under consistent training settings across a variety of datasets, including natural images, medical images, galaxy images, and remote sensing images. This comprehensive analysis aims to aid machine learning practitioners in selecting the most suitable backbone for their specific problem, especially in scenarios involving small datasets where fine-tuning a pre-trained network is crucial. Even though attention-based architectures are gaining popularity, we observed that they tend to perform poorly under low data finetuning tasks compared to CNNs. We also observed that some CNN architectures such as ConvNeXt, RegNet and EfficientNet performs well compared to others on a diverse set of domains consistently. Our findings provide actionable insights into the performance trade-offs and effectiveness of different backbones, facilitating informed decision-making in model selection for a broad spectrum of computer vision domains. Our code is available here: https://github.com/pranavphoenix/Backbones
Authors: Yiwei Ma, Xiaoshuai Sun, Jiayi Ji, Guannan Jiang, Weilin Zhuang, Rongrong Ji
Abstract: Text-based person retrieval (TPR) is a challenging task that involves retrieving a specific individual based on a textual description. Despite considerable efforts to bridge the gap between vision and language, the significant differences between these modalities continue to pose a challenge. Previous methods have attempted to align text and image samples in a modal-shared space, but they face uncertainties in optimization directions due to the movable features of both modalities and the failure to account for one-to-many relationships of image-text pairs in TPR datasets. To address this issue, we propose an effective bi-directional one-to-many embedding paradigm that offers a clear optimization direction for each sample, thus mitigating the optimization problem. Additionally, this embedding scheme generates multiple features for each sample without introducing trainable parameters, making it easier to align with several positive samples. Based on this paradigm, we propose a novel Bi-directional one-to-many Embedding Alignment (Beat) model to address the TPR task. Our experimental results demonstrate that the proposed Beat model achieves state-of-the-art performance on three popular TPR datasets, including CUHK-PEDES (65.61 R@1), ICFG-PEDES (58.25 R@1), and RSTPReID (48.10 R@1). Furthermore, additional experiments on MS-COCO, CUB, and Flowers datasets further demonstrate the potential of Beat to be applied to other image-text retrieval tasks.
Authors: Mark Hamilton, Andrew Zisserman, John R. Hershey, William T. Freeman
Abstract: We present DenseAV, a novel dual encoder grounding architecture that learns high-resolution, semantically meaningful, and audio-visually aligned features solely through watching videos. We show that DenseAV can discover the ``meaning'' of words and the ``location'' of sounds without explicit localization supervision. Furthermore, it automatically discovers and distinguishes between these two types of associations without supervision. We show that DenseAV's localization abilities arise from a new multi-head feature aggregation operator that directly compares dense image and audio representations for contrastive learning. In contrast, many other systems that learn ``global'' audio and video representations cannot localize words and sound. Finally, we contribute two new datasets to improve the evaluation of AV representations through speech and sound prompted semantic segmentation. On these and other datasets we show DenseAV dramatically outperforms the prior art on speech and sound prompted semantic segmentation. DenseAV outperforms the previous state-of-the-art, ImageBind, on cross-modal retrieval using fewer than half of the parameters. Project Page: \href{https://aka.ms/denseav}{https://aka.ms/denseav}
Authors: Ge Ya Luo, Zhi Hao Luo, Anthony Gosselin, Alexia Jolicoeur-Martineau, Christopher Pal
Abstract: With recent advances in video prediction, controllable video generation has been attracting more attention. Generating high fidelity videos according to simple and flexible conditioning is of particular interest. To this end, we propose a controllable video generation model using pixel level renderings of 2D or 3D bounding boxes as conditioning. In addition, we also create a bounding box predictor that, given the initial and ending frames' bounding boxes, can predict up to 15 bounding boxes per frame for all the frames in a 25-frame clip. We perform experiments across 3 well-known AV video datasets: KITTI, Virtual-KITTI 2 and BDD100k.
Authors: Shangyu Chen, Zizheng Pan, Jianfei Cai, Dinh Phung
Abstract: Personalizing a large-scale pretrained Text-to-Image (T2I) diffusion model is challenging as it typically struggles to make an appropriate trade-off between its training data distribution and the target distribution, i.e., learning a novel concept with only a few target images to achieve personalization (aligning with the personalized target) while preserving text editability (aligning with diverse text prompts). In this paper, we propose PaRa, an effective and efficient Parameter Rank Reduction approach for T2I model personalization by explicitly controlling the rank of the diffusion model parameters to restrict its initial diverse generation space into a small and well-balanced target space. Our design is motivated by the fact that taming a T2I model toward a novel concept such as a specific art style implies a small generation space. To this end, by reducing the rank of model parameters during finetuning, we can effectively constrain the space of the denoising sampling trajectories towards the target. With comprehensive experiments, we show that PaRa achieves great advantages over existing finetuning approaches on single/multi-subject generation as well as single-image editing. Notably, compared to the prevailing fine-tuning technique LoRA, PaRa achieves better parameter efficiency (2x fewer learnable parameters) and much better target image alignment.
Authors: Jie Liu, Yao Wu, Xiaotong Luo, Zongze Wu
Abstract: In industrial scenarios, it is crucial not only to identify anomalous items but also to classify the type of anomaly. However, research on anomaly multi-classification remains largely unexplored. This paper proposes a novel and valuable research task called anomaly multi-classification. Given the challenges in applying few-shot learning to this task, due to limited training data and unique characteristics of anomaly images, we introduce a baseline model that combines RelationNet and PatchCore. We propose a data generation method that creates pseudo classes and a corresponding proxy task, aiming to bridge the gap in transferring few-shot learning to industrial scenarios. Furthermore, we utilize contrastive learning to improve the vanilla baseline, achieving much better performance than directly fine-tune a ResNet. Experiments conducted on MvTec AD and MvTec3D AD demonstrate that our approach shows superior performance in this novel task.
Authors: Peiye Zhuang, Songfang Han, Chaoyang Wang, Aliaksandr Siarohin, Jiaxu Zou, Michael Vasilkovsky, Vladislav Shakhrai, Sergey Korolev, Sergey Tulyakov, Hsin-Ying Lee
Abstract: We propose a novel approach for 3D mesh reconstruction from multi-view images. Our method takes inspiration from large reconstruction models like LRM that use a transformer-based triplane generator and a Neural Radiance Field (NeRF) model trained on multi-view images. However, in our method, we introduce several important modifications that allow us to significantly enhance 3D reconstruction quality. First of all, we examine the original LRM architecture and find several shortcomings. Subsequently, we introduce respective modifications to the LRM architecture, which lead to improved multi-view image representation and more computationally efficient training. Second, in order to improve geometry reconstruction and enable supervision at full image resolution, we extract meshes from the NeRF field in a differentiable manner and fine-tune the NeRF model through mesh rendering. These modifications allow us to achieve state-of-the-art performance on both 2D and 3D evaluation metrics, such as a PSNR of 28.67 on Google Scanned Objects (GSO) dataset. Despite these superior results, our feed-forward model still struggles to reconstruct complex textures, such as text and portraits on assets. To address this, we introduce a lightweight per-instance texture refinement procedure. This procedure fine-tunes the triplane representation and the NeRF color estimation model on the mesh surface using the input multi-view images in just 4 seconds. This refinement improves the PSNR to 29.79 and achieves faithful reconstruction of complex textures, such as text. Additionally, our approach enables various downstream applications, including text- or image-to-3D generation.
Authors: Yue Lu, Shizhou Zhang, De Cheng, Yinghui Xing, Nannan Wang, Peng Wang, Yanning Zhang
Abstract: Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features, so as to ensure no interference on tasks that have been learned to overcome catastrophic forgetting in CL. However, different from the orthogonal projection in the traditional CNN architecture, the prompt gradient orthogonal projection in the ViT architecture shows completely different and greater challenges, i.e., 1) the high-order and non-linear self-attention operation; 2) the drift of prompt distribution brought by the LayerNorm in the transformer block. Theoretically, we have finally deduced two consistency conditions to achieve the prompt gradient orthogonal projection, which provide a theoretical guarantee of eliminating interference on previously learned knowledge via the self-attention mechanism in visual prompt tuning. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient orthogonal projection. Extensive experimental results demonstrate the effectiveness of anti-forgetting on four class-incremental benchmarks with diverse pre-trained baseline models, and our approach achieves superior performances to state-of-the-art methods. Our code is available in the supplemental material.
Authors: Hongjia Chen, Xin Xu, Fangling Pu
Abstract: Change detection (CD) in remote sensing imagery is a crucial task with applications in environmental monitoring, urban development, and disaster management. CD involves utilizing bi-temporal images to identify changes over time. The bi-temporal spatial relationships between features at the same location at different times play a key role in this process. However, existing change detection networks often do not fully leverage these spatial relationships during bi-temporal feature extraction and fusion. In this work, we propose SRC-Net: a bi-temporal spatial relationship concerned network for CD. The proposed SRC-Net includes a Perception and Interaction Module that incorporates spatial relationships and establishes a cross-branch perception mechanism to enhance the precision and robustness of feature extraction. Additionally, a Patch-Mode joint Feature Fusion Module is introduced to address information loss in current methods. It considers different change modes and concerns about spatial relationships, resulting in more expressive fusion features. Furthermore, we construct a novel network using these two relationship concerned modules and conducted experiments on the LEVIR-CD and WHU Building datasets. The experimental results demonstrate that our network outperforms state-of-the-art (SOTA) methods while maintaining a modest parameter count. We believe our approach sets a new paradigm for change detection and will inspire further advancements in the field. The code and models are publicly available at https://github.com/Chnja/SRCNet.
Authors: Yuxin Hong, Xiao Zhang, Xin Zhang, Joey Tianyi Zhou
Abstract: In the medical field, managing high-dimensional massive medical imaging data and performing reliable medical analysis from it is a critical challenge, especially in resource-limited environments such as remote medical facilities and mobile devices. This necessitates effective dataset compression techniques to reduce storage, transmission, and computational cost. However, existing coreset selection methods are primarily designed for natural image datasets, and exhibit doubtful effectiveness when applied to medical image datasets due to challenges such as intra-class variation and inter-class similarity. In this paper, we propose a novel coreset selection strategy termed as Evolution-aware VAriance (EVA), which captures the evolutionary process of model training through a dual-window approach and reflects the fluctuation of sample importance more precisely through variance measurement. Extensive experiments on medical image datasets demonstrate the effectiveness of our strategy over previous SOTA methods, especially at high compression rates. EVA achieves 98.27% accuracy with only 10% training data, compared to 97.20% for the full training set. None of the compared baseline methods can exceed Random at 5% selection rate, while EVA outperforms Random by 5.61%, showcasing its potential for efficient medical image analysis.
Authors: Bowen Dang, Xi Zhao
Abstract: This paper presents a novel method for generating diverse 3D human poses in scenes with semantic control. Existing methods heavily rely on the human-scene interaction dataset, resulting in a limited diversity of the generated human poses. To overcome this challenge, we propose to decouple the pose and interaction generation process. Our approach consists of three stages: pose generation, contact generation, and putting human into the scene. We train a pose generator on the human dataset to learn rich pose prior, and a contact generator on the human-scene interaction dataset to learn human-scene contact prior. Finally, the placing module puts the human body into the scene in a suitable and natural manner. The experimental results on the PROX dataset demonstrate that our method produces more physically plausible interactions and exhibits more diverse human poses. Furthermore, experiments on the MP3D-R dataset further validates the generalization ability of our method.
Authors: Hang Fu, Genyun Sun, Yinhe Li, Jinchang Ren, Aizhu Zhang, Cheng Jing, Pedram Ghamisi
Abstract: Haze contamination in hyperspectral remote sensing images (HSI) can lead to spatial visibility degradation and spectral distortion. Haze in HSI exhibits spatial irregularity and inhomogeneous spectral distribution, with few dehazing networks available. Current CNN and Transformer-based dehazing methods fail to balance global scene recovery, local detail retention, and computational efficiency. Inspired by the ability of Mamba to model long-range dependencies with linear complexity, we explore its potential for HSI dehazing and propose the first HSI Dehazing Mamba (HDMba) network. Specifically, we design a novel window selective scan module (WSSM) that captures local dependencies within windows and global correlations between windows by partitioning them. This approach improves the ability of conventional Mamba in local feature extraction. By modeling the local and global spectral-spatial information flow, we achieve a comprehensive analysis of hazy regions. The DehazeMamba layer (DML), constructed by WSSM, and residual DehazeMamba (RDM) blocks, composed of DMLs, are the core components of the HDMba framework. These components effectively characterize the complex distribution of haze in HSIs, aiding in scene reconstruction and dehazing. Experimental results on the Gaofen-5 HSI dataset demonstrate that HDMba outperforms other state-of-the-art methods in dehazing performance. The code will be available at https://github.com/RsAI-lab/HDMba.
Authors: Xinhao Zhong, Hao Fang, Bin Chen, Xulin Gu, Tao Dai, Meikang Qiu, Shu-Tao Xia
Abstract: Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current methods have integrated parameterization techniques to boost synthetic dataset performance by shifting the optimization space from pixel to another informative feature domain. However, they limit themselves to a fixed optimization space for distillation, neglecting the diverse guidance across different informative latent spaces. To overcome this limitation, we propose a novel parameterization method dubbed Hierarchical Generative Latent Distillation (H-GLaD), to systematically explore hierarchical layers within the generative adversarial networks (GANs). This allows us to progressively span from the initial latent space to the final pixel space. In addition, we introduce a novel class-relevant feature distance metric to alleviate the computational burden associated with synthetic dataset evaluation, bridging the gap between synthetic and original datasets. Experimental results demonstrate that the proposed H-GLaD achieves a significant improvement in both same-architecture and cross-architecture performance with equivalent time consumption.
Authors: Sanjoy Kundu, Shubham Trehan, Sathyanarayanan N. Aakur
Abstract: Learning to infer labels in an open world, i.e., in an environment where the target "labels" are unknown, is an important characteristic for achieving autonomy. Foundation models pre-trained on enormous amounts of data have shown remarkable generalization skills through prompting, particularly in zero-shot inference. However, their performance is restricted to the correctness of the target label's search space. In an open world, this target search space can be unknown or exceptionally large, which severely restricts the performance of such models. To tackle this challenging problem, we propose a neuro-symbolic framework called ALGO - Action Learning with Grounded Object recognition that uses symbolic knowledge stored in large-scale knowledge bases to infer activities in egocentric videos with limited supervision using two steps. First, we propose a neuro-symbolic prompting approach that uses object-centric vision-language models as a noisy oracle to ground objects in the video through evidence-based reasoning. Second, driven by prior commonsense knowledge, we discover plausible activities through an energy-based symbolic pattern theory framework and learn to ground knowledge-based action (verb) concepts in the video. Extensive experiments on four publicly available datasets (EPIC-Kitchens, GTEA Gaze, GTEA Gaze Plus) demonstrate its performance on open-world activity inference.
Authors: Zheng Chen, Haotong Qin, Yong Guo, Xiongfei Su, Xin Yuan, Linghe Kong, Yulun Zhang
Abstract: Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating DMs. Nonetheless, due to the model structure and the multi-step iterative attribute of DMs, existing binarization methods result in significant performance degradation. In this paper, we introduce a novel binarized diffusion model, BI-DiffSR, for image SR. First, for the model structure, we design a UNet architecture optimized for binarization. We propose the consistent-pixel-downsample (CP-Down) and consistent-pixel-upsample (CP-Up) to maintain dimension consistent and facilitate the full-precision information transfer. Meanwhile, we design the channel-shuffle-fusion (CS-Fusion) to enhance feature fusion in skip connection. Second, for the activation difference across timestep, we design the timestep-aware redistribution (TaR) and activation function (TaA). The TaR and TaA dynamically adjust the distribution of activations based on different timesteps, improving the flexibility and representation alability of the binarized module. Comprehensive experiments demonstrate that our BI-DiffSR outperforms existing binarization methods. Code is available at https://github.com/zhengchen1999/BI-DiffSR.
Authors: Christoph Liebender, Ranulfo Bezerra, Kazunori Ohno, Satoshi Tadokoro
Abstract: The use of AI in public spaces continually raises concerns about privacy and the protection of sensitive data. An example is the deployment of detection and recognition methods on humans, where images are provided by surveillance cameras. This results in the acquisition of great amounts of sensitive data, since the capture and transmission of images taken by such cameras happens unaltered, for them to be received by a server on the network. However, many applications do not explicitly require the identity of a given person in a scene; An anonymized representation containing information of the person's position while preserving the context of them in the scene suffices. We show how using a customized loss function on region of interests (ROI) can achieve sufficient anonymization such that human faces become unrecognizable while persons are kept detectable, by training an end-to-end optimized autoencoder for learned image compression that utilizes the flexibility of the learned analysis and reconstruction transforms for the task of mutating parts of the compression result. This approach enables compression and anonymization in one step on the capture device, instead of transmitting sensitive, nonanonymized data over the network. Additionally, we evaluate how this anonymization impacts the average precision of pre-trained foundation models on detecting faces (MTCNN) and humans (YOLOv8) in comparison to non-ANN based methods, while considering compression rate and latency.
Authors: Hou-I Liu, Yu-Wen Tseng, Kai-Cheng Chang, Pin-Jyun Wang, Hong-Han Shuai, Wen-Huang Cheng
Abstract: Despite notable advancements in the field of computer vision, the precise detection of tiny objects continues to pose a significant challenge, largely owing to the minuscule pixel representation allocated to these objects in imagery data. This challenge resonates profoundly in the domain of geoscience and remote sensing, where high-fidelity detection of tiny objects can facilitate a myriad of applications ranging from urban planning to environmental monitoring. In this paper, we propose a new framework, namely, DeNoising FPN with Trans R-CNN (DNTR), to improve the performance of tiny object detection. DNTR consists of an easy plug-in design, DeNoising FPN (DN-FPN), and an effective Transformer-based detector, Trans R-CNN. Specifically, feature fusion in the feature pyramid network is important for detecting multiscale objects. However, noisy features may be produced during the fusion process since there is no regularization between the features of different scales. Therefore, we introduce a DN-FPN module that utilizes contrastive learning to suppress noise in each level's features in the top-down path of FPN. Second, based on the two-stage framework, we replace the obsolete R-CNN detector with a novel Trans R-CNN detector to focus on the representation of tiny objects with self-attention. Experimental results manifest that our DNTR outperforms the baselines by at least 17.4\% in terms of APvt on the AI-TOD dataset and 9.6\% in terms of AP on the VisDrone dataset, respectively. Our code will be available at this \href{this https URL}{https://github.com/hoiliu-0801/DNTR}.
Authors: Muthukumar K A, Amit Gurung, Priya Ranjan
Abstract: Classifying 3D MRI images for early detection of Alzheimer's disease is a critical task in medical imaging. Traditional approaches using Convolutional Neural Networks (CNNs) and Transformers face significant challenges in this domain. CNNs, while effective in capturing local spatial features, struggle with long-range dependencies and often require extensive computational resources for high-resolution 3D data. Transformers, on the other hand, excel in capturing global context but suffer from quadratic complexity in inference time and require substantial memory, making them less efficient for large-scale 3D MRI data. To address these limitations, we propose the use of Vision Mamba, an advanced model based on State Space Models (SSMs), for the classification of 3D MRI images to detect Alzheimer's disease. Vision Mamba leverages dynamic state representations and the selective scan algorithm, allowing it to efficiently capture and retain important spatial information across 3D volumes. By dynamically adjusting state transitions based on input features, Vision Mamba can selectively retain relevant information, leading to more accurate and computationally efficient processing of 3D MRI data. Our approach combines the parallelizable nature of convolutional operations during training with the efficient, recurrent processing of states during inference. This architecture not only improves computational efficiency but also enhances the model's ability to handle long-range dependencies within 3D medical images. Experimental results demonstrate that Vision Mamba outperforms traditional CNN and Transformer models accuracy, making it a promising tool for the early detection of Alzheimer's disease using 3D MRI data.
Authors: Qingsong Xie, Zhenyi Liao, Zhijie Deng, Chen chen, Shixiang Tang, Haonan Lu
Abstract: Distilling large latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face a dilemma where they either (i) depend on multiple individual distilled models for different sampling budgets, or (ii) sacrifice generation quality with limited (e.g., 2-4) and/or moderate (e.g., 5-8) sampling steps. To address these, we extend the recent multistep consistency distillation (MCD) strategy to representative LDMs, establishing the Multistep Latent Consistency Models (MLCMs) approach for low-cost high-quality image synthesis. MLCM serves as a unified model for various sampling steps due to the promise of MCD. We further augment MCD with a progressive training strategy to strengthen inter-segment consistency to boost the quality of few-step generations. We take the states from the sampling trajectories of the teacher model as training data for MLCMs to lift the requirements for high-quality training datasets and to bridge the gap between the training and inference of the distilled model. MLCM is compatible with preference learning strategies for further improvement of visual quality and aesthetic appeal. Empirically, MLCM can generate high-quality, delightful images with only 2-8 sampling steps. On the MSCOCO-2017 5K benchmark, MLCM distilled from SDXL gets a CLIP Score of 33.30, Aesthetic Score of 6.19, and Image Reward of 1.20 with only 4 steps, substantially surpassing 4-step LCM [23], 8-step SDXL-Lightning [17], and 8-step HyperSD [33]. We also demonstrate the versatility of MLCMs in applications including controllable generation, image style transfer, and Chinese-to-image generation.
Authors: Tangfei Liao, Xiaoqin Zhang, Guobao Xiao, Min Li, Tao Wang, Mang Ye
Abstract: Pre-training has emerged as a simple yet powerful methodology for representation learning across various domains. However, due to the expensive training cost and limited data, pre-training has not yet been extensively studied in correspondence pruning. To tackle these challenges, we propose a pre-training method to acquire a generic inliers-consistent representation by reconstructing masked correspondences, providing a strong initial representation for downstream tasks. Toward this objective, a modicum of true correspondences naturally serve as input, thus significantly reducing pre-training overhead. In practice, we introduce CorrMAE, an extension of the mask autoencoder framework tailored for the pre-training of correspondence pruning. CorrMAE involves two main phases, \ie correspondence learning and matching point reconstruction, guiding the reconstruction of masked correspondences through learning visible correspondence consistency. Herein, we employ a dual-branch structure with an ingenious positional encoding to reconstruct unordered and irregular correspondences. Also, a bi-level designed encoder is proposed for correspondence learning, which offers enhanced consistency learning capability and transferability. Extensive experiments have shown that the model pre-trained with our CorrMAE outperforms prior work on multiple challenging benchmarks. Meanwhile, our CorrMAE is primarily a task-driven pre-training method, and can achieve notable improvements for downstream tasks by pre-training on the targeted dataset. We hope this work can provide a starting point for correspondence pruning pre-training.
Authors: Hanlin Chen, Fangyin Wei, Chen Li, Tianxin Huang, Yunsong Wang, Gim Hee Lee
Abstract: Although 3D Gaussian Splatting has been widely studied because of its realistic and efficient novel-view synthesis, it is still challenging to extract a high-quality surface from the point-based representation. Previous works improve the surface by incorporating geometric priors from the off-the-shelf normal estimator. However, there are two main limitations: 1) Supervising normal rendered from 3D Gaussians updates only the rotation parameter while neglecting other geometric parameters; 2) The inconsistency of predicted normal maps across multiple views may lead to severe reconstruction artifacts. In this paper, we propose a Depth-Normal regularizer that directly couples normal with other geometric parameters, leading to full updates of the geometric parameters from normal regularization. We further propose a confidence term to mitigate inconsistencies of normal predictions across multiple views. Moreover, we also introduce a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling. Compared with Gaussian-based baselines, experiments show that our approach obtains better reconstruction quality and maintains competitive appearance quality at faster training speed and 100+ FPS rendering. Our code will be made open-source upon paper acceptance.
Authors: Matthias Pijarowski, Alexander Wolpert, Martin Heckmann, Michael Teutsch
Abstract: Visually detecting camouflaged objects is a hard problem for both humans and computer vision algorithms. Strong similarities between object and background appearance make the task significantly more challenging than traditional object detection or segmentation tasks. Current state-of-the-art models use either convolutional neural networks or vision transformers as feature extractors. They are trained in a fully supervised manner and thus need a large amount of labeled training data. In this paper, both self-supervised and frugal learning methods are introduced to the task of Camouflaged Object Detection (COD). The overall goal is to fine-tune two COD reference methods, namely SINet-V2 and HitNet, pre-trained for camouflaged animal detection to the task of camouflaged human detection. Therefore, we use the public dataset CPD1K that contains camouflaged humans in a forest environment. We create a strong baseline using supervised frugal transfer learning for the fine-tuning task. Then, we analyze three pseudo-labeling approaches to perform the fine-tuning task in a self-supervised manner. Our experiments show that we achieve similar performance by pure self-supervision compared to fully supervised frugal learning.
Authors: Changsong Liu, Wei Zhang, Yanyan Liu, Yuming Li, Wenlin Li, Yimeng Fan, Liang Zhang
Abstract: Edge detection is a fundamental task in computer vision and it has made great progress under the development of deep convolutional neural networks (DCNNs), some of them have achieved a beyond human-level performance. However, recent top-performing edge detection methods tend to generate thick and blurred edge lines. In this work, we propose an effective method to solve this problem. Our approach consists of a lightweight pre-trained backbone, multi-scale contextual enhancement module aggregating gradient information (MCGI), boundary correction module (BCM), and boundary refinement module (BRM). In addition to this, we construct a novel hybrid loss function based on the Tversky index for solving the issue of imbalanced pixel distribution. We test our method on three standard benchmarks and the experiment results illustrate that our method improves the visual effect of edge maps and achieves a top performance among several state-of-the-art methods on the BSDS500 dataset (ODS F-score in standard evaluation is 0.829, in crispness evaluation is 0.720), NYUD-V2 dataset (ODS F-score in standard evaluation is 0.768, in crispness evaluation is \textbf{0.546}), and BIPED dataset (ODS F-score in standard evaluation is 0.903).
Authors: Daizong Liu, Yang Liu, Wencan Huang, Wei Hu
Abstract: Text-guided 3D visual grounding (T-3DVG), which aims to locate a specific object that semantically corresponds to a language query from a complicated 3D scene, has drawn increasing attention in the 3D research community over the past few years. Compared to 2D visual grounding, this task presents great potential and challenges due to its closer proximity to the real world and the complexity of data collection and 3D point cloud source processing. In this survey, we attempt to provide a comprehensive overview of the T-3DVG progress, including its fundamental elements, recent research advances, and future research directions. To the best of our knowledge, this is the first systematic survey on the T-3DVG task. Specifically, we first provide a general structure of the T-3DVG pipeline with detailed components in a tutorial style, presenting a complete background overview. Then, we summarize the existing T-3DVG approaches into different categories and analyze their strengths and weaknesses. We also present the benchmark datasets and evaluation metrics to assess their performances. Finally, we discuss the potential limitations of existing T-3DVG and share some insights on several promising research directions. The latest papers are continually collected at https://github.com/liudaizong/Awesome-3D-Visual-Grounding.
URLs: https://github.com/liudaizong/Awesome-3D-Visual-Grounding.
Authors: Abbas Khan, Muhammad Asad, Martin Benning, Caroline Roney, Gregory Slabaugh
Abstract: Convolutional Neural Networks (CNNs) and Transformer-based self-attention models have become standard for medical image segmentation. This paper demonstrates that convolution and self-attention, while widely used, are not the only effective methods for segmentation. Breaking with convention, we present a Convolution and self-Attention Free Mamba-based semantic Segmentation Network named CAF-MambaSegNet. Specifically, we design a Mamba-based Channel Aggregator and Spatial Aggregator, which are applied independently in each encoder-decoder stage. The Channel Aggregator extracts information across different channels, and the Spatial Aggregator learns features across different spatial locations. We also propose a Linearly Interconnected Factorized Mamba (LIFM) Block to reduce the computational complexity of a Mamba and to enhance its decision function by introducing a non-linearity between two factorized Mamba blocks. Our goal is not to outperform state-of-the-art results but to show how this innovative, convolution and self-attention-free method can inspire further research beyond well-established CNNs and Transformers, achieving linear complexity and reducing the number of parameters. Source code and pre-trained models will be publicly available.
Authors: Shengjian Wu, Li Sun, Qingli Li
Abstract: DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge compared with CNN-based detectors. This paper aims to stabilize DETR training through the online distillation. It utilizes a teacher model, accumulated by Exponential Moving Average (EMA), and distills its knowledge into the online model in following three aspects. First, the matching relation between object queries and ground truth (GT) boxes in the teacher is employed to guide the student, so queries within the student are not only assigned labels based on their own predictions, but also refer to the matching results from the teacher. Second, the teacher's initial query is given to the online student, and its prediction is directly constrained by the corresponding output from the teacher. Finally, the object queries from teacher's different decoding stages are used to build the auxiliary groups to accelerate the convergence. For each GT, two queries with the least matching costs are selected into this extra group, and they predict the GT box and participate the optimization. Extensive experiments show that the proposed OD-DETR successfully stabilizes the training, and significantly increases the performance without bringing in more parameters.
Authors: Chen Ma, Ningfei Wang, Zhengyu Zhao, Qi Alfred Chen, Chao Shen
Abstract: Autonomous Driving (AD) systems critically depend on visual perception for real-time object detection and multiple object tracking (MOT) to ensure safe driving. However, high latency in these visual perception components can lead to significant safety risks, such as vehicle collisions. While previous research has extensively explored latency attacks within the digital realm, translating these methods effectively to the physical world presents challenges. For instance, existing attacks rely on perturbations that are unrealistic or impractical for AD, such as adversarial perturbations affecting areas like the sky, or requiring large patches that obscure most of a camera's view, thus making them impossible to be conducted effectively in the real world. In this paper, we introduce SlowPerception, the first physical-world latency attack against AD perception, via generating projector-based universal perturbations. SlowPerception strategically creates numerous phantom objects on various surfaces in the environment, significantly increasing the computational load of Non-Maximum Suppression (NMS) and MOT, thereby inducing substantial latency. Our SlowPerception achieves second-level latency in physical-world settings, with an average latency of 2.5 seconds across different AD perception systems, scenarios, and hardware configurations. This performance significantly outperforms existing state-of-the-art latency attacks. Additionally, we conduct AD system-level impact assessments, such as vehicle collisions, using industry-grade AD systems with production-grade AD simulators with a 97% average rate. We hope that our analyses can inspire further research in this critical domain, enhancing the robustness of AD systems against emerging vulnerabilities.
Authors: Muhammad Nawfal Meeran, Gokul Adethya T, Bhanu Pratyush Mantha
Abstract: In the domain of large foundation models, the Segment Anything Model (SAM) has gained notable recognition for its exceptional performance in image segmentation. However, tackling the video camouflage object detection (VCOD) task presents a unique challenge. Camouflaged objects typically blend into the background, making them difficult to distinguish in still images. Additionally, ensuring temporal consistency in this context is a challenging problem. As a result, SAM encounters limitations and falls short when applied to the VCOD task. To overcome these challenges, we propose a new method called the SAM Propagation Module (SAM-PM). Our propagation module enforces temporal consistency within SAM by employing spatio-temporal cross-attention mechanisms. Moreover, we exclusively train the propagation module while keeping the SAM network weights frozen, allowing us to integrate task-specific insights with the vast knowledge accumulated by the large model. Our method effectively incorporates temporal consistency and domain-specific expertise into the segmentation network with an addition of less than 1% of SAM's parameters. Extensive experimentation reveals a substantial performance improvement in the VCOD benchmark when compared to the most recent state-of-the-art techniques. Code and pre-trained weights are open-sourced at https://github.com/SpiderNitt/SAM-PM
Authors: Chen Ma, Ningfei Wang, Zhengyu Zhao, Qian Wang, Qi Alfred Chen, Chao Shen
Abstract: Recent research in adversarial machine learning has focused on visual perception in Autonomous Driving (AD) and has shown that printed adversarial patches can attack object detectors. However, it is important to note that AD visual perception encompasses more than just object detection; it also includes Multiple Object Tracking (MOT). MOT enhances the robustness by compensating for object detection errors and requiring consistent object detection results across multiple frames before influencing tracking results and driving decisions. Thus, MOT makes attacks on object detection alone less effective. To attack such robust AD visual perception, a digital hijacking attack has been proposed to cause dangerous driving scenarios. However, this attack has limited effectiveness. In this paper, we introduce a novel physical-world adversarial patch attack, ControlLoc, designed to exploit hijacking vulnerabilities in entire AD visual perception. ControlLoc utilizes a two-stage process: initially identifying the optimal location for the adversarial patch, and subsequently generating the patch that can modify the perceived location and shape of objects with the optimal location. Extensive evaluations demonstrate the superior performance of ControlLoc, achieving an impressive average attack success rate of around 98.1% across various AD visual perceptions and datasets, which is four times greater effectiveness than the existing hijacking attack. The effectiveness of ControlLoc is further validated in physical-world conditions, including real vehicle tests under different conditions such as outdoor light conditions with an average attack success rate of 77.5%. AD system-level impact assessments are also included, such as vehicle collision, using industry-grade AD systems and production-grade AD simulators with an average vehicle collision rate and unnecessary emergency stop rate of 81.3%.
Authors: Leigang Qu, Haochuan Li, Tan Wang, Wenjie Wang, Yongqi Li, Liqiang Nie, Tat-Seng Chua
Abstract: How humans can efficiently and effectively acquire images has always been a perennial question. A typical solution is text-to-image retrieval from an existing database given the text query; however, the limited database typically lacks creativity. By contrast, recent breakthroughs in text-to-image generation have made it possible to produce fancy and diverse visual content, but it faces challenges in synthesizing knowledge-intensive images. In this work, we rethink the relationship between text-to-image generation and retrieval and propose a unified framework in the context of Multimodal Large Language Models (MLLMs). Specifically, we first explore the intrinsic discriminative abilities of MLLMs and introduce a generative retrieval method to perform retrieval in a training-free manner. Subsequently, we unify generation and retrieval in an autoregressive generation way and propose an autonomous decision module to choose the best-matched one between generated and retrieved images as the response to the text query. Additionally, we construct a benchmark called TIGeR-Bench, including creative and knowledge-intensive domains, to standardize the evaluation of unified text-to-image generation and retrieval. Extensive experimental results on TIGeR-Bench and two retrieval benchmarks, i.e., Flickr30K and MS-COCO, demonstrate the superiority and effectiveness of our proposed method.
