Authors: Denis Zavadski, Damjan Kal\v{s}an, Carsten Rother
Abstract: This work addresses the task of zero-shot monocular depth estimation. A recent advance in this field has been the idea of utilising Text-to-Image foundation models, such as Stable Diffusion. Foundation models provide a rich and generic image representation, and therefore, little training data is required to reformulate them as a depth estimation model that predicts highly-detailed depth maps and has good generalisation capabilities. However, the realisation of this idea has so far led to approaches which are, unfortunately, highly inefficient at test-time due to the underlying iterative denoising process. In this work, we propose a different realisation of this idea and present PrimeDepth, a method that is highly efficient at test time while keeping, or even enhancing, the positive aspects of diffusion-based approaches. Our key idea is to extract from Stable Diffusion a rich, but frozen, image representation by running a single denoising step. This representation, we term preimage, is then fed into a refiner network with an architectural inductive bias, before entering the downstream task. We validate experimentally that PrimeDepth is two orders of magnitude faster than the leading diffusion-based method, Marigold, while being more robust for challenging scenarios and quantitatively marginally superior. Thereby, we reduce the gap to the currently leading data-driven approach, Depth Anything, which is still quantitatively superior, but predicts less detailed depth maps and requires 20 times more labelled data. Due to the complementary nature of our approach, even a simple averaging between PrimeDepth and Depth Anything predictions can improve upon both methods and sets a new state-of-the-art in zero-shot monocular depth estimation. In future, data-driven approaches may also benefit from integrating our preimage.
Authors: Qifan Fu, Xiaohang Yang, Muhammad Asad, Changjae Oh, Shanxin Yuan, Gregory Slabaugh
Abstract: Diffusion models have shown their remarkable ability to synthesize images, including the generation of humans in specific poses. However, current models face challenges in adequately expressing conditional control for detailed hand pose generation, leading to significant distortion in the hand regions. To tackle this problem, we first curate the How2Sign dataset to provide richer and more accurate hand pose annotations. In addition, we introduce adaptive, multi-modal fusion to integrate characters' physical features expressed in different modalities such as skeleton, depth, and surface normal. Furthermore, we propose a novel Region-Aware Cycle Loss (RACL) that enables the diffusion model training to focus on improving the hand region, resulting in improved quality of generated hand gestures. More specifically, the proposed RACL computes a weighted keypoint distance between the full-body pose keypoints from the generated image and the ground truth, to generate higher-quality hand poses while balancing overall pose accuracy. Moreover, we use two hand region metrics, named hand-PSNR and hand-Distance for hand pose generation evaluations. Our experimental evaluations demonstrate the effectiveness of our proposed approach in improving the quality of digital human pose generation using diffusion models, especially the quality of the hand region. The source code is available at https://github.com/fuqifan/Region-Aware-Cycle-Loss.
Authors: Karim Radouane, Sylvie Ranwez, Julien Lagarde, Andon Tchechmedjiev
Abstract: In this paper, we address a challenging task, synchronous motion captioning, that aim to generate a language description synchronized with human motion sequences. This task pertains to numerous applications, such as aligned sign language transcription, unsupervised action segmentation and temporal grounding. Our method introduces mechanisms to control self- and cross-attention distributions of the Transformer, allowing interpretability and time-aligned text generation. We achieve this through masking strategies and structuring losses that push the model to maximize attention only on the most important frames contributing to the generation of a motion word. These constraints aim to prevent undesired mixing of information in attention maps and to provide a monotonic attention distribution across tokens. Thus, the cross attentions of tokens are used for progressive text generation in synchronization with human motion sequences. We demonstrate the superior performance of our approach through evaluation on the two available benchmark datasets, KIT-ML and HumanML3D. As visual evaluation is essential for this task, we provide a comprehensive set of animated visual illustrations in the code repository: https://github.com/rd20karim/Synch-Transformer.
Authors: Qiao Xiao, Boqian Wu, Lu Yin, Christopher Neil Gadzinski, Tianjin Huang, Mykola Pechenizkiy, Decebal Constantin Mocanu
Abstract: While deep learning has demonstrated impressive progress, it remains a daunting challenge to learn from hard samples as these samples are usually noisy and intricate. These hard samples play a crucial role in the optimal performance of deep neural networks. Most research on Sparse Neural Networks (SNNs) has focused on standard training data, leaving gaps in understanding their effectiveness on complex and challenging data. This paper's extensive investigation across scenarios reveals that most SNNs trained on challenging samples can often match or surpass dense models in accuracy at certain sparsity levels, especially with limited data. We observe that layer-wise density ratios tend to play an important role in SNN performance, particularly for methods that train from scratch without pre-trained initialization. These insights enhance our understanding of SNNs' behavior and potential for efficient learning approaches in data-centric AI. Our code is publicly available at: \url{https://github.com/QiaoXiao7282/hard_sample_learners}.
Authors: Yiwen Guan, Viet Anh Trinh, Vivek Voleti, Jacob Whitehill
Abstract: Decoder-only discrete-token language models have recently achieved significant success in automatic speech recognition. However, systematic analyses of how different modalities impact performance in specific scenarios remain limited. In this paper, we investigate the effects of multiple modalities on recognition accuracy on both synthetic and real-world datasets. Our experiments suggest that: (1) Integrating more modalities can increase accuracy; in particular, our paper is, to our best knowledge, the first to show the benefit of combining audio, image context, and lip information; (2) Images as a supplementary modality for speech recognition provide the greatest benefit at moderate noise levels, moreover, they exhibit a different trend compared to inherently synchronized modalities like lip movements; (3) Performance improves on both synthetic and real-world datasets when the most relevant visual information is filtered as a preprocessing step.
Authors: Wei Liu, Saurabh Prasad, Melba Crawford
Abstract: In the past three years, there has been significant interest in hyperspectral imagery (HSI) classification using vision Transformers for analysis of remotely sensed data. Previous research predominantly focused on the empirical integration of convolutional neural networks (CNNs) to augment the network's capability to extract local feature information. Yet, the theoretical justification for vision Transformers out-performing CNN architectures in HSI classification remains a question. To address this issue, a unified hierarchical spectral vision Transformer architecture, specifically tailored for HSI classification, is investigated. In this streamlined yet effective vision Transformer architecture, multiple mixer modules are strategically integrated separately. These include the CNN-mixer, which executes convolution operations; the spatial self-attention (SSA)-mixer and channel self-attention (CSA)-mixer, both of which are adaptations of classical self-attention blocks; and hybrid models such as the SSA+CNN-mixer and CSA+CNN-mixer, which merge convolution with self-attention operations. This integration facilitates the development of a broad spectrum of vision Transformer-based models tailored for HSI classification. In terms of the training process, a comprehensive analysis is performed, contrasting classical CNN models and vision Transformer-based counterparts, with particular attention to disturbance robustness and the distribution of the largest eigenvalue of the Hessian. From the evaluations conducted on various mixer models rooted in the unified architecture, it is concluded that the unique strength of vision Transformers can be attributed to their overarching architecture, rather than being exclusively reliant on individual multi-head self-attention (MSA) components.
Authors: Hongyu Sun, Yongcai Wang, Peng Wang, Haoran Deng, Xudong Cai, Deying Li
Abstract: View-based methods have demonstrated promising performance in 3D shape understanding. However, they tend to make strong assumptions about the relations between views or learn the multi-view correlations indirectly, which limits the flexibility of exploring inter-view correlations and the effectiveness of target tasks. To overcome the above problems, this paper investigates flexible organization and explicit correlation learning for multiple views. In particular, we propose to incorporate different views of a 3D shape into a permutation-invariant set, referred to as \emph{View Set}, which removes rigid relation assumptions and facilitates adequate information exchange and fusion among views. Based on that, we devise a nimble Transformer model, named \emph{VSFormer}, to explicitly capture pairwise and higher-order correlations of all elements in the set. Meanwhile, we theoretically reveal a natural correspondence between the Cartesian product of a view set and the correlation matrix in the attention mechanism, which supports our model design. Comprehensive experiments suggest that VSFormer has better flexibility, efficient inference efficiency and superior performance. Notably, VSFormer reaches state-of-the-art results on various 3d recognition datasets, including ModelNet40, ScanObjectNN and RGBD. It also establishes new records on the SHREC'17 retrieval benchmark. The code and datasets are available at \url{https://github.com/auniquesun/VSFormer}.
Authors: Neelabh Sinha, Vinija Jain, Aman Chadha
Abstract: Visual Question-Answering (VQA) has become a key use-case in several applications to aid user experience, particularly after Vision-Language Models (VLMs) achieving good results in zero-shot inference. But evaluating different VLMs for an application requirement using a standardized framework in practical settings is still challenging. This paper introduces a comprehensive framework for evaluating VLMs tailored to VQA tasks in practical settings. We present a novel dataset derived from established VQA benchmarks, annotated with task types, application domains, and knowledge types, three key practical aspects on which tasks can vary. We also introduce GoEval, a multimodal evaluation metric developed using GPT-4o, achieving a correlation factor of 56.71% with human judgments. Our experiments with ten state-of-the-art VLMs reveals that no single model excelling universally, making appropriate selection a key design decision. Proprietary models such as Gemini-1.5-Pro and GPT-4o-mini generally outperform others, though open-source models like InternVL-2-8B and CogVLM-2-Llama-3-19B demonstrate competitive strengths in specific contexts, while providing additional advantages. This study guides the selection of VLMs based on specific task requirements and resource constraints, and can also be extended to other vision-language tasks.
Authors: Tetsushi Ohki, Yuya Sato, Masakatsu Nishigaki, Koichi Ito
Abstract: Demographic bias is one of the major challenges for face recognition systems. The majority of existing studies on demographic biases are heavily dependent on specific demographic groups or demographic classifier, making it difficult to address performance for unrecognised groups. This paper introduces ``LabellessFace'', a novel framework that improves demographic bias in face recognition without requiring demographic group labeling typically required for fairness considerations. We propose a novel fairness enhancement metric called the class favoritism level, which assesses the extent of favoritism towards specific classes across the dataset. Leveraging this metric, we introduce the fair class margin penalty, an extension of existing margin-based metric learning. This method dynamically adjusts learning parameters based on class favoritism levels, promoting fairness across all attributes. By treating each class as an individual in facial recognition systems, we facilitate learning that minimizes biases in authentication accuracy among individuals. Comprehensive experiments have demonstrated that our proposed method is effective for enhancing fairness while maintaining authentication accuracy.
Authors: Xinrun Chen, Chengliang Wang, Haojian Ning, Mengzhan Zhang, Mei Shen, Shiying Li
Abstract: Segmentation of indicated targets aids in the precise analysis of optical coherence tomography angiography (OCTA) samples. Existing segmentation methods typically perform on 2D projection targets, making it challenging to capture the variance of segmented objects through the 3D volume. To address this limitation, the low-rank adaptation technique is adopted to fine-tune the Segment Anything Model (SAM) version 2, enabling the tracking and segmentation of specified objects across the OCTA scanning layer sequence. To further this work, a prompt point generation strategy in frame sequence and a sparse annotation method to acquire retinal vessel (RV) layer masks are proposed. This method is named SAM-OCTA2 and has been experimented on the OCTA-500 dataset. It achieves state-of-the-art performance in segmenting the foveal avascular zone (FAZ) on regular 2D en-face and effectively tracks local vessels across scanning layer sequences. The code is available at: https://github.com/ShellRedia/SAM-OCTA2.
Authors: Guang Yang, Jie Li, Xin Liu, Zhusi Zhong, Xinbo Gao
Abstract: Image fusion combines images from multiple domains into one image, containing complementary information from source domains. Existing methods take pixel intensity, texture and high-level vision task information as the standards to determine preservation of information, lacking enhancement for human perception. We introduce an image fusion method, Hierarchical Perception Fusion (HPFusion), which leverages Large Vision-Language Model to incorporate hierarchical human semantic priors, preserving complementary information that satisfies human visual system. We propose multiple questions that humans focus on when viewing an image pair, and answers are generated via the Large Vision-Language Model according to images. The texts of answers are encoded into the fusion network, and the optimization also aims to guide the human semantic distribution of the fused image more similarly to source images, exploring complementary information within the human perception domain. Extensive experiments demonstrate our HPFusoin can achieve high-quality fusion results both for information preservation and human visual enhancement.