Authors: Size Wu, Sheng Jin, Wenwei Zhang, Lumin Xu, Wentao Liu, Wei Li, Chen Change Loy
Abstract: Endowing Large Multimodal Models (LMMs) with visual grounding capability can significantly enhance AIs' understanding of the visual world and their interaction with humans. However, existing methods typically fine-tune the parameters of LMMs to learn additional segmentation tokens and overfit grounding and segmentation datasets. Such a design would inevitably cause a catastrophic diminution in the indispensable conversational capability of general AI assistants. In this paper, we comprehensively evaluate state-of-the-art grounding LMMs across a suite of multimodal question-answering benchmarks, observing pronounced performance drops that indicate vanishing general knowledge comprehension and weakened instruction following ability. To address this issue, we present F-LMM -- grounding frozen off-the-shelf LMMs in human-AI conversations -- a straightforward yet effective design based on the fact that word-pixel correspondences conducive to visual grounding inherently exist in the attention weights of well-trained LMMs. Using only a few trainable CNN layers, we can translate word-pixel attention weights to mask logits, which a SAM-based mask refiner can further optimise. Our F-LMM neither learns special segmentation tokens nor utilises high-quality grounded instruction-tuning data, but achieves competitive performance on referring expression segmentation and panoptic narrative grounding benchmarks while completely preserving LMMs' original conversational ability. Additionally, with instruction-following ability preserved and grounding ability obtained, our F-LMM can perform visual chain-of-thought reasoning and better resist object hallucinations.
Authors: Akash Modi, Sumit Kumar Jha, Purnendu Mishra, Rajiv Kumar, Kiran Aatre, Gursewak Singh, Shubham Mathur
Abstract: Digital pathology and microscopy image analysis are widely employed in the segmentation of digitally scanned IHC slides, primarily to identify cancer and pinpoint regions of interest (ROI) indicative of tumor presence. However, current ROI segmentation models are either stain-specific or suffer from the issues of stain and scanner variance due to different staining protocols or modalities across multiple labs. Also, tissues like Ductal Carcinoma in Situ (DCIS), acini, etc. are often classified as Tumors due to their structural similarities and color compositions. In this paper, we proposed a novel convolutional neural network (CNN) based Multi-class Tissue Segmentation model for histopathology whole-slide Breast slides which classify tumors and segments other tissue regions such as Ducts, acini, DCIS, Squamous epithelium, Blood Vessels, Necrosis, etc. as a separate class. Our unique pixel-aligned non-linear merge across spatial resolutions empowers models with both local and global fields of view for accurate detection of various classes. Our proposed model is also able to separate bad regions such as folds, artifacts, blurry regions, bubbles, etc. from tissue regions using multi-level context from different resolutions of WSI. Multi-phase iterative training with context-aware augmentation and increasing noise was used to efficiently train a multi-stain generic model with partial and noisy annotations from 513 slides. Our training pipeline used 12 million patches generated using context-aware augmentations which made our model stain and scanner invariant across data sources. To extrapolate stain and scanner invariance, our model was evaluated on 23000 patches which were for a completely new stain (Hematoxylin and Eosin) from a completely new scanner (Motic) from a different lab. The mean IOU was 0.72 which is on par with model performance on other data sources and scanners.
Authors: Ricard Durall, Laura Montilla, Esteban Durall
Abstract: Accurate and efficient label of aerial images is essential for informed decision-making and resource allocation, whether in identifying crop types or delineating land-use patterns. The development of a comprehensive toolbox for manipulating and annotating aerial imagery represents a significant leap forward in remote sensing and spatial analysis. In this report, we introduce BOSC, a toolbox that enables researchers and practitioners to extract actionable insights with unprecedented accuracy and efficiency, addressing a critical need in today's abundance of drone and satellite resources. For more information or to explore BOSC, please visit our repository.
Authors: Zeyu Wang, Chen Li, Huiying Xu, Xinzhong Zhu
Abstract: Propelled by the rapid advancement of deep learning technologies, the YOLO series has set a new benchmark for real-time object detectors. Researchers have continuously explored innovative applications of reparameterization, efficient layer aggregation networks, and anchor-free techniques on the foundation of YOLO. To further enhance detection performance, Transformer-based structures have been introduced, significantly expanding the model's receptive field and achieving notable performance gains. However, such improvements come at a cost, as the quadratic complexity of the self-attention mechanism increases the computational burden of the model. Fortunately, the emergence of State Space Models (SSM) as an innovative technology has effectively mitigated the issues caused by quadratic complexity. In light of these advancements, we introduce Mamba-YOLO a novel object detection model based on SSM. Mamba-YOLO not only optimizes the SSM foundation but also adapts specifically for object detection tasks. Given the potential limitations of SSM in sequence modeling, such as insufficient receptive field and weak image locality, we have designed the LSBlock and RGBlock. These modules enable more precise capture of local image dependencies and significantly enhance the robustness of the model. Extensive experimental results on the publicly available benchmark datasets COCO and VOC demonstrate that Mamba-YOLO surpasses the existing YOLO series models in both performance and competitiveness, showcasing its substantial potential and competitive edge.The PyTorch code is available at:\url{https://github.com/HZAI-ZJNU/Mamba-YOLO}
Authors: Jun Yu, Yunxiang Zhang, Fengzhao Sun, Leilei Wang, Renjie Lu
Abstract: In this report, we present our solution for the semantic segmentation in adverse weather, in UG2+ Challenge at CVPR 2024. To achieve robust and accurate segmentation results across various weather conditions, we initialize the InternImage-H backbone with pre-trained weights from the large-scale joint dataset and enhance it with the state-of-the-art Upernet segmentation method. Specifically, we utilize offline and online data augmentation approaches to extend the train set, which helps us to further improve the performance of the segmenter. As a result, our proposed solution demonstrates advanced performance on the test set and achieves 3rd position in this challenge.
Authors: William Avery, Mustafa Munir, Radu Marculescu
Abstract: To compete with existing mobile architectures, MobileViG introduces Sparse Vision Graph Attention (SVGA), a fast token-mixing operator based on the principles of GNNs. However, MobileViG scales poorly with model size, falling at most 1% behind models with similar latency. This paper introduces Mobile Graph Convolution (MGC), a new vision graph neural network (ViG) module that solves this scaling problem. Our proposed mobile vision architecture, MobileViGv2, uses MGC to demonstrate the effectiveness of our approach. MGC improves on SVGA by increasing graph sparsity and introducing conditional positional encodings to the graph operation. Our smallest model, MobileViGv2-Ti, achieves a 77.7% top-1 accuracy on ImageNet-1K, 2% higher than MobileViG-Ti, with 0.9 ms inference latency on the iPhone 13 Mini NPU. Our largest model, MobileViGv2-B, achieves an 83.4% top-1 accuracy, 0.8% higher than MobileViG-B, with 2.7 ms inference latency. Besides image classification, we show that MobileViGv2 generalizes well to other tasks. For object detection and instance segmentation on MS COCO 2017, MobileViGv2-M outperforms MobileViG-M by 1.2 $AP^{box}$ and 0.7 $AP^{mask}$, and MobileViGv2-B outperforms MobileViG-B by 1.0 $AP^{box}$ and 0.7 $AP^{mask}$. For semantic segmentation on ADE20K, MobileViGv2-M achieves 42.9% $mIoU$ and MobileViGv2-B achieves 44.3% $mIoU$. Our code can be found at \url{https://github.com/SLDGroup/MobileViGv2}.
Authors: Rui Zhang, Tianyue Luo, Weidong Yang, Ben Fei, Jingyi Xu, Qingyuan Zhou, Keyi Liu, Ying He
Abstract: 3D Gaussian Splatting (3D-GS) has made a notable advancement in the field of neural rendering, 3D scene reconstruction, and novel view synthesis. Nevertheless, 3D-GS encounters the main challenge when it comes to accurately representing physical reflections, especially in the case of total reflection and semi-reflection that are commonly found in real-world scenes. This limitation causes reflections to be mistakenly treated as independent elements with physical presence, leading to imprecise reconstructions. Herein, to tackle this challenge, we propose RefGaussian to disentangle reflections from 3D-GS for realistically modeling reflections. Specifically, we propose to split a scene into transmitted and reflected components and represent these components using two Spherical Harmonics (SH). Given that this decomposition is not fully determined, we employ local regularization techniques to ensure local smoothness for both the transmitted and reflected components, thereby achieving more plausible decomposition outcomes than 3D-GS. Experimental results demonstrate that our approach achieves superior novel view synthesis and accurate depth estimation outcomes. Furthermore, it enables the utilization of scene editing applications, ensuring both high-quality results and physical coherence.
Authors: Zhiyuan Cheng, Cheng Han, James Liang, Qifan Wang, Xiangyu Zhang, Dongfang Liu
Abstract: Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE models, leveraging view synthesis without the need for ground-truth depth. We enhance adversarial robustness against real-world attacks by incorporating L_0-norm-bounded perturbation during training. We evaluate our method against supervised learning-based and contrastive learning-based approaches specifically designed for MDE. Our experiments with two representative MDE networks demonstrate improved robustness against various adversarial attacks, with minimal impact on benign performance.
Authors: Vincenzo Liguori
Abstract: This paper discusses a simple and effective method for the summation of long sequences of floating point numbers. The method comprises two phases: an accumulation phase where the mantissas of the floating point numbers are added to accumulators indexed by the exponents and a reconstruction phase where the actual summation result is finalised. Various architectural details are given for both FPGAs and ASICs including fusing the operation with a multiplier, creating efficient MACs. Some results are presented for FPGAs, including a tensor core capable of multiplying and accumulating two 4x4 matrices of bfloat16 values every clock cycle using ~6,400 LUTs + 64 DSP48 in AMD FPGAs at 700+ MHz. The method is then extended to posits and logarithmic numbers.
Authors: Yilin Wang, Haiyang Xu, Xiang Zhang, Zeyuan Chen, Zhizhou Sha, Zirui Wang, Zhuowen Tu
Abstract: We provide a two-way integration for the widely adopted ControlNet by integrating external condition generation algorithms into a single dense prediction method and incorporating its individually trained image generation processes into a single model. Despite its tremendous success, the ControlNet of a two-stage pipeline bears limitations in being not self-contained (e.g. calls the external condition generation algorithms) with a large model redundancy (separately trained models for different types of conditioning inputs). Our proposed OmniControlNet consolidates 1) the condition generation (e.g., HED edges, depth maps, user scribble, and animal pose) by a single multi-tasking dense prediction algorithm under the task embedding guidance and 2) the image generation process for different conditioning types under the textual embedding guidance. OmniControlNet achieves significantly reduced model complexity and redundancy while capable of producing images of comparable quality for conditioned text-to-image generation.
Authors: Yunchao Zhang, Guandao Yang, Leonidas Guibas, Yanchao Yang
Abstract: 3D Gaussians, as a low-level scene representation, typically involve thousands to millions of Gaussians. This makes it difficult to control the scene in ways that reflect the underlying dynamic structure, where the number of independent entities is typically much smaller. In particular, it can be challenging to animate and move objects in the scene, which requires coordination among many Gaussians. To address this issue, we develop a mutual information shaping technique that enforces movement resonance between correlated Gaussians in a motion network. Such correlations can be learned from putative 2D object masks in different views. By approximating the mutual information with the Jacobians of the motions, our method ensures consistent movements of the Gaussians composing different objects under various perturbations. In particular, we develop an efficient contrastive training pipeline with lightweight optimization to shape the motion network, avoiding the need for re-shaping throughout the motion sequence. Notably, our training only touches a small fraction of all Gaussians in the scene yet attains the desired compositional behavior according to the underlying dynamic structure. The proposed technique is evaluated on challenging scenes and demonstrates significant performance improvement in promoting consistent movements and 3D object segmentation while inducing low computation and memory requirements.
Authors: Ovi Paul, Abu Bakar Siddik Nayem, Anis Sarker, Amin Ahsan Ali, M Ashraful Amin, AKM Mahbubur Rahman
Abstract: Land Use Land Cover (LULC) analysis on satellite images using deep learning-based methods is significantly helpful in understanding the geography, socio-economic conditions, poverty levels, and urban sprawl in developing countries. Recent works involve segmentation with LULC classes such as farmland, built-up areas, forests, meadows, water bodies, etc. Training deep learning methods on satellite images requires large sets of images annotated with LULC classes. However, annotated data for developing countries are scarce due to a lack of funding, absence of dedicated residential/industrial/economic zones, a large population, and diverse building materials. BD-SAT provides a high-resolution dataset that includes pixel-by-pixel LULC annotations for Dhaka metropolitan city and surrounding rural/urban areas. Using a strict and standardized procedure, the ground truth is created using Bing satellite imagery with a ground spatial distance of 2.22 meters per pixel. A three-stage, well-defined annotation process has been followed with support from GIS experts to ensure the reliability of the annotations. We performed several experiments to establish benchmark results. The results show that the annotated BD-SAT is sufficient to train large deep learning models with adequate accuracy for five major LULC classes: forest, farmland, built-up areas, water bodies, and meadows.
Authors: Yueyu Hu, Ran Gong, Yao Wang
Abstract: Point cloud is a promising 3D representation for volumetric streaming in emerging AR/VR applications. Despite recent advances in point cloud compression, decoding and rendering high-quality images from lossy compressed point clouds is still challenging in terms of quality and complexity, making it a major roadblock to achieve real-time 6-Degree-of-Freedom video streaming. In this paper, we address this problem by developing a point cloud compression scheme that generates a bit stream that can be directly decoded to renderable 3D Gaussians. The encoder and decoder are jointly optimized to consider both bit-rates and rendering quality. It significantly improves the rendering quality while substantially reducing decoding and rendering time, compared to existing point cloud compression methods. Furthermore, the proposed scheme generates a scalable bit stream, allowing multiple levels of details at different bit-rate ranges. Our method supports real-time color decoding and rendering of high quality point clouds, thus paving the way for interactive 3D streaming applications with free view points.
Authors: Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma, Amir Houmansadr
Abstract: We present a simple yet effective method to improve the robustness of Convolutional Neural Networks (CNNs) against adversarial examples by post-processing an adversarially trained model. Our technique, MeanSparse, cascades the activation functions of a trained model with novel operators that sparsify mean-centered feature vectors. This is equivalent to reducing feature variations around the mean, and we show that such reduced variations merely affect the model's utility, yet they strongly attenuate the adversarial perturbations and decrease the attacker's success rate. Our experiments show that, when applied to the top models in the RobustBench leaderboard, it achieves a new robustness record of 72.08% (from 71.07%) and 59.64% (from 59.56%) on CIFAR-10 and ImageNet, respectively, in term of AutoAttack accuracy. Code is available at https://github.com/SPIN-UMass/MeanSparse
Authors: Jinwoo Ahn, Junhyeok Park, Min-Jun Kim, Kang-Hyeon Kim, So-Yeong Sohn, Yun-Ji Lee, Du-Seong Chang, Yu-Jung Heo, Eun-Sol Kim
Abstract: In this paper, the solution of HYU MLLAB KT Team to the Multimodal Algorithmic Reasoning Task: SMART-101 CVPR 2024 Challenge is presented. Beyond conventional visual question-answering problems, the SMART-101 challenge aims to achieve human-level multimodal understanding by tackling complex visio-linguistic puzzles designed for children in the 6-8 age group. To solve this problem, we suggest two main ideas. First, to utilize the reasoning ability of a large-scale language model (LLM), the given visual cues (images) are grounded in the text modality. For this purpose, we generate highly detailed text captions that describe the context of the image and use these captions as input for the LLM. Second, due to the nature of puzzle images, which often contain various geometric visual patterns, we utilize an object detection algorithm to ensure these patterns are not overlooked in the captioning process. We employed the SAM algorithm, which can detect various-size objects, to capture the visual features of these geometric patterns and used this information as input for the LLM. Under the puzzle split configuration, we achieved an option selection accuracy Oacc of 29.5 on the test set and a weighted option selection accuracy (WOSA) of 27.1 on the challenge set.
Authors: David Romero, Chenyang Lyu, Haryo Akbarianto Wibowo, Teresa Lynn, Injy Hamed, Aditya Nanda Kishore, Aishik Mandal, Alina Dragonetti, Artem Abzaliev, Atnafu Lambebo Tonja, Bontu Fufa Balcha, Chenxi Whitehouse, Christian Salamea, Dan John Velasco, David Ifeoluwa Adelani, David Le Meur, Emilio Villa-Cueva, Fajri Koto, Fauzan Farooqui, Frederico Belcavello, Ganzorig Batnasan, Gisela Vallejo, Grainne Caulfield, Guido Ivetta, Haiyue Song, Henok Biadglign Ademtew, Hern\'an Maina, Holy Lovenia, Israel Abebe Azime, Jan Christian Blaise Cruz, Jay Gala, Jiahui Geng, Jesus-German Ortiz-Barajas, Jinheon Baek, Jocelyn Dunstan, Laura Alonso Alemany, Kumaranage Ravindu Yasas Nagasinghe, Luciana Benotti, Luis Fernando D'Haro, Marcelo Viridiano, Marcos Estecha-Garitagoitia, Maria Camila Buitrago Cabrera, Mario Rodr\'iguez-Cantelar, M\'elanie Jouitteau, Mihail Mihaylov, Mohamed Fazli Mohamed Imam, Muhammad Farid Adilazuarda, Munkhjargal Gochoo, Munkh-Erdene Otgonbold, Naome Etori, Olivier Niyomugisha, Paula M\'onica Silva, Pranjal Chitale, Raj Dabre, Rendi Chevi, Ruochen Zhang, Ryandito Diandaru, Samuel Cahyawijaya, Santiago G\'ongora, Soyeong Jeong, Sukannya Purkayastha, Tatsuki Kuribayashi, Thanmay Jayakumar, Tiago Timponi Torrent, Toqeer Ehsan, Vladimir Araujo, Yova Kementchedjhieva, Zara Burzo, Zheng Wei Lim, Zheng Xin Yong, Oana Ignat, Joan Nwatu, Rada Mihalcea, Thamar Solorio, Alham Fikri Aji
Abstract: Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 28 countries on four continents, covering 26 languages with 11 scripts, providing a total of 9k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field.
Authors: Jian Xu, Chaojie Ji, Yankai Cao, Ye Li, Ruxin Wang
Abstract: Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains. Under the domain-hungry configuration, how to expand the coverage of source domain and find intrinsic causal features across different distributions is the key to enhancing the models' generalization ability. Existing methods mainly depend on the meticulous design of finite image-level transformation techniques and learning invariant features across domains based on statistical correlation between samples and labels in source domain. This makes it difficult to capture stable semantics between source and target domains, which hinders the improvement of the model's generalization performance. In this paper, we propose a novel causality-inspired latent feature augmentation method for Single-DG by learning the meta-knowledge of feature-level transformation based on causal learning and interventions. Instead of strongly relying on the finite image-level transformation, with the learned meta-knowledge, we can generate diverse implicit feature-level transformations in latent space based on the consistency of causal features and diversity of non-causal features, which can better compensate for the domain-hungry defect and reduce the strong reliance on initial finite image-level transformations and capture more stable domain-invariant causal features for generalization. Extensive experiments on several open-access benchmarks demonstrate the outstanding performance of our model over other state-of-the-art single domain generalization and also multi-source domain generalization methods.
Authors: Yebin Lee, Imseong Park, Myungjoo Kang
Abstract: Most existing image captioning evaluation metrics focus on assigning a single numerical score to a caption by comparing it with reference captions. However, these methods do not provide an explanation for the assigned score. Moreover, reference captions are expensive to acquire. In this paper, we propose FLEUR, an explainable reference-free metric to introduce explainability into image captioning evaluation metrics. By leveraging a large multimodal model, FLEUR can evaluate the caption against the image without the need for reference captions, and provide the explanation for the assigned score. We introduce score smoothing to align as closely as possible with human judgment and to be robust to user-defined grading criteria. FLEUR achieves high correlations with human judgment across various image captioning evaluation benchmarks and reaches state-of-the-art results on Flickr8k-CF, COMPOSITE, and Pascal-50S within the domain of reference-free evaluation metrics. Our source code and results are publicly available at: https://github.com/Yebin46/FLEUR.
Authors: Xian Sun, Qiwei Yan, Chubo Deng, Chenglong Liu, Yi Jiang, Zhongyan Hou, Wanxuan Lu, Fanglong Yao, Xiaoyu Liu, Lingxiang Hao, Hongfeng Yu
Abstract: Scene Graph Generation (SGG) is a high-level visual understanding and reasoning task aimed at extracting entities (such as objects) and their interrelationships from images. Significant progress has been made in the study of SGG in natural images in recent years, but its exploration in the domain of remote sensing images remains very limited. The complex characteristics of remote sensing images necessitate higher time and manual interpretation costs for annotation compared to natural images. The lack of a large-scale public SGG benchmark is a major impediment to the advancement of SGG-related research in aerial imagery. In this paper, we introduce the first publicly available large-scale, million-level relation dataset in the field of remote sensing images which is named as ReCon1M. Specifically, our dataset is built upon Fair1M and comprises 21,392 images. It includes annotations for 859,751 object bounding boxes across 60 different categories, and 1,149,342 relation triplets across 64 categories based on these bounding boxes. We provide a detailed description of the dataset's characteristics and statistical information. We conducted two object detection tasks and three sub-tasks within SGG on this dataset, assessing the performance of mainstream methods on these tasks.
Authors: Shijie Lian, Ziyi Zhang, Hua Li, Wenjie Li, Laurence Tianruo Yang, Sam Kwong, Runmin Cong
Abstract: With the breakthrough of large models, Segment Anything Model (SAM) and its extensions have been attempted to apply in diverse tasks of computer vision. Underwater salient instance segmentation is a foundational and vital step for various underwater vision tasks, which often suffer from low segmentation accuracy due to the complex underwater circumstances and the adaptive ability of models. Moreover, the lack of large-scale datasets with pixel-level salient instance annotations has impeded the development of machine learning techniques in this field. To address these issues, we construct the first large-scale underwater salient instance segmentation dataset (USIS10K), which contains 10,632 underwater images with pixel-level annotations in 7 categories from various underwater scenes. Then, we propose an Underwater Salient Instance Segmentation architecture based on Segment Anything Model (USIS-SAM) specifically for the underwater domain. We devise an Underwater Adaptive Visual Transformer (UA-ViT) encoder to incorporate underwater domain visual prompts into the segmentation network. We further design an out-of-the-box underwater Salient Feature Prompter Generator (SFPG) to automatically generate salient prompters instead of explicitly providing foreground points or boxes as prompts in SAM. Comprehensive experimental results show that our USIS-SAM method can achieve superior performance on USIS10K datasets compared to the state-of-the-art methods. Datasets and codes are released on https://github.com/LiamLian0727/USIS10K.
Authors: Dongjie Yang, Suyuan Huang, Chengqiang Lu, Xiaodong Han, Haoxin Zhang, Yan Gao, Yao Hu, Hai Zhao
Abstract: Advancements in multimodal learning, particularly in video understanding and generation, require high-quality video-text datasets for improved model performance. Vript addresses this issue with a meticulously annotated corpus of 12K high-resolution videos, offering detailed, dense, and script-like captions for over 420K clips. Each clip has a caption of ~145 words, which is over 10x longer than most video-text datasets. Unlike captions only documenting static content in previous datasets, we enhance video captioning to video scripting by documenting not just the content, but also the camera operations, which include the shot types (medium shot, close-up, etc) and camera movements (panning, tilting, etc). By utilizing the Vript, we explore three training paradigms of aligning more text with the video modality rather than clip-caption pairs. This results in Vriptor, a top-performing video captioning model among open-source models, comparable to GPT-4V in performance. Vriptor is also a powerful model capable of end-to-end generation of dense and detailed captions for long videos. Moreover, we introduce Vript-Hard, a benchmark consisting of three video understanding tasks that are more challenging than existing benchmarks: Vript-HAL is the first benchmark evaluating action and object hallucinations in video LLMs, Vript-RR combines reasoning with retrieval resolving question ambiguity in long-video QAs, and Vript-ERO is a new task to evaluate the temporal understanding of events in long videos rather than actions in short videos in previous works. All code, models, and datasets are available in https://github.com/mutonix/Vript.
Authors: Sunjae Yoon, Gwanhyeong Koo, Geonwoo Kim, Chang D. Yoo
Abstract: In video editing, the hallmark of a quality edit lies in its consistent and unobtrusive adjustment. Modification, when integrated, must be smooth and subtle, preserving the natural flow and aligning seamlessly with the original vision. Therefore, our primary focus is on overcoming the current challenges in high quality edit to ensure that each edit enhances the final product without disrupting its intended essence. However, quality deterioration such as blurring and flickering is routinely observed in recent diffusion video editing systems. We confirm that this deterioration often stems from high-frequency leak: the diffusion model fails to accurately synthesize high-frequency components during denoising process. To this end, we devise Frequency Adapting Group (FRAG) which enhances the video quality in terms of consistency and fidelity by introducing a novel receptive field branch to preserve high-frequency components during the denoising process. FRAG is performed in a model-agnostic manner without additional training and validates the effectiveness on video editing benchmarks (i.e., TGVE, DAVIS).
Authors: Ke Niu, Haiyang Yu, Xuelin Qian, Teng Fu, Bin Li, Xiangyang Xue
Abstract: Existing person re-identification (Re-ID) methods principally deploy the ImageNet-1K dataset for model initialization, which inevitably results in sub-optimal situations due to the large domain gap. One of the key challenges is that building large-scale person Re-ID datasets is time-consuming. Some previous efforts address this problem by collecting person images from the internet e.g., LUPerson, but it struggles to learn from unlabeled, uncontrollable, and noisy data. In this paper, we present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities without requiring any cost of data collection and annotation. Technically, this paradigm unfolds in two stages: generation and filtering. During the generation stage, we propose Language Prompts Enhancement (LPE) to ensure the ID consistency between the input image sequence and the generated images. In the diffusion process, we propose a Diversity Injection (DI) module to increase attribute diversity. In order to make the generated data have higher quality, we apply a Re-ID confidence threshold filter to further remove the low-quality images. Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities. Next, we build a stronger person Re-ID backbone pre-trained on our Diff-Person. Extensive experiments are conducted on four person Re-ID benchmarks in six widely used settings. Compared with other pre-training and self-supervised competitors, our approach shows significant superiority.
Authors: Hao Sun, Yu Song
Abstract: Large models have demonstrated exceptional generalization capabilities in computer vision and natural language processing. Recent efforts have focused on enhancing these models with multimodal processing abilities. However, addressing the challenges posed by scenarios where one modality is absent remains a significant hurdle. In response to this issue, we propose a robust latent representation tuning method for large models. Specifically, our approach introduces a modality latent translation module to maximize the correlation between modalities. Following this, a newly designed fusion module is employed to facilitate information interaction between the modalities. In this framework, not only are common semantics refined during training, but the method also yields robust representations in the absence of one modality. Importantly, our method maintains the frozen state of the image and text foundation models to preserve their abilities acquired through large-scale pretraining. We conduct experiments on several public datasets, and the results underscore the effectiveness of our proposed method.
Authors: Jinnan Chen, Chen Li, Jianfeng Zhang, Hanlin Chen, Buzhen Huang, Gim Hee Lee
Abstract: In this work, we tackle the task of learning generalizable 3D human Gaussians from a single image. The main challenge for this task is to recover detailed geometry and appearance, especially for the unobserved regions. To this end, we propose single-view generalizable Human Gaussian model (HGM), a diffusion-guided framework for 3D human modeling from a single image. We design a diffusion-based coarse-to-fine pipeline, where the diffusion model is adapted to refine novel-view images rendered from a coarse human Gaussian model. The refined images are then used together with the input image to learn a refined human Gaussian model. Although effective in hallucinating the unobserved views, the approach may generate unrealistic human pose and shapes due to the lack of supervision. We circumvent this problem by further encoding the geometric priors from SMPL model. Specifically, we propagate geometric features from SMPL volume to the predicted Gaussians via sparse convolution and attention mechanism. We validate our approach on publicly available datasets and demonstrate that it significantly surpasses state-of-the-art methods in terms of PSNR and SSIM. Additionally, our method exhibits strong generalization for in-the-wild images.
Authors: Yiren Song, Shijie Huang, Chen Yao, Xiaojun Ye, Hai Ci, Jiaming Liu, Yuxuan Zhang, Mike Zheng Shou
Abstract: The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Generating detailed, step-by-step painting processes is essential for art education and research, yet remains largely underexplored. Traditional stroke-based rendering methods break down images into sequences of brushstrokes, yet they fall short of replicating the authentic processes of artists, with limitations confined to basic brushstroke modifications. Text-to-image models utilizing diffusion processes generate images through iterative denoising, also diverge substantially from artists' painting process. To address these challenges, we introduce ProcessPainter, a text-to-video model that is initially pre-trained on synthetic data and subsequently fine-tuned with a select set of artists' painting sequences using the LoRA model. This approach successfully generates painting processes from text prompts for the first time. Furthermore, we introduce an Artwork Replication Network capable of accepting arbitrary-frame input, which facilitates the controlled generation of painting processes, decomposing images into painting sequences, and completing semi-finished artworks. This paper offers new perspectives and tools for advancing art education and image generation technology.
Authors: Jia-wei Chen, Yu-jie Xiong, Yong-bin Gao
Abstract: Mamba, based on state space model (SSM) with its linear complexity and great success in classification provide its superiority in 3D point cloud analysis. Prior to that, Transformer has emerged as one of the most prominent and successful architectures for point cloud analysis. We present PointABM, a hybrid model that integrates the Mamba and Transformer architectures for enhancing local feature to improve performance of 3D point cloud analysis. In order to enhance the extraction of global features, we introduce a bidirectional SSM (bi-SSM) framework, which comprises both a traditional token forward SSM and an innovative backward SSM. To enhance the bi-SSM's capability of capturing more comprehensive features without disrupting the sequence relationships required by the bidirectional Mamba, we introduce Transformer, utilizing its self-attention mechanism to process point clouds. Extensive experimental results demonstrate that integrating Mamba with Transformer significantly enhance the model's capability to analysis 3D point cloud.
Authors: Dongyoon Hwang, Byungkun Lee, Hojoon Lee, Hyunseung Kim, Jaegul Choo
Abstract: Vision Transformers (ViT), when paired with large-scale pretraining, have shown remarkable performance across various computer vision tasks, primarily due to their weak inductive bias. However, while such weak inductive bias aids in pretraining scalability, this may hinder the effective adaptation of ViTs for visuo-motor control tasks as a result of the absence of control-centric inductive biases. Such absent inductive biases include spatial locality and translation equivariance bias which convolutions naturally offer. To this end, we introduce Convolution Injector (CoIn), an add-on module that injects convolutions which are rich in locality and equivariance biases into a pretrained ViT for effective adaptation in visuo-motor control. We evaluate CoIn with three distinct types of pretrained ViTs (CLIP, MVP, VC-1) across 12 varied control tasks within three separate domains (Adroit, MetaWorld, DMC), and demonstrate that CoIn consistently enhances control task performance across all experimented environments and models, validating the effectiveness of providing pretrained ViTs with control-centric biases.
Authors: Victor Boutin, Rishav Mukherji, Aditya Agrawal, Sabine Muzellec, Thomas Fel, Thomas Serre, Rufin VanRullen
Abstract: Humans can effortlessly draw new categories from a single exemplar, a feat that has long posed a challenge for generative models. However, this gap has started to close with recent advances in diffusion models. This one-shot drawing task requires powerful inductive biases that have not been systematically investigated. Here, we study how different inductive biases shape the latent space of Latent Diffusion Models (LDMs). Along with standard LDM regularizers (KL and vector quantization), we explore supervised regularizations (including classification and prototype-based representation) and contrastive inductive biases (using SimCLR and redundancy reduction objectives). We demonstrate that LDMs with redundancy reduction and prototype-based regularizations produce near-human-like drawings (regarding both samples' recognizability and originality) -- better mimicking human perception (as evaluated psychophysically). Overall, our results suggest that the gap between humans and machines in one-shot drawings is almost closed.
Authors: Zijian Chen, Wei Sun, Yuan Tian, Jun Jia, Zicheng Zhang, Jiarui Wang, Ru Huang, Xiongkuo Min, Guangtao Zhai, Wenjun Zhang
Abstract: Assessing action quality is both imperative and challenging due to its significant impact on the quality of AI-generated videos, further complicated by the inherently ambiguous nature of actions within AI-generated video (AIGV). Current action quality assessment (AQA) algorithms predominantly focus on actions from real specific scenarios and are pre-trained with normative action features, thus rendering them inapplicable in AIGVs. To address these problems, we construct GAIA, a Generic AI-generated Action dataset, by conducting a large-scale subjective evaluation from a novel causal reasoning-based perspective, resulting in 971,244 ratings among 9,180 video-action pairs. Based on GAIA, we evaluate a suite of popular text-to-video (T2V) models on their ability to generate visually rational actions, revealing their pros and cons on different categories of actions. We also extend GAIA as a testbed to benchmark the AQA capacity of existing automatic evaluation methods. Results show that traditional AQA methods, action-related metrics in recent T2V benchmarks, and mainstream video quality methods correlate poorly with human opinions, indicating a sizable gap between current models and human action perception patterns in AIGVs. Our findings underscore the significance of action quality as a unique perspective for studying AIGVs and can catalyze progress towards methods with enhanced capacities for AQA in AIGVs.