Authors: Suzhen Wang, Yifeng Ma, Yu Ding, Zhipeng Hu, Changjie Fan, Tangjie Lv, Zhidong Deng, Xin Yu
Abstract: Individuals have unique facial expression and head pose styles that reflect their personalized speaking styles. Existing one-shot talking head methods cannot capture such personalized characteristics and therefore fail to produce diverse speaking styles in the final videos. To address this challenge, we propose a one-shot style-controllable talking face generation method that can obtain speaking styles from reference speaking videos and drive the one-shot portrait to speak with the reference speaking styles and another piece of audio. Our method aims to synthesize the style-controllable coefficients of a 3D Morphable Model (3DMM), including facial expressions and head movements, in a unified framework. Specifically, the proposed framework first leverages a style encoder to extract the desired speaking styles from the reference videos and transform them into style codes. Then, the framework uses a style-aware decoder to synthesize the coefficients of 3DMM from the audio input and style codes. During decoding, our framework adopts a two-branch architecture, which generates the stylized facial expression coefficients and stylized head movement coefficients, respectively. After obtaining the coefficients of 3DMM, an image renderer renders the expression coefficients into a specific person's talking-head video. Extensive experiments demonstrate that our method generates visually authentic talking head videos with diverse speaking styles from only one portrait image and an audio clip.
Authors: Zimeng Fang, Chao Liang, Xue Zhou, Shuyuan Zhu, Xi Li
Abstract: Multi-object tracking (MOT) emerges as a pivotal and highly promising branch in the field of computer vision. Classical closed-vocabulary MOT (CV-MOT) methods aim to track objects of predefined categories. Recently, some open-vocabulary MOT (OV-MOT) methods have successfully addressed the problem of tracking unknown categories. However, we found that the CV-MOT and OV-MOT methods each struggle to excel in the tasks of the other. In this paper, we present a unified framework, Associate Everything Detected (AED), that simultaneously tackles CV-MOT and OV-MOT by integrating with any off-the-shelf detector and supports unknown categories. Different from existing tracking-by-detection MOT methods, AED gets rid of prior knowledge (e.g. motion cues) and relies solely on highly robust feature learning to handle complex trajectories in OV-MOT tasks while keeping excellent performance in CV-MOT tasks. Specifically, we model the association task as a similarity decoding problem and propose a sim-decoder with an association-centric learning mechanism. The sim-decoder calculates similarities in three aspects: spatial, temporal, and cross-clip. Subsequently, association-centric learning leverages these threefold similarities to ensure that the extracted features are appropriate for continuous tracking and robust enough to generalize to unknown categories. Compared with existing powerful OV-MOT and CV-MOT methods, AED achieves superior performance on TAO, SportsMOT, and DanceTrack without any prior knowledge. Our code is available at https://github.com/balabooooo/AED.
Authors: Jiajun Zhang, Yuxiang Zhang, Liang An, Mengcheng Li, Hongwen Zhang, Zonghai Hu, Yebin Liu
Abstract: Dynamic and dexterous manipulation of objects presents a complex challenge, requiring the synchronization of hand motions with the trajectories of objects to achieve seamless and physically plausible interactions. In this work, we introduce ManiDext, a unified hierarchical diffusion-based framework for generating hand manipulation and grasp poses based on 3D object trajectories. Our key insight is that accurately modeling the contact correspondences between objects and hands during interactions is crucial. Therefore, we propose a continuous correspondence embedding representation that specifies detailed hand correspondences at the vertex level between the object and the hand. This embedding is optimized directly on the hand mesh in a self-supervised manner, with the distance between embeddings reflecting the geodesic distance. Our framework first generates contact maps and correspondence embeddings on the object's surface. Based on these fine-grained correspondences, we introduce a novel approach that integrates the iterative refinement process into the diffusion process during the second stage of hand pose generation. At each step of the denoising process, we incorporate the current hand pose residual as a refinement target into the network, guiding the network to correct inaccurate hand poses. Introducing residuals into each denoising step inherently aligns with traditional optimization process, effectively merging generation and refinement into a single unified framework. Extensive experiments demonstrate that our approach can generate physically plausible and highly realistic motions for various tasks, including single and bimanual hand grasping as well as manipulating both rigid and articulated objects. Code will be available for research purposes.
Authors: Dewen Zhang, Wangpeng An, Hayaru Shouno
Abstract: Current multimodal models are well-suited for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions, primarily due to the lack of specialized instruction-following data. We introduce a new method for generating such data by integrating human keypoints with traditional visual features like captions and bounding boxes. Our approach produces datasets designed for fine-tuning models to excel in human-centric activities, focusing on three specific types: conversation, detailed description, and complex reasoning. We fine-tuned the LLaVA-7B model with this novel dataset, achieving significant improvements across various human pose-related tasks. Experimental results show an overall improvement of 21.18% compared to the original LLaVA-7B model. These findings demonstrate the effectiveness of keypoints-assisted data in enhancing multimodal models.
Authors: Xuesong Li, Xinge Zhu, Yuexin Ma, Subhan Khan, Jose Guivant
Abstract: In this paper, we propose an algorithm for registering sequential bounding boxes with point cloud streams. Unlike popular point cloud registration techniques, the alignment of the point cloud and the bounding box can rely on the properties of the bounding box, such as size, shape, and temporal information, which provides substantial support and performance gains. Motivated by this, we propose a new approach to tackle this problem. Specifically, we model the registration process through an overall objective function that includes the final goal and all constraints. We then optimize the function using gradient descent. Our experiments show that the proposed method performs remarkably well with a 40\% improvement in IoU and demonstrates more robust registration between point cloud streams and sequential bounding boxes
Authors: Daniel Miao, Gilad Lerman, Joe Kileel
Abstract: The block tensor of trifocal tensors provides crucial geometric information on the three-view geometry of a scene. The underlying synchronization problem seeks to recover camera poses (locations and orientations up to a global transformation) from the block trifocal tensor. We establish an explicit Tucker factorization of this tensor, revealing a low multilinear rank of $(6,4,4)$ independent of the number of cameras under appropriate scaling conditions. We prove that this rank constraint provides sufficient information for camera recovery in the noiseless case. The constraint motivates a synchronization algorithm based on the higher-order singular value decomposition of the block trifocal tensor. Experimental comparisons with state-of-the-art global synchronization methods on real datasets demonstrate the potential of this algorithm for significantly improving location estimation accuracy. Overall this work suggests that higher-order interactions in synchronization problems can be exploited to improve performance, beyond the usual pairwise-based approaches.
Authors: Arya Farkhondeh, Samy Tafasca, Jean-Marc Odobez
Abstract: Hand-Object Interaction (HOI) is gaining significant attention, particularly with the creation of numerous egocentric datasets driven by AR/VR applications. However, third-person view HOI has received less attention, especially in terms of datasets. Most third-person view datasets are curated for action recognition tasks and feature pre-segmented clips of high-level daily activities, leaving a gap for in-the-wild datasets. To address this gap, we propose ChildPlay-Hand, a novel dataset that includes person and object bounding boxes, as well as manipulation actions. ChildPlay-Hand is unique in: (1) providing per-hand annotations; (2) featuring videos in uncontrolled settings with natural interactions, involving both adults and children; (3) including gaze labels from the ChildPlay-Gaze dataset for joint modeling of manipulations and gaze. The manipulation actions cover the main stages of an HOI cycle, such as grasping, holding or operating, and different types of releasing. To illustrate the interest of the dataset, we study two tasks: object in hand detection (OiH), i.e. if a person has an object in their hand, and manipulation stages (ManiS), which is more fine-grained and targets the main stages of manipulation. We benchmark various spatio-temporal and segmentation networks, exploring body vs. hand-region information and comparing pose and RGB modalities. Our findings suggest that ChildPlay-Hand is a challenging new benchmark for modeling HOI in the wild.
Authors: Ali Mehrabian, Parsa Mojarad Adi, Moein Heidari, Ilker Hacihaliloglu
Abstract: Implicit neural representations (INRs) use neural networks to provide continuous and resolution-independent representations of complex signals with a small number of parameters. However, existing INR models often fail to capture important frequency components specific to each task. To address this issue, in this paper, we propose a Fourier Kolmogorov Arnold network (FKAN) for INRs. The proposed FKAN utilizes learnable activation functions modeled as Fourier series in the first layer to effectively control and learn the task-specific frequency components. In addition, the activation functions with learnable Fourier coefficients improve the ability of the network to capture complex patterns and details, which is beneficial for high-resolution and high-dimensional data. Experimental results show that our proposed FKAN model outperforms three state-of-the-art baseline schemes, and improves the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) for the image representation task and intersection over union (IoU) for the 3D occupancy volume representation task, respectively.
Authors: Deng Junli, Luo Yihao, Yang Xueting, Li Siyou, Wang Wei, Guo Jinyang, Shi Ping
Abstract: In the domain of photorealistic avatar generation, the fidelity of audio-driven lip motion synthesis is essential for realistic virtual interactions. Existing methods face two key challenges: a lack of vivacity due to limited diversity in generated lip poses and noticeable anamorphose motions caused by poor temporal coherence. To address these issues, we propose LawDNet, a novel deep-learning architecture enhancing lip synthesis through a Local Affine Warping Deformation mechanism. This mechanism models the intricate lip movements in response to the audio input by controllable non-linear warping fields. These fields consist of local affine transformations focused on abstract keypoints within deep feature maps, offering a novel universal paradigm for feature warping in networks. Additionally, LawDNet incorporates a dual-stream discriminator for improved frame-to-frame continuity and employs face normalization techniques to handle pose and scene variations. Extensive evaluations demonstrate LawDNet's superior robustness and lip movement dynamism performance compared to previous methods. The advancements presented in this paper, including the methodologies, training data, source codes, and pre-trained models, will be made accessible to the research community.
Authors: Zhixian He, Pengcheng Zhao, Fuwei Zhang, Shujin Lin
Abstract: In the domain of video question answering (VideoQA), the impact of question types on VQA systems, despite its critical importance, has been relatively under-explored to date. However, the richness of question types directly determines the range of concepts a model needs to learn, thereby affecting the upper limit of its learning capability. This paper focuses on exploring the significance of different question types for VQA systems and their impact on performance, revealing a series of issues such as insufficient learning and model degradation due to uneven distribution of question types. Particularly, considering the significant variation in dependency on temporal information across different question types, and given that the representation of such information coincidentally represents a principal challenge and difficulty for VideoQA as opposed to ImageQA. To address these challenges, we propose QTG-VQA, a novel architecture that incorporates question-type-guided attention and adaptive learning mechanism. Specifically, as to temporal-type questions, we design Masking Frame Modeling technique to enhance temporal modeling, aimed at encouraging the model to grasp richer visual-language relationships and manage more intricate temporal dependencies. Furthermore, a novel evaluation metric tailored to question types is introduced. Experimental results confirm the effectiveness of our approach.
Authors: Jiabao Wang, Zhaojiang Liu, Qiang Meng, Liujiang Yan, Ke Wang, Jie Yang, Wei Liu, Qibin Hou, Ming-Ming Cheng
Abstract: Occupancy prediction, aiming at predicting the occupancy status within voxelized 3D environment, is quickly gaining momentum within the autonomous driving community. Mainstream occupancy prediction works first discretize the 3D environment into voxels, then perform classification on such dense grids. However, inspection on sample data reveals that the vast majority of voxels is unoccupied. Performing classification on these empty voxels demands suboptimal computation resource allocation, and reducing such empty voxels necessitates complex algorithm designs. To this end, we present a novel perspective on the occupancy prediction task: formulating it as a streamlined set prediction paradigm without the need for explicit space modeling or complex sparsification procedures. Our proposed framework, called OPUS, utilizes a transformer encoder-decoder architecture to simultaneously predict occupied locations and classes using a set of learnable queries. Firstly, we employ the Chamfer distance loss to scale the set-to-set comparison problem to unprecedented magnitudes, making training such model end-to-end a reality. Subsequently, semantic classes are adaptively assigned using nearest neighbor search based on the learned locations. In addition, OPUS incorporates a suite of non-trivial strategies to enhance model performance, including coarse-to-fine learning, consistent point sampling, and adaptive re-weighting, etc. Finally, compared with current state-of-the-art methods, our lightest model achieves superior RayIoU on the Occ3D-nuScenes dataset at near 2x FPS, while our heaviest model surpasses previous best results by 6.1 RayIoU.
Authors: Qiyuan Wang, Shang Zhao, Zikang Xu, S Kevin Zhou
Abstract: Surgical instrument segmentation is instrumental to minimally invasive surgeries and related applications. Most previous methods formulate this task as single-frame-based instance segmentation while ignoring the natural temporal and stereo attributes of a surgical video. As a result, these methods are less robust against the appearance variation through temporal motion and view change. In this work, we propose a novel LACOSTE model that exploits Location-Agnostic COntexts in Stereo and TEmporal images for improved surgical instrument segmentation. Leveraging a query-based segmentation model as core, we design three performance-enhancing modules. Firstly, we design a disparity-guided feature propagation module to enhance depth-aware features explicitly. To generalize well for even only a monocular video, we apply a pseudo stereo scheme to generate complementary right images. Secondly, we propose a stereo-temporal set classifier, which aggregates stereo-temporal contexts in a universal way for making a consolidated prediction and mitigates transient failures. Finally, we propose a location-agnostic classifier to decouple the location bias from mask prediction and enhance the feature semantics. We extensively validate our approach on three public surgical video datasets, including two benchmarks from EndoVis Challenges and one real radical prostatectomy surgery dataset GraSP. Experimental results demonstrate the promising performances of our method, which consistently achieves comparable or favorable results with previous state-of-the-art approaches.