Authors: Yihao Huang, Qing Guo, Felix Juefei-Xu, Ming Hu, Xiaojun Jia, Xiaochun Cao, Geguang Pu, Yang Liu
Abstract: Universal adversarial perturbation (UAP), also known as image-agnostic perturbation, is a fixed perturbation map that can fool the classifier with high probabilities on arbitrary images, making it more practical for attacking deep models in the real world. Previous UAP methods generate a scale-fixed and texture-fixed perturbation map for all images, which ignores the multi-scale objects in images and usually results in a low fooling ratio. Since the widely used convolution neural networks tend to classify objects according to semantic information stored in local textures, it seems a reasonable and intuitive way to improve the UAP from the perspective of utilizing local contents effectively. In this work, we find that the fooling ratios significantly increase when we add a constraint to encourage a small-scale UAP map and repeat it vertically and horizontally to fill the whole image domain. To this end, we propose texture scale-constrained UAP (TSC-UAP), a simple yet effective UAP enhancement method that automatically generates UAPs with category-specific local textures that can fool deep models more easily. Through a low-cost operation that restricts the texture scale, TSC-UAP achieves a considerable improvement in the fooling ratio and attack transferability for both data-dependent and data-free UAP methods. Experiments conducted on two state-of-the-art UAP methods, eight popular CNN models and four classical datasets show the remarkable performance of TSC-UAP.
Authors: Haochuan Jiang, Guanyu Yang, Kaizhu Huang, Rui Zhang
Abstract: Due to the huge category number, the sophisticated combinations of various strokes and radicals, and the free writing or printing styles, generating Chinese characters with diverse styles is always considered as a difficult task. In this paper, an efficient and generalized deep framework, namely, the W-Net, is introduced for the one-shot arbitrary-style Chinese character generation task. Specifically, given a single character (one-shot) with a specific style (e.g., a printed font or hand-writing style), the proposed W-Net model is capable of learning and generating any arbitrary characters sharing the style similar to the given single character. Such appealing property was rarely seen in the literature. We have compared the proposed W-Net framework to many other competitive methods. Experimental results showed the proposed method is significantly superior in the one-shot setting.
Authors: Meng-Li Shih, Wei-Chiu Ma, Aleksander Holynski, Forrester Cole, Brian L. Curless, Janne Kontkanen
Abstract: We propose ExtraNeRF, a novel method for extrapolating the range of views handled by a Neural Radiance Field (NeRF). Our main idea is to leverage NeRFs to model scene-specific, fine-grained details, while capitalizing on diffusion models to extrapolate beyond our observed data. A key ingredient is to track visibility to determine what portions of the scene have not been observed, and focus on reconstructing those regions consistently with diffusion models. Our primary contributions include a visibility-aware diffusion-based inpainting module that is fine-tuned on the input imagery, yielding an initial NeRF with moderate quality (often blurry) inpainted regions, followed by a second diffusion model trained on the input imagery to consistently enhance, notably sharpen, the inpainted imagery from the first pass. We demonstrate high-quality results, extrapolating beyond a small number of (typically six or fewer) input views, effectively outpainting the NeRF as well as inpainting newly disoccluded regions inside the original viewing volume. We compare with related work both quantitatively and qualitatively and show significant gains over prior art.
Authors: Donggeun Ko, Sangwoo Jo, Dongjun Lee, Namjun Park, Jaekwang Kim
Abstract: Dataset bias is a significant challenge in machine learning, where specific attributes, such as texture or color of the images are unintentionally learned resulting in detrimental performance. To address this, previous efforts have focused on debiasing models either by developing novel debiasing algorithms or by generating synthetic data to mitigate the prevalent dataset biases. However, generative approaches to date have largely relied on using bias-specific samples from the dataset, which are typically too scarce. In this work, we propose, DiffInject, a straightforward yet powerful method to augment synthetic bias-conflict samples using a pretrained diffusion model. This approach significantly advances the use of diffusion models for debiasing purposes by manipulating the latent space. Our framework does not require any explicit knowledge of the bias types or labelling, making it a fully unsupervised setting for debiasing. Our methodology demonstrates substantial result in effectively reducing dataset bias.
Authors: Leonardo Scabini, Andre Sacilotti, Kallil M. Zielinski, Lucas C. Ribas, Bernard De Baets, Odemir M. Bruno
Abstract: Texture, a significant visual attribute in images, has been extensively investigated across various image recognition applications. Convolutional Neural Networks (CNNs), which have been successful in many computer vision tasks, are currently among the best texture analysis approaches. On the other hand, Vision Transformers (ViTs) have been surpassing the performance of CNNs on tasks such as object recognition, causing a paradigm shift in the field. However, ViTs have so far not been scrutinized for texture recognition, hindering a proper appreciation of their potential in this specific setting. For this reason, this work explores various pre-trained ViT architectures when transferred to tasks that rely on textures. We review 21 different ViT variants and perform an extensive evaluation and comparison with CNNs and hand-engineered models on several tasks, such as assessing robustness to changes in texture rotation, scale, and illumination, and distinguishing color textures, material textures, and texture attributes. The goal is to understand the potential and differences among these models when directly applied to texture recognition, using pre-trained ViTs primarily for feature extraction and employing linear classifiers for evaluation. We also evaluate their efficiency, which is one of the main drawbacks in contrast to other methods. Our results show that ViTs generally outperform both CNNs and hand-engineered models, especially when using stronger pre-training and tasks involving in-the-wild textures (images from the internet). We highlight the following promising models: ViT-B with DINO pre-training, BeiTv2, and the Swin architecture, as well as the EfficientFormer as a low-cost alternative. In terms of efficiency, although having a higher number of GFLOPs and parameters, ViT-B and BeiT(v2) can achieve a lower feature extraction time on GPUs compared to ResNet50.
Authors: Juhyeong Seon, Woobin Im, Sebin Lee, Jumin Lee, Sung-Eui Yoon
Abstract: Audio-visual segmentation (AVS) aims to segment sound sources in the video sequence, requiring a pixel-level understanding of audio-visual correspondence. As the Segment Anything Model (SAM) has strongly impacted extensive fields of dense prediction problems, prior works have investigated the introduction of SAM into AVS with audio as a new modality of the prompt. Nevertheless, constrained by SAM's single-frame segmentation scheme, the temporal context across multiple frames of audio-visual data remains insufficiently utilized. To this end, we study the extension of SAM's capabilities to the sequence of audio-visual scenes by analyzing contextual cross-modal relationships across the frames. To achieve this, we propose a Spatio-Temporal, Bidirectional Audio-Visual Attention (ST-BAVA) module integrated into the middle of SAM's image encoder and mask decoder. It adaptively updates the audio-visual features to convey the spatio-temporal correspondence between the video frames and audio streams. Extensive experiments demonstrate that our proposed model outperforms the state-of-the-art methods on AVS benchmarks, especially with an 8.3% mIoU gain on a challenging multi-sources subset.
Authors: Ra\"ul P\'erez-Gonzalo, Andreas Espersen, Antonio Agudo
Abstract: Rate-distortion optimization through neural networks has accomplished competitive results in compression efficiency and image quality. This learning-based approach seeks to minimize the compromise between compression rate and reconstructed image quality by automatically extracting and retaining crucial information, while discarding less critical details. A successful technique consists in introducing a deep hyperprior that operates within a 2-level nested latent variable model, enhancing compression by capturing complex data dependencies. This paper extends this concept by designing a generalized L-level nested generative model with a Markov chain structure. We demonstrate as L increases that a trainable prior is detrimental and explore a common dimensionality along the distinct latent variables to boost compression performance. As this structured framework can represent autoregressive coders, we outperform the hyperprior model and achieve state-of-the-art performance while reducing substantially the computational cost. Our experimental evaluation is performed on wind turbine scenarios to study its application on visual inspections
Authors: Tuel Alexandre, Kerdreux Thomas, Thiry Louis
Abstract: Black carbon (BC) is an important pollutant aerosol emitted by numerous human activities, including gas flaring. Improper combustion in flaring activities can release large amounts of BC, which is harmful to human health and has a strong climate warming effect. To our knowledge, no study has ever directly monitored BC emissions from satellite imagery. Previous works quantified BC emissions indirectly, by applying emission coefficients to flaring volumes estimated from satellite imagery. Here, we develop a deep learning framework and apply it to Sentinel-2 imagery over North Africa during 2022 to detect and quantify BC emissions from gas flaring. We find that BC emissions in this region amount to about 1 million tCO$_{2,\mathrm{eq}}$, or 1 million passenger cars, more than a quarter of which are due to 10 sites alone. This work demonstrates the operational monitoring of BC emissions from flaring, a key step in implementing effective mitigation policies to reduce the climate impact of oil and gas operations.
Authors: Faegheh Sardari, Armin Mustafa, Philip J. B. Jackson, Adrian Hilton
Abstract: Unlike the sparse label action detection task, where a single action occurs in each timestamp of a video, in a dense multi-label scenario, actions can overlap. To address this challenging task, it is necessary to simultaneously learn (i) temporal dependencies and (ii) co-occurrence action relationships. Recent approaches model temporal information by extracting multi-scale features through hierarchical transformer-based networks. However, the self-attention mechanism in transformers inherently loses temporal positional information. We argue that combining this with multiple sub-sampling processes in hierarchical designs can lead to further loss of positional information. Preserving this information is essential for accurate action detection. In this paper, we address this issue by proposing a novel transformer-based network that (a) employs a non-hierarchical structure when modelling different ranges of temporal dependencies and (b) embeds relative positional encoding in its transformer layers. Furthermore, to model co-occurrence action relationships, current methods explicitly embed class relations into the transformer network. However, these approaches are not computationally efficient, as the network needs to compute all possible pair action class relations. We also overcome this challenge by introducing a novel learning paradigm that allows the network to benefit from explicitly modelling temporal co-occurrence action dependencies without imposing their additional computational costs during inference. We evaluate the performance of our proposed approach on two challenging dense multi-label benchmark datasets and show that our method improves the current state-of-the-art results.
Authors: Jiajun He, Tomoki Toda
Abstract: Moment retrieval aims to locate the most relevant moment in an untrimmed video based on a given natural language query. Existing solutions can be roughly categorized into moment-based and clip-based methods. The former often involves heavy computations, while the latter, due to overlooking coarse-grained information, typically underperforms compared to moment-based models. Hence, this paper proposes a novel 2-Dimensional Pointer-based Machine Reading Comprehension for Moment Retrieval Choice (2DP-2MRC) model to address the issue of imprecise localization in clip-based methods while maintaining lower computational complexity than moment-based methods. Specifically, we introduce an AV-Encoder to capture coarse-grained information at moment and video levels. Additionally, a 2D pointer encoder module is introduced to further enhance boundary detection for target moment. Extensive experiments on the HiREST dataset demonstrate that 2DP-2MRC significantly outperforms existing baseline models.
Authors: Abdulwahab Felemban, Eslam Mohamed Bakr, Xiaoqian Shen, Jian Ding, Abduallah Mohamed, Mohamed Elhoseiny
Abstract: We introduce iMotion-LLM: a Multimodal Large Language Models (LLMs) with trajectory prediction, tailored to guide interactive multi-agent scenarios. Different from conventional motion prediction approaches, iMotion-LLM capitalizes on textual instructions as key inputs for generating contextually relevant trajectories.By enriching the real-world driving scenarios in the Waymo Open Dataset with textual motion instructions, we created InstructWaymo. Leveraging this dataset, iMotion-LLM integrates a pretrained LLM, fine-tuned with LoRA, to translate scene features into the LLM input space. iMotion-LLM offers significant advantages over conventional motion prediction models. First, it can generate trajectories that align with the provided instructions if it is a feasible direction. Second, when given an infeasible direction, it can reject the instruction, thereby enhancing safety. These findings act as milestones in empowering autonomous navigation systems to interpret and predict the dynamics of multi-agent environments, laying the groundwork for future advancements in this field.
Authors: Xin Jin, Pengyi Jiao, Zheng-Peng Duan, Xingchao Yang, Chun-Le Guo, Bo Ren, Chongyi Li
Abstract: Volumetric rendering based methods, like NeRF, excel in HDR view synthesis from RAWimages, especially for nighttime scenes. While, they suffer from long training times and cannot perform real-time rendering due to dense sampling requirements. The advent of 3D Gaussian Splatting (3DGS) enables real-time rendering and faster training. However, implementing RAW image-based view synthesis directly using 3DGS is challenging due to its inherent drawbacks: 1) in nighttime scenes, extremely low SNR leads to poor structure-from-motion (SfM) estimation in distant views; 2) the limited representation capacity of spherical harmonics (SH) function is unsuitable for RAW linear color space; and 3) inaccurate scene structure hampers downstream tasks such as refocusing. To address these issues, we propose LE3D (Lighting Every darkness with 3DGS). Our method proposes Cone Scatter Initialization to enrich the estimation of SfM, and replaces SH with a Color MLP to represent the RAW linear color space. Additionally, we introduce depth distortion and near-far regularizations to improve the accuracy of scene structure for downstream tasks. These designs enable LE3D to perform real-time novel view synthesis, HDR rendering, refocusing, and tone-mapping changes. Compared to previous volumetric rendering based methods, LE3D reduces training time to 1% and improves rendering speed by up to 4,000 times for 2K resolution images in terms of FPS. Code and viewer can be found in https://github.com/Srameo/LE3D .
Authors: Tiago Sousa, Beno\^it Ries, Nicolas Guelfi
Abstract: The scarcity of high-quality Earth Observation (EO) imagery poses a significant challenge, despite its critical role in enabling precise analysis and informed decision-making across various sectors. This scarcity is primarily due to atmospheric conditions, seasonal variations, and limited geographical coverage, which complicates the application of Artificial Intelligence (AI) in EO. Data augmentation, a widely used technique in AI that involves generating additional data mainly through parameterized image transformations, has been employed to increase the volume and diversity of data. However, this method often falls short in generating sufficient diversity across key semantic axes, adversely affecting the accuracy of EO applications. To address this issue, we propose a novel four-stage approach aimed at improving the diversity of augmented data by integrating diffusion models. Our approach employs meta-prompts for instruction generation, harnesses general-purpose vision-language models for generating rich captions, fine-tunes an Earth Observation diffusion model, and iteratively augments data. We conducted extensive experiments using four different data augmentation techniques, and our approach consistently demonstrated improvements, outperforming the established augmentation methods, revealing its effectiveness in generating semantically rich and diverse EO images.
Authors: Fan Liu, Liang Yao, Shengxiang Xu, Chuanyi Zhang, Xinlei Zhang, Ting Wu
Abstract: The development of multi-modal object detection for Unmanned Aerial Vehicles (UAVs) typically relies on a large amount of pixel-aligned multi-modal image data. However, existing datasets face challenges such as limited modalities, high construction costs, and imprecise annotations. To this end, we propose a synthetic multi-modal UAV-based object detection dataset, UEMM-Air. Specially, we simulate various UAV flight scenarios and object types using the Unreal Engine (UE). Then we design the UAV's flight logic to automatically collect data from different scenarios, perspectives, and altitudes. Finally, we propose a novel heuristic automatic annotation algorithm to generate accurate object detection labels. In total, our UEMM-Air consists of 20k pairs of images with 5 modalities and precise annotations. Moreover, we conduct numerous experiments and establish new benchmark results on our dataset. We found that models pre-trained on UEMM-Air exhibit better performance on downstream tasks compared to other similar datasets. The dataset is publicly available (https://github.com/1e12Leon/UEMM-Air) to support the research of multi-modal UAV object detection models.
Authors: Talha Uddin Sheikh, Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
Abstract: Document layout analysis is a key area in document research, involving techniques like text mining and visual analysis. Despite various methods developed to tackle layout analysis, a critical but frequently overlooked problem is the scarcity of labeled data needed for analyses. With the rise of internet use, an overwhelming number of documents are now available online, making the process of accurately labeling them for research purposes increasingly challenging and labor-intensive. Moreover, the diversity of documents online presents a unique set of challenges in maintaining the quality and consistency of these labels, further complicating document layout analysis in the digital era. To address this, we employ a vision-based approach for analyzing document layouts designed to train a network without labels. Instead, we focus on pre-training, initially generating simple object masks from the unlabeled document images. These masks are then used to train a detector, enhancing object detection and segmentation performance. The model's effectiveness is further amplified through several unsupervised training iterations, continuously refining its performance. This approach significantly advances document layout analysis, particularly precision and efficiency, without labels.
Authors: Hoang H. Le, Duy M. H. Nguyen, Omair Shahzad Bhatti, Laszlo Kopacsi, Thinh P. Ngo, Binh T. Nguyen, Michael Barz, Daniel Sonntag
Abstract: Understanding human visual processing in dynamic environments is essential for psychology and human-centered interaction design. Mobile eye-tracking systems, combining egocentric video and gaze signals, offer valuable insights. However, manual analysis of these recordings is time-intensive. In this work, we present a novel human-centered learning algorithm designed for automated object recognition within mobile eye-tracking settings. Our approach seamlessly integrates an object detector with an inductive message-passing network technique (I-MPN), harnessing node features such as node profile information and positions. This integration enables our algorithm to learn embedding functions capable of generalizing to new object angle views, thereby facilitating rapid adaptation and efficient reasoning in dynamic contexts as users navigate through their environment. Through experiments conducted on three distinct video sequences, our \textit{interactive-based method} showcases significant performance improvements over fixed training/testing algorithms, even when trained on considerably smaller annotated samples collected through user feedback. Furthermore, we showcase exceptional efficiency in data annotation processes, surpassing approaches that use complete object detectors, combine detectors with convolutional networks, or employ interactive video segmentation.
Authors: Xiaojie Li, Chenghao Gu, Shuzhao Xie, Yunpeng Bai, Weixiang Zhang, Zhi Wang
Abstract: Fine-Tuning Diffusion Models enable a wide range of personalized generation and editing applications on diverse visual modalities. While Low-Rank Adaptation (LoRA) accelerates the fine-tuning process, it still requires multiple reference images and time-consuming training, which constrains its scalability for large-scale and real-time applications. In this paper, we propose \textit{View Iterative Self-Attention Control (VisCtrl)} to tackle this challenge. Specifically, VisCtrl is a training-free method that injects the appearance and structure of a user-specified subject into another subject in the target image, unlike previous approaches that require fine-tuning the model. Initially, we obtain the initial noise for both the reference and target images through DDIM inversion. Then, during the denoising phase, features from the reference image are injected into the target image via the self-attention mechanism. Notably, by iteratively performing this feature injection process, we ensure that the reference image features are gradually integrated into the target image. This approach results in consistent and harmonious editing with only one reference image in a few denoising steps. Moreover, benefiting from our plug-and-play architecture design and the proposed Feature Gradual Sampling strategy for multi-view editing, our method can be easily extended to edit in complex visual domains. Extensive experiments show the efficacy of VisCtrl across a spectrum of tasks, including personalized editing of images, videos, and 3D scenes.
Authors: Simon Doll, Niklas Hanselmann, Lukas Schneider, Richard Schulz, Marius Cordts, Markus Enzweiler, Hendrik P. A. Lensch
Abstract: State-of-the-art approaches for autonomous driving integrate multiple sub-tasks of the overall driving task into a single pipeline that can be trained in an end-to-end fashion by passing latent representations between the different modules. In contrast to previous approaches that rely on a unified grid to represent the belief state of the scene, we propose dedicated representations to disentangle dynamic agents and static scene elements. This allows us to explicitly compensate for the effect of both ego and object motion between consecutive time steps and to flexibly propagate the belief state through time. Furthermore, dynamic objects can not only attend to the input camera images, but also directly benefit from the inferred static scene structure via a novel dynamic-static cross-attention. Extensive experiments on the challenging nuScenes benchmark demonstrate the benefits of the proposed dual-stream design, especially for modelling highly dynamic agents in the scene, and highlight the improved temporal consistency of our approach. Our method titled DualAD not only outperforms independently trained single-task networks, but also improves over previous state-of-the-art end-to-end models by a large margin on all tasks along the functional chain of driving.
Authors: Yuqi Ma, Huamin Wang, Hangchi Shen, Xuemei Chen, Shukai Duan, Shiping Wen
Abstract: Recently, brain-inspired spiking neural networks (SNNs) have attracted great research attention owing to their inherent bio-interpretability, event-triggered properties and powerful perception of spatiotemporal information, which is beneficial to handling event-based neuromorphic datasets. In contrast to conventional static image datasets, event-based neuromorphic datasets present heightened complexity in feature extraction due to their distinctive time series and sparsity characteristics, which influences their classification accuracy. To overcome this challenge, a novel approach termed Neuromorphic Momentum Contrast Learning (NeuroMoCo) for SNNs is introduced in this paper by extending the benefits of self-supervised pre-training to SNNs to effectively stimulate their potential. This is the first time that self-supervised learning (SSL) based on momentum contrastive learning is realized in SNNs. In addition, we devise a novel loss function named MixInfoNCE tailored to their temporal characteristics to further increase the classification accuracy of neuromorphic datasets, which is verified through rigorous ablation experiments. Finally, experiments on DVS-CIFAR10, DVS128Gesture and N-Caltech101 have shown that NeuroMoCo of this paper establishes new state-of-the-art (SOTA) benchmarks: 83.6% (Spikformer-2-256), 98.62% (Spikformer-2-256), and 84.4% (SEW-ResNet-18), respectively.
Authors: Adam Van Etten
Abstract: We explore methods to detect automobiles in Planet imagery and build a large scale vector field for moving objects. Planet operates two distinct constellations: high-resolution SkySat satellites as well as medium-resolution SuperDove satellites. We show that both static and moving cars can be identified reliably in high-resolution SkySat imagery. We are able to estimate the speed and heading of moving vehicles by leveraging the inter-band displacement (or "rainbow" effect) of moving objects. Identifying cars and trucks in medium-resolution SuperDove imagery is far more difficult, though a similar rainbow effect is observed in these satellites and enables moving vehicles to be detected and vectorized. The frequent revisit of Planet satellites enables the categorization of automobile and truck activity patterns over broad areas of interest and lengthy timeframes.
Authors: Daniel Brignac, Abhijit Mahalanobis
Abstract: Deep learners tend to perform well when trained under the closed set assumption but struggle when deployed under open set conditions. This motivates the field of Open Set Recognition in which we seek to give deep learners the ability to recognize whether a data sample belongs to the known classes trained on or comes from the surrounding infinite world. Existing open set recognition methods typically rely upon a single function for the dual task of distinguishing between knowns and unknowns as well as making known class distinction. This dual process leaves performance on the table as the function is not specialized for either task. In this work, we introduce Cascading Unknown Detection with Known Classification (Cas-DC), where we instead learn specialized functions in a cascading fashion for both known/unknown detection and fine class classification amongst the world of knowns. Our experiments and analysis demonstrate that Cas-DC handily outperforms modern methods in open set recognition when compared using AUROC scores and correct classification rate at various true positive rates.
Authors: Carolina Lopez Olmos, Alexandros Neophytou, Sunando Sengupta, Dim P. Papadopoulos
Abstract: Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development of these models, and mitigation through hard prompting or embedding alteration, are the most common present solutions. Our work introduces a novel approach to achieve diverse and inclusive synthetic images by learning a direction in the latent space and solely modifying the initial Gaussian noise provided for the diffusion process. Maintaining a neutral prompt and untouched embeddings, this approach successfully adapts to diverse debiasing scenarios, such as geographical biases. Moreover, our work proves it is possible to linearly combine these learned latent directions to introduce new mitigations, and if desired, integrate it with text embedding adjustments. Furthermore, text-to-image models lack transparency for assessing bias in outputs, unless visually inspected. Thus, we provide a tool to empower developers to select their desired concepts to mitigate. The project page with code is available online.
Authors: Xuanyu Yi, Zike Wu, Qiuhong Shen, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang
Abstract: Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representation for improved visual quality and rendering efficiency. However, we observe that existing Gaussian reconstruction models often suffer from multi-view inconsistency and blurred textures. We attribute this to the compromise of multi-view information propagation in favor of adopting powerful yet computationally intensive architectures (\eg, Transformers). To address this issue, we introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor based on the RNN-like State Space Model (SSM). Our Gaussian reconstructor propagates causal context containing multi-view information for cross-view self-refinement while generating a long sequence of Gaussians for fine-detail modeling with linear complexity. With off-the-shelf multi-view diffusion models integrated, MVGamba unifies 3D generation tasks from a single image, sparse images, or text prompts. Extensive experiments demonstrate that MVGamba outperforms state-of-the-art baselines in all 3D content generation scenarios with approximately only $0.1\times$ of the model size.
Authors: Daniel Bogdoll, No\"el Ollick, Tim Joseph, J. Marius Z\"ollner
Abstract: Dealing with atypical traffic scenarios remains a challenging task in autonomous driving. However, most anomaly detection approaches cannot be trained on raw sensor data but require exposure to outlier data and powerful semantic segmentation models trained in a supervised fashion. This limits the representation of normality to labeled data, which does not scale well. In this work, we revisit unsupervised anomaly detection and present UMAD, leveraging generative world models and unsupervised image segmentation. Our method outperforms state-of-the-art unsupervised anomaly detection.
Authors: Marek Wodzinski, Kamil Kwarciak, Mateusz Daniol, Daria Hemmerling
Abstract: Modeling and manufacturing of personalized cranial implants are important research areas that may decrease the waiting time for patients suffering from cranial damage. The modeling of personalized implants may be partially automated by the use of deep learning-based methods. However, this task suffers from difficulties with generalizability into data from previously unseen distributions that make it difficult to use the research outcomes in real clinical settings. Due to difficulties with acquiring ground-truth annotations, different techniques to improve the heterogeneity of datasets used for training the deep networks have to be considered and introduced. In this work, we present a large-scale study of several augmentation techniques, varying from classical geometric transformations, image registration, variational autoencoders, and generative adversarial networks, to the most recent advances in latent diffusion models. We show that the use of heavy data augmentation significantly increases both the quantitative and qualitative outcomes, resulting in an average Dice Score above 0.94 for the SkullBreak and above 0.96 for the SkullFix datasets. Moreover, we show that the synthetically augmented network successfully reconstructs real clinical defects. The work is a considerable contribution to the field of artificial intelligence in the automatic modeling of personalized cranial implants.
Authors: Yi Gu, Zhendong Wang, Yueqin Yin, Yujia Xie, Mingyuan Zhou
Abstract: Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory. The Diffusion-DPO technique made initial strides by employing pairwise preference learning in diffusion models tailored for specific text prompts. We introduce Diffusion-RPO, a new method designed to align diffusion-based T2I models with human preferences more effectively. This approach leverages both prompt-image pairs with identical prompts and those with semantically related content across various modalities. Furthermore, we have developed a new evaluation metric, style alignment, aimed at overcoming the challenges of high costs, low reproducibility, and limited interpretability prevalent in current evaluations of human preference alignment. Our findings demonstrate that Diffusion-RPO outperforms established methods such as Supervised Fine-Tuning and Diffusion-DPO in tuning Stable Diffusion versions 1.5 and XL-1.0, achieving superior results in both automated evaluations of human preferences and style alignment. Our code is available at https://github.com/yigu1008/Diffusion-RPO
Authors: Peng Xia, Ming Hu, Feilong Tang, Wenxue Li, Wenhao Zheng, Lie Ju, Peibo Duan, Huaxiu Yao, Zongyuan Ge
Abstract: Diabetic Retinopathy (DR), induced by diabetes, poses a significant risk of visual impairment. Accurate and effective grading of DR aids in the treatment of this condition. Yet existing models experience notable performance degradation on unseen domains due to domain shifts. Previous methods address this issue by simulating domain style through simple visual transformation and mitigating domain noise via learning robust representations. However, domain shifts encompass more than image styles. They overlook biases caused by implicit factors such as ethnicity, age, and diagnostic criteria. In our work, we propose a novel framework where representations of paired data from different domains are decoupled into semantic features and domain noise. The resulting augmented representation comprises original retinal semantics and domain noise from other domains, aiming to generate enhanced representations aligned with real-world clinical needs, incorporating rich information from diverse domains. Subsequently, to improve the robustness of the decoupled representations, class and domain prototypes are employed to interpolate the disentangled representations while data-aware weights are designed to focus on rare classes and domains. Finally, we devise a robust pixel-level semantic alignment loss to align retinal semantics decoupled from features, maintaining a balance between intra-class diversity and dense class features. Experimental results on multiple benchmarks demonstrate the effectiveness of our method on unseen domains. The code implementations are accessible on https://github.com/richard-peng-xia/DECO.
Authors: Julia Yang, Alina Jade Barnett, Jon Donnelly, Satvik Kishore, Jerry Fang, Fides Regina Schwartz, Chaofan Chen, Joseph Y. Lo, Cynthia Rudin
Abstract: Digital mammography is essential to breast cancer detection, and deep learning offers promising tools for faster and more accurate mammogram analysis. In radiology and other high-stakes environments, uninterpretable ("black box") deep learning models are unsuitable and there is a call in these fields to make interpretable models. Recent work in interpretable computer vision provides transparency to these formerly black boxes by utilizing prototypes for case-based explanations, achieving high accuracy in applications including mammography. However, these models struggle with precise feature localization, reasoning on large portions of an image when only a small part is relevant. This paper addresses this gap by proposing a novel multi-scale interpretable deep learning model for mammographic mass margin classification. Our contribution not only offers an interpretable model with reasoning aligned with radiologist practices, but also provides a general architecture for computer vision with user-configurable prototypes from coarse- to fine-grained prototypes.
Authors: Jiawen Chen, Muqing Zhou, Wenrong Wu, Jinwei Zhang, Yun Li, Didong Li
Abstract: Recent advances in multi-modal algorithms have driven and been driven by the increasing availability of large image-text datasets, leading to significant strides in various fields, including computational pathology. However, in most existing medical image-text datasets, the text typically provides high-level summaries that may not sufficiently describe sub-tile regions within a large pathology image. For example, an image might cover an extensive tissue area containing cancerous and healthy regions, but the accompanying text might only specify that this image is a cancer slide, lacking the nuanced details needed for in-depth analysis. In this study, we introduce STimage-1K4M, a novel dataset designed to bridge this gap by providing genomic features for sub-tile images. STimage-1K4M contains 1,149 images derived from spatial transcriptomics data, which captures gene expression information at the level of individual spatial spots within a pathology image. Specifically, each image in the dataset is broken down into smaller sub-image tiles, with each tile paired with 15,000-30,000 dimensional gene expressions. With 4,293,195 pairs of sub-tile images and gene expressions, STimage-1K4M offers unprecedented granularity, paving the way for a wide range of advanced research in multi-modal data analysis an innovative applications in computational pathology, and beyond.
Authors: Daniel Bogdoll, Jan Imhof, Tim Joseph, J. Marius Z\"ollner
Abstract: In autonomous driving, the most challenging scenarios are the ones that can only be detected within their temporal context. Most video anomaly detection approaches focus either on surveillance or traffic accidents, which are only a subfield of autonomous driving. In this work, we present HF$^2$-VAD$_{AD}$, a variation of the HF$^2$-VAD surveillance video anomaly detection method for autonomous driving. We learn a representation of normality from a vehicle's ego perspective and evaluate pixel-wise anomaly detections in rare and critical scenarios.
Authors: Jiwoo Hong, Sayak Paul, Noah Lee, Kashif Rasul, James Thorne, Jongheon Jeong
Abstract: Modern alignment techniques based on human preferences, such as RLHF and DPO, typically employ divergence regularization relative to the reference model to ensure training stability. However, this often limits the flexibility of models during alignment, especially when there is a clear distributional discrepancy between the preference data and the reference model. In this paper, we focus on the alignment of recent text-to-image diffusion models, such as Stable Diffusion XL (SDXL), and find that this "reference mismatch" is indeed a significant problem in aligning these models due to the unstructured nature of visual modalities: e.g., a preference for a particular stylistic aspect can easily induce such a discrepancy. Motivated by this observation, we propose a novel and memory-friendly preference alignment method for diffusion models that does not depend on any reference model, coined margin-aware preference optimization (MaPO). MaPO jointly maximizes the likelihood margin between the preferred and dispreferred image sets and the likelihood of the preferred sets, simultaneously learning general stylistic features and preferences. For evaluation, we introduce two new pairwise preference datasets, which comprise self-generated image pairs from SDXL, Pick-Style and Pick-Safety, simulating diverse scenarios of reference mismatch. Our experiments validate that MaPO can significantly improve alignment on Pick-Style and Pick-Safety and general preference alignment when used with Pick-a-Pic v2, surpassing the base SDXL and other existing methods. Our code, models, and datasets are publicly available via https://mapo-t2i.github.io
Authors: Jing Yang, Kyle Fogarty, Fangcheng Zhong, Cengiz Oztireli
Abstract: Despite the growing success of 3D-aware GANs, which can be trained on 2D images to generate high-quality 3D assets, they still rely on multi-view images with camera annotations to synthesize sufficient details from all viewing directions. However, the scarce availability of calibrated multi-view image datasets, especially in comparison to single-view images, has limited the potential of 3D GANs. Moreover, while bypassing camera pose annotations with a camera distribution constraint reduces dependence on exact camera parameters, it still struggles to generate a consistent orientation of 3D assets. To this end, we propose SYM3D, a novel 3D-aware GAN designed to leverage the prevalent reflectional symmetry structure found in natural and man-made objects, alongside a proposed view-aware spatial attention mechanism in learning the 3D representation. We evaluate SYM3D on both synthetic (ShapeNet Chairs, Cars, and Airplanes) and real-world datasets (ABO-Chair), demonstrating its superior performance in capturing detailed geometry and texture, even when trained on only single-view images. Finally, we demonstrate the effectiveness of incorporating symmetry regularization in helping reduce artifacts in the modeling of 3D assets in the text-to-3D task.
Authors: Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu, Bang Liu, Yoshua Bengio
Abstract: We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
Authors: Zhen Xing, Qi Dai, Zejia Weng, Zuxuan Wu, Yu-Gang Jiang
Abstract: Text-guided video prediction (TVP) involves predicting the motion of future frames from the initial frame according to an instruction, which has wide applications in virtual reality, robotics, and content creation. Previous TVP methods make significant breakthroughs by adapting Stable Diffusion for this task. However, they struggle with frame consistency and temporal stability primarily due to the limited scale of video datasets. We observe that pretrained Image2Video diffusion models possess good priors for video dynamics but they lack textual control. Hence, transferring Image2Video models to leverage their video dynamic priors while injecting instruction control to generate controllable videos is both a meaningful and challenging task. To achieve this, we introduce the Multi-Modal Large Language Model (MLLM) to predict future video states based on initial frames and text instructions. More specifically, we design a dual query transformer (DQFormer) architecture, which integrates the instructions and frames into the conditional embeddings for future frame prediction. Additionally, we develop Long-Short Term Temporal Adapters and Spatial Adapters that can quickly transfer general video diffusion models to specific scenarios with minimal training costs. Experimental results show that our method significantly outperforms state-of-the-art techniques on four datasets: Something Something V2, Epic Kitchen-100, Bridge Data, and UCF-101. Notably, AID achieves 91.2% and 55.5% FVD improvements on Bridge and SSv2 respectively, demonstrating its effectiveness in various domains. More examples can be found at our website https://chenhsing.github.io/AID.