Authors: Lei Yu, Jintao Fei, Xinyi Liu, Yang Yao, Jun Zhao, Guoxin Wang, Xin Li
Abstract: Video-based physiology, exemplified by remote photoplethysmography (rPPG), extracts physiological signals such as pulse and respiration by analyzing subtle changes in video recordings. This non-contact, real-time monitoring method holds great potential for home settings. Despite the valuable contributions of public benchmark datasets to this technology, there is currently no dataset specifically designed for passive home monitoring. Existing datasets are often limited to close-up, static, frontal recordings and typically include only 1-2 physiological signals. To advance video-based physiology in real home settings, we introduce the MHAD dataset. It comprises 1,440 videos from 40 subjects, capturing 6 typical activities from 3 angles in a real home environment. Additionally, 5 physiological signals were recorded, making it a comprehensive video-based physiology dataset. MHAD is compatible with the rPPG-toolbox and has been validated using several unsupervised and supervised methods. Our dataset is publicly available at https://github.com/jdh-algo/MHAD-Dataset.
Authors: Pei Liu, Luping Ji, Jiaxiang Gou, Bo Fu, Mao Ye
Abstract: Histopathology Whole-Slide Images (WSIs) provide an important tool to assess cancer prognosis in computational pathology (CPATH). While existing survival analysis (SA) approaches have made exciting progress, they are generally limited to adopting highly-expressive architectures and only coarse-grained patient-level labels to learn prognostic visual representations from gigapixel WSIs. Such learning paradigm suffers from important performance bottlenecks, when facing present scarce training data and standard multi-instance learning (MIL) framework in CPATH. To break through it, this paper, for the first time, proposes a new Vision-Language-based SA (VLSA) paradigm. Concretely, (1) VLSA is driven by pathology VL foundation models. It no longer relies on high-capability networks and shows the advantage of data efficiency. (2) In vision-end, VLSA encodes prognostic language prior and then employs it as auxiliary signals to guide the aggregating of prognostic visual features at instance level, thereby compensating for the weak supervision in MIL. Moreover, given the characteristics of SA, we propose i) ordinal survival prompt learning to transform continuous survival labels into textual prompts; and ii) ordinal incidence function as prediction target to make SA compatible with VL-based prediction. VLSA's predictions can be interpreted intuitively by our Shapley values-based method. The extensive experiments on five datasets confirm the effectiveness of our scheme. Our VLSA could pave a new way for SA in CPATH by offering weakly-supervised MIL an effective means to learn valuable prognostic clues from gigapixel WSIs. Our source code is available at https://github.com/liupei101/VLSA.
Authors: Andrea Dosi, Massimo Brescia, Stefano Cavuoti, Mariarca D'Aniello, Michele Delli Veneri, Carlo Donadio, Adriano Ettari, Giuseppe Longo, Alvi Rownok, Luca Sannino, Maria Zampella
Abstract: Deep learning has revolutionized the field of hyperspectral image (HSI) analysis, enabling the extraction of complex and hierarchical features. While convolutional neural networks (CNNs) have been the backbone of HSI classification, their limitations in capturing global contextual features have led to the exploration of Vision Transformers (ViTs). This paper introduces AMBER, an advanced SegFormer specifically designed for multi-band image segmentation. AMBER enhances the original SegFormer by incorporating three-dimensional convolutions to handle hyperspectral data. Our experiments, conducted on the Indian Pines, Pavia University, and PRISMA datasets, show that AMBER outperforms traditional CNN-based methods in terms of Overall Accuracy, Kappa coefficient, and Average Accuracy on the first two datasets, and achieves state-of-the-art performance on the PRISMA dataset.
Authors: Xiaobin Hong, Tarmizi Adam, Masitah Ghazali
Abstract: Person Re-Identification (Re-ID) has gained popularity in computer vision, enabling cross-camera pedestrian recognition. Although the development of deep learning has provided a robust technical foundation for person Re-ID research, most existing person Re-ID methods overlook the potential relationships among local person features, failing to adequately address the impact of pedestrian pose variations and local body parts occlusion. Therefore, we propose a Transformer-enhanced Graph Convolutional Network (Tran-GCN) model to improve Person Re-Identification performance in monitoring videos. The model comprises four key components: (1) A Pose Estimation Learning branch is utilized to estimate pedestrian pose information and inherent skeletal structure data, extracting pedestrian key point information; (2) A Transformer learning branch learns the global dependencies between fine-grained and semantically meaningful local person features; (3) A Convolution learning branch uses the basic ResNet architecture to extract the person's fine-grained local features; (4) A Graph Convolutional Module (GCM) integrates local feature information, global feature information, and body information for more effective person identification after fusion. Quantitative and qualitative analysis experiments conducted on three different datasets (Market-1501, DukeMTMC-ReID, and MSMT17) demonstrate that the Tran-GCN model can more accurately capture discriminative person features in monitoring videos, significantly improving identification accuracy.
Authors: Tianlong Xu, Yi-Fan Zhang, Zhendong Chu, Shen Wang, Qingsong Wen
Abstract: Students frequently make mistakes while solving mathematical problems, and traditional error correction methods are both time-consuming and labor-intensive. This paper introduces an innovative \textbf{V}irtual \textbf{A}I \textbf{T}eacher system designed to autonomously analyze and correct student \textbf{E}rrors (VATE). Leveraging advanced large language models (LLMs), the system uses student drafts as a primary source for error analysis, which enhances understanding of the student's learning process. It incorporates sophisticated prompt engineering and maintains an error pool to reduce computational overhead. The AI-driven system also features a real-time dialogue component for efficient student interaction. Our approach demonstrates significant advantages over traditional and machine learning-based error correction methods, including reduced educational costs, high scalability, and superior generalizability. The system has been deployed on the Squirrel AI learning platform for elementary mathematics education, where it achieves 78.3\% accuracy in error analysis and shows a marked improvement in student learning efficiency. Satisfaction surveys indicate a strong positive reception, highlighting the system's potential to transform educational practices.
Authors: Xingxing Wei, Caixin Kang, Yinpeng Dong, Zhengyi Wang, Shouwei Ruan, Yubo Chen, Hang Su
Abstract: Adversarial patches present significant challenges to the robustness of deep learning models, making the development of effective defenses become critical for real-world applications. This paper introduces DIFFender, a novel DIFfusion-based DeFender framework that leverages the power of a text-guided diffusion model to counter adversarial patch attacks. At the core of our approach is the discovery of the Adversarial Anomaly Perception (AAP) phenomenon, which enables the diffusion model to accurately detect and locate adversarial patches by analyzing distributional anomalies. DIFFender seamlessly integrates the tasks of patch localization and restoration within a unified diffusion model framework, enhancing defense efficacy through their close interaction. Additionally, DIFFender employs an efficient few-shot prompt-tuning algorithm, facilitating the adaptation of the pre-trained diffusion model to defense tasks without the need for extensive retraining. Our comprehensive evaluation, covering image classification and face recognition tasks, as well as real-world scenarios, demonstrates DIFFender's robust performance against adversarial attacks. The framework's versatility and generalizability across various settings, classifiers, and attack methodologies mark a significant advancement in adversarial patch defense strategies. Except for the popular visible domain, we have identified another advantage of DIFFender: its capability to easily expand into the infrared domain. Consequently, we demonstrate the good flexibility of DIFFender, which can defend against both infrared and visible adversarial patch attacks alternatively using a universal defense framework.
Authors: David Tschirschwitz, Volker Rodehorst
Abstract: Annotation errors are a challenge not only during training of machine learning models, but also during their evaluation. Label variations and inaccuracies in datasets often manifest as contradictory examples that deviate from established labeling conventions. Such inconsistencies, when significant, prevent models from achieving optimal performance on metrics such as mean Average Precision (mAP). We introduce the notion of "label convergence" to describe the highest achievable performance under the constraint of contradictory test annotations, essentially defining an upper bound on model accuracy. Recognizing that noise is an inherent characteristic of all data, our study analyzes five real-world datasets, including the LVIS dataset, to investigate the phenomenon of label convergence. We approximate that label convergence is between 62.63-67.52 mAP@[0.5:0.95:0.05] for LVIS with 95% confidence, attributing these bounds to the presence of real annotation errors. With current state-of-the-art (SOTA) models at the upper end of the label convergence interval for the well-studied LVIS dataset, we conclude that model capacity is sufficient to solve current object detection problems. Therefore, future efforts should focus on three key aspects: (1) updating the problem specification and adjusting evaluation practices to account for unavoidable label noise, (2) creating cleaner data, especially test data, and (3) including multi-annotated data to investigate annotation variation and make these issues visible from the outset.
Authors: Yechan Kim, SooYeon Kim, Moongu Jeon
Abstract: Data augmentation has seen significant advancements in computer vision to improve model performance over the years, particularly in scenarios with limited and insufficient data. Currently, most studies focus on adjusting the image or its features to expand the size, quality, and variety of samples during training in various tasks including object detection. However, we argue that it is necessary to investigate bounding box transformations as a model regularization technique rather than image-level transformations, especially in aerial imagery due to potentially inconsistent bounding box annotations. Hence, this letter presents a thorough investigation of bounding box transformation in terms of scaling, rotation, and translation for remote sensing object detection. We call this augmentation strategy NBBOX (Noise Injection into Bounding Box). We conduct extensive experiments on DOTA and DIOR-R, both well-known datasets that include a variety of rotated generic objects in aerial images. Experimental results show that our approach significantly improves remote sensing object detection without whistles and bells and it is more time-efficient than other state-of-the-art augmentation strategies.
Authors: Amirreza Mahbod, Nematollah Saeidi, Sepideh Hatamikia, Ramona Woitek
Abstract: Medical image retrieval refers to the task of finding similar images for given query images in a database, with applications such as diagnosis support, treatment planning, and educational tools for inexperienced medical practitioners. While traditional medical image retrieval was performed using clinical metadata, content-based medical image retrieval (CBMIR) relies on the characteristic features of the images, such as color, texture, shape, and spatial features. Many approaches have been proposed for CBMIR, and among them, using pre-trained convolutional neural networks (CNNs) is a widely utilized approach. However, considering the recent advances in the development of foundation models for various computer vision tasks, their application for CBMIR can be also investigated for its potentially superior performance. In this study, we used several pre-trained feature extractors from well-known pre-trained CNNs (VGG19, ResNet-50, DenseNet121, and EfficientNetV2M) and pre-trained foundation models (MedCLIP, BioMedCLIP, OpenCLIP, CONCH and UNI) and investigated the CBMIR performance on a subset of the MedMNIST V2 dataset, including eight types of 2D and 3D medical images. Furthermore, we also investigated the effect of image size on the CBMIR performance. Our results show that, overall, for the 2D datasets, foundation models deliver superior performance by a large margin compared to CNNs, with UNI providing the best overall performance across all datasets and image sizes. For 3D datasets, CNNs and foundation models deliver more competitive performance, with CONCH achieving the best overall performance. Moreover, our findings confirm that while using larger image sizes (especially for 2D datasets) yields slightly better performance, competitive CBMIR performance can still be achieved even with smaller image sizes. Our codes to generate and reproduce the results are available on GitHub.
Authors: Elliot Vincent, Mehra\"il Saroufim, Jonathan Chemla, Yves Ubelmann, Philippe Marquis, Jean Ponce, Mathieu Aubry
Abstract: Archaeological sites are the physical remains of past human activity and one of the main sources of information about past societies and cultures. However, they are also the target of malevolent human actions, especially in countries having experienced inner turmoil and conflicts. Because monitoring these sites from space is a key step towards their preservation, we introduce the DAFA Looted Sites dataset, \datasetname, a labeled multi-temporal remote sensing dataset containing 55,480 images acquired monthly over 8 years across 675 Afghan archaeological sites, including 135 sites looted during the acquisition period. \datasetname~is particularly challenging because of the limited number of training samples, the class imbalance, the weak binary annotations only available at the level of the time series, and the subtlety of relevant changes coupled with important irrelevant ones over a long time period. It is also an interesting playground to assess the performance of satellite image time series (SITS) classification methods on a real and important use case. We evaluate a large set of baselines, outline the substantial benefits of using foundation models and show the additional boost that can be provided by using complete time series instead of using a single image.
Authors: Zhaoyu Chen, Xing Li, Qian Huang, Qiang Geng, Tianjin Yang, Shihao Han
Abstract: Point cloud sequence-based 3D action recognition has achieved impressive performance and efficiency. However, existing point cloud sequence modeling methods cannot adequately balance the precision of limb micro-movements with the integrity of posture macro-structure, leading to the loss of crucial information cues in action inference. To overcome this limitation, we introduce D-Hyperpoint, a novel data type generated through a D-Hyperpoint Embedding module. D-Hyperpoint encapsulates both regional-momentary motion and global-static posture, effectively summarizing the unit human action at each moment. In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints. Finally, we propose KAN-HyperpointNet, a spatio-temporal decoupled network architecture for 3D action recognition. Extensive experiments on two public datasets: MSR Action3D and NTU-RGB+D 60, demonstrate the state-of-the-art performance of our method.
Authors: Yan Feng, Alexander Carballo, Keisuke Fujii, Robin Karlsson, Ming Ding, Kazuya Takeda
Abstract: Pedestrian action prediction is of great significance for many applications such as autonomous driving. However, state-of-the-art methods lack explainability to make trustworthy predictions. In this paper, a novel framework called MulCPred is proposed that explains its predictions based on multi-modal concepts represented by training samples. Previous concept-based methods have limitations including: 1) they cannot directly apply to multi-modal cases; 2) they lack locality to attend to details in the inputs; 3) they suffer from mode collapse. These limitations are tackled accordingly through the following approaches: 1) a linear aggregator to integrate the activation results of the concepts into predictions, which associates concepts of different modalities and provides ante-hoc explanations of the relevance between the concepts and the predictions; 2) a channel-wise recalibration module that attends to local spatiotemporal regions, which enables the concepts with locality; 3) a feature regularization loss that encourages the concepts to learn diverse patterns. MulCPred is evaluated on multiple datasets and tasks. Both qualitative and quantitative results demonstrate that MulCPred is promising in improving the explainability of pedestrian action prediction without obvious performance degradation. Furthermore, by removing unrecognizable concepts from MulCPred, the cross-dataset prediction performance is improved, indicating the feasibility of further generalizability of MulCPred.
Authors: Yi-Chia Chang, Adam J. Stewart, Favyen Bastani, Piper Wolters, Shreya Kannan, George R. Huber, Jingtong Wang, Arindam Banerjee
Abstract: Foundation models pre-trained using self-supervised and weakly-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text generation, and image recognition. Recently, the Earth observation (EO) field has produced several foundation models pre-trained directly on multispectral satellite imagery (e.g., Sentinel-2) for applications like precision agriculture, wildfire and drought monitoring, and natural disaster response. However, few studies have investigated the ability of these models to generalize to new geographic locations, and potential concerns of geospatial bias -- models trained on data-rich developed countries not transferring well to data-scarce developing countries -- remain. We investigate the ability of popular EO foundation models to transfer to new geographic regions in the agricultural domain, where differences in farming practices and class imbalance make transfer learning particularly challenging. We first select six crop classification datasets across five continents, normalizing for dataset size and harmonizing classes to focus on four major cereal grains: maize, soybean, rice, and wheat. We then compare three popular foundation models, pre-trained on SSL4EO-S12, SatlasPretrain, and ImageNet, using in-distribution (ID) and out-of-distribution (OOD) evaluation. Experiments show that pre-trained weights designed explicitly for Sentinel-2, such as SSL4EO-S12, outperform general pre-trained weights like ImageNet. Furthermore, the benefits of pre-training on OOD data are the most significant when only 10--100 ID training samples are used. Transfer learning and pre-training with OOD and limited ID data show promising applications, as many developing regions have scarce crop type labels. All harmonized datasets and experimental code are open-source and available for download.
Authors: Daniel Khalil, Christina Liu, Pietro Perona, Jennifer J. Sun, Markus Marks
Abstract: The study of social interactions and collective behaviors through multi-agent video analysis is crucial in biology. While self-supervised keypoint discovery has emerged as a promising solution to reduce the need for manual keypoint annotations, existing methods often struggle with videos containing multiple interacting agents, especially those of the same species and color. To address this, we introduce B-KinD-multi, a novel approach that leverages pre-trained video segmentation models to guide keypoint discovery in multi-agent scenarios. This eliminates the need for time-consuming manual annotations on new experimental settings and organisms. Extensive evaluations demonstrate improved keypoint regression and downstream behavioral classification in videos of flies, mice, and rats. Furthermore, our method generalizes well to other species, including ants, bees, and humans, highlighting its potential for broad applications in automated keypoint annotation for multi-agent behavior analysis. Code available under: https://danielpkhalil.github.io/B-KinD-Multi
Authors: Hugo Porta, Emanuele Dalsasso, Diego Marcos, Devis Tuia
Abstract: Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity between parts of the test image and the prototypes. This improves interpretability since the user can inspect the link between the predicted output and the patterns learned by the model in terms of prototypical information. In this paper, we propose a method for interpretable semantic segmentation that leverages multi-scale image representation for prototypical part learning. First, we introduce a prototype layer that explicitly learns diverse prototypical parts at several scales, leading to multi-scale representations in the prototype activation output. Then, we propose a sparse grouping mechanism that produces multi-scale sparse groups of these scale-specific prototypical parts. This provides a deeper understanding of the interactions between multi-scale object representations while enhancing the interpretability of the segmentation model. The experiments conducted on Pascal VOC, Cityscapes, and ADE20K demonstrate that the proposed method increases model sparsity, improves interpretability over existing prototype-based methods, and narrows the performance gap with the non-interpretable counterpart models. Code is available at github.com/eceo-epfl/ScaleProtoSeg.
Authors: Emanuele Vivoli, Andrey Barsky, Mohamed Ali Souibgui, Artemis LLabres, Marco Bertini, Dimosthenis Karatzas
Abstract: Vision-language models have recently evolved into versatile systems capable of high performance across a range of tasks, such as document understanding, visual question answering, and grounding, often in zero-shot settings. Comics Understanding, a complex and multifaceted field, stands to greatly benefit from these advances. Comics, as a medium, combine rich visual and textual narratives, challenging AI models with tasks that span image classification, object detection, instance segmentation, and deeper narrative comprehension through sequential panels. However, the unique structure of comics -- characterized by creative variations in style, reading order, and non-linear storytelling -- presents a set of challenges distinct from those in other visual-language domains. In this survey, we present a comprehensive review of Comics Understanding from both dataset and task perspectives. Our contributions are fivefold: (1) We analyze the structure of the comics medium, detailing its distinctive compositional elements; (2) We survey the widely used datasets and tasks in comics research, emphasizing their role in advancing the field; (3) We introduce the Layer of Comics Understanding (LoCU) framework, a novel taxonomy that redefines vision-language tasks within comics and lays the foundation for future work; (4) We provide a detailed review and categorization of existing methods following the LoCU framework; (5) Finally, we highlight current research challenges and propose directions for future exploration, particularly in the context of vision-language models applied to comics. This survey is the first to propose a task-oriented framework for comics intelligence and aims to guide future research by addressing critical gaps in data availability and task definition. A project associated with this survey is available at https://github.com/emanuelevivoli/awesome-comics-understanding.
URLs: https://github.com/emanuelevivoli/awesome-comics-understanding.
Authors: Xin Hu, Janet Wang, Jihun Hamm, Rie R Yotsu, Zhengming Ding
Abstract: Current AI-assisted skin image diagnosis has achieved dermatologist-level performance in classifying skin cancer, driven by rapid advancements in deep learning architectures. However, unlike traditional vision tasks, skin images in general present unique challenges due to the limited availability of well-annotated datasets, complex variations in conditions, and the necessity for detailed interpretations to ensure patient safety. Previous segmentation methods have sought to reduce image noise and enhance diagnostic performance, but these techniques require fine-grained, pixel-level ground truth masks for training. In contrast, with the rise of foundation models, the Segment Anything Model (SAM) has been introduced to facilitate promptable segmentation, enabling the automation of the segmentation process with simple yet effective prompts. Efforts applying SAM predominantly focus on dermatoscopy images, which present more easily identifiable lesion boundaries than clinical photos taken with smartphones. This limitation constrains the practicality of these approaches to real-world applications. To overcome the challenges posed by noisy clinical photos acquired via non-standardized protocols and to improve diagnostic accessibility, we propose a novel Cross-Attentive Fusion framework for interpretable skin lesion diagnosis. Our method leverages SAM to generate visual concepts for skin diseases using prompts, integrating local visual concepts with global image features to enhance model performance. Extensive evaluation on two skin disease datasets demonstrates our proposed method's effectiveness on lesion diagnosis and interpretability.
Authors: Zheming Zuo, Joseph Smith, Jonathan Stonehouse, Boguslaw Obara
Abstract: Image segmentation is a crucial task in computer vision, with wide-ranging applications in industry. The Segment Anything Model (SAM) has recently attracted intensive attention; however, its application in industrial inspection, particularly for segmenting commercial anti-counterfeit codes, remains challenging. Unlike open-source datasets, industrial settings often face issues such as small sample sizes and complex textures. Additionally, computational cost is a key concern due to the varying number of trainable parameters. To address these challenges, we propose an Augmentation-based Model Re-adaptation Framework (AMRF). This framework leverages data augmentation techniques during training to enhance the generalisation of segmentation models, allowing them to adapt to newly released datasets with temporal disparity. By observing segmentation masks from conventional models (FCN and U-Net) and a pre-trained SAM model, we determine a minimal augmentation set that optimally balances training efficiency and model performance. Our results demonstrate that the fine-tuned FCN surpasses its baseline by 3.29% and 3.02% in cropping accuracy, and 5.27% and 4.04% in classification accuracy on two temporally continuous datasets. Similarly, the fine-tuned U-Net improves upon its baseline by 7.34% and 4.94% in cropping, and 8.02% and 5.52% in classification. Both models outperform the top-performing SAM models (ViT-Large and ViT-Base) by an average of 11.75% and 9.01% in cropping accuracy, and 2.93% and 4.83% in classification accuracy, respectively.
Authors: Aleksei Krotov, Alison Tebo, Dylan K. Picart, Aaron Dean Algave
Abstract: The growth of deep learning (DL) relies heavily on huge amounts of labelled data for tasks such as natural language processing and computer vision. Specifically, in image-to-text or image-to-image pipelines, opinion (sentiment) may be inadvertently learned by a model from human-generated image captions. Additionally, learning may be affected by the variety and diversity of the provided captions. While labelling large datasets has largely relied on crowd-sourcing or data-worker pools, evaluating the quality of such training data is crucial. This study proposes an evaluation method focused on sentiment and semantic richness. That method was applied to the COCO-MS dataset, comprising approximately 150K images with segmented objects and corresponding crowd-sourced captions. We employed pre-trained models (Twitter-RoBERTa-base and BERT-base) to extract sentiment scores and variability of semantic embeddings from captions. The relation of the sentiment score and semantic variability with object categories was examined using multiple linear regression. Results indicate that while most captions were neutral, about 6% of the captions exhibited strong sentiment influenced by specific object categories. Semantic variability of within-image captions remained low and uncorrelated with object categories. Model-generated captions showed less than 1.5% of strong sentiment which was not influenced by object categories and did not correlate with the sentiment of the respective human-generated captions. This research demonstrates an approach to assess the quality of crowd- or worker-sourced captions informed by image content.
Authors: Dawei Yan, Pengcheng Li, Yang Li, Hao Chen, Qingguo Chen, Weihua Luo, Wei Dong, Qingsen Yan, Haokui Zhang, Chunhua Shen
Abstract: Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the connector and enhancing the language model component, while neglecting improvements to the vision encoder itself. In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction. Specifically, inspired by the purpose-driven logic inherent in human behavior, we use learnable latent embeddings as a bridge to analyze textual instruction and add the analysis results to the vision encoder as guidance, refining it. Subsequently, another set of latent embeddings extracts additional detailed text-guided information from high-resolution local patches as auxiliary information. Finally, with the guidance of text, the vision encoder can extract text-related features, similar to how humans focus on the most relevant parts of an image when considering a question. This results in generating better answers. Experiments on various datasets validate the effectiveness of the proposed method. Remarkably, without the need for additional training data, our propsoed method can bring more benefits to the baseline (LLaVA-1.5) compared with other concurrent methods. Furthermore, the proposed method consistently brings improvement in different settings.