Authors: Asmar Nadeem, Faegheh Sardari, Robert Dawes, Syed Sameed Husain, Adrian Hilton, Armin Mustafa
Abstract: Existing video captioning benchmarks and models lack coherent representations of causal-temporal narrative, which is sequences of events linked through cause and effect, unfolding over time and driven by characters or agents. This lack of narrative restricts models' ability to generate text descriptions that capture the causal and temporal dynamics inherent in video content. To address this gap, we propose NarrativeBridge, an approach comprising of: (1) a novel Causal-Temporal Narrative (CTN) captions benchmark generated using a large language model and few-shot prompting, explicitly encoding cause-effect temporal relationships in video descriptions, evaluated automatically to ensure caption quality and relevance; and (2) a dedicated Cause-Effect Network (CEN) architecture with separate encoders for capturing cause and effect dynamics independently, enabling effective learning and generation of captions with causal-temporal narrative. Extensive experiments demonstrate that CEN is more accurate in articulating the causal and temporal aspects of video content than the second best model (GIT): 17.88 and 17.44 CIDEr on the MSVD and MSR-VTT datasets, respectively. The proposed framework understands and generates nuanced text descriptions with intricate causal-temporal narrative structures present in videos, addressing a critical limitation in video captioning. For project details, visit https://narrativebridge.github.io/.
Authors: Sigal Raab, Inbar Gat, Nathan Sala, Guy Tevet, Rotem Shalev-Arkushin, Ohad Fried, Amit H. Bermano, Daniel Cohen-Or
Abstract: Given the remarkable results of motion synthesis with diffusion models, a natural question arises: how can we effectively leverage these models for motion editing? Existing diffusion-based motion editing methods overlook the profound potential of the prior embedded within the weights of pre-trained models, which enables manipulating the latent feature space; hence, they primarily center on handling the motion space. In this work, we explore the attention mechanism of pre-trained motion diffusion models. We uncover the roles and interactions of attention elements in capturing and representing intricate human motion patterns, and carefully integrate these elements to transfer a leader motion to a follower one while maintaining the nuanced characteristics of the follower, resulting in zero-shot motion transfer. Editing features associated with selected motions allows us to confront a challenge observed in prior motion diffusion approaches, which use general directives (e.g., text, music) for editing, ultimately failing to convey subtle nuances effectively. Our work is inspired by how a monkey closely imitates what it sees while maintaining its unique motion patterns; hence we call it Monkey See, Monkey Do, and dub it MoMo. Employing our technique enables accomplishing tasks such as synthesizing out-of-distribution motions, style transfer, and spatial editing. Furthermore, diffusion inversion is seldom employed for motions; as a result, editing efforts focus on generated motions, limiting the editability of real ones. MoMo harnesses motion inversion, extending its application to both real and generated motions. Experimental results show the advantage of our approach over the current art. In particular, unlike methods tailored for specific applications through training, our approach is applied at inference time, requiring no training. Our webpage is at https://monkeyseedocg.github.io.
Authors: Louis Blankemeier, Joseph Paul Cohen, Ashwin Kumar, Dave Van Veen, Syed Jamal Safdar Gardezi, Magdalini Paschali, Zhihong Chen, Jean-Benoit Delbrouck, Eduardo Reis, Cesar Truyts, Christian Bluethgen, Malte Engmann Kjeldskov Jensen, Sophie Ostmeier, Maya Varma, Jeya Maria Jose Valanarasu, Zhongnan Fang, Zepeng Huo, Zaid Nabulsi, Diego Ardila, Wei-Hung Weng, Edson Amaro Junior, Neera Ahuja, Jason Fries, Nigam H. Shah, Andrew Johnston, Robert D. Boutin, Andrew Wentland, Curtis P. Langlotz, Jason Hom, Sergios Gatidis, Akshay S. Chaudhari
Abstract: Over 85 million computed tomography (CT) scans are performed annually in the US, of which approximately one quarter focus on the abdomen. Given the current radiologist shortage, there is a large impetus to use artificial intelligence to alleviate the burden of interpreting these complex imaging studies. Prior state-of-the-art approaches for automated medical image interpretation leverage vision language models (VLMs). However, current medical VLMs are generally limited to 2D images and short reports, and do not leverage electronic health record (EHR) data for supervision. We introduce Merlin - a 3D VLM that we train using paired CT scans (6+ million images from 15,331 CTs), EHR diagnosis codes (1.8+ million codes), and radiology reports (6+ million tokens). We evaluate Merlin on 6 task types and 752 individual tasks. The non-adapted (off-the-shelf) tasks include zero-shot findings classification (31 findings), phenotype classification (692 phenotypes), and zero-shot cross-modal retrieval (image to findings and image to impressions), while model adapted tasks include 5-year disease prediction (6 diseases), radiology report generation, and 3D semantic segmentation (20 organs). We perform internal validation on a test set of 5,137 CTs, and external validation on 7,000 clinical CTs and on two public CT datasets (VerSe, TotalSegmentator). Beyond these clinically-relevant evaluations, we assess the efficacy of various network architectures and training strategies to depict that Merlin has favorable performance to existing task-specific baselines. We derive data scaling laws to empirically assess training data needs for requisite downstream task performance. Furthermore, unlike conventional VLMs that require hundreds of GPUs for training, we perform all training on a single GPU.
Authors: Fangliangzi Meng, Hongrun Zhang, Ruodan Yan, Guohui Chuai, Chao Li, Qi Liu
Abstract: The characterization of Tumor MicroEnvironment (TME) is challenging due to its complexity and heterogeneity. Relatively consistent TME characteristics embedded within highly specific tissue features, render them difficult to predict. The capability to accurately classify TME subtypes is of critical significance for clinical tumor diagnosis and precision medicine. Based on the observation that tumors with different origins share similar microenvironment patterns, we propose PathoTME, a genomics-guided Siamese representation learning framework employing Whole Slide Image (WSI) for pan-cancer TME subtypes prediction. Specifically, we utilize Siamese network to leverage genomic information as a regularization factor to assist WSI embeddings learning during the training phase. Additionally, we employ Domain Adversarial Neural Network (DANN) to mitigate the impact of tissue type variations. To eliminate domain bias, a dynamic WSI prompt is designed to further unleash the model's capabilities. Our model achieves better performance than other state-of-the-art methods across 23 cancer types on TCGA dataset. Our code is available at https://github.com/Mengflz/PathoTME.
Authors: Danpeng Chen, Hai Li, Weicai Ye, Yifan Wang, Weijian Xie, Shangjin Zhai, Nan Wang, Haomin Liu, Hujun Bao, Guofeng Zhang
Abstract: Recently, 3D Gaussian Splatting (3DGS) has attracted widespread attention due to its high-quality rendering, and ultra-fast training and rendering speed. However, due to the unstructured and irregular nature of Gaussian point clouds, it is difficult to guarantee geometric reconstruction accuracy and multi-view consistency simply by relying on image reconstruction loss. Although many studies on surface reconstruction based on 3DGS have emerged recently, the quality of their meshes is generally unsatisfactory. To address this problem, we propose a fast planar-based Gaussian splatting reconstruction representation (PGSR) to achieve high-fidelity surface reconstruction while ensuring high-quality rendering. Specifically, we first introduce an unbiased depth rendering method, which directly renders the distance from the camera origin to the Gaussian plane and the corresponding normal map based on the Gaussian distribution of the point cloud, and divides the two to obtain the unbiased depth. We then introduce single-view geometric, multi-view photometric, and geometric regularization to preserve global geometric accuracy. We also propose a camera exposure compensation model to cope with scenes with large illumination variations. Experiments on indoor and outdoor scenes show that our method achieves fast training and rendering while maintaining high-fidelity rendering and geometric reconstruction, outperforming 3DGS-based and NeRF-based methods.
Authors: Ting-Hsuan Chen, Jiewen Chan, Hau-Shiang Shiu, Shih-Han Yen, Chang-Han Yeh, Yu-Lun Liu
Abstract: We propose a video editing framework, NaRCan, which integrates a hybrid deformation field and diffusion prior to generate high-quality natural canonical images to represent the input video. Our approach utilizes homography to model global motion and employs multi-layer perceptrons (MLPs) to capture local residual deformations, enhancing the model's ability to handle complex video dynamics. By introducing a diffusion prior from the early stages of training, our model ensures that the generated images retain a high-quality natural appearance, making the produced canonical images suitable for various downstream tasks in video editing, a capability not achieved by current canonical-based methods. Furthermore, we incorporate low-rank adaptation (LoRA) fine-tuning and introduce a noise and diffusion prior update scheduling technique that accelerates the training process by 14 times. Extensive experimental results show that our method outperforms existing approaches in various video editing tasks and produces coherent and high-quality edited video sequences. See our project page for video results at https://koi953215.github.io/NaRCan_page/.
Authors: Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang, Bingyue Peng, Ping Luo, Zehuan Yuan
Abstract: We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive models, e.g., Llama, without inductive biases on visual signals can achieve state-of-the-art image generation performance if scaling properly. We reexamine design spaces of image tokenizers, scalability properties of image generation models, and their training data quality. The outcome of this exploration consists of: (1) An image tokenizer with downsample ratio of 16, reconstruction quality of 0.94 rFID and codebook usage of 97% on ImageNet benchmark. (2) A series of class-conditional image generation models ranging from 111M to 3.1B parameters, achieving 2.18 FID on ImageNet 256x256 benchmarks, outperforming the popular diffusion models such as LDM, DiT. (3) A text-conditional image generation model with 775M parameters, from two-stage training on LAION-COCO and high aesthetics quality images, demonstrating competitive performance of visual quality and text alignment. (4) We verify the effectiveness of LLM serving frameworks in optimizing the inference speed of image generation models and achieve 326% - 414% speedup. We release all models and codes to facilitate open-source community of visual generation and multimodal foundation models.
Authors: Haozhe Xie, Zhaoxi Chen, Fangzhou Hong, Ziwei Liu
Abstract: 3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However, adapting 3D-GS from finite-scale 3D objects and humans to infinite-scale 3D cities is non-trivial. Unbounded 3D city generation entails significant storage overhead (out-of-memory issues), arising from the need to expand points to billions, often demanding hundreds of Gigabytes of VRAM for a city scene spanning 10km^2. In this paper, we propose GaussianCity, a generative Gaussian Splatting framework dedicated to efficiently synthesizing unbounded 3D cities with a single feed-forward pass. Our key insights are two-fold: 1) Compact 3D Scene Representation: We introduce BEV-Point as a highly compact intermediate representation, ensuring that the growth in VRAM usage for unbounded scenes remains constant, thus enabling unbounded city generation. 2) Spatial-aware Gaussian Attribute Decoder: We present spatial-aware BEV-Point decoder to produce 3D Gaussian attributes, which leverages Point Serializer to integrate the structural and contextual characteristics of BEV points. Extensive experiments demonstrate that GaussianCity achieves state-of-the-art results in both drone-view and street-view 3D city generation. Notably, compared to CityDreamer, GaussianCity exhibits superior performance with a speedup of 60 times (10.72 FPS v.s. 0.18 FPS).
Authors: Xiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park, Ricardo Martin Brualla, Philipp Henzler
Abstract: Existing methods for relightable view synthesis -- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoints under a target illumination -- are based on inverse rendering, and attempt to disentangle the object geometry, materials, and lighting that explain the input images. Furthermore, this typically involves optimization through differentiable Monte Carlo rendering, which is brittle and computationally-expensive. In this work, we propose a simpler approach: we first relight each input image using an image diffusion model conditioned on lighting and then reconstruct a Neural Radiance Field (NeRF) with these relit images, from which we render novel views under the target lighting. We demonstrate that this strategy is surprisingly competitive and achieves state-of-the-art results on multiple relighting benchmarks. Please see our project page at https://illuminerf.github.io/.
Authors: Huseyin Tuna Erdinc, Rafael Orozco, Felix J. Herrmann
Abstract: In this study, we introduce a novel approach to synthesizing subsurface velocity models using diffusion generative models. Conventional methods rely on extensive, high-quality datasets, which are often inaccessible in subsurface applications. Our method leverages incomplete well and seismic observations to produce high-fidelity velocity samples without requiring fully sampled training datasets. The results demonstrate that our generative model accurately captures long-range structures, aligns with ground-truth velocity models, achieves high Structural Similarity Index (SSIM) scores, and provides meaningful uncertainty estimations. This approach facilitates realistic subsurface velocity synthesis, offering valuable inputs for full-waveform inversion and enhancing seismic-based subsurface modeling.
Authors: Danyi Huang, Ziang Liu, Yizhou Li
Abstract: One of the most effective ways to treat liver cancer is to perform precise liver resection surgery, the key step of which includes precise digital image segmentation of the liver and its tumor. However, traditional liver parenchymal segmentation techniques often face several challenges in performing liver segmentation: lack of precision, slow processing speed, and computational burden. These shortcomings limit the efficiency of surgical planning and execution. In this work, the model initially describes in detail a new image enhancement algorithm that enhances the key features of an image by adaptively adjusting the contrast and brightness of the image. Then, a deep learning-based segmentation network was introduced, which was specially trained on the enhanced images to optimize the detection accuracy of tumor regions. In addition, multi-scale analysis techniques have been incorporated into the study, allowing the model to analyze images at different resolutions to capture more nuanced tumor features. In the presentation of the experimental results, the study used the 3Dircadb dataset to test the effectiveness of the proposed method. The experimental results show that compared with the traditional image segmentation method, the new method using image enhancement technology has significantly improved the accuracy and recall rate of tumor identification.
Authors: M. J. J. de Grauw, E. Th. Scholten, E. J. Smit, M. J. C. M. Rutten, M. Prokop, B. van Ginneken, A. Hering
Abstract: Size measurements of tumor manifestations on follow-up CT examinations are crucial for evaluating treatment outcomes in cancer patients. Efficient lesion segmentation can speed up these radiological workflows. While numerous benchmarks and challenges address lesion segmentation in specific organs like the liver, kidneys, and lungs, the larger variety of lesion types encountered in clinical practice demands a more universal approach. To address this gap, we introduced the ULS23 benchmark for 3D universal lesion segmentation in chest-abdomen-pelvis CT examinations. The ULS23 training dataset contains 38,693 lesions across this region, including challenging pancreatic, colon and bone lesions. For evaluation purposes, we curated a dataset comprising 775 lesions from 284 patients. Each of these lesions was identified as a target lesion in a clinical context, ensuring diversity and clinical relevance within this dataset. The ULS23 benchmark is publicly accessible via uls23.grand-challenge.org, enabling researchers worldwide to assess the performance of their segmentation methods. Furthermore, we have developed and publicly released our baseline semi-supervised 3D lesion segmentation model. This model achieved an average Dice coefficient of 0.703 $\pm$ 0.240 on the challenge test set. We invite ongoing submissions to advance the development of future ULS models.
Authors: Eddy Solomon, Patricia M. Johnson, Zhengguo Tan, Radhika Tibrewala, Yvonne W. Lui, Florian Knoll, Linda Moy, Sungheon Gene Kim, Laura Heacock
Abstract: This data curation work introduces the first large-scale dataset of radial k-space and DICOM data for breast DCE-MRI acquired in diagnostic breast MRI exams. Our dataset includes case-level labels indicating patient age, menopause status, lesion status (negative, benign, and malignant), and lesion type for each case. The public availability of this dataset and accompanying reconstruction code will support research and development of fast and quantitative breast image reconstruction and machine learning methods.
Authors: Abhiram Anand Thiruthummal, Eun-jin Kim, Sergiy Shelyag
Abstract: Artificial neural networks (ANNs) are powerful tools capable of approximating any arbitrary mathematical function, but their interpretability remains limited, rendering them as black box models. To address this issue, numerous methods have been proposed to enhance the explainability and interpretability of ANNs. In this study, we introduce the application of information geometric framework to investigate phase transition-like behavior during the training of ANNs and relate these transitions to overfitting in certain models. The evolution of ANNs during training is studied by looking at the probability distribution of its parameters. Information geometry utilizing the principles of differential geometry, offers a unique perspective on probability and statistics by considering probability density functions as points on a Riemannian manifold. We create this manifold using a metric based on Fisher information to define a distance and a velocity. By parameterizing this distance and velocity with training steps, we study how the ANN evolves as training progresses. Utilizing standard datasets like MNIST, FMNIST and CIFAR-10, we observe a transition in the motion on the manifold while training the ANN and this transition is identified with over-fitting in the ANN models considered. The information geometric transitions observed is shown to be mathematically similar to the phase transitions in physics. Preliminary results showing finite-size scaling behavior is also provided. This work contributes to the development of robust tools for improving the explainability and interpretability of ANNs, aiding in our understanding of the variability of the parameters these complex models exhibit during training.
Authors: Sungwoo Park, Dongjun Kim, Ahmed Alaa
Abstract: In this paper, we introduce a new class of score-based generative models (SGMs) designed to handle high-cardinality data distributions by leveraging concepts from mean-field theory. We present mean-field chaos diffusion models (MF-CDMs), which address the curse of dimensionality inherent in high-cardinality data by utilizing the propagation of chaos property of interacting particles. By treating high-cardinality data as a large stochastic system of interacting particles, we develop a novel score-matching method for infinite-dimensional chaotic particle systems and propose an approximation scheme that employs a subdivision strategy for efficient training. Our theoretical and empirical results demonstrate the scalability and effectiveness of MF-CDMs for managing large high-cardinality data structures, such as 3D point clouds.
Authors: Qinting Jiang, Chuyang Ye, Dongyan Wei, Yuan Xue, Jingyan Jiang, Zhi Wang
Abstract: Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for multimedia applications. Existing test-time adaptation (TTA) methods are challenged by dynamic, multiple test distributions within batches. This work provides a new perspective on analyzing batch normalization techniques through class-related and class-irrelevant features, our observations reveal combining source and test batch normalization statistics robustly characterizes target distributions. However, test statistics must have high similarity. We thus propose Discover Your Neighbours (DYN), the first backward-free approach specialized for dynamic TTA. The core innovation is identifying similar samples via instance normalization statistics and clustering into groups which provides consistent class-irrelevant representations. Specifically, Our DYN consists of layer-wise instance statistics clustering (LISC) and cluster-aware batch normalization (CABN). In LISC, we perform layer-wise clustering of approximate feature samples at each BN layer by calculating the cosine similarity of instance normalization statistics across the batch. CABN then aggregates SBN and TCN statistics to collaboratively characterize the target distribution, enabling more robust representations. Experimental results validate DYN's robustness and effectiveness, demonstrating maintained performance under dynamic data stream patterns.
Authors: Aghiles Kebaili, J\'er\^ome Lapuyade-Lahorgue, Pierre Vera, Su Ruan
Abstract: Despite the increasing use of deep learning in medical image segmentation, the limited availability of annotated training data remains a major challenge due to the time-consuming data acquisition and privacy regulations. In the context of segmentation tasks, providing both medical images and their corresponding target masks is essential. However, conventional data augmentation approaches mainly focus on image synthesis. In this study, we propose a novel slice-based latent diffusion architecture designed to address the complexities of volumetric data generation in a slice-by-slice fashion. This approach extends the joint distribution modeling of medical images and their associated masks, allowing a simultaneous generation of both under data-scarce regimes. Our approach mitigates the computational complexity and memory expensiveness typically associated with diffusion models. Furthermore, our architecture can be conditioned by tumor characteristics, including size, shape, and relative position, thereby providing a diverse range of tumor variations. Experiments on a segmentation task using the BRATS2022 confirm the effectiveness of the synthesized volumes and masks for data augmentation.
Authors: Sana Ayromlou, Teresa Tsang, Purang Abolmaesumi, Xiaoxiao Li
Abstract: In real-world clinical settings, traditional deep learning-based classification methods struggle with diagnosing newly introduced disease types because they require samples from all disease classes for offline training. Class incremental learning offers a promising solution by adapting a deep network trained on specific disease classes to handle new diseases. However, catastrophic forgetting occurs, decreasing the performance of earlier classes when adapting the model to new data. Prior proposed methodologies to overcome this require perpetual storage of previous samples, posing potential practical concerns regarding privacy and storage regulations in healthcare. To this end, we propose a novel data-free class incremental learning framework that utilizes data synthesis on learned classes instead of data storage from previous classes. Our key contributions include acquiring synthetic data known as Continual Class-Specific Impression (CCSI) for previously inaccessible trained classes and presenting a methodology to effectively utilize this data for updating networks when introducing new classes. We obtain CCSI by employing data inversion over gradients of the trained classification model on previous classes starting from the mean image of each class inspired by common landmarks shared among medical images and utilizing continual normalization layers statistics as a regularizer in this pixel-wise optimization process. Subsequently, we update the network by combining the synthesized data with new class data and incorporate several losses, including an intra-domain contrastive loss to generalize the deep network trained on the synthesized data to real data, a margin loss to increase separation among previous classes and new ones, and a cosine-normalized cross-entropy loss to alleviate the adverse effects of imbalanced distributions in training data.
Authors: Xiangrui Kong, Thomas Braunl, Marco Fahmi, Yue Wang
Abstract: Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased remarkable abilities in processing and interacting with complex information. In autonomous driving, LLMs and MLLMs are extensively used, requiring access to sensitive vehicle data such as precise locations, images, and road conditions. These data are transmitted to an LLM-based inference cloud for advanced analysis. However, concerns arise regarding data security, as the protection against data and privacy breaches primarily depends on the LLM's inherent security measures, without additional scrutiny or evaluation of the LLM's inference outputs. Despite its importance, the security aspect of LLMs in autonomous driving remains underexplored. Addressing this gap, our research introduces a novel security framework for autonomous vehicles, utilizing a multi-agent LLM approach. This framework is designed to safeguard sensitive information associated with autonomous vehicles from potential leaks, while also ensuring that LLM outputs adhere to driving regulations and align with human values. It includes mechanisms to filter out irrelevant queries and verify the safety and reliability of LLM outputs. Utilizing this framework, we evaluated the security, privacy, and cost aspects of eleven large language model-driven autonomous driving cues. Additionally, we performed QA tests on these driving prompts, which successfully demonstrated the framework's efficacy.
Authors: Philip Sosnin, Mark N. M\"uller, Maximilian Baader, Calvin Tsay, Matthew Wicker
Abstract: Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. However, provably bounding model behavior under such attacks remains an open problem. In this work, we address this challenge and develop the first framework providing provable guarantees on the behavior of models trained with potentially manipulated data. In particular, our framework certifies robustness against untargeted and targeted poisoning as well as backdoor attacks for both input and label manipulations. Our method leverages convex relaxations to over-approximate the set of all possible parameter updates for a given poisoning threat model, allowing us to bound the set of all reachable parameters for any gradient-based learning algorithm. Given this set of parameters, we provide bounds on worst-case behavior, including model performance and backdoor success rate. We demonstrate our approach on multiple real-world datasets from applications including energy consumption, medical imaging, and autonomous driving.
Authors: Qi Qi, Quanqi Hu, Qihang Lin, Tianbao Yang
Abstract: This paper studies learning fair encoders in a self-supervised learning (SSL) setting, in which all data are unlabeled and only a small portion of them are annotated with sensitive attribute. Adversarial fair representation learning is well suited for this scenario by minimizing a contrastive loss over unlabeled data while maximizing an adversarial loss of predicting the sensitive attribute over the data with sensitive attribute. Nevertheless, optimizing adversarial fair representation learning presents significant challenges due to solving a non-convex non-concave minimax game. The complexity deepens when incorporating a global contrastive loss that contrasts each anchor data point against all other examples. A central question is ``{\it can we design a provable yet efficient algorithm for solving adversarial fair self-supervised contrastive learning}?'' Building on advanced optimization techniques, we propose a stochastic algorithm dubbed SoFCLR with a convergence analysis under reasonable conditions without requring a large batch size. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach for downstream classification with eight fairness notions.
Authors: David R Wessels, David M Knigge, Samuele Papa, Riccardo Valperga, Sharvaree Vadgama, Efstratios Gavves, Erik J Bekkers
Abstract: Recently, Neural Fields have emerged as a powerful modelling paradigm to represent continuous signals. In a conditional neural field, a field is represented by a latent variable that conditions the NeF, whose parametrisation is otherwise shared over an entire dataset. We propose Equivariant Neural Fields based on cross attention transformers, in which NeFs are conditioned on a geometric conditioning variable, a latent point cloud, that enables an equivariant decoding from latent to field. Our equivariant approach induces a steerability property by which both field and latent are grounded in geometry and amenable to transformation laws if the field transforms, the latent represents transforms accordingly and vice versa. Crucially, the equivariance relation ensures that the latent is capable of (1) representing geometric patterns faitfhully, allowing for geometric reasoning in latent space, (2) weightsharing over spatially similar patterns, allowing for efficient learning of datasets of fields. These main properties are validated using classification experiments and a verification of the capability of fitting entire datasets, in comparison to other non-equivariant NeF approaches. We further validate the potential of ENFs by demonstrate unique local field editing properties.
Authors: Mengfei Du, Binhao Wu, Zejun Li, Xuanjing Huang, Zhongyu Wei
Abstract: The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving the gap between current LVLMs and qualified embodied intelligence unknown. Therefore, we construct EmbSpatial-Bench, a benchmark for evaluating embodied spatial understanding of LVLMs.The benchmark is automatically derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective.Experiments expose the insufficient capacity of current LVLMs (even GPT-4V). We further present EmbSpatial-SFT, an instruction-tuning dataset designed to improve LVLMs' embodied spatial understanding.
Authors: Zijia Song, Zelin Zang, Yelin Wang, Guozheng Yang, Jiangbin Zheng, Kaicheng yu, Wanyu Chen, Stan Z. Li
Abstract: Multimodal fusion breaks through the barriers between diverse modalities and has already yielded numerous impressive performances. However, in various specialized fields, it is struggling to obtain sufficient alignment data for the training process, which seriously limits the use of previously elegant models. Thus, semi-supervised learning attempts to achieve multimodal alignment with fewer matched pairs but traditional methods like pseudo-labeling are difficult to apply in domains with no label information. To address these problems, we transform semi-supervised multimodal alignment into a manifold matching problem and propose a new method based on CLIP, named Gentle-CLIP. Specifically, we design a novel semantic density distribution loss to explore implicit semantic alignment information from unpaired multimodal data by constraining the latent representation distribution with fine granularity, thus eliminating the need for numerous strictly matched pairs. Meanwhile, we introduce multi-kernel maximum mean discrepancy as well as self-supervised contrastive loss to pull separate modality distributions closer and enhance the stability of the representation distribution. In addition, the contrastive loss used in CLIP is employed on the supervised matched data to prevent negative optimization. Extensive experiments conducted on a range of tasks in various fields, including protein, remote sensing, and the general vision-language field, demonstrate the effectiveness of our proposed Gentle-CLIP.
Authors: Sravanti Addepalli, Priyam Dey, R. Venkatesh Babu
Abstract: The need for abundant labelled data in supervised Adversarial Training (AT) has prompted the use of Self-Supervised Learning (SSL) techniques with AT. However, the direct application of existing SSL methods to adversarial training has been sub-optimal due to the increased training complexity of combining SSL with AT. A recent approach, DeACL, mitigates this by utilizing supervision from a standard SSL teacher in a distillation setting, to mimic supervised AT. However, we find that there is still a large performance gap when compared to supervised adversarial training, specifically on larger models. In this work, investigate the key reason for this gap and propose Projected Feature Adversarial Training (ProFeAT) to bridge the same. We show that the sub-optimal distillation performance is a result of mismatch in training objectives of the teacher and student, and propose to use a projection head at the student, that allows it to leverage weak supervision from the teacher while also being able to learn adversarially robust representations that are distinct from the teacher. We further propose appropriate attack and defense losses at the feature and projector, alongside a combination of weak and strong augmentations for the teacher and student respectively, to improve the training data diversity without increasing the training complexity. Through extensive experiments on several benchmark datasets and models, we demonstrate significant improvements in both clean and robust accuracy when compared to existing SSL-AT methods, setting a new state-of-the-art. We further report on-par/ improved performance when compared to TRADES, a popular supervised-AT method.
Authors: Ziqiang Liu, Feiteng Fang, Xi Feng, Xinrun Du, Chenhao Zhang, Zekun Wang, Yuelin Bai, Qixuan Zhao, Liyang Fan, Chengguang Gan, Hongquan Lin, Jiaming Li, Yuansheng Ni, Haihong Wu, Yaswanth Narsupalli, Zhigang Zheng, Chengming Li, Xiping Hu, Ruifeng Xu, Xiaojun Chen, Min Yang, Jiaheng Liu, Ruibo Liu, Wenhao Huang, Ge Zhang, Shiwen Ni
Abstract: The rapid advancements in the development of multimodal large language models (MLLMs) have consistently led to new breakthroughs on various benchmarks. In response, numerous challenging and comprehensive benchmarks have been proposed to more accurately assess the capabilities of MLLMs. However, there is a dearth of exploration of the higher-order perceptual capabilities of MLLMs. To fill this gap, we propose the Image Implication understanding Benchmark, II-Bench, which aims to evaluate the model's higher-order perception of images. Through extensive experiments on II-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on II-Bench. The pinnacle accuracy of MLLMs attains 74.8%, whereas human accuracy averages 90%, peaking at an impressive 98%. Subsequently, MLLMs perform worse on abstract and complex images, suggesting limitations in their ability to understand high-level semantics and capture image details. Finally, it is observed that most models exhibit enhanced accuracy when image sentiment polarity hints are incorporated into the prompts. This observation underscores a notable deficiency in their inherent understanding of image sentiment. We believe that II-Bench will inspire the community to develop the next generation of MLLMs, advancing the journey towards expert artificial general intelligence (AGI). II-Bench is publicly available at https://huggingface.co/datasets/m-a-p/II-Bench.
Authors: Khaled Alrfou, Tian Zhao
Abstract: Medical image segmentation is crucial for disease diagnosis and monitoring. Though effective, the current segmentation networks such as UNet struggle with capturing long-range features. More accurate models such as TransUNet, Swin-UNet, and CS-UNet have higher computation complexity. To address this problem, we propose GCtx-UNet, a lightweight segmentation architecture that can capture global and local image features with accuracy better or comparable to the state-of-the-art approaches. GCtx-UNet uses vision transformer that leverages global context self-attention modules joined with local self-attention to model long and short range spatial dependencies. GCtx-UNet is evaluated on the Synapse multi-organ abdominal CT dataset, the ACDC cardiac MRI dataset, and several polyp segmentation datasets. In terms of Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD) metrics, GCtx-UNet outperformed CNN-based and Transformer-based approaches, with notable gains in the segmentation of complex and small anatomical structures. Moreover, GCtx-UNet is much more efficient than the state-of-the-art approaches with smaller model size, lower computation workload, and faster training and inference speed, making it a practical choice for clinical applications.
Authors: Xin Wang, Zhiyun Song, Yitao Zhu, Sheng Wang, Lichi Zhang, Dinggang Shen, Qian Wang
Abstract: In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for both image visualization and subsequent analysis tasks, which often require isotropic voxel spacing. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. However, most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios. In this work, we propose a self-supervised super-resolution framework for inter-slice super-resolution of MR images. Our framework is first featured by pre-training on video dataset, as temporal correlation of videos is found beneficial for modeling the spatial relation among MR slices. Then, we use public high-quality MR dataset to fine-tune our pre-trained model, for enhancing awareness of our model to medical data. Finally, given a target dataset at hand, we utilize self-supervised fine-tuning to further ensure our model works well with user-specific super-resolution tasks. The proposed method demonstrates superior performance compared to other self-supervised methods and also holds the potential to benefit various downstream applications.
Authors: Zhongping Ji
Abstract: Recently, State Space Models (SSMs), with Mamba as a prime example, have shown great promise for long-range dependency modeling with linear complexity. Then, Vision Mamba and the subsequent architectures are presented successively, and they perform well on visual tasks. The crucial step of applying Mamba to visual tasks is to construct 2D visual features in sequential manners. To effectively organize and construct visual features within the 2D image space through 1D selective scan, we propose a novel Multi-Head Scan (MHS) module. The embeddings extracted from the preceding layer are projected into multiple lower-dimensional subspaces. Subsequently, within each subspace, the selective scan is performed along distinct scan routes. The resulting sub-embeddings, obtained from the multi-head scan process, are then integrated and ultimately projected back into the high-dimensional space. Moreover, we incorporate a Scan Route Attention (SRA) mechanism to enhance the module's capability to discern complex structures. To validate the efficacy of our module, we exclusively substitute the 2D-Selective-Scan (SS2D) block in VM-UNet with our proposed module, and we train our models from scratch without using any pre-trained weights. The results indicate a significant improvement in performance while reducing the parameters of the original VM-UNet. The code for this study is publicly available at https://github.com/PixDeep/MHS-VM.
Authors: Peng Xia, Ze Chen, Juanxi Tian, Yangrui Gong, Ruibo Hou, Yue Xu, Zhenbang Wu, Zhiyuan Fan, Yiyang Zhou, Kangyu Zhu, Wenhao Zheng, Zhaoyang Wang, Xiao Wang, Xuchao Zhang, Chetan Bansal, Marc Niethammer, Junzhou Huang, Hongtu Zhu, Yun Li, Jimeng Sun, Zongyuan Ge, Gang Li, James Zou, Huaxiu Yao
Abstract: Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://github.com/richard-peng-xia/CARES.
Authors: Donghu Kim, Hojoon Lee, Kyungmin Lee, Dongyoon Hwang, Jaegul Choo
Abstract: Recently, various pre-training methods have been introduced in vision-based Reinforcement Learning (RL). However, their generalization ability remains unclear due to evaluations being limited to in-distribution environments and non-unified experimental setups. To address this, we introduce the Atari Pre-training Benchmark (Atari-PB), which pre-trains a ResNet-50 model on 10 million transitions from 50 Atari games and evaluates it across diverse environment distributions. Our experiments show that pre-training objectives focused on learning task-agnostic features (e.g., identifying objects and understanding temporal dynamics) enhance generalization across different environments. In contrast, objectives focused on learning task-specific knowledge (e.g., identifying agents and fitting reward functions) improve performance in environments similar to the pre-training dataset but not in varied ones. We publicize our codes, datasets, and model checkpoints at https://github.com/dojeon-ai/Atari-PB.
Authors: Fudong Lin, Kaleb Guillot, Summer Crawford, Yihe Zhang, Xu Yuan, Nian-Feng Tzeng
Abstract: Precise crop yield predictions are of national importance for ensuring food security and sustainable agricultural practices. While AI-for-science approaches have exhibited promising achievements in solving many scientific problems such as drug discovery, precipitation nowcasting, etc., the development of deep learning models for predicting crop yields is constantly hindered by the lack of an open and large-scale deep learning-ready dataset with multiple modalities to accommodate sufficient information. To remedy this, we introduce the CropNet dataset, the first terabyte-sized, publicly available, and multi-modal dataset specifically targeting climate change-aware crop yield predictions for the contiguous United States (U.S.) continent at the county level. Our CropNet dataset is composed of three modalities of data, i.e., Sentinel-2 Imagery, WRF-HRRR Computed Dataset, and USDA Crop Dataset, for over 2200 U.S. counties spanning 6 years (2017-2022), expected to facilitate researchers in developing versatile deep learning models for timely and precisely predicting crop yields at the county-level, by accounting for the effects of both short-term growing season weather variations and long-term climate change on crop yields. Besides, we develop the CropNet package, offering three types of APIs, for facilitating researchers in downloading the CropNet data on the fly over the time and region of interest, and flexibly building their deep learning models for accurate crop yield predictions. Extensive experiments have been conducted on our CropNet dataset via employing various types of deep learning solutions, with the results validating the general applicability and the efficacy of the CropNet dataset in climate change-aware crop yield predictions.
Authors: Zonghao Ying, Aishan Liu, Xianglong Liu, Dacheng Tao
Abstract: The recent release of GPT-4o has garnered widespread attention due to its powerful general capabilities. While its impressive performance is widely acknowledged, its safety aspects have not been sufficiently explored. Given the potential societal impact of risky content generated by advanced generative AI such as GPT-4o, it is crucial to rigorously evaluate its safety. In response to this question, this paper for the first time conducts a rigorous evaluation of GPT-4o against jailbreak attacks. Specifically, this paper adopts a series of multi-modal and uni-modal jailbreak attacks on 4 commonly used benchmarks encompassing three modalities (\ie, text, speech, and image), which involves the optimization of over 4,000 initial text queries and the analysis and statistical evaluation of nearly 8,000+ response on GPT-4o. Our extensive experiments reveal several novel observations: (1) In contrast to the previous version (such as GPT-4V), GPT-4o has enhanced safety in the context of text modality jailbreak; (2) The newly introduced audio modality opens up new attack vectors for jailbreak attacks on GPT-4o; (3) Existing black-box multimodal jailbreak attack methods are largely ineffective against GPT-4o and GPT-4V. These findings provide critical insights into the safety implications of GPT-4o and underscore the need for robust alignment guardrails in large models. Our code is available at \url{https://github.com/NY1024/Jailbreak_GPT4o}.
Authors: Matthias J. Ehrhardt, Zeljko Kereta, Jingwei Liang, Junqi Tang
Abstract: Stochastic optimisation algorithms are the de facto standard for machine learning with large amounts of data. Handling only a subset of available data in each optimisation step dramatically reduces the per-iteration computational costs, while still ensuring significant progress towards the solution. Driven by the need to solve large-scale optimisation problems as efficiently as possible, the last decade has witnessed an explosion of research in this area. Leveraging the parallels between machine learning and inverse problems has allowed harnessing the power of this research wave for solving inverse problems. In this survey, we provide a comprehensive account of the state-of-the-art in stochastic optimisation from the viewpoint of inverse problems. We present algorithms with diverse modalities of problem randomisation and discuss the roles of variance reduction, acceleration, higher-order methods, and other algorithmic modifications, and compare theoretical results with practical behaviour. We focus on the potential and the challenges for stochastic optimisation that are unique to inverse imaging problems and are not commonly encountered in machine learning. We conclude the survey with illustrative examples from imaging problems to examine the advantages and disadvantages that this new generation of algorithms bring to the field of inverse problems.
Authors: Shenghao Li, Luchao Pang, Xianglong Hu
Abstract: This paper presents a novel approach to visual simultaneous localization and mapping (SLAM) using multiple RGB-D cameras. The proposed method, Multicam-SLAM, significantly enhances the robustness and accuracy of SLAM systems by capturing more comprehensive spatial information from various perspectives. This method enables the accurate determination of pose relationships among multiple cameras without the need for overlapping fields of view. The proposed Muticam-SLAM includes a unique multi-camera model, a multi-keyframes structure, and several parallel SLAM threads. The multi-camera model allows for the integration of data from multiple cameras, while the multi-keyframes and parallel SLAM threads ensure efficient and accurate pose estimation and mapping. Extensive experiments in various environments demonstrate the superior accuracy and robustness of the proposed method compared to conventional single-camera SLAM systems. The results highlight the potential of the proposed Multicam-SLAM for more complex and challenging applications. Code is available at \url{https://github.com/AlterPang/Multi_ORB_SLAM}.
Authors: Ruodan Yan, Carola-Bibiane Sch\"onlieb, Chao Li
Abstract: Perfusion MRI (pMRI) offers valuable insights into tumor vascularity and promises to predict tumor genotypes, thus benefiting prognosis for glioma patients, yet effective models tailored to 4D pMRI are still lacking. This study presents the first attempt to model 4D pMRI using a GNN-based spatiotemporal model PerfGAT, integrating spatial information and temporal kinetics to predict Isocitrate DeHydrogenase (IDH) mutation status in glioma patients. Specifically, we propose a graph structure learning approach based on edge attention and negative graphs to optimize temporal correlations modeling. Moreover, we design a dual-attention feature fusion module to integrate spatiotemporal features while addressing tumor-related brain regions. Further, we develop a class-balanced augmentation methods tailored to spatiotemporal data, which could mitigate the common label imbalance issue in clinical datasets. Our experimental results demonstrate that the proposed method outperforms other state-of-the-art approaches, promising to model pMRI effectively for patient characterization.
Authors: Jordan Voas, Raymond Mooney, David Harwath
Abstract: We introduce Semantic Parsing in Contextual Environments (SPICE), a task designed to enhance artificial agents' contextual awareness by integrating multimodal inputs with prior contexts. SPICE goes beyond traditional semantic parsing by offering a structured, interpretable framework for dynamically updating an agent's knowledge with new information, mirroring the complexity of human communication. We develop the VG-SPICE dataset, crafted to challenge agents with visual scene graph construction from spoken conversational exchanges, highlighting speech and visual data integration. We also present the Audio-Vision Dialogue Scene Parser (AViD-SP) developed for use on VG-SPICE. These innovations aim to improve multimodal information processing and integration. Both the VG-SPICE dataset and the AViD-SP model are publicly available.
Authors: Oishi Banerjee, Hong-Yu Zhou, Subathra Adithan, Stephen Kwak, Kay Wu, Pranav Rajpurkar
Abstract: Recent advances in generative vision-language models (VLMs) have exciting potential implications for AI in radiology, yet VLMs are also known to produce hallucinations, nonsensical text, and other unwanted behaviors that can waste clinicians' time and cause patient harm. Drawing on recent work on direct preference optimization (DPO), we propose a simple method for modifying the behavior of pretrained VLMs performing radiology report generation by suppressing unwanted types of generations. We apply our method to the prevention of hallucinations of prior exams, addressing a long-established problem behavior in models performing chest X-ray report generation. Across our experiments, we find that DPO fine-tuning achieves a 3.2-4.8x reduction in lines hallucinating prior exams while maintaining model performance on clinical accuracy metrics. Our work is, to the best of our knowledge, the first work to apply DPO to medical VLMs, providing a data- and compute- efficient way to suppress problem behaviors while maintaining overall clinical accuracy.
Authors: Salma Kharrat, Marco Canini, Samuel Horvath
Abstract: This work tackles the challenges of data heterogeneity and communication limitations in decentralized federated learning. We focus on creating a collaboration graph that guides each client in selecting suitable collaborators for training personalized models that leverage their local data effectively. Our approach addresses these issues through a novel, communication-efficient strategy that enhances resource efficiency. Unlike traditional methods, our formulation identifies collaborators at a granular level by considering combinatorial relations of clients, enhancing personalization while minimizing communication overhead. We achieve this through a bi-level optimization framework that employs a constrained greedy algorithm, resulting in a resource-efficient collaboration graph for personalized learning. Extensive evaluation against various baselines across diverse datasets demonstrates the superiority of our method, named DPFL. DPFL consistently outperforms other approaches, showcasing its effectiveness in handling real-world data heterogeneity, minimizing communication overhead, enhancing resource efficiency, and building personalized models in decentralized federated learning scenarios.
Authors: Chaofan Tao, Fengmao Lv, Lixin Duan, Min Wu
Abstract: How to effectively learn from unlabeled data from the target domain is crucial for domain adaptation, as it helps reduce the large performance gap due to domain shift or distribution change. In this paper, we propose an easy-to-implement method dubbed MiniMax Entropy Networks (MMEN) based on adversarial learning. Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples with the help of labeled source samples. Specifically, we set an unfair multi-class classifier named categorical discriminator, which classifies source samples accurately but be confused about the categories of target samples. The generator learns a common subspace that aligns the unlabeled samples based on the target pseudo-labels. For MMEN, we also provide theoretical explanations to show that the learning of feature alignment reduces domain mismatch at the category level. Experimental results on various benchmark datasets demonstrate the effectiveness of our method over existing state-of-the-art baselines.
Authors: Tobias Schlosser, Frederik Beuth, Danny Kowerko
Abstract: Whereas conventional state-of-the-art image processing systems of recording and output devices almost exclusively utilize square arranged methods, biological models, however, suggest an alternative, evolutionarily-based structure. Inspired by the human visual perception system, hexagonal image processing in the context of machine learning offers a number of key advantages that can benefit both researchers and users alike. The hexagonal deep learning framework Hexnet leveraged in this contribution serves therefore the generation of hexagonal images by utilizing hexagonal deep neural networks (H-DNN). As the results of our created test environment show, the proposed models can surpass current approaches of conventional image generation. While resulting in a reduction of the models' complexity in the form of trainable parameters, they furthermore allow an increase of test rates in comparison to their square counterparts.
Authors: Jiawen Zhu, Xin Chen, Pengyu Zhang, Xinying Wang, Dong Wang, Wenda Zhao, Huchuan Lu
Abstract: The dominant trackers generate a fixed-size rectangular region based on the previous prediction or initial bounding box as the model input, i.e., search region. While this manner obtains promising tracking efficiency, a fixed-size search region lacks flexibility and is likely to fail in some cases, e.g., fast motion and distractor interference. Trackers tend to lose the target object due to the limited search region or experience interference from distractors due to the excessive search region. Drawing inspiration from the pattern humans track an object, we propose a novel tracking paradigm, called Search Region Regulation Tracking (SRRT) that applies a small eyereach when the target is captured and zooms out the search field when the target is about to be lost. SRRT applies a proposed search region regulator to estimate an optimal search region dynamically for each frame, by which the tracker can flexibly respond to transient changes in the location of object occurrences. To adapt the object's appearance variation during online tracking, we further propose a lockingstate determined updating strategy for reference frame updating. The proposed SRRT is concise without bells and whistles, yet achieves evident improvements and competitive results with other state-of-the-art trackers on eight benchmarks. On the large-scale LaSOT benchmark, SRRT improves SiamRPN++ and TransT with absolute gains of 4.6% and 3.1% in terms of AUC. The code and models will be released.
Authors: Futian Weng, Yuanting Ma, Jinghan Sun, Shijun Shan, Qiyuan Li, Jianping Zhu, Yang Wang, Yan Xu
Abstract: Dermatological diseases are among the most common disorders worldwide. This paper presents the first study of the interpretability and imbalanced semi-supervised learning of the multiclass intelligent skin diagnosis framework (ISDL) using 58,457 skin images with 10,857 unlabeled samples. Pseudo-labelled samples from minority classes have a higher probability at each iteration of class-rebalancing self-training, thereby promoting the utilization of unlabeled samples to solve the class imbalance problem. Our ISDL achieved a promising performance with an accuracy of 0.979, sensitivity of 0.975, specificity of 0.973, macro-F1 score of 0.974 and area under the receiver operating characteristic curve (AUC) of 0.999 for multi-label skin disease classification. The Shapley Additive explanation (SHAP) method is combined with our ISDL to explain how the deep learning model makes predictions. This finding is consistent with the clinical diagnosis. We also proposed a sampling distribution optimisation strategy to select pseudo-labelled samples in a more effective manner using ISDLplus. Furthermore, it has the potential to relieve the pressure placed on professional doctors, as well as help with practical issues associated with a shortage of such doctors in rural areas.
Authors: Junyu Chen, Jie An, Hanjia Lyu, Christopher Kanan, Jiebo Luo
Abstract: Visual-textual sentiment analysis aims to predict sentiment with the input of a pair of image and text, which poses a challenge in learning effective features for diverse input images. To address this, we propose a holistic method that achieves robust visual-textual sentiment analysis by exploiting a rich set of powerful pre-trained visual and textual prior models. The proposed method consists of four parts: (1) a visual-textual branch to learn features directly from data for sentiment analysis, (2) a visual expert branch with a set of pre-trained "expert" encoders to extract selected semantic visual features, (3) a CLIP branch to implicitly model visual-textual correspondence, and (4) a multimodal feature fusion network based on BERT to fuse multimodal features and make sentiment predictions. Extensive experiments on three datasets show that our method produces better visual-textual sentiment analysis performance than existing methods.
Authors: Tejas Karkera, Chandranath Adak, Soumi Chattopadhyay, Muhammad Saqib
Abstract: Diabetic Retinopathy (DR) is considered one of the significant concerns worldwide, primarily due to its impact on causing vision loss among most people with diabetes. The severity of DR is typically comprehended manually by ophthalmologists from fundus photography-based retina images. This paper deals with an automated understanding of the severity stages of DR. In the literature, researchers have focused on this automation using traditional machine learning-based algorithms and convolutional architectures. However, the past works hardly focused on essential parts of the retinal image to improve the model performance. In this study, we adopt and fine-tune transformer-based learning models to capture the crucial features of retinal images for a more nuanced understanding of DR severity. Additionally, we explore the effectiveness of image transformers to infer the degree of DR severity from fundus photographs. For experiments, we utilized the publicly available APTOS-2019 blindness detection dataset, where the performances of the transformer-based models were quite encouraging.
Authors: Chang Liu, Wenzhao Xiang, Yuan He, Hui Xue, Shibao Zheng, Hang Su
Abstract: Deep neural networks (DNNs) may suffer from significantly degenerated performance when the training and test data are of different underlying distributions. Despite the importance of model generalization to out-of-distribution (OOD) data, the accuracy of state-of-the-art (SOTA) models on OOD data can plummet. Recent work has demonstrated that regular or off-manifold adversarial examples, as a special case of data augmentation, can be used to improve OOD generalization. Inspired by this, we theoretically prove that on-manifold adversarial examples can better benefit OOD generalization. Nevertheless, it is nontrivial to generate on-manifold adversarial examples because the real manifold is generally complex. To address this issue, we proposed a novel method of Augmenting data with Adversarial examples via a Wavelet module (AdvWavAug), an on-manifold adversarial data augmentation technique that is simple to implement. In particular, we project a benign image into a wavelet domain. With the assistance of the sparsity characteristic of wavelet transformation, we can modify an image on the estimated data manifold. We conduct adversarial augmentation based on AdvProp training framework. Extensive experiments on different models and different datasets, including ImageNet and its distorted versions, demonstrate that our method can improve model generalization, especially on OOD data. By integrating AdvWavAug into the training process, we have achieved SOTA results on some recent transformer-based models.
Authors: Yining Shi, Kun Jiang, Jiusi Li, Zelin Qian, Junze Wen, Mengmeng Yang, Ke Wang, Diange Yang
Abstract: Grid-centric perception is a crucial field for mobile robot perception and navigation. Nonetheless, grid-centric perception is less prevalent than object-centric perception as autonomous vehicles need to accurately perceive highly dynamic, large-scale traffic scenarios and the complexity and computational costs of grid-centric perception are high. In recent years, the rapid development of deep learning techniques and hardware provides fresh insights into the evolution of grid-centric perception. The fundamental difference between grid-centric and object-centric pipeline lies in that grid-centric perception follows a geometry-first paradigm which is more robust to the open-world driving scenarios with endless long-tailed semantically-unknown obstacles. Recent researches demonstrate the great advantages of grid-centric perception, such as comprehensive fine-grained environmental representation, greater robustness to occlusion and irregular shaped objects, better ground estimation, and safer planning policies. There is also a growing trend that the capacity of occupancy networks are greatly expanded to 4D scene perception and prediction and latest techniques are highly related to new research topics such as 4D occupancy forecasting, generative AI and world models in the field of autonomous driving. Given the lack of current surveys for this rapidly expanding field, we present a hierarchically-structured review of grid-centric perception for autonomous vehicles. We organize previous and current knowledge of occupancy grid techniques along the main vein from 2D BEV grids to 3D occupancy to 4D occupancy forecasting. We additionally summarize label-efficient occupancy learning and the role of grid-centric perception in driving systems. Lastly, we present a summary of the current research trend and provide future outlooks.
Authors: Samuele Poppi, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Abstract: Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single round. We achieve this by modulating the network's components using memory matrices, enabling the network to demonstrate selective unlearning behavior for any class after training. By discovering weights that are specific to each class, our approach also recovers a representation of the classes which is explainable by design. We test the proposed framework on small- and medium-scale image classification datasets, with both convolution- and Transformer-based backbones, showcasing the potential for explainable solutions through unlearning.
Authors: Felix Ott, Lucas Heublein, David R\"ugamer, Bernd Bischl, Christopher Mutschler
Abstract: The localization of objects is a crucial task in various applications such as robotics, virtual and augmented reality, and the transportation of goods in warehouses. Recent advances in deep learning have enabled the localization using monocular visual cameras. While structure from motion (SfM) predicts the absolute pose from a point cloud, absolute pose regression (APR) methods learn a semantic understanding of the environment through neural networks. However, both fields face challenges caused by the environment such as motion blur, lighting changes, repetitive patterns, and feature-less structures. This study aims to address these challenges by incorporating additional information and regularizing the absolute pose using relative pose regression (RPR) methods. RPR methods suffer under different challenges, i.e., motion blur. The optical flow between consecutive images is computed using the Lucas-Kanade algorithm, and the relative pose is predicted using an auxiliary small recurrent convolutional network. The fusion of absolute and relative poses is a complex task due to the mismatch between the global and local coordinate systems. State-of-the-art methods fusing absolute and relative poses use pose graph optimization (PGO) to regularize the absolute pose predictions using relative poses. In this work, we propose recurrent fusion networks to optimally align absolute and relative pose predictions to improve the absolute pose prediction. We evaluate eight different recurrent units and construct a simulation environment to pre-train the APR and RPR networks for better generalized training. Additionally, we record a large database of different scenarios in a challenging large-scale indoor environment that mimics a warehouse with transportation robots. We conduct hyperparameter searches and experiments to show the effectiveness of our recurrent fusion method compared to PGO.
Authors: Junyu Chen, Jie An, Hanjia Lyu, Christopher Kanan, Jiebo Luo
Abstract: Assessing the artness of AI-generated images continues to be a challenge within the realm of image generation. Most existing metrics cannot be used to perform instance-level and reference-free artness evaluation. This paper presents ArtScore, a metric designed to evaluate the degree to which an image resembles authentic artworks by artists (or conversely photographs), thereby offering a novel approach to artness assessment. We first blend pre-trained models for photo and artwork generation, resulting in a series of mixed models. Subsequently, we utilize these mixed models to generate images exhibiting varying degrees of artness with pseudo-annotations. Each photorealistic image has a corresponding artistic counterpart and a series of interpolated images that range from realistic to artistic. This dataset is then employed to train a neural network that learns to estimate quantized artness levels of arbitrary images. Extensive experiments reveal that the artness levels predicted by ArtScore align more closely with human artistic evaluation than existing evaluation metrics, such as Gram loss and ArtFID.
Authors: Chenghao Li, Chaoning Zhang, Atish Waghwase, Lik-Hang Lee, Francois Rameau, Yang Yang, Sung-Ho Bae, Choong Seon Hong
Abstract: Generative AI (AIGC, a.k.a. AI generated content) has made significant progress in recent years, with text-guided content generation being the most practical as it facilitates interaction between human instructions and AIGC. Due to advancements in text-to-image and 3D modeling technologies (like NeRF), text-to-3D has emerged as a nascent yet highly active research field. Our work conducts the first comprehensive survey and follows up on subsequent research progress in the overall field, aiming to help readers interested in this direction quickly catch up with its rapid development. First, we introduce 3D data representations, including both Euclidean and non-Euclidean data. Building on this foundation, we introduce various foundational technologies and summarize how recent work combines these foundational technologies to achieve satisfactory text-to-3D results. Additionally, we present mainstream baselines and research directions in recent text-to-3D technology, including fidelity, efficiency, consistency, controllability, diversity, and applicability. Furthermore, we summarize the usage of text-to-3D technology in various applications, including avatar generation, texture generation, shape editing, and scene generation.
Authors: Raman Dutt, Linus Ericsson, Pedro Sanchez, Sotirios A. Tsaftaris, Timothy Hospedales
Abstract: Foundation models have significantly advanced medical image analysis through the pre-train fine-tune paradigm. Among various fine-tuning algorithms, Parameter-Efficient Fine-Tuning (PEFT) is increasingly utilized for knowledge transfer across diverse tasks, including vision-language and text-to-image generation. However, its application in medical image analysis is relatively unexplored due to the lack of a structured benchmark for evaluating PEFT methods. This study fills this gap by evaluating 17 distinct PEFT algorithms across convolutional and transformer-based networks on image classification and text-to-image generation tasks using six medical datasets of varying size, modality, and complexity. Through a battery of over 700 controlled experiments, our findings demonstrate PEFT's effectiveness, particularly in low data regimes common in medical imaging, with performance gains of up to 22% in discriminative and generative tasks. These recommendations can assist the community in incorporating PEFT into their workflows and facilitate fair comparisons of future PEFT methods, ensuring alignment with advancements in other areas of machine learning and AI.
Authors: Abanob Soliman, Fabien Bonardi, D\'esir\'e Sidib\'e, Samia Bouchafa
Abstract: This paper presents a robust approach for a visual parallel tracking and mapping (PTAM) system that excels in challenging environments. Our proposed method combines the strengths of heterogeneous multi-modal visual sensors, including stereo event-based and frame-based sensors, in a unified reference frame through a novel spatio-temporal synchronization of stereo visual frames and stereo event streams. We employ deep learning-based feature extraction and description for estimation to enhance robustness further. We also introduce an end-to-end parallel tracking and mapping optimization layer complemented by a simple loop-closure algorithm for efficient SLAM behavior. Through comprehensive experiments on both small-scale and large-scale real-world sequences of VECtor and TUM-VIE benchmarks, our proposed method (DH-PTAM) demonstrates superior performance in terms of robustness and accuracy in adverse conditions, especially in large-scale HDR scenarios. Our implementation's research-based Python API is publicly available on GitHub for further research and development: https://github.com/AbanobSoliman/DH-PTAM.
Authors: Muhammad Maaz, Hanoona Rasheed, Salman Khan, Fahad Shahbaz Khan
Abstract: Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of \emph{video-based conversation} by introducing Video-ChatGPT. It is a multimodal model that merges a video-adapted visual encoder with an LLM. The resulting model is capable of understanding and generating detailed conversations about videos. We introduce a new dataset of 100,000 video-instruction pairs used to train Video-ChatGPT acquired via manual and semi-automated pipeline that is easily scalable and robust to label noise. We also develop a quantitative evaluation framework for video-based dialogue models to objectively analyze the strengths and weaknesses of video-based dialogue models. Code: https://github.com/mbzuai-oryx/Video-ChatGPT.
Authors: Muhammad Salman Ikrar Musyaffa, Novanto Yudistira, Muhammad Arif Rahman, Jati Batoro
Abstract: The rich diversity of herbal plants in Indonesia holds immense potential as alternative resources for traditional healing and ethnobotanical practices. However, the dwindling recognition of herbal plants due to modernization poses a significant challenge in preserving this valuable heritage. The accurate identification of these plants is crucial for the continuity of traditional practices and the utilization of their nutritional benefits. Nevertheless, the manual identification of herbal plants remains a time-consuming task, demanding expert knowledge and meticulous examination of plant characteristics. In response, the application of computer vision emerges as a promising solution to facilitate the efficient identification of herbal plants. This research addresses the task of classifying Indonesian herbal plants through the implementation of transfer learning of Convolutional Neural Networks (CNN). To support our study, we curated an extensive dataset of herbal plant images from Indonesia with careful manual selection. Subsequently, we conducted rigorous data preprocessing, and classification utilizing transfer learning methodologies with five distinct models: ResNet, DenseNet, VGG, ConvNeXt, and Swin Transformer. Our comprehensive analysis revealed that ConvNeXt achieved the highest accuracy, standing at an impressive 92.5%. Additionally, we conducted testing using a scratch model, resulting in an accuracy of 53.9%. The experimental setup featured essential hyperparameters, including the ExponentialLR scheduler with a gamma value of 0.9, a learning rate of 0.001, the Cross-Entropy Loss function, the Adam optimizer, and a training epoch count of 50. This study's outcomes offer valuable insights and practical implications for the automated identification of Indonesian medicinal plants.
Authors: Michail Mamalakis, Heloise de Vareilles, Atheer AI-Manea, Samantha C. Mitchell, Ingrid Arartz, Lynn Egeland Morch-Johnsen, Jane Garrison, Jon Simons, Pietro Lio, John Suckling, Graham Murray
Abstract: Detecting the significant features of the learning process of an artificial intelligence framework in the entire training and validation dataset can be determined as 'global' explanations. Studies in the literature lack of accurate, low-complexity, and three-dimensional (3D) global explanations which are crucial in neuroimaging, a field with a complex representational space that demands more than basic two-dimensional interpretations. To fill this gap, we developed a novel explainable artificial intelligence (XAI) 3D-Framework that provides robust, faithful, and low-complexity global explanations. We evaluated our framework on various 3D deep learning networks trained, validated, and tested on a well-annotated cohort of 596 subjects from the TOP-OSLO study. The focus was on the presence and absence of the paracingulate sulcus, a variable feature of brain morphology correlated with psychotic conditions. Our proposed 3D-Framework outperforms traditional XAI methods in terms of faithfulness for global explanations. As a result, we were able to use these robust explanations to uncover new patterns that not only enhance the credibility and reliability of the training process but also reveal promising new biomarkers and significantly related sub-regions. For the first time, our developed 3D-Framework proposes a way for the scientific community to utilize global explanations to discover novel patterns in this specific neuroscientific application and beyond. This study can helps improve the trustworthiness of AI training processes and push the boundaries of our understanding by revealing new patterns in neuroscience and beyond.
Authors: Eui Jun Hwang, Huije Lee, Jong C. Park
Abstract: Gloss-free Sign Language Production (SLP) offers a direct translation of spoken language sentences into sign language, bypassing the need for gloss intermediaries. This paper presents the Sign language Vector Quantization Network, a novel approach to SLP that leverages Vector Quantization to derive discrete representations from sign pose sequences. Our method, rooted in both manual and non-manual elements of signing, supports advanced decoding methods and integrates latent-level alignment for enhanced linguistic coherence. Through comprehensive evaluations, we demonstrate superior performance of our method over prior SLP methods and highlight the reliability of Back-Translation and Fr\'echet Gesture Distance as evaluation metrics.
Authors: Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, Wei-Chen Chiu
Abstract: While image data starts to enjoy the simple-but-effective self-supervised learning scheme built upon masking and self-reconstruction objective thanks to the introduction of tokenization procedure and vision transformer backbone, convolutional neural networks as another important and widely-adopted architecture for image data, though having contrastive-learning techniques to drive the self-supervised learning, still face the difficulty of leveraging such straightforward and general masking operation to benefit their learning process significantly. In this work, we aim to alleviate the burden of including masking operation into the contrastive-learning framework for convolutional neural networks as an extra augmentation method. In addition to the additive but unwanted edges (between masked and unmasked regions) as well as other adverse effects caused by the masking operations for ConvNets, which have been discussed by prior works, we particularly identify the potential problem where for one view in a contrastive sample-pair the randomly-sampled masking regions could be overly concentrated on important/salient objects thus resulting in misleading contrastiveness to the other view. To this end, we propose to explicitly take the saliency constraint into consideration in which the masked regions are more evenly distributed among the foreground and background for realizing the masking-based augmentation. Moreover, we introduce hard negative samples by masking larger regions of salient patches in an input image. Extensive experiments conducted on various datasets, contrastive learning mechanisms, and downstream tasks well verify the efficacy as well as the superior performance of our proposed method with respect to several state-of-the-art baselines.
Authors: Hantao Zhou, Rui Yang, Yachao Zhang, Haoran Duan, Yawen Huang, Runze Hu, Xiu Li, Yefeng Zheng
Abstract: The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions. Regrettably, the commonly used parallel head often lacks omni perceptual capabilities, such as deformation perception, global perception and cross-task perception. Despite numerous methods attempting to enhance these abilities from a single aspect, achieving a comprehensive and unified solution remains a significant challenge. In response to this challenge, we develop an innovative detection head, termed UniHead, to unify three perceptual abilities simultaneously. More precisely, our approach (1) introduces deformation perception, enabling the model to adaptively sample object features; (2) proposes a Dual-axial Aggregation Transformer (DAT) to adeptly model long-range dependencies, thereby achieving global perception; and (3) devises a Cross-task Interaction Transformer (CIT) that facilitates interaction between the classification and localization branches, thus aligning the two tasks. As a plug-and-play method, the proposed UniHead can be conveniently integrated with existing detectors. Extensive experiments on the COCO dataset demonstrate that our UniHead can bring significant improvements to many detectors. For instance, the UniHead can obtain +2.7 AP gains in RetinaNet, +2.9 AP gains in FreeAnchor, and +2.1 AP gains in GFL. The code is available at https://github.com/zht8506/UniHead.
Authors: Xin Wang, Ziwei Luo, Jing Hu, Chengming Feng, Shu Hu, Bin Zhu, Xi Wu, Hongtu Zhu, Xin Li, Siwei Lyu
Abstract: Most existing Image-to-Image Translation (I2IT) methods generate images in a single run of a deep learning (DL) model. However, designing such a single-step model is always challenging, requiring a huge number of parameters and easily falling into bad global minimums and overfitting. In this work, we reformulate I2IT as a step-wise decision-making problem via deep reinforcement learning (DRL) and propose a novel framework that performs RL-based I2IT (RL-I2IT). The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image. Considering that it is challenging to handle high dimensional continuous state and action spaces in the conventional RL framework, we introduce meta policy with a new concept Plan to the standard Actor-Critic model, which is of a lower dimension than the original image and can facilitate the actor to generate a tractable high dimensional action. In the RL-I2IT framework, we also employ a task-specific auxiliary learning strategy to stabilize the training process and improve the performance of the corresponding task. Experiments on several I2IT tasks demonstrate the effectiveness and robustness of the proposed method when facing high-dimensional continuous action space problems. Our implementation of the RL-I2IT framework is available at https://github.com/Algolzw/SPAC-Deformable-Registration.
URLs: https://github.com/Algolzw/SPAC-Deformable-Registration.
Authors: Lukas Strack, Futa Waseda, Huy H. Nguyen, Yinqiang Zheng, Isao Echizen
Abstract: Infrared detection is an emerging technique for safety-critical tasks owing to its remarkable anti-interference capability. However, recent studies have revealed that it is vulnerable to physically-realizable adversarial patches, posing risks in its real-world applications. To address this problem, we are the first to investigate defense strategies against adversarial patch attacks on infrared detection, especially human detection. We propose a straightforward defense strategy, patch-based occlusion-aware detection (POD), which efficiently augments training samples with random patches and subsequently detects them. POD not only robustly detects people but also identifies adversarial patch locations. Surprisingly, while being extremely computationally efficient, POD easily generalizes to state-of-the-art adversarial patch attacks that are unseen during training. Furthermore, POD improves detection precision even in a clean (i.e., no-attack) situation due to the data augmentation effect. Our evaluation demonstrates that POD is robust to adversarial patches of various shapes and sizes. The effectiveness of our baseline approach is shown to be a viable defense mechanism for real-world infrared human detection systems, paving the way for exploring future research directions.
Authors: Guanqi Zhan, Chuanxia Zheng, Weidi Xie, Andrew Zisserman
Abstract: Our objective in this paper is to probe large vision models to determine to what extent they 'understand' different physical properties of the 3D scene depicted in an image. To this end, we make the following contributions: (i) We introduce a general and lightweight protocol to evaluate whether features of an off-the-shelf large vision model encode a number of physical 'properties' of the 3D scene, by training discriminative classifiers on the features for these properties. The probes are applied on datasets of real images with annotations for the property. (ii) We apply this protocol to properties covering scene geometry, scene material, support relations, lighting, and view-dependent measures, and large vision models including CLIP, DINOv1, DINOv2, VQGAN, Stable Diffusion. (iii) We find that features from Stable Diffusion and DINOv2 are good for discriminative learning of a number of properties, including scene geometry, support relations, shadows and depth, but less performant for occlusion and material, while outperforming DINOv1, CLIP and VQGAN for all properties. (iv) It is observed that different time steps of Stable Diffusion features, as well as different transformer layers of DINO/CLIP/VQGAN, are good at different properties, unlocking potential applications of 3D physical understanding.