Authors: Kushal Vyas, Ahmed Imtiaz Humayun, Aniket Dashpute, Richard G. Baraniuk, Ashok Veeraraghavan, Guha Balakrishnan
Abstract: Implicit neural representations (INRs) have demonstrated success in a variety of applications, including inverse problems and neural rendering. An INR is typically trained to capture one signal of interest, resulting in learned neural features that are highly attuned to that signal. Assumed to be less generalizable, we explore the aspect of transferability of such learned neural features for fitting similar signals. We introduce a new INR training framework, STRAINER that learns transferrable features for fitting INRs to new signals from a given distribution, faster and with better reconstruction quality. Owing to the sequential layer-wise affine operations in an INR, we propose to learn transferable representations by sharing initial encoder layers across multiple INRs with independent decoder layers. At test time, the learned encoder representations are transferred as initialization for an otherwise randomly initialized INR. We find STRAINER to yield extremely powerful initialization for fitting images from the same domain and allow for $\approx +10dB$ gain in signal quality early on compared to an untrained INR itself. STRAINER also provides a simple way to encode data-driven priors in INRs. We evaluate STRAINER on multiple in-domain and out-of-domain signal fitting tasks and inverse problems and further provide detailed analysis and discussion on the transferability of STRAINER's features. Our demo can be accessed at https://colab.research.google.com/drive/1fBZAwqE8C_lrRPAe-hQZJTWrMJuAKtG2?usp=sharing .
URLs: https://colab.research.google.com/drive/1fBZAwqE8C_lrRPAe-hQZJTWrMJuAKtG2?usp=sharing
Authors: Yiyi Tao, Zhuoyue Wang, Hang Zhang, Lun Wang
Abstract: The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for performance, rendering end-to-end training increasingly prohibitive. In this paper, we propose NEVLP, a noise-robust framework for efficient vision-language pre-training that requires less pre-training data. Specifically, we bridge the modality gap between a frozen image encoder and a large language model with a transformer and introduce two innovative learning strategies: noise-adaptive learning and concept-enhanced learning to mitigate the impact of noise. In noise-adaptive learning, we estimate the noise probability of each image-text pair based on the transformer's memorization effect and employ noise-adaptive regularization on image-text contrastive learning to condition cross-modal alignment. In concept-enhanced learning, we enrich incomplete text by incorporating visual concepts (objects in the image) to provide prior information about existing objects for image-text matching and image-grounded text generation, thereby mitigating text incompletion. Our framework effectively utilizes noisy web data and achieves state-of-the-art performance with less pre-training data across a wide range of vision-language tasks, including image-text retrieval, image captioning, and visual question answering.
Authors: Yanguang Sun, Hanyu Xuan, Jian Yang, Lei Luo
Abstract: Recently, biological perception has been a powerful tool for handling the camouflaged object detection (COD) task. However, most existing methods are heavily dependent on the local spatial information of diverse scales from convolutional operations to optimize initial features. A commonly neglected point in these methods is the long-range dependencies between feature pixels from different scale spaces that can help the model build a global structure of the object, inducing a more precise image representation. In this paper, we propose a novel Global-Local Collaborative Optimization Network, called GLCONet. Technically, we first design a collaborative optimization strategy from the perspective of multi-source perception to simultaneously model the local details and global long-range relationships, which can provide features with abundant discriminative information to boost the accuracy in detecting camouflaged objects. Furthermore, we introduce an adjacent reverse decoder that contains cross-layer aggregation and reverse optimization to integrate complementary information from different levels for generating high-quality representations. Extensive experiments demonstrate that the proposed GLCONet method with different backbones can effectively activate potentially significant pixels in an image, outperforming twenty state-of-the-art methods on three public COD datasets. The source code is available at: \https://github.com/CSYSI/GLCONet.
Authors: Dongqi Fan, Tao Chen, Mingjie Wang, Rui Ma, Qiang Tang, Zili Yi, Qian Wang, Liang Chang
Abstract: Current Pose-Guided Person Image Synthesis (PGPIS) methods depend heavily on large amounts of labeled triplet data to train the generator in a supervised manner. However, they often falter when applied to in-the-wild samples, primarily due to the distribution gap between the training datasets and real-world test samples. While some researchers aim to enhance model generalizability through sophisticated training procedures, advanced architectures, or by creating more diverse datasets, we adopt the test-time fine-tuning paradigm to customize a pre-trained Text2Image (T2I) model. However, naively applying test-time tuning results in inconsistencies in facial identities and appearance attributes. To address this, we introduce a Visual Consistency Module (VCM), which enhances appearance consistency by combining the face, text, and image embedding. Our approach, named OnePoseTrans, requires only a single source image to generate high-quality pose transfer results, offering greater stability than state-of-the-art data-driven methods. For each test case, OnePoseTrans customizes a model in around 48 seconds with an NVIDIA V100 GPU.
Authors: Liao Shen, Tianqi Liu, Huiqiang Sun, Xinyi Ye, Baopu Li, Jianming Zhang, Zhiguo Cao
Abstract: We study the problem of generating intermediate images from image pairs with large motion while maintaining semantic consistency. Due to the large motion, the intermediate semantic information may be absent in input images. Existing methods either limit to small motion or focus on topologically similar objects, leading to artifacts and inconsistency in the interpolation results. To overcome this challenge, we delve into pre-trained image diffusion models for their capabilities in semantic cognition and representations, ensuring consistent expression of the absent intermediate semantic representations with the input. To this end, we propose DreamMover, a novel image interpolation framework with three main components: 1) A natural flow estimator based on the diffusion model that can implicitly reason about the semantic correspondence between two images. 2) To avoid the loss of detailed information during fusion, our key insight is to fuse information in two parts, high-level space and low-level space. 3) To enhance the consistency between the generated images and input, we propose the self-attention concatenation and replacement approach. Lastly, we present a challenging benchmark dataset InterpBench to evaluate the semantic consistency of generated results. Extensive experiments demonstrate the effectiveness of our method. Our project is available at https://dreamm0ver.github.io .
Authors: Zihan Su, Junhao Zhuang, Chun Yuan
Abstract: Recently, text-guided image editing has achieved significant success. However, existing methods can only apply simple textures like wood or gold when changing the texture of an object. Complex textures such as cloud or fire pose a challenge. This limitation stems from that the target prompt needs to contain both the input image content and
Authors: Cagri Gungor, Adriana Kovashka
Abstract: First-person activity recognition is rapidly growing due to the widespread use of wearable cameras but faces challenges from domain shifts across different environments, such as varying objects or background scenes. We propose a multimodal framework that improves domain generalization by integrating motion, audio, and appearance features. Key contributions include analyzing the resilience of audio and motion features to domain shifts, using audio narrations for enhanced audio-text alignment, and applying consistency ratings between audio and visual narrations to optimize the impact of audio in recognition during training. Our approach achieves state-of-the-art performance on the ARGO1M dataset, effectively generalizing across unseen scenarios and locations.
Authors: Cagri Gungor, Adriana Kovashka
Abstract: While motion has garnered attention in various tasks, its potential as a modality for weakly-supervised object detection (WSOD) in static images remains unexplored. Our study introduces an approach to enhance WSOD methods by integrating motion information. This method involves leveraging hallucinated motion from static images to improve WSOD on image datasets, utilizing a Siamese network for enhanced representation learning with motion, addressing camera motion through motion normalization, and selectively training images based on object motion. Experimental validation on the COCO and YouTube-BB datasets demonstrates improvements over a state-of-the-art method.
Authors: Zongyou Yu, Qiang Qu, Xiaoming Chen, Chen Wang
Abstract: Recent advancements in event-based zero-shot object recognition have demonstrated promising results. However, these methods heavily depend on extensive training and are inherently constrained by the characteristics of CLIP. To the best of our knowledge, this research is the first study to explore the understanding capabilities of large language models (LLMs) for event-based visual content. We demonstrate that LLMs can achieve event-based object recognition without additional training or fine-tuning in conjunction with CLIP, effectively enabling pure zero-shot event-based recognition. Particularly, we evaluate the ability of GPT-4o / 4turbo and two other open-source LLMs to directly recognize event-based visual content. Extensive experiments are conducted across three benchmark datasets, systematically assessing the recognition accuracy of these models. The results show that LLMs, especially when enhanced with well-designed prompts, significantly improve event-based zero-shot recognition performance. Notably, GPT-4o outperforms the compared models and exceeds the recognition accuracy of state-of-the-art event-based zero-shot methods on N-ImageNet by five orders of magnitude. The implementation of this paper is available at \url{https://github.com/ChrisYu-Zz/Pure-event-based-recognition-based-LLM}.
URLs: https://github.com/ChrisYu-Zz/Pure-event-based-recognition-based-LLM
Authors: Basavaraj Kaladagi, Jagadeesh Pujari
Abstract: Recognizing texts from camera images is a known hard problem because of the difficulties in text detection from the varied and complicated background. In this paper we propose a novel and efficient method to detect text region from images with complex background using Wavelet Transforms. The framework uses Wavelet Transformation of the original image in its grayscale form followed by Sub-band filtering. Then Region clustering technique is applied using centroids of the regions, further Bounding box is fitted to each region thus identifying the text regions. This method is much sophisticated and efficient than the previous methods as it doesn't stick to a particular font size of the text thus, making it generalized. The sample set used for experimental purpose consists of 50 images with varying backgrounds. Images with edge prominence are considered. Furthermore, our method can be easily customized for applications with different scopes.
Authors: Meng Lou, Yunxiang Fu, Yizhou Yu
Abstract: Due to the capability of dynamic state space models (SSMs) in capturing long-range dependencies with near-linear computational complexity, Mamba has shown notable performance in NLP tasks. This has inspired the rapid development of Mamba-based vision models, resulting in promising results in visual recognition tasks. However, such models are not capable of distilling features across layers through feature aggregation, interaction, and selection. Moreover, existing cross-layer feature aggregation methods designed for CNNs or ViTs are not practical in Mamba-based models due to high computational costs. Therefore, this paper aims to introduce an efficient cross-layer feature aggregation mechanism for Mamba-based vision backbone networks. Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX to effectively improve cross-layer feature interaction and reuse. Specifically, we build two different types of network layers: ganglion layers and normal layers. The former has higher connectivity and complexity, enabling multi-layer feature aggregation and interaction in an input-dependent manner. In contrast, the latter has lower connectivity and complexity. By interleaving these two types of layers, we design a new vision backbone network with sparsely cross-connected layers, achieving an excellent trade-off among model size, computational cost, memory cost, and accuracy in comparison to its counterparts. For instance, with fewer parameters, SparX-Mamba-T improves the top-1 accuracy of VMamba-T from 82.5% to 83.5%, while SparX-Swin-T achieves a 1.3% increase in top-1 accuracy compared to Swin-T. Extensive experimental results demonstrate that our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.
Authors: Yupeng Chen, Penglin Chen, Xiaoyu Zhang, Yixian Huang, Qian Xie
Abstract: The rapid development of diffusion models has significantly advanced AI-generated content (AIGC), particularly in Text-to-Image (T2I) and Text-to-Video (T2V) generation. Text-based video editing, leveraging these generative capabilities, has emerged as a promising field, enabling precise modifications to videos based on text prompts. Despite the proliferation of innovative video editing models, there is a conspicuous lack of comprehensive evaluation benchmarks that holistically assess these models' performance across various dimensions. Existing evaluations are limited and inconsistent, typically summarizing overall performance with a single score, which obscures models' effectiveness on individual editing tasks. To address this gap, we propose EditBoard, the first comprehensive evaluation benchmark for text-based video editing models. EditBoard encompasses nine automatic metrics across four dimensions, evaluating models on four task categories and introducing three new metrics to assess fidelity. This task-oriented benchmark facilitates objective evaluation by detailing model performance and providing insights into each model's strengths and weaknesses. By open-sourcing EditBoard, we aim to standardize evaluation and advance the development of robust video editing models.
Authors: He Wang, Yang Xu, Zebin Wu, Zhihui Wei
Abstract: Hyperspectral and multispectral image fusion aims to generate high spectral and spatial resolution hyperspectral images (HR-HSI) by fusing high-resolution multispectral images (HR-MSI) and low-resolution hyperspectral images (LR-HSI). However, existing fusion methods encounter challenges such as unknown degradation parameters, incomplete exploitation of the correlation between high-dimensional structures and deep image features. To overcome these issues, in this article, an unsupervised blind fusion method for hyperspectral and multispectral images based on Tucker decomposition and spatial spectral manifold learning (DTDNML) is proposed. We design a novel deep Tucker decomposition network that maps LR-HSI and HR-MSI into a consistent feature space, achieving reconstruction through decoders with shared parameter. To better exploit and fuse spatial-spectral features in the data, we design a core tensor fusion network that incorporates a spatial spectral attention mechanism for aligning and fusing features at different scales. Furthermore, to enhance the capacity in capturing global information, a Laplacian-based spatial-spectral manifold constraints is introduced in shared-decoders. Sufficient experiments have validated that this method enhances the accuracy and efficiency of hyperspectral and multispectral fusion on different remote sensing datasets. The source code is available at https://github.com/Shawn-H-Wang/DTDNML.