Authors: Shijie Ma, Huayi Xu, Mengjian Li, Weidong Geng, Yaxiong Wang, Meng Wang
Abstract: This paper targets to enhance the diffusion-based text-to-video generation by improving the two input prompts, including the noise and the text. Accommodated with this goal, we propose POS, a training-free Prompt Optimization Suite to boost text-to-video models. POS is motivated by two observations: (1) Video generation shows instability in terms of noise. Given the same text, different noises lead to videos that differ significantly in terms of both frame quality and temporal consistency. This observation implies that there exists an optimal noise matched to each textual input; To capture the potential noise, we propose an optimal noise approximator to approach the potential optimal noise. Particularly, the optimal noise approximator initially searches a video that closely relates to the text prompt and then inverts it into the noise space to serve as an improved noise prompt for the textual input. (2) Improving the text prompt via LLMs often causes semantic deviation. Many existing text-to-vision works have utilized LLMs to improve the text prompts for generation enhancement. However, existing methods often neglect the semantic alignment between the original text and the rewritten one. In response to this issue, we design a semantic-preserving rewriter to impose contraints in both rewritng and denoising phrases to preserve the semantic consistency. Extensive experiments on popular benchmarks show that our POS can improve the text-to-video models with a clear margin. The code will be open-sourced.
Authors: Chen Long-fei, Robert B. Fisher
Abstract: A new application for real-time monitoring of the lack of movement in older adults' own homes is proposed, aiming to support people's lives and independence in their later years. A lightweight camera monitoring system, based on an RGB-D camera and a compact computer processor, was developed and piloted in community homes to observe the daily behavior of older adults. Instances of body inactivity were detected in everyday scenarios anonymously and unobtrusively. These events can be explained at a higher level, such as a loss of consciousness or physiological deterioration. The accuracy of the inactivity monitoring system is assessed, and statistics of inactivity events related to the daily behavior of older adults are provided. The results demonstrate that our method achieves high accuracy in inactivity detection across various environments and camera views. It outperforms existing state-of-the-art vision-based models in challenging conditions like dim room lighting and TV flickering. However, the proposed method does require some ambient light to function effectively.
Authors: Jiaqi Yang, Bo Du, Liangpei Zhang
Abstract: Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-spatial properties, synthetic aperture radar (SAR) to provide structural information about the Earth's surface, and light detection and ranging (LiDAR) to cover altitude information about ground elevation. Therefore, a natural idea is to combine multimodal images for refined and accurate land-cover interpretation. Although many efforts have been attempted to achieve multi-source remote sensing image classification, there are still three issues as follows: 1) indiscriminate feature representation without sufficiently considering modal heterogeneity, 2) abundant features and complex computations associated with modeling long-range dependencies, and 3) overfitting phenomenon caused by sparsely labeled samples. To overcome the above barriers, a transformer-based heterogeneously salient graph representation (THSGR) approach is proposed in this paper. First, a multimodal heterogeneous graph encoder is presented to encode distinctively non-Euclidean structural features from heterogeneous data. Then, a self-attention-free multi-convolutional modulator is designed for effective and efficient long-term dependency modeling. Finally, a mean forward is put forward in order to avoid overfitting. Based on the above structures, the proposed model is able to break through modal gaps to obtain differentiated graph representation with competitive time cost, even for a small fraction of training samples. Experiments and analyses on three benchmark datasets with various state-of-the-art (SOTA) methods show the performance of the proposed approach.
Authors: Nikolaos Ioannis Bountos, Maria Sdraka, Angelos Zavras, Ilektra Karasante, Andreas Karavias, Themistocles Herekakis, Angeliki Thanasou, Dimitrios Michail, Ioannis Papoutsis
Abstract: Global floods, exacerbated by climate change, pose severe threats to human life, infrastructure, and the environment. Recent catastrophic events in Pakistan and New Zealand underscore the urgent need for precise flood mapping to guide restoration efforts, understand vulnerabilities, and prepare for future occurrences. While Synthetic Aperture Radar (SAR) remote sensing offers day-and-night, all-weather imaging capabilities, its application in deep learning for flood segmentation is limited by the lack of large annotated datasets. To address this, we introduce Kuro Siwo, a manually annotated multi-temporal dataset, spanning 43 flood events globally. Our dataset maps more than 338 billion $m^2$ of land, with 33 billion designated as either flooded areas or permanent water bodies. Kuro Siwo includes a highly processed product optimized for flood mapping based on SAR Ground Range Detected, and a primal SAR Single Look Complex product with minimal preprocessing, designed to promote research on the exploitation of both the phase and amplitude information and to offer maximum flexibility for downstream task preprocessing. To leverage advances in large scale self-supervised pretraining methods for remote sensing data, we augment Kuro Siwo with a large unlabeled set of SAR samples. Finally, we provide an extensive benchmark, namely BlackBench, offering strong baselines for a diverse set of flood events from Europe, America, Africa, Asia and Australia.
Authors: Niv Cohen, Issar Tzachor, Yedid Hoshen
Abstract: This paper proposes to use set features for detecting anomalies in samples that consist of unusual combinations of normal elements. Many leading methods discover anomalies by detecting an unusual part of a sample. For example, state-of-the-art segmentation-based approaches, first classify each element of the sample (e.g., image patch) as normal or anomalous and then classify the entire sample as anomalous if it contains anomalous elements. However, such approaches do not extend well to scenarios where the anomalies are expressed by an unusual combination of normal elements. In this paper, we overcome this limitation by proposing set features that model each sample by the distribution of its elements. We compute the anomaly score of each sample using a simple density estimation method, using fixed features. Our approach outperforms the previous state-of-the-art in image-level logical anomaly detection and sequence-level time series anomaly detection.
Authors: Xin Liu, Yichen Zhu, Jindong Gu, Yunshi Lan, Chao Yang, Yu Qiao
Abstract: The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models (MLLMs) can be easily compromised by query-relevant images, as if the text query itself were malicious. To address this, we introduce MM-SafetyBench, a comprehensive framework designed for conducting safety-critical evaluations of MLLMs against such image-based manipulations. We have compiled a dataset comprising 13 scenarios, resulting in a total of 5,040 text-image pairs. Our analysis across 12 state-of-the-art models reveals that MLLMs are susceptible to breaches instigated by our approach, even when the equipped LLMs have been safety-aligned. In response, we propose a straightforward yet effective prompting strategy to enhance the resilience of MLLMs against these types of attacks. Our work underscores the need for a concerted effort to strengthen and enhance the safety measures of open-source MLLMs against potential malicious exploits. The resource is available at \href{this https URL}{https://github.com/isXinLiu/MM-SafetyBench}.
Authors: Israt Zarin Era, Imtiaz Ahmed, Zhichao Liu, Srinjoy Das
Abstract: Foundation models are currently driving a paradigm shift in computer vision tasks for various fields including biology, astronomy, and robotics among others, leveraging user-generated prompts to enhance their performance. In the manufacturing domain, accurate image-based defect segmentation is imperative to ensure product quality and facilitate real-time process control. However, such tasks are often characterized by multiple challenges including the absence of labels and the requirement for low latency inference among others. To address these issues, we construct a framework for image segmentation using a state-of-the-art Vision Transformer (ViT) based Foundation model (Segment Anything Model) with a novel multi-point prompt generation scheme using unsupervised clustering. Utilizing our framework we perform porosity segmentation in a case study of laser-based powder bed fusion (L-PBF) and obtain high accuracy without using any labeled data to guide the prompt tuning process. By capitalizing on lightweight foundation model inference combined with unsupervised prompt generation, we envision constructing a real-time anomaly detection pipeline that could revolutionize current laser additive manufacturing processes, thereby facilitating the shift towards Industry 4.0 and promoting defect-free production along with operational efficiency.
Authors: Guoqing Yang, Zhiming Luo, Jianzhe Gao, Yingxin Lai, Kun Yang, Yifan He, Shaozi Li
Abstract: Human behavior anomaly detection aims to identify unusual human actions, playing a crucial role in intelligent surveillance and other areas. The current mainstream methods still adopt reconstruction or future frame prediction techniques. However, reconstructing or predicting low-level pixel features easily enables the network to achieve overly strong generalization ability, allowing anomalies to be reconstructed or predicted as effectively as normal data. Different from their methods, inspired by the Student-Teacher Network, we propose a novel framework called the Multilevel Guidance-Exploration Network(MGENet), which detects anomalies through the difference in high-level representation between the Guidance and Exploration network. Specifically, we first utilize the pre-trained Normalizing Flow that takes skeletal keypoints as input to guide an RGB encoder, which takes unmasked RGB frames as input, to explore motion latent features. Then, the RGB encoder guides the mask encoder, which takes masked RGB frames as input, to explore the latent appearance feature. Additionally, we design a Behavior-Scene Matching Module(BSMM) to detect scene-related behavioral anomalies. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on ShanghaiTech and UBnormal datasets.
Authors: Haofei Xu, Anpei Chen, Yuedong Chen, Christos Sakaridis, Yulun Zhang, Marc Pollefeys, Andreas Geiger, Fisher Yu
Abstract: We present Multi-Baseline Radiance Fields (MuRF), a general feed-forward approach to solving sparse view synthesis under multiple different baseline settings (small and large baselines, and different number of input views). To render a target novel view, we discretize the 3D space into planes parallel to the target image plane, and accordingly construct a target view frustum volume. Such a target volume representation is spatially aligned with the target view, which effectively aggregates relevant information from the input views for high-quality rendering. It also facilitates subsequent radiance field regression with a convolutional network thanks to its axis-aligned nature. The 3D context modeled by the convolutional network enables our method to synthesis sharper scene structures than prior works. Our MuRF achieves state-of-the-art performance across multiple different baseline settings and diverse scenarios ranging from simple objects (DTU) to complex indoor and outdoor scenes (RealEstate10K and LLFF). We also show promising zero-shot generalization abilities on the Mip-NeRF 360 dataset, demonstrating the general applicability of MuRF.
Authors: Vsevolod Skorokhodov, Darya Drozdova, Dmitry Yudin
Abstract: Recently, there has been an increased interest in NeRF methods which reconstruct differentiable representation of three-dimensional scenes. One of the main limitations of such methods is their inability to assess the confidence of the model in its predictions. In this paper, we propose a new neural network model for the formation of extended vector representations, called uSF, which allows the model to predict not only color and semantic label of each point, but also estimate the corresponding values of uncertainty. We show that with a small number of images available for training, a model quantifying uncertainty performs better than a model without such functionality. Code of the uSF approach is publicly available at https://github.com/sevashasla/usf/.
Authors: Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu
Abstract: Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new samples (e.g., images). However, their remarkable generative performance is hindered by slow training and sampling. This is due to the necessity of tracking extensive forward and reverse diffusion trajectories, and employing a large model with numerous parameters across multiple timesteps (i.e., noise levels). To tackle these challenges, we present a multi-stage framework inspired by our empirical findings. These observations indicate the advantages of employing distinct parameters tailored to each timestep while retaining universal parameters shared across all time steps. Our approach involves segmenting the time interval into multiple stages where we employ custom multi-decoder U-net architecture that blends time-dependent models with a universally shared encoder. Our framework enables the efficient distribution of computational resources and mitigates inter-stage interference, which substantially improves training efficiency. Extensive numerical experiments affirm the effectiveness of our framework, showcasing significant training and sampling efficiency enhancements on three state-of-the-art diffusion models, including large-scale latent diffusion models. Furthermore, our ablation studies illustrate the impact of two important components in our framework: (i) a novel timestep clustering algorithm for stage division, and (ii) an innovative multi-decoder U-net architecture, seamlessly integrating universal and customized hyperparameters.
Authors: Yao Huang, Yinpeng Dong, Shouwei Ruan, Xiao Yang, Hang Su, Xingxing Wei
Abstract: Compared with transferable untargeted attacks, transferable targeted adversarial attacks could specify the misclassification categories of adversarial samples, posing a greater threat to security-critical tasks. In the meanwhile, 3D adversarial samples, due to their potential of multi-view robustness, can more comprehensively identify weaknesses in existing deep learning systems, possessing great application value. However, the field of transferable targeted 3D adversarial attacks remains vacant. The goal of this work is to develop a more effective technique that could generate transferable targeted 3D adversarial examples, filling the gap in this field. To achieve this goal, we design a novel framework named TT3D that could rapidly reconstruct from few multi-view images into Transferable Targeted 3D textured meshes. While existing mesh-based texture optimization methods compute gradients in the high-dimensional mesh space and easily fall into local optima, leading to unsatisfactory transferability and distinct distortions, TT3D innovatively performs dual optimization towards both feature grid and Multi-layer Perceptron (MLP) parameters in the grid-based NeRF space, which significantly enhances black-box transferability while enjoying naturalness. Experimental results show that TT3D not only exhibits superior cross-model transferability but also maintains considerable adaptability across different renders and vision tasks. More importantly, we produce 3D adversarial examples with 3D printing techniques in the real world and verify their robust performance under various scenarios.
Authors: Zhiming Hu, Jiahui Xu, Syn Schmitt, Andreas Bulling
Abstract: Human eye gaze plays a significant role in many virtual and augmented reality (VR/AR) applications, such as gaze-contingent rendering, gaze-based interaction, or eye-based activity recognition. However, prior works on gaze analysis and prediction have only explored eye-head coordination and were limited to human-object interactions. We first report a comprehensive analysis of eye-body coordination in various human-object and human-human interaction activities based on four public datasets collected in real-world (MoGaze), VR (ADT), as well as AR (GIMO and EgoBody) environments. We show that in human-object interactions, e.g. pick and place, eye gaze exhibits strong correlations with full-body motion while in human-human interactions, e.g. chat and teach, a person's gaze direction is correlated with the body orientation towards the interaction partner. Informed by these analyses we then present Pose2Gaze, a novel eye-body coordination model that uses a convolutional neural network and a spatio-temporal graph convolutional neural network to extract features from head direction and full-body poses, respectively, and then uses a convolutional neural network to predict eye gaze. We compare our method with state-of-the-art methods that predict eye gaze only from head movements and show that Pose2Gaze outperforms these baselines with an average improvement of 24.0% on MoGaze, 10.1% on ADT, 21.3% on GIMO, and 28.6% on EgoBody in mean angular error, respectively. We also show that our method significantly outperforms prior methods in the sample downstream task of eye-based activity recognition. These results underline the significant information content available in eye-body coordination during daily activities and open up a new direction for gaze prediction.
Authors: Yunye Gong, Robik Shrestha, Jared Claypoole, Michael Cogswell, Arijit Ray, Christopher Kanan, Ajay Divakaran
Abstract: We propose a novel VQA dataset, BloomVQA, to facilitate comprehensive evaluation of large vision-language models on comprehension tasks. Unlike current benchmarks that often focus on fact-based memorization and simple reasoning tasks without theoretical grounding, we collect multiple-choice samples based on picture stories that reflect different levels of comprehension, as laid out in Bloom's Taxonomy, a classic framework for learning assessment widely adopted in education research. Our data maps to a novel hierarchical graph representation which enables automatic data augmentation and novel measures characterizing model consistency. We perform graded evaluation and reliability analysis on recent multi-modal models. In comparison to low-level tasks, we observe decreased performance on tasks requiring advanced comprehension and cognitive skills with up to 38.0\% drop in VQA accuracy. In comparison to earlier models, GPT-4V demonstrates improved accuracy over all comprehension levels and shows a tendency of bypassing visual inputs especially for higher-level tasks. Current models also show consistency patterns misaligned with human comprehension in various scenarios, demonstrating the need for improvement based on theoretically-grounded criteria.
Authors: Lokesh Veeramacheneni (University of Bonn), Moritz Wolter (University of Bonn), Hildegard Kuehne (University of Bonn), Juergen Gall (University of Bonn)
Abstract: Modern metrics for generative learning like Fr\'echet Inception Distance (FID) demonstrate impressive performance. However, they suffer from various shortcomings, like a bias towards specific generators and datasets. To address this problem, we propose the Fr\'echet Wavelet Distance (FWD) as a domain-agnostic metric based on Wavelet Packet Transform ($W_p$). FWD provides a sight across a broad spectrum of frequencies in images with a high resolution, along with preserving both spatial and textural aspects. Specifically, we use Wp to project generated and dataset images to packet coefficient space. Further, we compute Fr\'echet distance with the resultant coefficients to evaluate the quality of a generator. This metric is general-purpose and dataset-domain agnostic, as it does not rely on any pre-trained network while being more interpretable because of frequency band transparency. We conclude with an extensive evaluation of a wide variety of generators across various datasets that the proposed FWD is able to generalize and improve robustness to domain shift and various corruptions compared to other metrics.
Authors: Jiawei Ren, Liang Pan, Jiaxiang Tang, Chi Zhang, Ang Cao, Gang Zeng, Ziwei Liu
Abstract: 4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality of details. In this paper, we introduce DreamGaussian4D (DG4D), an efficient 4D generation framework that builds on Gaussian Splatting (GS). Our key insight is that combining explicit modeling of spatial transformations with static GS makes an efficient and powerful representation for 4D generation. Moreover, video generation methods have the potential to offer valuable spatial-temporal priors, enhancing the high-quality 4D generation. Specifically, we propose an integral framework with two major modules: 1) Image-to-4D GS - we initially generate static GS with DreamGaussianHD, followed by HexPlane-based dynamic generation with Gaussian deformation; and 2) Video-to-Video Texture Refinement - we refine the generated UV-space texture maps and meanwhile enhance their temporal consistency by utilizing a pre-trained image-to-video diffusion model. Notably, DG4D reduces the optimization time from several hours to just a few minutes, allows the generated 3D motion to be visually controlled, and produces animated meshes that can be realistically rendered in 3D engines.
Authors: Shan Yang, Yongfei Zhang
Abstract: Multimodal large language models (MLLM) have achieved satisfactory results in many tasks. However, their performance in the task of ReID (ReID) has not been explored to date. This paper will investigate how to adapt them for the task of ReID. An intuitive idea is to fine-tune MLLM with ReID image-text datasets, and then use their visual encoder as a backbone for ReID. However, there still exist two apparent issues: (1) Designing instructions for ReID, MLLMs may overfit specific instructions, and designing a variety of instructions will lead to higher costs. (2) When fine-tuning the visual encoder of a MLLM, it is not trained synchronously with the ReID task. As a result, the effectiveness of the visual encoder fine-tuning cannot be directly reflected in the performance of the ReID task. To address these problems, this paper proposes MLLMReID: Multimodal Large Language Model-based ReID. Firstly, we proposed Common Instruction, a simple approach that leverages the essence ability of LLMs to continue writing, avoiding complex and diverse instruction design. Secondly, we propose a multi-task learning-based synchronization module to ensure that the visual encoder of the MLLM is trained synchronously with the ReID task. The experimental results demonstrate the superiority of our method.
Authors: Jiu-Cheng Xie, Jun Yang, Wenqing Wang, Feng Xu, Jiang Xiong, Hao Gao
Abstract: Face aging has received continuous research attention over the past two decades. Although previous works on this topic have achieved impressive success, two longstanding problems remain unsettled: 1) generating diverse and plausible facial aging patterns at the target age stage; 2) measuring the rationality of identity variation between the original portrait and its syntheses with age progression or regression. In this paper, we introduce ${\rm{DLAT}}^{\boldsymbol{+}}$ to realize Diverse and Lifespan Age Transformation on human faces, where the diversity jointly manifests in the transformation of facial textures and shapes. Apart from the diversity mechanism embedded in the model, multiple consistency restrictions are leveraged to keep it away from counterfactual aging syntheses. Moreover, we propose a new metric to assess the rationality of Identity Deviation under Age Gaps (IDAG) between the input face and its series of age-transformed generations, which is based on statistical laws summarized from plenty of genuine face-aging data. Extensive experimental results demonstrate the uniqueness and effectiveness of our method in synthesizing diverse and perceptually reasonable faces across the whole lifetime.
Authors: Jacob Fein-Ashley, Tian Ye, Sachini Wickramasinghe, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna
Abstract: Image classifiers often rely on convolutional neural networks (CNN) for their tasks, which are inherently more heavyweight than multilayer perceptrons (MLPs), which can be problematic in real-time applications. Additionally, many image classification models work on both RGB and grayscale datasets. Classifiers that operate solely on grayscale images are much less common. Grayscale image classification has diverse applications, including but not limited to medical image classification and synthetic aperture radar (SAR) automatic target recognition (ATR). Thus, we present a novel grayscale (single channel) image classification approach using a vectorized view of images. We exploit the lightweightness of MLPs by viewing images as a vector and reducing our problem setting to the grayscale image classification setting. We find that using a single graph convolutional layer batch-wise increases accuracy and reduces variance in the performance of our model. Moreover, we develop a customized accelerator on FPGA for the proposed model with several optimizations to improve its performance. Our experimental results on benchmark grayscale image datasets demonstrate the effectiveness of the proposed model, achieving vastly lower latency (up to 16$\times$ less) and competitive or leading performance compared to other state-of-the-art image classification models on various domain-specific grayscale image classification datasets.
Authors: Michal Shlapentokh-Rothman, Ansel Blume, Yao Xiao, Yuqun Wu, Sethuraman T V, Heyi Tao, Jae Yong Lee, Wilfredo Torres, Yu-Xiong Wang, Derek Hoiem
Abstract: We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images.
Authors: Idil Esen Zulfikar, Sabarinath Mahadevan, Paul Voigtlaender, Bastian Leibe
Abstract: Current state-of-the-art Video Object Segmentation (VOS) methods rely on dense per-object mask annotations both during training and testing. This requires time-consuming and costly video annotation mechanisms. We propose a novel Point-VOS task with a spatio-temporally sparse point-wise annotation scheme that substantially reduces the annotation effort. We apply our annotation scheme to two large-scale video datasets with text descriptions and annotate over 19M points across 133K objects in 32K videos. Based on our annotations, we propose a new Point-VOS benchmark, and a corresponding point-based training mechanism, which we use to establish strong baseline results. We show that existing VOS methods can easily be adapted to leverage our point annotations during training, and can achieve results close to the fully-supervised performance when trained on pseudo-masks generated from these points. In addition, we show that our data can be used to improve models that connect vision and language, by evaluating it on the Video Narrative Grounding (VNG) task. We will make our code and annotations available at https://pointvos.github.io.
Authors: Amelia Jim\'enez-S\'anchez, Natalia-Rozalia Avlona, Dovile Juodelyte, Th\'eo Sourget, Caroline Vang-Larsen, Anna Rogers, Hubert Dariusz Zaj\k{a}c, Veronika Cheplygina
Abstract: Medical Imaging (MI) datasets are fundamental to artificial intelligence in healthcare. The accuracy, robustness, and fairness of diagnostic algorithms depend on the data (and its quality) used to train and evaluate the models. MI datasets used to be proprietary, but have become increasingly available to the public, including on community-contributed platforms (CCPs) like Kaggle or HuggingFace. While open data is important to enhance the redistribution of data's public value, we find that the current CCP governance model fails to uphold the quality needed and recommended practices for sharing, documenting, and evaluating datasets. In this paper, we conduct an analysis of publicly available machine learning datasets on CCPs, discussing datasets' context, and identifying limitations and gaps in the current CCP landscape. We highlight differences between MI and computer vision datasets, particularly in the potentially harmful downstream effects from poor adoption of recommended dataset management practices. We compare the analyzed datasets across several dimensions, including data sharing, data documentation, and maintenance. We find vague licenses, lack of persistent identifiers and storage, duplicates, and missing metadata, with differences between the platforms. Our research contributes to efforts in responsible data curation and AI algorithms for healthcare.
Authors: Lorenzo Liso, Erik Sandstr\"om, Vladimir Yugay, Luc Van Gool, Martin R. Oswald
Abstract: Neural RGBD SLAM techniques have shown promise in dense Simultaneous Localization And Mapping (SLAM), yet face challenges such as error accumulation during camera tracking resulting in distorted maps. In response, we introduce Loopy-SLAM that globally optimizes poses and the dense 3D model. We use frame-to-model tracking using a data-driven point-based submap generation method and trigger loop closures online by performing global place recognition. Robust pose graph optimization is used to rigidly align the local submaps. As our representation is point based, map corrections can be performed efficiently without the need to store the entire history of input frames used for mapping as typically required by methods employing a grid based mapping structure. Evaluation on the synthetic Replica and real-world TUM-RGBD and ScanNet datasets demonstrate competitive or superior performance in tracking, mapping, and rendering accuracy when compared to existing dense neural RGBD SLAM methods. Project page: notchla.github.io/Loopy-SLAM.
Authors: Chris Hamblin, Thomas Fel, Srijani Saha, Talia Konkle, George Alvarez
Abstract: Efforts to decode neural network vision models necessitate a comprehensive grasp of both the spatial and semantic facets governing feature responses within images. Most research has primarily centered around attribution methods, which provide explanations in the form of heatmaps, showing where the model directs its attention for a given feature. However, grasping 'where' alone falls short, as numerous studies have highlighted the limitations of those methods and the necessity to understand 'what' the model has recognized at the focal point of its attention. In parallel, 'Feature visualization' offers another avenue for interpreting neural network features. This approach synthesizes an optimal image through gradient ascent, providing clearer insights into 'what' features respond to. However, feature visualizations only provide one global explanation per feature; they do not explain why features activate for particular images. In this work, we introduce a new method to the interpretability tool-kit, 'feature accentuation', which is capable of conveying both where and what in arbitrary input images induces a feature's response. At its core, feature accentuation is image-seeded (rather than noise-seeded) feature visualization. We find a particular combination of parameterization, augmentation, and regularization yields naturalistic visualizations that resemble the seed image and target feature simultaneously. Furthermore, we validate these accentuations are processed along a natural circuit by the model. We make our precise implementation of feature accentuation available to the community as the Faccent library, an extension of Lucent.
Authors: Jianrui Zhang, Mu Cai, Tengyang Xie, Yong Jae Lee
Abstract: We propose CounterCurate, a framework to comprehensively improve the visio-linguistic compositional reasoning capability for both contrastive and generative multimodal models. In particular, we identify two critical under-explored problems: the neglect of the physically grounded reasoning (counting and position understanding) and the potential of using highly capable text and image generation models for semantic counterfactual fine-tuning. Our work pioneers an approach that addresses these gaps. We first spotlight the near-chance performance of multimodal models like CLIP and LLaVA in physically grounded compositional reasoning. We then apply simple data augmentation using grounded image generation model GLIGEN to generate fine-tuning data, resulting in significant performance improvements: +33% and +37% for CLIP and LLaVA, respectively, on our newly curated Flickr30k-Positions benchmark. Moreover, we exploit the capabilities of high-performing text generation and image generation models, specifically GPT-4V and DALLE-3, to curate challenging semantic counterfactuals, thereby further enhancing compositional reasoning capabilities on benchmarks such as SugarCrepe, where CounterCurate outperforms GPT-4V. To facilitate future research, we release our code, dataset, benchmark, and checkpoints at https://countercurate.github.io.
Authors: Anja Deli\'c, Matej Grci\'c, Sini\v{s}a \v{S}egvi\'c
Abstract: Outlier detection is an essential capability in safety-critical applications of supervised visual recognition. Most of the existing methods deliver best results by encouraging standard closed-set models to produce low-confidence predictions in negative training data. However, that approach conflates prediction uncertainty with recognition of the negative class. We therefore reconsider direct prediction of K+1 logits that correspond to K groundtruth classes and one outlier class. This setup allows us to formulate a novel anomaly score as an ensemble of in-distribution uncertainty and the posterior of the outlier class which we term negative objectness. Now outliers can be independently detected due to i) high prediction uncertainty or ii) similarity with negative data. We embed our method into a dense prediction architecture with mask-level recognition over K+2 classes. The training procedure encourages the novel K+2-th class to learn negative objectness at pasted negative instances. Our models outperform the current state-of-the art on standard benchmarks for image-wide and pixel-level outlier detection with and without training on real negative data.
Authors: Chenying Liu, Conrad M Albrecht, Yi Wang, Xiao Xiang Zhu
Abstract: Compared to supervised deep learning, self-supervision provides remote sensing a tool to reduce the amount of exact, human-crafted geospatial annotations. While image-level information for unsupervised pretraining efficiently works for various classification downstream tasks, the performance on pixel-level semantic segmentation lags behind in terms of model accuracy. On the contrary, many easily available label sources (e.g., automatic labeling tools and land cover land use products) exist, which can provide a large amount of noisy labels for segmentation model training. In this work, we propose to exploit noisy semantic segmentation maps for model pretraining. Our experiments provide insights on robustness per network layer. The transfer learning settings test the cases when the pretrained encoders are fine-tuned for different label classes and decoders. The results from two datasets indicate the effectiveness of task-specific supervised pretraining with noisy labels. Our findings pave new avenues to improved model accuracy and novel pretraining strategies for efficient remote sensing image segmentation.
Authors: Minghan Li, Shuai Li, Xindong Zhang, Lei Zhang
Abstract: Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts throughout the entire video, making it hard to handle the different tasks with the same architecture. We make an attempt to address these issues and present a novel unified VS architecture, namely UniVS, by using prompts as queries. UniVS averages the prompt features of the target from previous frames as its initial query to explicitly decode masks, and introduces a target-wise prompt cross-attention layer in the mask decoder to integrate prompt features in the memory pool. By taking the predicted masks of entities from previous frames as their visual prompts, UniVS converts different VS tasks into prompt-guided target segmentation, eliminating the heuristic inter-frame matching process. Our framework not only unifies the different VS tasks but also naturally achieves universal training and testing, ensuring robust performance across different scenarios. UniVS shows a commendable balance between performance and universality on 10 challenging VS benchmarks, covering video instance, semantic, panoptic, object, and referring segmentation tasks. Code can be found at \url{https://github.com/MinghanLi/UniVS}.
Authors: Zhaorun Chen, Zhuokai Zhao, Hongyin Luo, Huaxiu Yao, Bo Li, Jiawei Zhou
Abstract: While large vision-language models (LVLMs) have demonstrated impressive capabilities in interpreting multi-modal contexts, they invariably suffer from object hallucinations (OH). We introduce HALC, a novel decoding algorithm designed to mitigate OH in LVLMs. HALC leverages distinct fine-grained optimal visual information in vision-language tasks and operates on both local and global contexts simultaneously. Specifically, HALC integrates a robust auto-focal grounding mechanism (locally) to correct hallucinated tokens on the fly, and a specialized beam search algorithm (globally) to significantly reduce OH while preserving text generation quality. Additionally, HALC can be integrated into any LVLMs as a plug-and-play module without extra training. Extensive experimental studies demonstrate the effectiveness of HALC in reducing OH, outperforming state-of-the-arts across four benchmarks.
Authors: Zishi Li, Xiaoxuan Ma, Qiuyan Shang, Wentao Zhu, Hai Ci, Yu Qiao, Yizhou Wang
Abstract: Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize the repetitiveness of actions, but their scalability is hindered due to the quadratic computational complexity. In this work, we introduce a novel approach that employs an action query representation to localize repeated action cycles with linear computational complexity. Based on this representation, we further develop two key components to tackle the essential challenges of temporal repetition counting. Firstly, to facilitate open-set action counting, we propose the dynamic update scheme on action queries. Unlike static action queries, this approach dynamically embeds video features into action queries, offering a more flexible and generalizable representation. Secondly, to distinguish between actions of interest and background noise actions, we incorporate inter-query contrastive learning to regularize the video representations corresponding to different action queries. As a result, our method significantly outperforms previous works, particularly in terms of long video sequences, unseen actions, and actions at various speeds. On the challenging RepCountA benchmark, we outperform the state-of-the-art method TransRAC by 26.5% in OBO accuracy, with a 22.7% mean error decrease and 94.1% computational burden reduction. Code is available at https://github.com/lizishi/DeTRC.
Authors: Sagi Eppel, Jolina Li, Manuel Drehwald, Alan Aspuru-Guzik
Abstract: Visual recognition of materials and their states is essential for understanding the physical world, from identifying wet regions on surfaces or stains on fabrics to detecting infected areas on plants or minerals in rocks. Collecting data that captures this vast variability is complex due to the scattered and gradual nature of material states. Manually annotating real-world images is constrained by cost and precision, while synthetic data, although accurate and inexpensive, lacks real-world diversity. This work aims to bridge this gap by infusing patterns automatically extracted from real-world images into synthetic data. Hence, patterns collected from natural images are used to generate and map materials into synthetic scenes. This unsupervised approach captures the complexity of the real world while maintaining the precision and scalability of synthetic data. We also present the first comprehensive benchmark for zero-shot material state segmentation, utilizing real-world images across a diverse range of domains, including food, soils, construction, plants, liquids, and more, each appears in various states such as wet, dry, infected, cooked, burned, and many others. The annotation includes partial similarity between regions with similar but not identical materials and hard segmentation of only identical material states. This benchmark eluded top foundation models, exposing the limitations of existing data collection methods. Meanwhile, nets trained on the infused data performed significantly better on this and related tasks. The dataset, code, and trained model are available. We also share 300,000 extracted textures and SVBRDF/PBR materials to facilitate future datasets generation.
Authors: Wenqi Zhu, Jiale Cao, Jin Xie, Shuangming Yang, Yanwei Pang
Abstract: Open-vocabulary video instance segmentation strives to segment and track instances belonging to an open set of categories in a video. The vision-language model Contrastive Language-Image Pre-training (CLIP) has shown robust zero-shot classification ability in image-level open-vocabulary task. In this paper, we propose a simple encoder-decoder network, called CLIP-VIS, to adapt CLIP for open-vocabulary video instance segmentation. Our CLIP-VIS adopts frozen CLIP image encoder and introduces three modules, including class-agnostic mask generation, temporal topK-enhanced matching, and weighted open-vocabulary classification. Given a set of initial queries, class-agnostic mask generation employs a transformer decoder to predict query masks and corresponding object scores and mask IoU scores. Then, temporal topK-enhanced matching performs query matching across frames by using K mostly matched frames. Finally, weighted open-vocabulary classification first generates query visual features with mask pooling, and second performs weighted classification using object scores and mask IoU scores.Our CLIP-VIS does not require the annotations of instance categories and identities. The experiments are performed on various video instance segmentation datasets, which demonstrate the effectiveness of our proposed method, especially on novel categories. When using ConvNeXt-B as backbone, our CLIP-VIS achieves the AP and APn scores of 32.2% and 40.2% on validation set of LV-VIS dataset, which outperforms OV2Seg by 11.1% and 23.9% respectively. We will release the source code and models at https://github.com/zwq456/CLIP-VIS.git.