Authors: Xiaolei Qin, Xin Su, Liangpei Zhang
Abstract: Satellite image time series (SITS) data provides continuous observations over time, allowing for the tracking of vegetation changes and growth patterns throughout the seasons and years. Numerous deep learning (DL) approaches using SITS for crop classification have emerged recently, with the latest approaches adopting Transformer for SITS classification. However, the quadratic complexity of self-attention in Transformer poses challenges for classifying long time series. While the cutting-edge Mamba architecture has demonstrated strength in various domains, including remote sensing image interpretation, its capacity to learn temporal representations in SITS data remains unexplored. Moreover, the existing SITS classification methods often depend solely on crop labels as supervision signals, which fails to fully exploit the temporal information. In this paper, we proposed a Satellite Image Time Series Mamba (SITSMamba) method for crop classification based on remote sensing time series data. The proposed SITSMamba contains a spatial encoder based on Convolutional Neural Networks (CNN) and a Mamba-based temporal encoder. To exploit richer temporal information from SITS, we design two branches of decoder used for different tasks. The first branch is a crop Classification Branch (CBranch), which includes a ConvBlock to decode the feature to a crop map. The second branch is a SITS Reconstruction Branch that uses a Linear layer to transform the encoded feature to predict the original input values. Furthermore, we design a Positional Weight (PW) applied to the RBranch to help the model learn rich latent knowledge from SITS. We also design two weighting factors to control the balance of the two branches during training. The code of SITSMamba is available at: https://github.com/XiaoleiQinn/SITSMamba.
Authors: Jungpil Shin, Najmul Hassan, Abu Saleh Musa Miah1, Satoshi Nishimura
Abstract: Human Activity Recognition (HAR) systems aim to understand human behaviour and assign a label to each action, attracting significant attention in computer vision due to their wide range of applications. HAR can leverage various data modalities, such as RGB images and video, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, and radar signals. Each modality provides unique and complementary information suited to different application scenarios. Consequently, numerous studies have investigated diverse approaches for HAR using these modalities. This paper presents a comprehensive survey of the latest advancements in HAR from 2014 to 2024, focusing on machine learning (ML) and deep learning (DL) approaches categorized by input data modalities. We review both single-modality and multi-modality techniques, highlighting fusion-based and co-learning frameworks. Additionally, we cover advancements in hand-crafted action features, methods for recognizing human-object interactions, and activity detection. Our survey includes a detailed dataset description for each modality and a summary of the latest HAR systems, offering comparative results on benchmark datasets. Finally, we provide insightful observations and propose effective future research directions in HAR.
Authors: Guandong Li
Abstract: E-commerce image generation has always been one of the core demands in the e-commerce field. The goal is to restore the missing background that matches the main product given. In the post-AIGC era, diffusion models are primarily used to generate product images, achieving impressive results. This paper systematically analyzes and addresses a core pain point in diffusion model generation: overcompletion, which refers to the difficulty in maintaining product features. We propose two solutions: 1. Using an instance mask fine-tuned inpainting model to mitigate this phenomenon; 2. Adopting a train-free mask guidance approach, which incorporates refined product masks as constraints when combining ControlNet and UNet to generate the main product, thereby avoiding overcompletion of the product. Our method has achieved promising results in practical applications and we hope it can serve as an inspiring technical report in this field.
Authors: Bochao Zou, Zizheng Guo, Wenfeng Qin, Xin Li, Kangsheng Wang, Huimin Ma
Abstract: Micro-expressions are involuntary facial movements that cannot be consciously controlled, conveying subtle cues with substantial real-world applications. The analysis of micro-expressions generally involves two main tasks: spotting micro-expression intervals in long videos and recognizing the emotions associated with these intervals. Previous deep learning methods have primarily relied on classification networks utilizing sliding windows. However, fixed window sizes and window-level hard classification introduce numerous constraints. Additionally, these methods have not fully exploited the potential of complementary pathways for spotting and recognition. In this paper, we present a novel temporal state transition architecture grounded in the state space model, which replaces conventional window-level classification with video-level regression. Furthermore, by leveraging the inherent connections between spotting and recognition tasks, we propose a synergistic strategy that enhances overall analysis performance. Extensive experiments demonstrate that our method achieves state-of-the-art performance. The codes and pre-trained models are available at https://github.com/zizheng-guo/ME-TST.
Authors: Ning-Chi Huang, Chi-Chih Chang, Wei-Cheng Lin, Endri Taka, Diana Marculescu, Kai-Chiang Wu
Abstract: $N{:}M$ sparsity is an emerging model compression method supported by more and more accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing $N{:}M$ sparsity methods compress neural networks with a uniform setting for all layers in a network or heuristically determine the layer-wise configuration by considering the number of parameters in each layer. However, very few methods have been designed for obtaining a layer-wise customized $N{:}M$ sparse configuration for vision transformers (ViTs), which usually consist of transformer blocks involving the same number of parameters. In this work, to address the challenge of selecting suitable sparse configuration for ViTs on $N{:}M$ sparsity-supporting accelerators, we propose ELSA, Exploiting Layer-wise $N{:}M$ Sparsity for ViTs. Considering not only all $N{:}M$ sparsity levels supported by a given accelerator but also the expected throughput improvement, our methodology can reap the benefits of accelerators supporting mixed sparsity by trading off negligible accuracy loss with both memory usage and inference time reduction for ViT models. For instance, our approach achieves a noteworthy 2.9$\times$ reduction in FLOPs for both Swin-B and DeiT-B with only a marginal degradation of accuracy on ImageNet. Our code will be released upon paper acceptance.
Authors: Nie Lin, Takehiko Ohkawa, Mingfang Zhang, Yifei Huang, Ryosuke Furuta, Yoichi Sato
Abstract: We present a contrastive learning framework based on in-the-wild hand images tailored for pre-training 3D hand pose estimators, dubbed HandCLR. Pre-training on large-scale images achieves promising results in various tasks, but prior 3D hand pose pre-training methods have not fully utilized the potential of diverse hand images accessible from in-the-wild videos. To facilitate scalable pre-training, we first prepare an extensive pool of hand images from in-the-wild videos and design our method with contrastive learning. Specifically, we collected over 2.0M hand images from recent human-centric videos, such as 100DOH and Ego4D. To extract discriminative information from these images, we focus on the similarity of hands; pairs of similar hand poses originating from different samples, and propose a novel contrastive learning method that embeds similar hand pairs closer in the latent space. Our experiments demonstrate that our method outperforms conventional contrastive learning approaches that produce positive pairs sorely from a single image with data augmentation. We achieve significant improvements over the state-of-the-art method in various datasets, with gains of 15% on FreiHand, 10% on DexYCB, and 4% on AssemblyHands.
Authors: Krzysztof Krawiec, Antoni Nowinowski
Abstract: Contemporary deep learning architectures lack principled means for capturing and handling fundamental visual concepts, like objects, shapes, geometric transforms, and other higher-level structures. We propose a neurosymbolic architecture that uses a domain-specific language to capture selected priors of image formation, including object shape, appearance, categorization, and geometric transforms. We express template programs in that language and learn their parameterization with features extracted from the scene by a convolutional neural network. When executed, the parameterized program produces geometric primitives which are rendered and assessed for correspondence with the scene content and trained via auto-association with gradient. We confront our approach with a baseline method on a synthetic benchmark and demonstrate its capacity to disentangle selected aspects of the image formation process, learn from small data, correct inference in the presence of noise, and out-of-sample generalization.
Authors: Yaning Zhang, Tianyi Wang, Zitong Yu, Zan Gao, Linlin Shen, Shengyong Chen
Abstract: The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations.
Authors: Haoyu Wu, Ziqiao Peng, Xukun Zhou, Yunfei Cheng, Jun He, Hongyan Liu, Zhaoxin Fan
Abstract: 3D face reconstruction from monocular images has promoted the development of various applications such as augmented reality. Though existing methods have made remarkable progress, most of them emphasize geometric reconstruction, while overlooking the importance of texture prediction. To address this issue, we propose VGG-Tex, a novel Vivid Geometry-Guided Facial Texture Estimation model designed for High Fidelity Monocular 3D Face Reconstruction. The core of this approach is leveraging 3D parametric priors to enhance the outcomes of 2D UV texture estimation. Specifically, VGG-Tex includes a Facial Attributes Encoding Module, a Geometry-Guided Texture Generator, and a Visibility-Enhanced Texture Completion Module. These components are responsible for extracting parametric priors, generating initial textures, and refining texture details, respectively. Based on the geometry-texture complementarity principle, VGG-Tex also introduces a Texture-guided Geometry Refinement Module to further balance the overall fidelity of the reconstructed 3D faces, along with corresponding losses. Comprehensive experiments demonstrate that our method significantly improves texture reconstruction performance compared to existing state-of-the-art methods.
Authors: Yinan Sun, Zicheng Zhang, Haoning Wu, Xiaohong Liu, Weisi Lin, Guangtao Zhai, Xiongkuo Min
Abstract: The rapid development of Multi-modality Large Language Models (MLLMs) has significantly influenced various aspects of industry and daily life, showcasing impressive capabilities in visual perception and understanding. However, these models also exhibit hallucinations, which limit their reliability as AI systems, especially in tasks involving low-level visual perception and understanding. We believe that hallucinations stem from a lack of explicit self-awareness in these models, which directly impacts their overall performance. In this paper, we aim to define and evaluate the self-awareness of MLLMs in low-level visual perception and understanding tasks. To this end, we present QL-Bench, a benchmark settings to simulate human responses to low-level vision, investigating self-awareness in low-level visual perception through visual question answering related to low-level attributes such as clarity and lighting. Specifically, we construct the LLSAVisionQA dataset, comprising 2,990 single images and 1,999 image pairs, each accompanied by an open-ended question about its low-level features. Through the evaluation of 15 MLLMs, we demonstrate that while some models exhibit robust low-level visual capabilities, their self-awareness remains relatively underdeveloped. Notably, for the same model, simpler questions are often answered more accurately than complex ones. However, self-awareness appears to improve when addressing more challenging questions. We hope that our benchmark will motivate further research, particularly focused on enhancing the self-awareness of MLLMs in tasks involving low-level visual perception and understanding.
Authors: Shahriar Rifat, Jonathan Ashdown, Francesco Restuccia
Abstract: Test Time Adaptation (TTA) has emerged as a practical solution to mitigate the performance degradation of Deep Neural Networks (DNNs) in the presence of corruption/ noise affecting inputs. Existing approaches in TTA continuously adapt the DNN, leading to excessive resource consumption and performance degradation due to accumulation of error stemming from lack of supervision. In this work, we propose Domain-Aware Real-Time Dynamic Adaptation (DARDA) to address such issues. Our key approach is to proactively learn latent representations of some corruption types, each one associated with a sub-network state tailored to correctly classify inputs affected by that corruption. After deployment, DARDA adapts the DNN to previously unseen corruptions in an unsupervised fashion by (i) estimating the latent representation of the ongoing corruption; (ii) selecting the sub-network whose associated corruption is the closest in the latent space to the ongoing corruption; and (iii) adapting DNN state, so that its representation matches the ongoing corruption. This way, DARDA is more resource efficient and can swiftly adapt to new distributions caused by different corruptions without requiring a large variety of input data. Through experiments with two popular mobile edge devices - Raspberry Pi and NVIDIA Jetson Nano - we show that DARDA reduces energy consumption and average cache memory footprint respectively by 1.74x and 2.64x with respect to the state of the art, while increasing the performance by 10.4%, 5.7% and 4.4% on CIFAR-10, CIFAR-100 and TinyImagenet.
Authors: Xiaolong Qian, Qi Jiang, Yao Gao, Shaohua Gao, Zhonghua Yi, Lei Sun, Kai Wei, Haifeng Li, Kailun Yang, Kaiwei Wang, Jian Bai
Abstract: Controllable Depth-of-Field (DoF) imaging commonly produces amazing visual effects based on heavy and expensive high-end lenses. However, confronted with the increasing demand for mobile scenarios, it is desirable to achieve a lightweight solution with Minimalist Optical Systems (MOS). This work centers around two major limitations of MOS, i.e., the severe optical aberrations and uncontrollable DoF, for achieving single-lens controllable DoF imaging via computational methods. A Depth-aware Controllable DoF Imaging (DCDI) framework is proposed equipped with All-in-Focus (AiF) aberration correction and monocular depth estimation, where the recovered image and corresponding depth map are utilized to produce imaging results under diverse DoFs of any high-end lens via patch-wise convolution. To address the depth-varying optical degradation, we introduce a Depth-aware Degradation-adaptive Training (DA2T) scheme. At the dataset level, a Depth-aware Aberration MOS (DAMOS) dataset is established based on the simulation of Point Spread Functions (PSFs) under different object distances. Additionally, we design two plug-and-play depth-aware mechanisms to embed depth information into the aberration image recovery for better tackling depth-aware degradation. Furthermore, we propose a storage-efficient Omni-Lens-Field model to represent the 4D PSF library of various lenses. With the predicted depth map, recovered image, and depth-aware PSF map inferred by Omni-Lens-Field, single-lens controllable DoF imaging is achieved. Comprehensive experimental results demonstrate that the proposed framework enhances the recovery performance, and attains impressive single-lens controllable DoF imaging results, providing a seminal baseline for this field. The source code and the established dataset will be publicly available at https://github.com/XiaolongQian/DCDI.
Authors: Shuzhao Xie, Weixiang Zhang, Chen Tang, Yunpeng Bai, Rongwei Lu, Shijia Ge, Zhi Wang
Abstract: 3D Gaussian Splatting demonstrates excellent quality and speed in novel view synthesis. Nevertheless, the huge file size of the 3D Gaussians presents challenges for transmission and storage. Current works design compact models to replace the substantial volume and attributes of 3D Gaussians, along with intensive training to distill information. These endeavors demand considerable training time, presenting formidable hurdles for practical deployment. To this end, we propose MesonGS, a codec for post-training compression of 3D Gaussians. Initially, we introduce a measurement criterion that considers both view-dependent and view-independent factors to assess the impact of each Gaussian point on the rendering output, enabling the removal of insignificant points. Subsequently, we decrease the entropy of attributes through two transformations that complement subsequent entropy coding techniques to enhance the file compression rate. More specifically, we first replace rotation quaternions with Euler angles; then, we apply region adaptive hierarchical transform to key attributes to reduce entropy. Lastly, we adopt finer-grained quantization to avoid excessive information loss. Moreover, a well-crafted finetune scheme is devised to restore quality. Extensive experiments demonstrate that MesonGS significantly reduces the size of 3D Gaussians while preserving competitive quality.
Authors: Qiaoyi Xue, Youdan Feng, Jiayi Liu, Tianming Xu, Kaixin Shen, Chuyun Shen, Yuhang Shi
Abstract: This study explores a workflow for automated segmentation of lesions in FDG and PSMA PET/CT images. Due to the substantial differences in image characteristics between FDG and PSMA, specialized preprocessing steps are required. Utilizing YOLOv8 for data classification, the FDG and PSMA images are preprocessed separately before feeding them into the segmentation models, aiming to improve lesion segmentation accuracy. The study focuses on evaluating the performance of automated segmentation workflow for multitracer PET images. The findings are expected to provide critical insights for enhancing diagnostic workflows and patient-specific treatment plans. Our code will be open-sourced and available at https://github.com/jiayiliu-pku/AP2024.
Authors: Haoyuan Sun, Bo Xia, Yongzhe Chang, Xueqian Wang
Abstract: Direct Preference Optimization (DPO) has recently expanded its successful application from aligning large language models (LLMs) to aligning text-to-image models with human preferences, which has generated considerable interest within the community. However, we have observed that these approaches rely solely on minimizing the reverse Kullback-Leibler divergence during alignment process between the fine-tuned model and the reference model, neglecting the incorporation of other divergence constraints. In this study, we focus on extending reverse Kullback-Leibler divergence in the alignment paradigm of text-to-image models to $f$-divergence, which aims to garner better alignment performance as well as good generation diversity. We provide the generalized formula of the alignment paradigm under the $f$-divergence condition and thoroughly analyze the impact of different divergence constraints on alignment process from the perspective of gradient fields. We conduct comprehensive evaluation on image-text alignment performance, human value alignment performance and generation diversity performance under different divergence constraints, and the results indicate that alignment based on Jensen-Shannon divergence achieves the best trade-off among them. The option of divergence employed for aligning text-to-image models significantly impacts the trade-off between alignment performance (especially human value alignment) and generation diversity, which highlights the necessity of selecting an appropriate divergence for practical applications.
Authors: Haisheng Su, Wei Wu, Junchi Yan
Abstract: Current end-to-end autonomous driving methods resort to unifying modular designs for various tasks (e.g. perception, prediction and planning). Although optimized in a planning-oriented spirit with a fully differentiable framework, existing end-to-end driving systems without ego-centric designs still suffer from unsatisfactory performance and inferior efficiency, owing to the rasterized scene representation learning and redundant information transmission. In this paper, we revisit the human driving behavior and propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving. Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner. The sparse perception module performs detection, tracking and online mapping based on sparse representation of the driving scene. The hierarchical interaction module aims to select the Closest In-Path Vehicle / Stationary (CIPV / CIPS) from coarse to fine, benefiting from an additional geometric prior. As for the iterative motion planner, both selected interactive agents and ego-vehicle are considered for joint motion prediction, where the output multi-modal ego-trajectories are optimized in an iterative fashion. Besides, both position-level motion diffusion and trajectory-level planning denoising are introduced for uncertainty modeling, thus facilitating the training stability and convergence of the whole framework. Extensive experiments conducted on nuScenes dataset demonstrate the superior planning performance and great efficiency of DiFSD, which significantly reduces the average L2 error by \textbf{66\%} and collision rate by \textbf{77\%} than UniAD while achieves \textbf{8.2$\times$} faster running efficiency.
Authors: Chengqin Wu, Shuai Yu, Qingson Hu, Jingxiang Xu, Lijun Zhang
Abstract: With the rapid development of marine engineering projects such as marine resource extraction and oceanic surveys, underwater visual imaging and analysis has become a critical technology. Unfortunately, due to the inevitable non-linear attenuation of light in underwater environments, underwater images and videos often suffer from low contrast, blurriness, and color degradation, which significantly complicate the subsequent research. Existing underwater image enhancement methods often treat the haze and color cast as a unified degradation process and disregard their independence and interdependence, which limits the performance improvement. Here, we propose a Vision Transformer (ViT)-based network (referred to as WaterFormer) to improve the underwater image quality. WaterFormer contains three major components: a dehazing block (DehazeFormer Block) to capture the self-correlated haze features and extract deep-level features, a Color Restoration Block (CRB) to capture self-correlated color cast features, and a Channel Fusion Block (CFB) to capture fusion features within the network. To ensure authenticity, a soft reconstruction layer based on the underwater imaging physics model is included. To improve the quality of the enhanced images, we introduce the Chromatic Consistency Loss and Sobel Color Loss to train the network. Comprehensive experimental results demonstrate that WaterFormer outperforms other state-of-the-art methods in enhancing underwater images.
Authors: Jiayi Liu, Qiaoyi Xue, Youdan Feng, Tianming Xu, Kaixin Shen, Chuyun Shen, Yuhang Shi
Abstract: The escalating global cancer burden underscores the critical need for precise diagnostic tools in oncology. This research employs deep learning to enhance lesion segmentation in PET/CT imaging, utilizing a dataset of 900 whole-body FDG-PET/CT and 600 PSMA-PET/CT studies from the AutoPET challenge III. Our methodical approach includes robust preprocessing and data augmentation techniques to ensure model robustness and generalizability. We investigate the influence of non-zero normalization and modifications to the data augmentation pipeline, such as the introduction of RandGaussianSharpen and adjustments to the Gamma transform parameter. This study aims to contribute to the standardization of preprocessing and augmentation strategies in PET/CT imaging, potentially improving the diagnostic accuracy and the personalized management of cancer patients. Our code will be open-sourced and available at https://github.com/jiayiliu-pku/DC2024.
Authors: Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler, David Acuna
Abstract: Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitatively reason about object sizes and distances remains underexplored. In this work, we introduce a manually annotated benchmark, Q-Spatial Bench, with 271 questions across five categories designed for quantitative spatial reasoning and systematically investigate the performance of state-of-the-art VLMs on this task. Our analysis reveals that reasoning about distances between objects is particularly challenging for SoTA VLMs; however, some VLMs significantly outperform others, with an over 40-point gap between the two best performing models. We also make the surprising observation that the success rate of the top-performing VLM increases by 19 points when a reasoning path using a reference object emerges naturally in the response. Inspired by this observation, we develop a zero-shot prompting technique, SpatialPrompt, that encourages VLMs to answer quantitative spatial questions using reference objects as visual cues. By instructing VLMs to use reference objects in their reasoning paths via SpatialPrompt, Gemini 1.5 Pro, Gemini 1.5 Flash, and GPT-4V improve their success rates by over 40, 20, and 30 points, respectively. We emphasize that these significant improvements are obtained without needing more data, model architectural modifications, or fine-tuning.
Authors: Shiqi Li, Jihua Zhu, Yifan Xie, Naiwen Hu, Mingchen Zhu, Zhongyu Li, Di Wang
Abstract: Multiple rotation averaging plays a crucial role in computer vision and robotics domains. The conventional optimization-based methods optimize a nonlinear cost function based on certain noise assumptions, while most previous learning-based methods require ground truth labels in the supervised training process. Recognizing the handcrafted noise assumption may not be reasonable in all real-world scenarios, this paper proposes an effective rotation averaging method for mining data patterns in a learning manner while avoiding the requirement of labels. Specifically, we apply deep matrix factorization to directly solve the multiple rotation averaging problem in unconstrained linear space. For deep matrix factorization, we design a neural network model, which is explicitly low-rank and symmetric to better suit the background of multiple rotation averaging. Meanwhile, we utilize a spanning tree-based edge filtering to suppress the influence of rotation outliers. What's more, we also adopt a reweighting scheme and dynamic depth selection strategy to further improve the robustness. Our method synthesizes the merit of both optimization-based and learning-based methods. Experimental results on various datasets validate the effectiveness of our proposed method.
Authors: Darshan Venkatrayappa
Abstract: Abnormal event detection or anomaly detection in surveillance videos is currently a challenge because of the diversity of possible events. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without supervision. In this work we propose an unsupervised approach for video anomaly detection with the aim to jointly optimize the objectives of the deep neural network and the anomaly detection task using a hybrid architecture. Initially, a convolutional autoencoder is pre-trained in an unsupervised manner with a fusion of depth, motion and appearance features. In the second step, we utilize the encoder part of the pre-trained autoencoder and extract the embeddings of the fused input. Now, we jointly train/ fine tune the encoder to map the embeddings to a hypercenter. Thus, embeddings of normal data fall near the hypercenter, whereas embeddings of anomalous data fall far away from the hypercenter.
Authors: Hui Shen, Zhongwei Wan, Xin Wang, Mi Zhang
Abstract: Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the training efficiency of Vim models. The key idea of Famba-V is to identify and fuse similar tokens across different Vim layers based on a suit of cross-layer strategies instead of simply applying token fusion uniformly across all the layers that existing works propose. We evaluate the performance of Famba-V on CIFAR-100. Our results show that Famba-V is able to enhance the training efficiency of Vim models by reducing both training time and peak memory usage during training. Moreover, the proposed cross-layer strategies allow Famba-V to deliver superior accuracy-efficiency trade-offs. These results all together demonstrate Famba-V as a promising efficiency enhancement technique for Vim models.
Authors: Anirudh Nanduri, Rama Chellappa
Abstract: Despite the remarkable performance of deep neural networks for face detection and recognition tasks in the visible spectrum, their performance on more challenging non-visible domains is comparatively still lacking. While significant research has been done in the fields of domain adaptation and domain generalization, in this paper we tackle scenarios in which these methods have limited applicability owing to the lack of training data from target domains. We focus on the problem of single-source (visible) and multi-target (SWIR, long-range/remote, surveillance, and body-worn) face recognition task. We show through experiments that a good template generation algorithm becomes crucial as the complexity of the target domain increases. In this context, we introduce a template generation algorithm called Norm Pooling (and a variant known as Sparse Pooling) and show that it outperforms average pooling across different domains and networks, on the IARPA JANUS Benchmark Multi-domain Face (IJB-MDF) dataset.
Authors: Oriel Perl, Ido Leshem, Uria Franko, Yuval Goldman
Abstract: In recent years, workplaces and educational institutes have widely adopted virtual meeting platforms. This has led to a growing interest in analyzing and extracting insights from these meetings, which requires effective detection and tracking of unique individuals. In practice, there is no standardization in video meetings recording layout, and how they are captured across the different platforms and services. This, in turn, creates a challenge in acquiring this data stream and analyzing it in a uniform fashion. Our approach provides a solution to the most general form of video recording, usually consisting of a grid of participants (\cref{fig:videomeeting}) from a single video source with no metadata on participant locations, while using the least amount of constraints and assumptions as to how the data was acquired. Conventional approaches often use YOLO models coupled with tracking algorithms, assuming linear motion trajectories akin to that observed in CCTV footage. However, such assumptions fall short in virtual meetings, where participant video feed window can abruptly change location across the grid. In an organic video meeting setting, participants frequently join and leave, leading to sudden, non-linear movements on the video grid. This disrupts optical flow-based tracking methods that depend on linear motion. Consequently, standard object detection and tracking methods might mistakenly assign multiple participants to the same tracker. In this paper, we introduce a novel approach to track and re-identify participants in remote video meetings, by utilizing the spatio-temporal priors arising from the data in our domain. This, in turn, increases tracking capabilities compared to the use of general object tracking. Our approach reduces the error rate by 95% on average compared to YOLO-based tracking methods as a baseline.