Authors: R. Kenny Jones, Siddhartha Chaudhuri, Daniel Ritchie
Abstract: People grasp flexible visual concepts from a few examples. We explore a neurosymbolic system that learns how to infer programs that capture visual concepts in a domain-general fashion. We introduce Template Programs: programmatic expressions from a domain-specific language that specify structural and parametric patterns common to an input concept. Our framework supports multiple concept-related tasks, including few-shot generation and co-segmentation through parsing. We develop a learning paradigm that allows us to train networks that infer Template Programs directly from visual datasets that contain concept groupings. We run experiments across multiple visual domains: 2D layouts, Omniglot characters, and 3D shapes. We find that our method outperforms task-specific alternatives, and performs competitively against domain-specific approaches for the limited domains where they exist.
Authors: Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, Shenghua Gao
Abstract: 3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. However, 3DGS fails to accurately represent surfaces due to the multi-view inconsistent nature of 3D Gaussians. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks. Unlike 3D Gaussians, 2D Gaussians provide view-consistent geometry while modeling surfaces intrinsically. To accurately recover thin surfaces and achieve stable optimization, we introduce a perspective-correct 2D splatting process utilizing ray-splat intersection and rasterization. Additionally, we incorporate depth distortion and normal consistency terms to further enhance the quality of the reconstructions. We demonstrate that our differentiable renderer allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
Authors: Thomas Melistas, Nikos Spyrou, Nefeli Gkouti, Pedro Sanchez, Athanasios Vlontzos, Yannis Panagakis, Giorgos Papanastasiou, Sotirios A. Tsaftaris
Abstract: Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal. To perform realistic edits in domains such as natural image or medical imaging, modifications must respect causal relationships inherent to the data generation process. Such image editing falls into the counterfactual image generation regime. Evaluating counterfactual image generation is substantially complex: not only it lacks observable ground truths, but also requires adherence to causal constraints. Although several counterfactual image generation methods and evaluation metrics exist, a comprehensive comparison within a unified setting is lacking. We present a comparison framework to thoroughly benchmark counterfactual image generation methods. We integrate all models that have been used for the task at hand and expand them to novel datasets and causal graphs, demonstrating the superiority of Hierarchical VAEs across most datasets and metrics. Our framework is implemented in a user-friendly Python package that can be extended to incorporate additional SCMs, causal methods, generative models, and datasets for the community to build on.
Authors: Phillip Howard, Anahita Bhiwandiwalla, Kathleen C. Fraser, Svetlana Kiritchenko
Abstract: With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on both an input image and a text prompt, enabling a variety of use cases such as visual question answering and multimodal chat. While prior studies have examined the social biases contained in text generated by LLMs, this topic has been relatively unexplored in LVLMs. Examining social biases in LVLMs is particularly challenging due to the confounding contributions of bias induced by information contained across the text and visual modalities. To address this challenging problem, we conduct a large-scale study of text generated by different LVLMs under counterfactual changes to input images. Specifically, we present LVLMs with identical open-ended text prompts while conditioning on images from different counterfactual sets, where each set contains images which are largely identical in their depiction of a common subject (e.g., a doctor), but vary only in terms of intersectional social attributes (e.g., race and gender). We comprehensively evaluate the text produced by different LVLMs under this counterfactual generation setting and find that social attributes such as race, gender, and physical characteristics depicted in input images can significantly influence toxicity and the generation of competency-associated words.
Authors: Gousia Habib, Shaima Qureshi, Malik ishfaq
Abstract: Biomedical image analysis is of paramount importance for the advancement of healthcare and medical research. Although conventional convolutional neural networks (CNNs) are frequently employed in this domain, facing limitations in capturing intricate spatial and temporal relationships at the pixel level due to their reliance on fixed-sized windows and immutable filter weights post-training. These constraints impede their ability to adapt to input fluctuations and comprehend extensive long-range contextual information. To overcome these challenges, a novel architecture based on self-attention mechanisms as an alternative to conventional CNNs.The proposed model utilizes attention-based mechanisms to surpass the limitations of CNNs. The key component of our strategy is the combination of non-overlapping (vanilla patching) and novel overlapped Shifted Patching Techniques (S.P.T.s), which enhances the model's capacity to capture local context and improves generalization. Additionally, we introduce the Lancoz5 interpolation technique, which adapts variable image sizes to higher resolutions, facilitating better analysis of high-resolution biomedical images. Our methods address critical challenges faced by attention-based vision models, including inductive bias, weight sharing, receptive field limitations, and efficient data handling. Experimental evidence shows the effectiveness of proposed model in generalizing to various biomedical imaging tasks. The attention-based model, combined with advanced data augmentation methodologies, exhibits robust modeling capabilities and superior performance compared to existing approaches. The integration of S.P.T.s significantly enhances the model's ability to capture local context, while the Lancoz5 interpolation technique ensures efficient handling of high-resolution images.
Authors: Vinkle Srivastav, Keqi Chen, Nicolas Padoy
Abstract: We present a new self-supervised approach, SelfPose3d, for estimating 3d poses of multiple persons from multiple camera views. Unlike current state-of-the-art fully-supervised methods, our approach does not require any 2d or 3d ground-truth poses and uses only the multi-view input images from a calibrated camera setup and 2d pseudo poses generated from an off-the-shelf 2d human pose estimator. We propose two self-supervised learning objectives: self-supervised person localization in 3d space and self-supervised 3d pose estimation. We achieve self-supervised 3d person localization by training the model on synthetically generated 3d points, serving as 3d person root positions, and on the projected root-heatmaps in all the views. We then model the 3d poses of all the localized persons with a bottleneck representation, map them onto all views obtaining 2d joints, and render them using 2d Gaussian heatmaps in an end-to-end differentiable manner. Afterwards, we use the corresponding 2d joints and heatmaps from the pseudo 2d poses for learning. To alleviate the intrinsic inaccuracy of the pseudo labels, we propose an adaptive supervision attention mechanism to guide the self-supervision. Our experiments and analysis on three public benchmark datasets, including Panoptic, Shelf, and Campus, show the effectiveness of our approach, which is comparable to fully-supervised methods. Code: https://github.com/CAMMA-public/SelfPose3D. Video demo: https://youtu.be/GAqhmUIr2E8.
URLs: https://github.com/CAMMA-public/SelfPose3D., https://youtu.be/GAqhmUIr2E8.
Authors: Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, Liwei Wang
Abstract: We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction". This simple, intuitive methodology allows autoregressive (AR) transformers to learn visual distributions fast and generalize well: VAR, for the first time, makes GPT-like AR models surpass diffusion transformers in image generation. On ImageNet 256x256 benchmark, VAR significantly improve AR baseline by improving Frechet inception distance (FID) from 18.65 to 1.73, inception score (IS) from 80.4 to 350.2, with around 20x faster inference speed. It is also empirically verified that VAR outperforms the Diffusion Transformer (DiT) in multiple dimensions including image quality, inference speed, data efficiency, and scalability. Scaling up VAR models exhibits clear power-law scaling laws similar to those observed in LLMs, with linear correlation coefficients near -0.998 as solid evidence. VAR further showcases zero-shot generalization ability in downstream tasks including image in-painting, out-painting, and editing. These results suggest VAR has initially emulated the two important properties of LLMs: Scaling Laws and zero-shot task generalization. We have released all models and codes to promote the exploration of AR/VAR models for visual generation and unified learning.
Authors: Chenqi Kong, Anwei Luo, Peijun Bao, Yi Yu, Haoliang Li, Zengwei Zheng, Shiqi Wang, Alex C. Kot
Abstract: Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance. However, these approaches still exhibit the following limitations: (1) Fully fine-tuning ViT-based models from ImageNet weights demands substantial computational and storage resources; (2) ViT-based methods struggle to capture local forgery clues, leading to model bias; (3) These methods limit their scope on only one or few face forgery features, resulting in limited generalizability. To tackle these challenges, this work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach. MoE-FFD only updates lightweight Low-Rank Adaptation (LoRA) and Adapter layers while keeping the ViT backbone frozen, thereby achieving parameter-efficient training. Moreover, MoE-FFD leverages the expressivity of transformers and local priors of CNNs to simultaneously extract global and local forgery clues. Additionally, novel MoE modules are designed to scale the model's capacity and smartly select optimal forgery experts, further enhancing forgery detection performance. Our proposed learning scheme can be seamlessly adapted to various transformer backbones in a plug-and-play manner. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art face forgery detection performance with significantly reduced parameter overhead. The code is released at: https://github.com/LoveSiameseCat/MoE-FFD.
Authors: Andre Rochow, Max Schwarz, Sven Behnke
Abstract: The task of face reenactment is to transfer the head motion and facial expressions from a driving video to the appearance of a source image, which may be of a different person (cross-reenactment). Most existing methods are CNN-based and estimate optical flow from the source image to the current driving frame, which is then inpainted and refined to produce the output animation. We propose a transformer-based encoder for computing a set-latent representation of the source image(s). We then predict the output color of a query pixel using a transformer-based decoder, which is conditioned with keypoints and a facial expression vector extracted from the driving frame. Latent representations of the source person are learned in a self-supervised manner that factorize their appearance, head pose, and facial expressions. Thus, they are perfectly suited for cross-reenactment. In contrast to most related work, our method naturally extends to multiple source images and can thus adapt to person-specific facial dynamics. We also propose data augmentation and regularization schemes that are necessary to prevent overfitting and support generalizability of the learned representations. We evaluated our approach in a randomized user study. The results indicate superior performance compared to the state-of-the-art in terms of motion transfer quality and temporal consistency.
Authors: Tommie Kerssies, Daan de Geus, Gijs Dubbelman
Abstract: Recent vision foundation models (VFMs) have demonstrated proficiency in various tasks but require supervised fine-tuning to perform the task of semantic segmentation effectively. Benchmarking their performance is essential for selecting current models and guiding future model developments for this task. The lack of a standardized benchmark complicates comparisons. Therefore, the primary objective of this paper is to study how VFMs should be benchmarked for semantic segmentation. To do so, various VFMs are fine-tuned under various settings, and the impact of individual settings on the performance ranking and training time is assessed. Based on the results, the recommendation is to fine-tune the ViT-B variants of VFMs with a 16x16 patch size and a linear decoder, as these settings are representative of using a larger model, more advanced decoder and smaller patch size, while reducing training time by more than 13 times. Using multiple datasets for training and evaluation is also recommended, as the performance ranking across datasets and domain shifts varies. Linear probing, a common practice for some VFMs, is not recommended, as it is not representative of end-to-end fine-tuning. The benchmarking setup recommended in this paper enables a performance analysis of VFMs for semantic segmentation. The findings of such an analysis reveal that pretraining with promptable segmentation is not beneficial, whereas masked image modeling (MIM) with abstract representations is crucial, even more important than the type of supervision used. The code for efficiently fine-tuning VFMs for semantic segmentation can be accessed through the project page at: https://tue-mps.github.io/benchmark-vfm-ss/.
Authors: Mingcheng Li, Dingkang Yang, Xiao Zhao, Shuaibing Wang, Yan Wang, Kun Yang, Mingyang Sun, Dongliang Kou, Ziyun Qian, Lihua Zhang
Abstract: Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. Most MSA efforts are based on the assumption of modality completeness. However, in real-world applications, some practical factors cause uncertain modality missingness, which drastically degrades the model's performance. To this end, we propose a Correlation-decoupled Knowledge Distillation (CorrKD) framework for the MSA task under uncertain missing modalities. Specifically, we present a sample-level contrastive distillation mechanism that transfers comprehensive knowledge containing cross-sample correlations to reconstruct missing semantics. Moreover, a category-guided prototype distillation mechanism is introduced to capture cross-category correlations using category prototypes to align feature distributions and generate favorable joint representations. Eventually, we design a response-disentangled consistency distillation strategy to optimize the sentiment decision boundaries of the student network through response disentanglement and mutual information maximization. Comprehensive experiments on three datasets indicate that our framework can achieve favorable improvements compared with several baselines.
Authors: Zhixiong Huang, Xinying Wang, Chengpei Xu, Jinjiang Li, Lin Feng
Abstract: Underwater scenes intrinsically involve degradation problems owing to heterogeneous ocean elements. Prevailing underwater image enhancement (UIE) methods stick to straightforward feature modeling to learn the mapping function, which leads to limited vision gain as it lacks more explicit physical cues (e.g., depth). In this work, we investigate injecting the depth prior into the deep UIE model for more precise scene enhancement capability. To this end, we present a novel depth-guided perception UIE framework, dubbed underwater variable zoom (UVZ). Specifically, UVZ resorts to a two-stage pipeline. First, a depth estimation network is designed to generate critical depth maps, combined with an auxiliary supervision network introduced to suppress estimation differences during training. Second, UVZ parses near-far scenarios by harnessing the predicted depth maps, enabling local and non-local perceiving in different regions. Extensive experiments on five benchmark datasets demonstrate that UVZ achieves superior visual gain and delivers promising quantitative metrics. Besides, UVZ is confirmed to exhibit good generalization in some visual tasks, especially in unusual lighting conditions. The code, models and results are available at: https://github.com/WindySprint/UVZ.
Authors: Diana Sungatullina, Tomas Pajdla
Abstract: We present an approach to backpropagating through minimal problem solvers in end-to-end neural network training. Traditional methods relying on manually constructed formulas, finite differences, and autograd are laborious, approximate, and unstable for complex minimal problem solvers. We show that using the Implicit function theorem (IFT) to calculate derivatives to backpropagate through the solution of a minimal problem solver is simple, fast, and stable. We compare our approach to (i) using the standard autograd on minimal problem solvers and relate it to existing backpropagation formulas through SVD-based and Eig-based solvers and (ii) implementing the backprop with an existing PyTorch Deep Declarative Networks (DDN) framework. We demonstrate our technique on a toy example of training outlier-rejection weights for 3D point registration and on a real application of training an outlier-rejection and RANSAC sampling network in image matching. Our method provides $100\%$ stability and is 10 times faster compared to autograd, which is unstable and slow, and compared to DDN, which is stable but also slow.
Authors: Hyunseo Kim, Hyeonseo Yang, Taekyung Kim, YoonSung Kim, Jin-Hwa Kim, Byoung-Tak Zhang
Abstract: Active view selection in 3D scene reconstruction has been widely studied since training on informative views is critical for reconstruction. Recently, Neural Radiance Fields (NeRF) variants have shown promising results in active 3D reconstruction using uncertainty-guided view selection. They utilize uncertainties estimated with neural networks that encode scene geometry and appearance. However, the choice of uncertainty integration methods, either voxel-based or neural rendering, has conventionally depended on the types of scene uncertainty being estimated, whether geometric or appearance-related. In this paper, we introduce Colorized Surface Voxel (CSV)-based view selection, a new next-best view (NBV) selection method exploiting surface voxel-based measurement of uncertainty in scene appearance. CSV encapsulates the uncertainty of estimated scene appearance (e.g., color uncertainty) and estimated geometric information (e.g., surface). Using the geometry information, we interpret the uncertainty of scene appearance 3D-wise during the aggregation of the per-voxel uncertainty. Consequently, the uncertainty from occluded and complex regions is recognized under challenging scenarios with limited input data. Our method outperforms previous works on popular datasets, DTU and Blender, and our new dataset with imbalanced viewpoints, showing that the CSV-based view selection significantly improves performance by up to 30%.
Authors: Nematollah Saeidi, Hossein Karshenas, Bijan Shoushtarian, Sepideh Hatamikia, Ramona Woitek, Amirreza Mahbod
Abstract: Breast cancer is the most common cancer type in women worldwide. Early detection and appropriate treatment can significantly reduce its impact. While histopathology examinations play a vital role in rapid and accurate diagnosis, they often require a substantial workforce and experienced medical experts for proper recognition and cancer grading. Automated image retrieval systems have the potential to assist pathologists in identifying cancerous tissues, thereby accelerating the diagnostic process. Nevertheless, due to considerable variability among the tissue and cell patterns in histological images, proposing an accurate image retrieval model is very challenging. This work introduces a novel attention-based adversarially regularized variational graph autoencoder model for breast histological image retrieval. Additionally, we incorporated cluster-guided contrastive learning as the graph feature extractor to boost the retrieval performance. We evaluated the performance of the proposed model on two publicly available datasets of breast cancer histological images and achieved superior or very competitive retrieval performance, with average mAP scores of 96.5% for the BreakHis dataset and 94.7% for the BACH dataset, and mVP scores of 91.9% and 91.3%, respectively. Our proposed retrieval model has the potential to be used in clinical settings to enhance diagnostic performance and ultimately benefit patients.
Authors: Ting Liu, Xuyang Liu, Siteng Huang, Honggang Chen, Quanjun Yin, Long Qin, Donglin Wang, Yue Hu
Abstract: Visual grounding (VG) is a challenging task to localize an object in an image based on a textual description. Recent surge in the scale of VG models has substantially improved performance, but also introduced a significant burden on computational costs during fine-tuning. In this paper, we explore applying parameter-efficient transfer learning (PETL) to efficiently transfer the pre-trained vision-language knowledge to VG. Specifically, we propose \textbf{DARA}, a novel PETL method comprising \underline{\textbf{D}}omain-aware \underline{\textbf{A}}dapters (DA Adapters) and \underline{\textbf{R}}elation-aware \underline{\textbf{A}}dapters (RA Adapters) for VG. DA Adapters first transfer intra-modality representations to be more fine-grained for the VG domain. Then RA Adapters share weights to bridge the relation between two modalities, improving spatial reasoning. Empirical results on widely-used benchmarks demonstrate that DARA achieves the best accuracy while saving numerous updated parameters compared to the full fine-tuning and other PETL methods. Notably, with only \textbf{2.13\%} tunable backbone parameters, DARA improves average accuracy by \textbf{0.81\%} across the three benchmarks compared to the baseline model. Our code is available at \url{https://github.com/liuting20/DARA}.
Authors: Evan M. Williams, Kathleen M. Carley
Abstract: We evaluate the zero-shot ability of GPT-4 and LLaVa to perform simple Visual Network Analysis (VNA) tasks on small-scale graphs. We evaluate the Vision Language Models (VLMs) on 5 tasks related to three foundational network science concepts: identifying nodes of maximal degree on a rendered graph, identifying whether signed triads are balanced or unbalanced, and counting components. The tasks are structured to be easy for a human who understands the underlying graph theoretic concepts, and can all be solved by counting the appropriate elements in graphs. We find that while GPT-4 consistently outperforms LLaVa, both models struggle with every visual network analysis task we propose. We publicly release the first benchmark for the evaluation of VLMs on foundational VNA tasks.
Authors: Wenhao Wu
Abstract: This paper undertakes an empirical study to revisit the latest advancements in Multimodal Large Language Models (MLLMs): Video Assistant. This study, namely FreeVA, aims to extend existing image-based MLLM to the video domain in a training-free manner. The study provides an essential, yet must-know baseline, and reveals several surprising findings: 1) FreeVA, leveraging only offline image-based MLLM without additional training, excels in zero-shot video question-answering (e.g., MSVD-QA, ActivityNet-QA, and MSRVTT-QA), even surpassing state-of-the-art methods that involve video instruction tuning. 2) While mainstream video-based MLLMs typically initialize with an image-based MLLM (e.g., LLaVA) and then fine-tune using video instruction tuning, the study indicates that utilizing the widely adopted VideoInstruct-100K for video instruction tuning doesn't actually lead to better performance compared to not training at all. 3) The commonly used evaluation metrics in existing works are significantly influenced by changes in the GPT API version over time. If ignored, this could affect the fairness and uniformity of comparisons between different methods and impact the analysis and judgment of researchers in the field. The advancement of MLLMs is currently thriving, drawing numerous researchers into the field. We aim for this work to serve as a plug-and-play, simple yet effective baseline, encouraging the direct evaluation of existing MLLMs in video domain while also standardizing the field of video conversational models to a certain extent. Also, we encourage researchers to reconsider: Have current video MLLM methods truly acquired knowledge beyond image MLLM? Code is available at https://github.com/whwu95/FreeVA
Authors: Takahiro Shindo, Taiju Watanabe, Yui Tatsumi, Hiroshi Watanabe
Abstract: As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these use cases, the scalable coding method proves effective because the tasks require occasional image checking by humans. Existing image compression methods for humans and machines meet these requirements to some extent. However, these compression methods are effective solely for specific image recognition models. We propose a learning-based scalable image coding method for humans and machines that is compatible with numerous image recognition models. We combine an image compression model for machines with a compression model, providing additional information to facilitate image decoding for humans. The features in these compression models are fused using a feature fusion network to achieve efficient image compression. Our method's additional information compression model is adjusted to reduce the number of parameters by enabling combinations of features of different sizes in the feature fusion network. Our approach confirms that the feature fusion network efficiently combines image compression models while reducing the number of parameters. Furthermore, we demonstrate the effectiveness of the proposed scalable coding method by evaluating the image compression performance in terms of decoded image quality and bitrate.
Authors: Siming He, Zach Osman, Pratik Chaudhari
Abstract: For robotics applications where there is a limited number of (typically ego-centric) views, parametric representations such as neural radiance fields (NeRFs) generalize better than non-parametric ones such as Gaussian splatting (GS) to views that are very different from those in the training data; GS however can render much faster than NeRFs. We develop a procedure to convert back and forth between the two. Our approach achieves the best of both NeRFs (superior PSNR, SSIM, and LPIPS on dissimilar views, and a compact representation) and GS (real-time rendering and ability for easily modifying the representation); the computational cost of these conversions is minor compared to training the two from scratch.
Authors: Hongsheng Wang, Weiyue Zhang, Sihao Liu, Xinrui Zhou, Jing Li, Zhanyun Tang, Shengyu Zhang, Fei Wu, Feng Lin
Abstract: Although 3D Gaussian Splatting (3DGS) has recently made progress in 3D human reconstruction, it primarily relies on 2D pixel-level supervision, overlooking the geometric complexity and topological relationships of different body parts. To address this gap, we introduce the Hierarchical Graph Human Gaussian Control (HUGS) framework for achieving high-fidelity 3D human reconstruction. Our approach involves leveraging explicitly semantic priors of body parts to ensure the consistency of geometric topology, thereby enabling the capture of the complex geometrical and topological associations among body parts. Additionally, we disentangle high-frequency features from global human features to refine surface details in body parts. Extensive experiments demonstrate that our method exhibits superior performance in human body reconstruction, particularly in enhancing surface details and accurately reconstructing body part junctions. Codes are available at https://wanghongsheng01.github.io/HUGS/.
Authors: Antoine Legrand, Renaud Detry, Christophe De Vleeschouwer
Abstract: We address the estimation of the 6D pose of an unknown target spacecraft relative to a monocular camera, a key step towards the autonomous rendezvous and proximity operations required by future Active Debris Removal missions. We present a novel method that enables an "off-the-shelf" spacecraft pose estimator, which is supposed to known the target CAD model, to be applied on an unknown target. Our method relies on an in-the wild NeRF, i.e., a Neural Radiance Field that employs learnable appearance embeddings to represent varying illumination conditions found in natural scenes. We train the NeRF model using a sparse collection of images that depict the target, and in turn generate a large dataset that is diverse both in terms of viewpoint and illumination. This dataset is then used to train the pose estimation network. We validate our method on the Hardware-In-the-Loop images of SPEED+ that emulate lighting conditions close to those encountered on orbit. We demonstrate that our method successfully enables the training of an off-the-shelf spacecraft pose estimation network from a sparse set of images. Furthermore, we show that a network trained using our method performs similarly to a model trained on synthetic images generated using the CAD model of the target.
Authors: Zihan Zheng, Houqiang Zhong, Qiang Hu, Xiaoyun Zhang, Li Song, Ya Zhang, Yanfeng Wang
Abstract: Neural Radiance Field (NeRF) excels in photo-realistically static scenes, inspiring numerous efforts to facilitate volumetric videos. However, rendering dynamic and long-sequence radiance fields remains challenging due to the significant data required to represent volumetric videos. In this paper, we propose a novel end-to-end joint optimization scheme of dynamic NeRF representation and compression, called JointRF, thus achieving significantly improved quality and compression efficiency against the previous methods. Specifically, JointRF employs a compact residual feature grid and a coefficient feature grid to represent the dynamic NeRF. This representation handles large motions without compromising quality while concurrently diminishing temporal redundancy. We also introduce a sequential feature compression subnetwork to further reduce spatial-temporal redundancy. Finally, the representation and compression subnetworks are end-to-end trained combined within the JointRF. Extensive experiments demonstrate that JointRF can achieve superior compression performance across various datasets.
Authors: Manoj Kumar, Neil Houlsby, Emiel Hoogeboom
Abstract: We investigate the task of adapting image generative models to different datasets without finetuneing. To this end, we introduce Semantica, an image-conditioned diffusion model capable of generating images based on the semantics of a conditioning image. Semantica is trained exclusively on web-scale image pairs, that is it receives a random image from a webpage as conditional input and models another random image from the same webpage. Our experiments highlight the expressivity of pretrained image encoders and necessity of semantic-based data filtering in achieving high-quality image generation. Once trained, it can adaptively generate new images from a dataset by simply using images from that dataset as input. We study the transfer properties of Semantica on ImageNet, LSUN Churches, LSUN Bedroom and SUN397.
Authors: Xiyao Wang, Jiuhai Chen, Zhaoyang Wang, Yuhang Zhou, Yiyang Zhou, Huaxiu Yao, Tianyi Zhou, Tom Goldstein, Parminder Bhatia, Furong Huang, Cao Xiao
Abstract: Large vision-language models (LVLMs) have achieved impressive results in various visual question-answering and reasoning tasks through vision instruction tuning on specific datasets. However, there is still significant room for improvement in the alignment between visual and language modalities. Previous methods to enhance this alignment typically require external models or data, heavily depending on their capabilities and quality, which inevitably sets an upper bound on performance. In this paper, we propose SIMA, a framework that enhances visual and language modality alignment through self-improvement, eliminating the needs for external models or data. SIMA leverages prompts from existing vision instruction tuning datasets to self-generate responses and employs an in-context self-critic mechanism to select response pairs for preference tuning. The key innovation is the introduction of three vision metrics during the in-context self-critic process, which can guide the LVLM in selecting responses that enhance image comprehension. Through experiments across 14 hallucination and comprehensive benchmarks, we demonstrate that SIMA not only improves model performance across all benchmarks but also achieves superior modality alignment, outperforming previous approaches.
Authors: Hanjun Luo, Ziye Deng, Ruizhe Chen, Zuozhu Liu
Abstract: The rapid development and reduced barriers to entry for Text-to-Image (T2I) models have raised concerns about the biases in their outputs, but existing research lacks a holistic definition and evaluation framework of biases, limiting the enhancement of debiasing techniques. To address this issue, we introduce FAIntbench, a holistic and precise benchmark for biases in T2I models. In contrast to existing benchmarks that evaluate bias in limited aspects, FAIntbench evaluate biases from four dimensions: manifestation of bias, visibility of bias, acquired attributes, and protected attributes. We applied FAIntbench to evaluate seven recent large-scale T2I models and conducted human evaluation, whose results demonstrated the effectiveness of FAIntbench in identifying various biases. Our study also revealed new research questions about biases, including the side-effect of distillation. The findings presented here are preliminary, highlighting the potential of FAIntbench to advance future research aimed at mitigating the biases in T2I models. Our benchmark is publicly available to ensure the reproducibility.
Authors: Yunsong Wang, Tianxin Huang, Hanlin Chen, Gim Hee Lee
Abstract: Empowering 3D Gaussian Splatting with generalization ability is appealing. However, existing generalizable 3D Gaussian Splatting methods are largely confined to narrow-range interpolation between stereo images due to their heavy backbones, thus lacking the ability to accurately localize 3D Gaussian and support free-view synthesis across wide view range. In this paper, we present a novel framework FreeSplat that is capable of reconstructing geometrically consistent 3D scenes from long sequence input towards free-view synthesis.Specifically, we firstly introduce Low-cost Cross-View Aggregation achieved by constructing adaptive cost volumes among nearby views and aggregating features using a multi-scale structure. Subsequently, we present the Pixel-wise Triplet Fusion to eliminate redundancy of 3D Gaussians in overlapping view regions and to aggregate features observed across multiple views. Additionally, we propose a simple but effective free-view training strategy that ensures robust view synthesis across broader view range regardless of the number of views. Our empirical results demonstrate state-of-the-art novel view synthesis peformances in both novel view rendered color maps quality and depth maps accuracy across different numbers of input views. We also show that FreeSplat performs inference more efficiently and can effectively reduce redundant Gaussians, offering the possibility of feed-forward large scene reconstruction without depth priors.
Authors: Vaibhav Vavilala, Florian Kluger, Seemandhar Jain, Bodo Rosenhahn, David Forsyth
Abstract: Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established vision problem. This is a good model of a difficult fitting problem: different scenes require different numbers of primitives and primitives interact strongly, but any proposed solution can be evaluated at inference time. The state of the art method involves a learned regression procedure to predict a start point consisting of a fixed number of primitives, followed by a descent method to refine the geometry and remove redundant primitives. Methods are evaluated by accuracy in depth and normal prediction and in scene segmentation. This paper shows that very significant improvements in accuracy can be obtained by (a) incorporating a small number of negative primitives and (b) ensembling over a number of different regression procedures. Ensembling is by refining each predicted start point, then choosing the best by fitting loss. Extensive experiments on a standard dataset confirm that negative primitives are useful in a large fraction of images, and that our refine-then-choose strategy outperforms choose-then-refine, confirming that the fitting problem is very difficult.
Authors: Alessio Mazzucchelli, Adrian Garcia-Garcia, Elena Garces, Fernando Rivas-Manzaneque, Francesc Moreno-Noguer, Adrian Penate-Sanchez
Abstract: Advances in NERFs have allowed for 3D scene reconstructions and novel view synthesis. Yet, efficiently editing these representations while retaining photorealism is an emerging challenge. Recent methods face three primary limitations: they're slow for interactive use, lack precision at object boundaries, and struggle to ensure multi-view consistency. We introduce IReNe to address these limitations, enabling swift, near real-time color editing in NeRF. Leveraging a pre-trained NeRF model and a single training image with user-applied color edits, IReNe swiftly adjusts network parameters in seconds. This adjustment allows the model to generate new scene views, accurately representing the color changes from the training image while also controlling object boundaries and view-specific effects. Object boundary control is achieved by integrating a trainable segmentation module into the model. The process gains efficiency by retraining only the weights of the last network layer. We observed that neurons in this layer can be classified into those responsible for view-dependent appearance and those contributing to diffuse appearance. We introduce an automated classification approach to identify these neuron types and exclusively fine-tune the weights of the diffuse neurons. This further accelerates training and ensures consistent color edits across different views. A thorough validation on a new dataset, with edited object colors, shows significant quantitative and qualitative advancements over competitors, accelerating speeds by 5x to 500x.
Authors: Xinyue Chen, Miaojing Shi
Abstract: The performance of supervised semantic segmentation methods highly relies on the availability of large-scale training data. To alleviate this dependence, few-shot semantic segmentation (FSS) is introduced to leverage the model trained on base classes with sufficient data into the segmentation of novel classes with few data. FSS methods face the challenge of model generalization on novel classes due to the distribution shift between base and novel classes. To overcome this issue, we propose a class-shared memory (CSM) module consisting of a set of learnable memory vectors. These memory vectors learn elemental object patterns from base classes during training whilst re-encoding query features during both training and inference, thereby improving the distribution alignment between base and novel classes. Furthermore, to cope with the performance degradation resulting from the intra-class variance across images, we introduce an uncertainty-based feature augmentation (UFA) module to produce diverse query features during training for improving the model's robustness. We integrate CSM and UFA into representative FSS works, with experimental results on the widely-used PASCAL-5$^i$ and COCO-20$^i$ datasets demonstrating the superior performance of ours over state of the art.
Authors: Harshvardhan Mestha, Tejas Agrawal, Karan Bania, Shreyas V, Yash Bhisikar
Abstract: Large vision-language models (VLMs) are shown to learn rich joint image-text representations enabling high performances in relevant downstream tasks. However, they fail to showcase their quantitative understanding of objects, and they lack good counting-aware representation. This paper conducts a reproducibility study of 'Teaching CLIP to Count to Ten' (Paiss et al., 2023), which presents a method to finetune a CLIP model (Radford et al., 2021) to improve zero-shot counting accuracy in an image while maintaining the performance for zero-shot classification by introducing a counting-contrastive loss term. We improve the model's performance on a smaller subset of their training data with lower computational resources. We verify these claims by reproducing their study with our own code. The implementation can be found at https://github.com/SforAiDl/CountCLIP.
Authors: Behzad Vahedi, Benjamin Lucas, Farnoush Banaei-Kashani, Andrew P. Barrett, Walter N. Meier, Siri Jodha Khalsa, Morteza Karimzadeh
Abstract: Sea ice, crucial to the Arctic and Earth's climate, requires consistent monitoring and high-resolution mapping. Manual sea ice mapping, however, is time-consuming and subjective, prompting the need for automated deep learning-based classification approaches. However, training these algorithms is challenging because expert-generated ice charts, commonly used as training data, do not map single ice types but instead map polygons with multiple ice types. Moreover, the distribution of various ice types in these charts is frequently imbalanced, resulting in a performance bias towards the dominant class. In this paper, we present a novel GeoAI approach to training sea ice classification by formalizing it as a partial label learning task with explicit confidence scores to address multiple labels and class imbalance. We treat the polygon-level labels as candidate partial labels, assign the corresponding ice concentrations as confidence scores to each candidate label, and integrate them with focal loss to train a Convolutional Neural Network (CNN). Our proposed approach leads to enhanced performance for sea ice classification in Sentinel-1 dual-polarized SAR images, improving classification accuracy (from 87% to 92%) and weighted average F-1 score (from 90% to 93%) compared to the conventional training approach of using one-hot encoded labels and Categorical Cross-Entropy loss. It also improves the F-1 score in 4 out of the 6 sea ice classes.
Authors: Quynh Phung, Songwei Ge, Jia-Bin Huang
Abstract: Despite the advances in text-to-image synthesis, particularly with diffusion models, generating visual instructions that require consistent representation and smooth state transitions of objects across sequential steps remains a formidable challenge. This paper introduces a simple, training-free framework to tackle the issues, capitalizing on the advancements in diffusion models and large language models (LLMs). Our approach systematically integrates text comprehension and image generation to ensure visual instructions are visually appealing and maintain consistency and accuracy throughout the instruction sequence. We validate the effectiveness by testing multi-step instructions and comparing the text alignment and consistency with several baselines. Our experiments show that our approach can visualize coherent and visually pleasing instructions
Authors: Chaerin Min, Srinath Sridhar
Abstract: Grasping is an important human activity that has long been studied in robotics, computer vision, and cognitive science. Most existing works study grasping from the perspective of synthesizing hand poses conditioned on 3D or 2D object representations. We propose GenHeld to address the inverse problem of synthesizing held objects conditioned on 3D hand model or 2D image. Given a 3D model of hand, GenHeld 3D can select a plausible held object from a large dataset using compact object representations called object codes.The selected object is then positioned and oriented to form a plausible grasp without changing hand pose. If only a 2D hand image is available, GenHeld 2D can edit this image to add or replace a held object. GenHeld 2D operates by combining the abilities of GenHeld 3D with diffusion-based image editing. Results and experiments show that we outperform baselines and can generate plausible held objects in both 2D and 3D. Our experiments demonstrate that our method achieves high quality and plausibility of held object synthesis in both 3D and 2D.
Authors: Cory Braker Scott
Abstract: This preliminary paper presents initial explorations in rendering Iterated Function System (IFS) fractals using a differentiable rendering pipeline. Differentiable rendering is a recent innovation at the intersection of computer graphics and machine learning. A fractal rendering pipeline composed of differentiable operations opens up many possibilities for generating fractals that meet particular criteria. In this paper I demonstrate this pipeline by generating IFS fractals with fixed points that resemble a given target image - a famous problem known as the \emph{inverse IFS problem}. The main contributions of this work are as follows: 1) I demonstrate (and make code available) this rendering pipeline; 2) I discuss some of the nuances and pitfalls in gradient-descent-based optimization over fractal structures; 3) I discuss best practices to address some of these pitfalls; and finally 4) I discuss directions for further experiments to validate the technique.
Authors: Tobias Schlosser, Frederik Beuth, Trixy Meyer, Arunodhayan Sampath Kumar, Gabriel Stolze, Olga Furashova, Katrin Engelmann, Danny Kowerko
Abstract: In ophthalmology, intravitreal operative medication therapy (IVOM) is a widespread treatment for diseases related to the age-related macular degeneration (AMD), the diabetic macular edema (DME), as well as the retinal vein occlusion (RVO). However, in real-world settings, patients often suffer from loss of vision on time scales of years despite therapy, whereas the prediction of the visual acuity (VA) and the earliest possible detection of deterioration under real-life conditions is challenging due to heterogeneous and incomplete data. In this contribution, we present a workflow for the development of a research-compatible data corpus fusing different IT systems of the department of ophthalmology of a German maximum care hospital. The extensive data corpus allows predictive statements of the expected progression of a patient and his or her VA in each of the three diseases. For the disease AMD, we found out a significant deterioration of the visual acuity over time. Within our proposed multistage system, we subsequently classify the VA progression into the three groups of therapy "winners", "stabilizers", and "losers" (WSL classification scheme). Our OCT biomarker classification using an ensemble of deep neural networks results in a classification accuracy (F1-score) of over 98 %, enabling us to complete incomplete OCT documentations while allowing us to exploit them for a more precise VA modeling process. Our VA prediction requires at least four VA examinations and optionally OCT biomarkers from the same time period to predict the VA progression within a forecasted time frame, whereas our prediction is currently restricted to IVOM / no therapy. We achieve a final prediction accuracy of 69 % in macro average F1-score, while being in the same range as the ophthalmologists with 57.8 and 50 +- 10.7 % F1-score.
Authors: Shakir Showkat Sofi, Ivan Oseledets
Abstract: The majority of real-world processes are spatiotemporal, and the data generated by them exhibits both spatial and temporal evolution. Weather is one of the most essential processes in this domain, and weather forecasting has become a crucial part of our daily routine. Weather data analysis is considered the most complex and challenging task. Although numerical weather prediction models are currently state-of-the-art, they are resource-intensive and time-consuming. Numerous studies have proposed time series-based models as a viable alternative to numerical forecasts. Recent research in the area of time series analysis indicates significant advancements, particularly regarding the use of state-space-based models (white box) and, more recently, the integration of machine learning and deep neural network-based models (black box). The most famous examples of such models are RNNs and transformers. These models have demonstrated remarkable results in the field of time-series analysis and have demonstrated effectiveness in modelling temporal correlations. It is crucial to capture both temporal and spatial correlations for a spatiotemporal process, as the values at nearby locations and time affect the values of a spatiotemporal process at a specific point. This self-contained paper explores various regional data-driven weather forecasting methods, i.e., forecasting over multiple latitude-longitude points (matrix-shaped spatial grid) to capture spatiotemporal correlations. The results showed that spatiotemporal prediction models reduced computational costs while improving accuracy. In particular, the proposed tensor train dynamic mode decomposition-based forecasting model has comparable accuracy to the state-of-the-art models without the need for training. We provide convincing numerical experiments to show that the proposed approach is practical.
Authors: Nikhil Singh, Chih-Wei Wu, Iroro Orife, Mahdi Kalayeh
Abstract: Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual scene. Consider, for example, different conversations on the same crowded street. The effect of such counterfactual pairs on audiovisual representation learning has not been previously explored. To investigate this, we use dubbed versions of movies and television shows to augment cross-modal contrastive learning. Our approach learns to represent alternate audio tracks, differing only in speech, similarly to the same video. Our results, from a comprehensive set of experiments investigating different training strategies, show this general approach improves performance on a range of downstream auditory and audiovisual tasks, without majorly affecting linguistic task performance overall. These findings highlight the importance of considering speech variation when learning scene-level audiovisual correspondences and suggest that dubbed audio can be a useful augmentation technique for training audiovisual models toward more robust performance on diverse downstream tasks.
Authors: Jiangyi Fang, Liyue Chen, Di Chai, Yayao Hong, Xiuhuai Xie, Longbiao Chen, Leye Wang
Abstract: Spatiotemporal crowd flow prediction is one of the key technologies in smart cities. Currently, there are two major pain points that plague related research and practitioners. Firstly, crowd flow is related to multiple domain knowledge factors; however, due to the diversity of application scenarios, it is difficult for subsequent work to make reasonable and comprehensive use of domain knowledge. Secondly, with the development of deep learning technology, the implementation of relevant techniques has become increasingly complex; reproducing advanced models has become a time-consuming and increasingly cumbersome task. To address these issues, we design and implement a spatiotemporal crowd flow prediction toolbox called UCTB (Urban Computing Tool Box), which integrates multiple spatiotemporal domain knowledge and state-of-the-art models simultaneously. The relevant code and supporting documents have been open-sourced at https://github.com/uctb/UCTB.
Authors: Sabine Muzellec, Thomas Fel, Victor Boutin, L\'eo and\'eol, Rufin VanRullen, Thomas Serre
Abstract: Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process. We have identified a significant limitation in one type of attribution methods, known as ``white-box" methods. Although highly efficient, as we will show, these methods rely on a gradient signal that is often contaminated by high-frequency artifacts. To overcome this limitation, we introduce a new approach called "FORGrad". This simple method effectively filters out these high-frequency artifacts using optimal cut-off frequencies tailored to the unique characteristics of each model architecture. Our findings show that FORGrad consistently enhances the performance of already existing white-box methods, enabling them to compete effectively with more accurate yet computationally demanding "black-box" methods. We anticipate that our research will foster broader adoption of simpler and more efficient white-box methods for explainability, offering a better balance between faithfulness and computational efficiency.
Authors: Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, Wei-Chen Chiu
Abstract: Text-to-image diffusion models, e.g. Stable Diffusion (SD), lately have shown remarkable ability in high-quality content generation, and become one of the representatives for the recent wave of transformative AI. Nevertheless, such advance comes with an intensifying concern about the misuse of this generative technology, especially for producing copyrighted or NSFW (i.e. not safe for work) images. Although efforts have been made to filter inappropriate images/prompts or remove undesirable concepts/styles via model fine-tuning, the reliability of these safety mechanisms against diversified problematic prompts remains largely unexplored. In this work, we propose Prompting4Debugging (P4D) as a debugging and red-teaming tool that automatically finds problematic prompts for diffusion models to test the reliability of a deployed safety mechanism. We demonstrate the efficacy of our P4D tool in uncovering new vulnerabilities of SD models with safety mechanisms. Particularly, our result shows that around half of prompts in existing safe prompting benchmarks which were originally considered "safe" can actually be manipulated to bypass many deployed safety mechanisms, including concept removal, negative prompt, and safety guidance. Our findings suggest that, without comprehensive testing, the evaluations on limited safe prompting benchmarks can lead to a false sense of safety for text-to-image models.
Authors: Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, Qing Qu
Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We confirm this phenomenon through comprehensive experiments, implying that different diffusion models consistently reach the same data distribution and scoring function regardless of diffusion model frameworks, model architectures, or training procedures. More strikingly, our further investigation implies that diffusion models are learning distinct distributions affected by the training data size. This is supported by the fact that the model reproducibility manifests in two distinct training regimes: (i) "memorization regime", where the diffusion model overfits to the training data distribution, and (ii) "generalization regime", where the model learns the underlying data distribution. Our study also finds that this valuable property generalizes to many variants of diffusion models, including those for conditional use, solving inverse problems, and model fine-tuning. Finally, our work raises numerous intriguing theoretical questions for future investigation and highlights practical implications regarding training efficiency, model privacy, and the controlled generation of diffusion models.
Authors: Guy Ohayon, Tomer Michaeli, Michael Elad
Abstract: We study the behavior of deterministic methods for solving inverse problems in imaging. These methods are commonly designed to achieve two goals: (1) attaining high perceptual quality, and (2) generating reconstructions that are consistent with the measurements. We provide a rigorous proof that the better a predictor satisfies these two requirements, the larger its Lipschitz constant must be, regardless of the nature of the degradation involved. In particular, to approach perfect perceptual quality and perfect consistency, the Lipschitz constant of the model must grow to infinity. This implies that such methods are necessarily more susceptible to adversarial attacks. We demonstrate our theory on single image super-resolution algorithms, addressing both noisy and noiseless settings. We also show how this undesired behavior can be leveraged to explore the posterior distribution, thereby allowing the deterministic model to imitate stochastic methods.
Authors: Shivam Gupta, Aditya Parulekar, Eric Price, Zhiyang Xun
Abstract: Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works~\cite{chen2022,chen2022improved,benton2023linear} have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the \emph{sample complexity} of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work~\cite{BMR20} showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an \emph{exponential improvement} in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.
Authors: Xin Wang, Lizhi Wang, Xiangtian Ma, Maoqing Zhang, Lin Zhu, Hua Huang
Abstract: Dual-Camera Compressed Hyperspectral Imaging (DCCHI) offers the capability to reconstruct 3D Hyperspectral Image (HSI) by fusing compressive and Panchromatic (PAN) image, which has shown great potential for snapshot hyperspectral imaging in practice. In this paper, we introduce a novel DCCHI reconstruction network, the Intra-Inter Similarity Exploiting Transformer (In2SET). Our key insight is to make full use of the PAN image to assist the reconstruction. To this end, we propose using the intra-similarity within the PAN image as a proxy for approximating the intra-similarity in the original HSI, thereby offering an enhanced content prior for more accurate HSI reconstruction. Furthermore, we aim to align the features from the underlying HSI with those of the PAN image, maintaining semantic consistency and introducing new contextual information for the reconstruction process. By integrating In2SET into a PAN-guided unrolling framework, our method substantially enhances the spatial-spectral fidelity and detail of the reconstructed images, providing a more comprehensive and accurate depiction of the scene. Extensive experiments conducted on both real and simulated datasets demonstrate that our approach consistently outperforms existing state-of-the-art methods in terms of reconstruction quality and computational complexity. Code will be released.
Authors: Isaiah Lahr, Saghir Alfasly, Peyman Nejat, Jibran Khan, Luke Kottom, Vaishnavi Kumbhar, Areej Alsaafin, Abubakr Shafique, Sobhan Hemati, Ghazal Alabtah, Nneka Comfere, Dennis Murphee, Aaron Mangold, Saba Yasir, Chady Meroueh, Lisa Boardman, Vijay H. Shah, Joaquin J. Garcia, H. R. Tizhoosh
Abstract: Searching for similar images in archives of histology and histopathology images is a crucial task that may aid in patient matching for various purposes, ranging from triaging and diagnosis to prognosis and prediction. Whole slide images (WSIs) are highly detailed digital representations of tissue specimens mounted on glass slides. Matching WSI to WSI can serve as the critical method for patient matching. In this paper, we report extensive analysis and validation of four search methods bag of visual words (BoVW), Yottixel, SISH, RetCCL, and some of their potential variants. We analyze their algorithms and structures and assess their performance. For this evaluation, we utilized four internal datasets ($1269$ patients) and three public datasets ($1207$ patients), totaling more than $200,000$ patches from $38$ different classes/subtypes across five primary sites. Certain search engines, for example, BoVW, exhibit notable efficiency and speed but suffer from low accuracy. Conversely, search engines like Yottixel demonstrate efficiency and speed, providing moderately accurate results. Recent proposals, including SISH, display inefficiency and yield inconsistent outcomes, while alternatives like RetCCL prove inadequate in both accuracy and efficiency. Further research is imperative to address the dual aspects of accuracy and minimal storage requirements in histopathological image search.
Authors: Huy Tran, Yikun Bai, Abihith Kothapalli, Ashkan Shahbazi, Xinran Liu, Rocio Diaz Martin, Soheil Kolouri
Abstract: Comparing spherical probability distributions is of great interest in various fields, including geology, medical domains, computer vision, and deep representation learning. The utility of optimal transport-based distances, such as the Wasserstein distance, for comparing probability measures has spurred active research in developing computationally efficient variations of these distances for spherical probability measures. This paper introduces a high-speed and highly parallelizable distance for comparing spherical measures using the stereographic projection and the generalized Radon transform, which we refer to as the Stereographic Spherical Sliced Wasserstein (S3W) distance. We carefully address the distance distortion caused by the stereographic projection and provide an extensive theoretical analysis of our proposed metric and its rotationally invariant variation. Finally, we evaluate the performance of the proposed metrics and compare them with recent baselines in terms of both speed and accuracy through a wide range of numerical studies, including gradient flows and self-supervised learning. Our code is available at https://github.com/mint-vu/s3wd.
Authors: Qixiang Ma, Antoine {\L}ucas, Huazhong Shu, Adrien Kaladji, Pascal Haigron
Abstract: Deep-learning-based automated segmentation of vascular structures in preoperative CT scans contributes to computer-assisted diagnosis and intervention procedure in vascular diseases. While CT angiography (CTA) is the common standard, non-contrast CT imaging is significant as a contrast-risk-free alternative, avoiding complications associated with contrast agents. However, the challenges of labor-intensive labeling and high labeling variability due to the ambiguity of vascular boundaries hinder conventional strong-label-based, fully-supervised learning in non-contrast CTs. This paper introduces a weakly-supervised framework using ellipses' topology in slices, including 1) an efficient annotation process based on predefined standards, 2) ellipse-fitting processing, 3) the generation of 2D Gaussian heatmaps serving as pseudo labels, 4) a training process through a combination of voxel reconstruction loss and distribution loss with the pseudo labels. We assess the effectiveness of the proposed method on one local and two public datasets comprising non-contrast CT scans, particularly focusing on the abdominal aorta. On the local dataset, our weakly-supervised learning approach based on pseudo labels outperforms strong-label-based fully-supervised learning (1.54\% of Dice score on average), reducing labeling time by around 82.0\%. The efficiency in generating pseudo labels allows the inclusion of label-agnostic external data in the training set, leading to an additional improvement in performance (2.74\% of Dice score on average) with a reduction of 66.3\% labeling time, where the labeling time remains considerably less than that of strong labels. On the public dataset, the pseudo labels achieve an overall improvement of 1.95\% in Dice score for 2D models while a reduction of 11.65 voxel spacing in Hausdorff distance for 3D model.
Authors: Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Aakriti Jain, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
Abstract: Large Language Models are prone to biased predictions and hallucinations, underlining the paramount importance of understanding their model-internal reasoning process. However, achieving faithful attributions for the entirety of a black-box transformer model and maintaining computational efficiency is an unsolved challenge. By extending the Layer-wise Relevance Propagation attribution method to handle attention layers, we address these challenges effectively. While partial solutions exist, our method is the first to faithfully and holistically attribute not only input but also latent representations of transformer models with the computational efficiency similar to a single backward pass. Through extensive evaluations against existing methods on LLaMa 2, Mixtral 8x7b, Flan-T5 and vision transformer architectures, we demonstrate that our proposed approach surpasses alternative methods in terms of faithfulness and enables the understanding of latent representations, opening up the door for concept-based explanations. We provide an LRP library at https://github.com/rachtibat/LRP-eXplains-Transformers.
URLs: https://github.com/rachtibat/LRP-eXplains-Transformers.
Authors: Nate Gillman, Michael Freeman, Daksh Aggarwal, Chia-Hong Hsu, Calvin Luo, Yonglong Tian, Chen Sun
Abstract: As synthetic data becomes higher quality and proliferates on the internet, machine learning models are increasingly trained on a mix of human- and machine-generated data. Despite the successful stories of using synthetic data for representation learning, using synthetic data for generative model training creates "self-consuming loops" which may lead to training instability or even collapse, unless certain conditions are met. Our paper aims to stabilize self-consuming generative model training. Our theoretical results demonstrate that by introducing an idealized correction function, which maps a data point to be more likely under the true data distribution, self-consuming loops can be made exponentially more stable. We then propose self-correction functions, which rely on expert knowledge (e.g. the laws of physics programmed in a simulator), and aim to approximate the idealized corrector automatically and at scale. We empirically validate the effectiveness of self-correcting self-consuming loops on the challenging human motion synthesis task, and observe that it successfully avoids model collapse, even when the ratio of synthetic data to real data is as high as 100%.
Authors: Zihao Luo, Xilie Xu, Feng Liu, Yun Sing Koh, Di Wang, Jingfeng Zhang
Abstract: Low-rank adaptation (LoRA) is an efficient strategy for adapting latent diffusion models (LDMs) on a private dataset to generate specific images by minimizing the adaptation loss. However, the LoRA-adapted LDMs are vulnerable to membership inference (MI) attacks that can judge whether a particular data point belongs to the private dataset, thus leading to the privacy leakage. To defend against MI attacks, we first propose a straightforward solution: Membership-Privacy-preserving LoRA (MP-LoRA). MP-LoRA is formulated as a min-max optimization problem where a proxy attack model is trained by maximizing its MI gain while the LDM is adapted by minimizing the sum of the adaptation loss and the MI gain of the proxy attack model. However, we empirically find that MP-LoRA has the issue of unstable optimization, and theoretically analyze that the potential reason is the unconstrained local smoothness, which impedes the privacy-preserving adaptation. To mitigate this issue, we further propose a Stable Membership-Privacy-preserving LoRA (SMP-LoRA) that adapts the LDM by minimizing the ratio of the adaptation loss to the MI gain. Besides, we theoretically prove that the local smoothness of SMP-LoRA can be constrained by the gradient norm, leading to improved convergence. Our experimental results corroborate that SMP-LoRA can indeed defend against MI attacks and generate high-quality images. Our code is available at https://github.com/WilliamLUO0/StablePrivateLoRA.
Authors: Cong Geng, Tian Han, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, S{\o}ren Hauberg, Bo Li
Abstract: Generative models have shown strong generation ability while efficient likelihood estimation is less explored. Energy-based models~(EBMs) define a flexible energy function to parameterize unnormalized densities efficiently but are notorious for being difficult to train. Adversarial EBMs introduce a generator to form a minimax training game to avoid expensive MCMC sampling used in traditional EBMs, but a noticeable gap between adversarial EBMs and other strong generative models still exists. Inspired by diffusion-based models, we embedded EBMs into each denoising step to split a long-generated process into several smaller steps. Besides, we employ a symmetric Jeffrey divergence and introduce a variational posterior distribution for the generator's training to address the main challenges that exist in adversarial EBMs. Our experiments show significant improvement in generation compared to existing adversarial EBMs, while also providing a useful energy function for efficient density estimation.
Authors: Yubiao Yue, Zhenzhang Li
Abstract: Since the era of deep learning, convolutional neural networks (CNNs) and vision transformers (ViTs) have been extensively studied and widely used in medical image classification tasks. Unfortunately, CNN's limitations in modeling long-range dependencies result in poor classification performances. In contrast, ViTs are hampered by the quadratic computational complexity of their self-attention mechanism, making them difficult to deploy in real-world settings with limited computational resources. Recent studies have shown that state space models (SSMs) represented by Mamba can effectively model long-range dependencies while maintaining linear computational complexity. Inspired by it, we proposed MedMamba, the first vision Mamba for generalized medical image classification. Concretely, we introduced a novel hybrid basic block named SS-Conv-SSM, which integrates the convolutional layers for extracting local features with the abilities of SSM to capture long-range dependencies, aiming to model medical images from different image modalities efficiently. By employing the grouped convolution strategy and channel-shuffle operation, MedMamba successfully provides fewer model parameters and a lower computational burden for efficient applications. To demonstrate the potential of MedMamba, we conducted extensive experiments using 16 datasets containing ten imaging modalities and 411,007 images. Experimental results show that the proposed MedMamba demonstrates competitive performance in classifying various medical images compared with the state-of-the-art methods. Our work is aims to establish a new baseline for medical image classification and provide valuable insights for developing more powerful SSM-based artificial intelligence algorithms and application systems in the medical field. The source codes and all pre-trained weights of MedMamba are available at https://github.com/YubiaoYue/MedMamba.
Authors: Nishant Kumar, Ziyan Tao, Jaikirat Singh, Yang Li, Peiwen Sun, Binghui Zhao, Stefan Gumhold
Abstract: Image fusion typically employs non-invertible neural networks to merge multiple source images into a single fused image. However, for clinical experts, solely relying on fused images may be insufficient for making diagnostic decisions, as the fusion mechanism blends features from source images, thereby making it difficult to interpret the underlying tumor pathology. We introduce FusionINN, a novel decomposable image fusion framework, capable of efficiently generating fused images and also decomposing them back to the source images. FusionINN is designed to be bijective by including a latent image alongside the fused image, while ensuring minimal transfer of information from the source images to the latent representation. To the best of our knowledge, we are the first to investigate the decomposability of fused images, which is particularly crucial for life-sensitive applications such as medical image fusion compared to other tasks like multi-focus or multi-exposure image fusion. Our extensive experimentation validates FusionINN over existing discriminative and generative fusion methods, both subjectively and objectively. Moreover, compared to a recent denoising diffusion-based fusion model, our approach offers faster and qualitatively better fusion results.
Authors: Brian B. Moser, Federico Raue, Andreas Dengel
Abstract: In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset pruning to solve these challenges. We introduce a novel approach that reduces a dataset to a core-set of training samples, selected based on their loss values as determined by a simple pre-trained SR model. By focusing the training on just 50\% of the original dataset, specifically on the samples characterized by the highest loss values, we achieve results comparable to or surpassing those obtained from training on the entire dataset. Interestingly, our analysis reveals that the top 5\% of samples with the highest loss values negatively affect the training process. Excluding these samples and adjusting the selection to favor easier samples further enhances training outcomes. Our work opens new perspectives to the untapped potential of dataset pruning in image SR. It suggests that careful selection of training data based on loss-value metrics can lead to better SR models, challenging the conventional wisdom that more data inevitably leads to better performance.
Authors: Fouad Trad, Ali Chehab
Abstract: The success of Large Language Models (LLMs) has led to a parallel rise in the development of Large Multimodal Models (LMMs), which have begun to transform a variety of applications. These sophisticated multimodal models are designed to interpret and analyze complex data by integrating multiple modalities such as text and images, thereby opening new avenues for a range of applications. This paper investigates the applicability and effectiveness of prompt-engineered LMMs that process both images and text, including models such as LLaVA, BakLLaVA, Moondream, Gemini-pro-vision, and GPT-4o, compared to fine-tuned Vision Transformer (ViT) models in addressing critical security challenges. We focus on two distinct security tasks: 1) a visually evident task of detecting simple triggers, such as small pixel variations in images that could be exploited to access potential backdoors in the models, and 2) a visually non-evident task of malware classification through visual representations. In the visually evident task, some LMMs, such as Gemini-pro-vision and GPT-4o, have demonstrated the potential to achieve good performance with careful prompt engineering, with GPT-4o achieving the highest accuracy and F1-score of 91.9\% and 91\%, respectively. However, the fine-tuned ViT models exhibit perfect performance in this task due to its simplicity. For the visually non-evident task, the results highlight a significant divergence in performance, with ViT models achieving F1-scores of 97.11\% in predicting 25 malware classes and 97.61\% in predicting 5 malware families, whereas LMMs showed suboptimal performance despite iterative prompt improvements. This study not only showcases the strengths and limitations of prompt-engineered LMMs in cybersecurity applications but also emphasizes the unmatched efficacy of fine-tuned ViT models for precise and dependable tasks.
Authors: Huiyi Wang, Haodong Lu, Lina Yao, Dong Gong
Abstract: Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable representation in pre-trained models (PTMs), PTM-based CL methods perform effective continual adaptation on downstream tasks by adding learnable adapters or prompts upon the frozen PTMs. However, many existing PTM-based CL methods use restricted adaptation on a fixed set of these modules to avoid forgetting, suffering from limited CL ability. Periodically adding task-specific modules results in linear model growth rate and impaired knowledge reuse. We propose Self-Expansion of pre-trained models with Modularized Adaptation (SEMA), a novel approach to enhance the control of stability-plasticity balance in PTM-based CL. SEMA automatically decides to reuse or add adapter modules on demand in CL, depending on whether significant distribution shift that cannot be handled is detected at different representation levels. We design modular adapter consisting of a functional adapter and a representation descriptor. The representation descriptors are trained as a distribution shift indicator and used to trigger self-expansion signals. For better composing the adapters, an expandable weighting router is learned jointly for mixture of adapter outputs. SEMA enables better knowledge reuse and sub-linear expansion rate. Extensive experiments demonstrate the effectiveness of the proposed self-expansion method, achieving state-of-the-art performance compared to PTM-based CL methods without memory rehearsal.
Authors: Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip H. S. Torr, Adel Bibi, Mohamed Elhoseiny
Abstract: We propose and study a realistic Continual Learning (CL) setting where learning algorithms are granted a restricted computational budget per time step while training. We apply this setting to large-scale semi-supervised Continual Learning scenarios with sparse label rates. Previous proficient CL methods perform very poorly in this challenging setting. Overfitting to the sparse labeled data and insufficient computational budget are the two main culprits for such a poor performance. Our new setting encourages learning methods to effectively and efficiently utilize the unlabeled data during training. To that end, we propose a simple but highly effective baseline, DietCL, which utilizes both unlabeled and labeled data jointly. DietCL meticulously allocates computational budget for both types of data. We validate our baseline, at scale, on several datasets, e.g., CLOC, ImageNet10K, and CGLM, under constraint budget setups. DietCL outperforms, by a large margin, all existing supervised CL algorithms as well as more recent continual semi-supervised methods. Our extensive analysis and ablations demonstrate that DietCL is stable under a full spectrum of label sparsity, computational budget, and various other ablations.
Authors: Letitia Parcalabescu, Anette Frank
Abstract: Vision and language model (VLM) decoders are currently the best-performing architectures on multimodal tasks. Next to predictions, they can also produce explanations, either in post-hoc or CoT settings. However, it is not clear how much they use the vision and text modalities when generating predictions or explanations. In this work, we investigate if VLMs rely on modalities differently when they produce explanations as opposed to providing answers. We also evaluate the self-consistency of VLM decoders in both post-hoc and CoT explanation settings, by extending existing unimodal tests and measures to VLM decoders. We find that VLMs are less self-consistent than LLMs. Text contributions in VL decoders are more important than image contributions in all examined tasks. Moreover, the contributions of images are significantly stronger for explanation generation compared to answer generation. This difference is even larger in CoT compared to post-hoc explanations. Lastly, we provide an up-to-date benchmarking of state-of-the-art VL decoders on the VALSE benchmark, which before only covered VL encoders. We find that VL decoders still struggle with most phenomena tested by VALSE.
Authors: Ola Shorinwa, Johnathan Tucker, Aliyah Smith, Aiden Swann, Timothy Chen, Roya Firoozi, Monroe Kennedy III, Mac Schwager
Abstract: We present Splat-MOVER, a modular robotics stack for open-vocabulary robotic manipulation, which leverages the editability of Gaussian Splatting (GSplat) scene representations to enable multi-stage manipulation tasks. Splat-MOVER consists of: (i) ASK-Splat, a GSplat representation that distills semantic and grasp affordance features into the 3D scene. ASK-Splat enables geometric, semantic, and affordance understanding of 3D scenes, which is critical in many robotics tasks; (ii) SEE-Splat, a real-time scene-editing module using 3D semantic masking and infilling to visualize the motions of objects that result from robot interactions in the real-world. SEE-Splat creates a "digital twin" of the evolving environment throughout the manipulation task; and (iii) Grasp-Splat, a grasp generation module that uses ASK-Splat and SEE-Splat to propose affordance-aligned candidate grasps for open-world objects. ASK-Splat is trained in real-time from RGB images in a brief scanning phase prior to operation, while SEE-Splat and Grasp-Splat run in real-time during operation. We demonstrate the superior performance of Splat-MOVER in hardware experiments on a Kinova robot compared to two recent baselines in four single-stage, open-vocabulary manipulation tasks and in four multi-stage manipulation tasks, using the edited scene to reflect changes due to prior manipulation stages, which is not possible with existing baselines. The project page is available at https://splatmover.github.io, and the code for the project will be made available after review.
Authors: Yingqing He, Zhaoyang Liu, Jingye Chen, Zeyue Tian, Hongyu Liu, Xiaowei Chi, Runtao Liu, Ruibin Yuan, Yazhou Xing, Wenhai Wang, Jifeng Dai, Yong Zhang, Wei Xue, Qifeng Liu, Yike Guo, Qifeng Chen
Abstract: With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal understanding. This survey elaborates on multimodal generation and editing across various domains, comprising image, video, 3D, and audio. Specifically, we summarize the notable advancements with milestone works in these fields and categorize these studies into LLM-based and CLIP/T5-based methods. Then, we summarize the various roles of LLMs in multimodal generation and exhaustively investigate the critical technical components behind these methods and the multimodal datasets utilized in these studies. Additionally, we dig into tool-augmented multimodal agents that can leverage existing generative models for human-computer interaction. Lastly, we discuss the advancements in the generative AI safety field, investigate emerging applications, and discuss future prospects. Our work provides a systematic and insightful overview of multimodal generation and processing, which is expected to advance the development of Artificial Intelligence for Generative Content (AIGC) and world models. A curated list of all related papers can be found at https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation
URLs: https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation
Authors: Xiaolun Jing, Genke Yang, Jian Chu
Abstract: CLIP4Clip model transferred from the CLIP has been the de-factor standard to solve the video clip retrieval task from frame-level input, triggering the surge of CLIP4Clip-based models in the video-text retrieval domain. In this work, we rethink the inherent limitation of widely-used mean pooling operation in the frame features aggregation and investigate the adaptions of excitation and aggregation design for discriminative video representation generation. We present a novel excitationand-aggregation design, including (1) The excitation module is available for capturing non-mutuallyexclusive relationships among frame features and achieving frame-wise features recalibration, and (2) The aggregation module is applied to learn exclusiveness used for frame representations aggregation. Similarly, we employ the cascade of sequential module and aggregation design to generate discriminative video representation in the sequential type. Besides, we adopt the excitation design in the tight type to obtain representative frame features for multi-modal interaction. The proposed modules are evaluated on three benchmark datasets of MSR-VTT, ActivityNet and DiDeMo, achieving MSR-VTT (43.9 R@1), ActivityNet (44.1 R@1) and DiDeMo (31.0 R@1). They outperform the CLIP4Clip results by +1.2% (+0.5%), +4.5% (+1.9%) and +9.5% (+2.7%) relative (absolute) improvements, demonstrating the superiority of our proposed excitation and aggregation designs. We hope our work will serve as an alternative for frame representations aggregation and facilitate future research.
Authors: Desislav Ivanov, Carlo Alberto Barbano, Marco Grangetto
Abstract: Traditional staining normalization approaches, e.g. Macenko, typically rely on the choice of a single representative reference image, which may not adequately account for the diverse staining patterns of datasets collected in practical scenarios. In this study, we introduce a novel approach that leverages multiple reference images to enhance robustness against stain variation. Our method is parameter-free and can be adopted in existing computational pathology pipelines with no significant changes. We evaluate the effectiveness of our method through experiments using a deep-learning pipeline for automatic nuclei segmentation on colorectal images. Our results show that by leveraging multiple reference images, better results can be achieved when generalizing to external data, where the staining can widely differ from the training set.
Authors: Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, Rowan Wang, Zico Kolter, Matt Fredrikson, Dan Hendrycks
Abstract: AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with "circuit breakers." Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, circuit-breaking directly controls the representations that are responsible for harmful outputs in the first place. Our technique can be applied to both text-only and multimodal language models to prevent the generation of harmful outputs without sacrificing utility -- even in the presence of powerful unseen attacks. Notably, while adversarial robustness in standalone image recognition remains an open challenge, circuit breakers allow the larger multimodal system to reliably withstand image "hijacks" that aim to produce harmful content. Finally, we extend our approach to AI agents, demonstrating considerable reductions in the rate of harmful actions when they are under attack. Our approach represents a significant step forward in the development of reliable safeguards to harmful behavior and adversarial attacks.