Authors: Diego Porres
Abstract: The latent space of many generative models are rich in unexplored valleys and mountains. The majority of tools used for exploring them are so far limited to Graphical User Interfaces (GUIs). While specialized hardware can be used for this task, we show that a simple feature extraction of pre-trained Convolutional Neural Networks (CNNs) from a live RGB camera feed does a very good job at manipulating the latent space with simple changes in the scene, with vast room for improvement. We name this new paradigm Visual-reactive Interpolation, and the full code can be found at https://github.com/PDillis/stylegan3-fun.
Authors: Teerapong Panboonyuen
Abstract: This paper introduces a novel framework for detecting and segmenting critical road assets on Thai highways using an advanced Refined Generalized Focal Loss (REG) formulation. Integrated into state-of-the-art vision-based detection and segmentation models, the proposed method effectively addresses class imbalance and the challenges of localizing small, underrepresented road elements, including pavilions, pedestrian bridges, information signs, single-arm poles, bus stops, warning signs, and concrete guardrails. To improve both detection and segmentation accuracy, a multi-task learning strategy is adopted, optimizing REG across multiple tasks. REG is further enhanced by incorporating a spatial-contextual adjustment term, which accounts for the spatial distribution of road assets, and a probabilistic refinement that captures prediction uncertainty in complex environments, such as varying lighting conditions and cluttered backgrounds. Our rigorous mathematical formulation demonstrates that REG minimizes localization and classification errors by applying adaptive weighting to hard-to-detect instances while down-weighting easier examples. Experimental results show a substantial performance improvement, achieving a mAP50 of 80.34 and an F1-score of 77.87, significantly outperforming conventional methods. This research underscores the capability of advanced loss function refinements to enhance the robustness and accuracy of road asset detection and segmentation, thereby contributing to improved road safety and infrastructure management. For an in-depth discussion of the mathematical background and related methods, please refer to previous work available at \url{https://github.com/kaopanboonyuen/REG}.
Authors: Qilong Zhangli, Di Liu, Abhishek Aich, Dimitris Metaxas, Samuel Schulter
Abstract: Leveraging multiple training datasets to scale up image segmentation models is beneficial for increasing robustness and semantic understanding. Individual datasets have well-defined ground truth with non-overlapping mask layouts and mutually exclusive semantics. However, merging them for multi-dataset training disrupts this harmony and leads to semantic inconsistencies; for example, the class "person" in one dataset and class "face" in another will require multilabel handling for certain pixels. Existing methods struggle with this setting, particularly when evaluated on label spaces mixed from the individual training sets. To overcome these issues, we introduce a simple yet effective multi-dataset training approach by integrating language-based embeddings of class names and label space-specific query embeddings. Our method maintains high performance regardless of the underlying inconsistencies between training datasets. Notably, on four benchmark datasets with label space inconsistencies during inference, we outperform previous methods by 1.6% mIoU for semantic segmentation, 9.1% PQ for panoptic segmentation, 12.1% AP for instance segmentation, and 3.0% in the newly proposed PIQ metric.
Authors: Vitor Guizilini, Pavel Tokmakov, Achal Dave, Rares Ambrus
Abstract: 3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors capable of generating accurate predictions across domains. As a result, state of the art approaches show impressive performance in zero-shot relative and metric depth estimation. Recently, diffusion models have exhibited remarkable scalability and generalizable properties in their learned representations. However, because these models repurpose tools originally designed for image generation, they can only operate on dense ground-truth, which is not available for most depth labels, especially in real-world settings. In this paper we present GRIN, an efficient diffusion model designed to ingest sparse unstructured training data. We use image features with 3D geometric positional encodings to condition the diffusion process both globally and locally, generating depth predictions at a pixel-level. With comprehensive experiments across eight indoor and outdoor datasets, we show that GRIN establishes a new state of the art in zero-shot metric monocular depth estimation even when trained from scratch.
Authors: Karthick Panner Selvam, Raul Ramos-Pollan, Freddie Kalaitzis
Abstract: This study investigates the efficacy of Low-Rank Adaptation (LoRA) in fine-tuning Earth Observation (EO) foundation models for flood segmentation. We hypothesize that LoRA, a parameter-efficient technique, can significantly accelerate the adaptation of large-scale EO models to this critical task while maintaining high performance. We apply LoRA to fine-tune a state-of-the-art EO foundation model pre-trained on diverse satellite imagery, using a curated dataset of flood events. Our results demonstrate that LoRA-based fine-tuning (r-256) improves F1 score by 6.66 points and IoU by 0.11 compared to a frozen encoder baseline, while significantly reducing computational costs. Notably, LoRA outperforms full fine-tuning, which proves computationally infeasible on our hardware. We further assess generalization through out-of-distribution (OOD) testing on a geographically distinct flood event. While LoRA configurations show improved OOD performance over the baseline. This work contributes to research on efficient adaptation of foundation models for specialized EO tasks, with implications for rapid response systems in disaster management. Our findings demonstrate LoRA's potential for enabling faster deployment of accurate flood segmentation models in resource-constrained, time-critical scenarios.
Authors: Keshav Bimbraw, Haichong K. Zhang, Bashima Islam
Abstract: Ultrasound imaging of the forearm has demonstrated significant potential for accurate hand gesture classification. Despite this progress, there has been limited focus on developing a stand-alone end- to-end gesture recognition system which makes it mobile, real-time and more user friendly. To bridge this gap, this paper explores the deployment of deep neural networks for forearm ultrasound-based hand gesture recognition on edge devices. Utilizing quantization techniques, we achieve substantial reductions in model size while maintaining high accuracy and low latency. Our best model, with Float16 quantization, achieves a test accuracy of 92% and an inference time of 0.31 seconds on a Raspberry Pi. These results demonstrate the feasibility of efficient, real-time gesture recognition on resource-limited edge devices, paving the way for wearable ultrasound-based systems.
Authors: Xiang Fang, Arvind Easwaran, Blaise Genest
Abstract: Out-of-distribution (OOD) detection targets to detect and reject test samples with semantic shifts, to prevent models trained on in-distribution (ID) dataset from producing unreliable predictions. Existing works only extract the appearance features on image datasets, and cannot handle dynamic multimedia scenarios with much motion information. Therefore, we target a more realistic and challenging OOD detection task: OOD action detection (ODAD). Given an untrimmed video, ODAD first classifies the ID actions and recognizes the OOD actions, and then localizes ID and OOD actions. To this end, in this paper, we propose a novel Uncertainty-Guided Appearance-Motion Association Network (UAAN), which explores both appearance features and motion contexts to reason spatial-temporal inter-object interaction for ODAD.Firstly, we design separate appearance and motion branches to extract corresponding appearance-oriented and motion-aspect object representations. In each branch, we construct a spatial-temporal graph to reason appearance-guided and motion-driven inter-object interaction. Then, we design an appearance-motion attention module to fuse the appearance and motion features for final action detection. Experimental results on two challenging datasets show that UAAN beats state-of-the-art methods by a significant margin, illustrating its effectiveness.
Authors: Raffi Hagopian, Timothy Strebel, Simon Bernatz, Gregory A Myers, Erik Offerman, Eric Zuniga, Cy Y Kim, Angie T Ng, James A Iwaz, Sunny P Singh, Evan P Carey, Michael J Kim, R Spencer Schaefer, Jeannie Yu, Amilcare Gentili, Hugo JWL Aerts
Abstract: Coronary artery calcium (CAC) is highly predictive of cardiovascular events. While millions of chest CT scans are performed annually in the United States, CAC is not routinely quantified from scans done for non-cardiac purposes. A deep learning algorithm was developed using 446 expert segmentations to automatically quantify CAC on non-contrast, non-gated CT scans (AI-CAC). Our study differs from prior works as we leverage imaging data across the Veterans Affairs national healthcare system, from 98 medical centers, capturing extensive heterogeneity in imaging protocols, scanners, and patients. AI-CAC performance on non-gated scans was compared against clinical standard ECG-gated CAC scoring. Non-gated AI-CAC differentiated zero vs. non-zero and less than 100 vs. 100 or greater Agatston scores with accuracies of 89.4% (F1 0.93) and 87.3% (F1 0.89), respectively, in 795 patients with paired gated scans within a year of a non-gated CT scan. Non-gated AI-CAC was predictive of 10-year all-cause mortality (CAC 0 vs. >400 group: 25.4% vs. 60.2%, Cox HR 3.49, p < 0.005), and composite first-time stroke, MI, or death (CAC 0 vs. >400 group: 33.5% vs. 63.8%, Cox HR 3.00, p < 0.005). In a screening dataset of 8,052 patients with low-dose lung cancer-screening CTs (LDCT), 3,091/8,052 (38.4%) individuals had AI-CAC >400. Four cardiologists qualitatively reviewed LDCT images from a random sample of >400 AI-CAC patients and verified that 527/531 (99.2%) would benefit from lipid-lowering therapy. To the best of our knowledge, this is the first non-gated CT CAC algorithm developed across a national healthcare system, on multiple imaging protocols, without filtering intra-cardiac hardware, and compared against a strong gated CT reference. We report superior performance relative to previous CAC algorithms evaluated against paired gated scans that included patients with intra-cardiac hardware.
Authors: Atsuya Nakata, Takao Yamanaka
Abstract: Omni-directional images have been increasingly used in various applications, including virtual reality and SNS (Social Networking Services). However, their availability is comparatively limited in contrast to normal field of view (NFoV) images, since specialized cameras are required to take omni-directional images. Consequently, several methods have been proposed based on generative adversarial networks (GAN) to synthesize omni-directional images, but these approaches have shown difficulties in training of the models, due to instability and/or significant time consumption in the training. To address these problems, this paper proposes a novel omni-directional image synthesis method, 2S-ODIS (Two-Stage Omni-Directional Image Synthesis), which generated high-quality omni-directional images but drastically reduced the training time. This was realized by utilizing the VQGAN (Vector Quantized GAN) model pre-trained on a large-scale NFoV image database such as ImageNet without fine-tuning. Since this pre-trained model does not represent distortions of omni-directional images in the equi-rectangular projection (ERP), it cannot be applied directly to the omni-directional image synthesis in ERP. Therefore, two-stage structure was adopted to first create a global coarse image in ERP and then refine the image by integrating multiple local NFoV images in the higher resolution to compensate the distortions in ERP, both of which are based on the pre-trained VQGAN model. As a result, the proposed method, 2S-ODIS, achieved the reduction of the training time from 14 days in OmniDreamer to four days in higher image quality.
Authors: Hao-Chiang Shao, Guan-Yu Chen, Yu-Hsien Lin, Chia-Wen Lin, Shao-Yun Fang, Pin-Yian Tsai, Yan-Hsiu Liu
Abstract: Recent advances in VLSI fabrication technology have led to die shrinkage and increased layout density, creating an urgent demand for advanced hotspot detection techniques. However, by taking an object detection network as the backbone, recent learning-based hotspot detectors learn to recognize only the problematic layout patterns in the training data. This fact makes these hotspot detectors difficult to generalize to real-world scenarios. We propose a novel lithography simulator-powered hotspot detection framework to overcome this difficulty. Our framework integrates a lithography simulator with an object detection backbone, merging the extracted latent features from both the simulator and the object detector via well-designed cross-attention blocks. Consequently, the proposed framework can be used to detect potential hotspot regions based on I) the variation of possible circuit shape deformation estimated by the lithography simulator, and ii) the problematic layout patterns already known. To this end, we utilize RetinaNet with a feature pyramid network as the object detection backbone and leverage LithoNet as the lithography simulator. Extensive experiments demonstrate that our proposed simulator-guided hotspot detection framework outperforms previous state-of-the-art methods on real-world data.
Authors: Shih-Chieh Su
Abstract: Imagine a human artist looking at the generated photo of a diffusion model, and hoping to create a painting out of it. There could be some feature of the object in the photo that the artist wants to emphasize, some color to disperse, some silhouette to twist, or some part of the scene to be materialized. These intentions can be viewed as the modification of the cross attention from the text prompt onto UNet, during the desoising diffusion. This work presents AttnMod, to modify attention for creating new unpromptable art styles out of existing diffusion models. The style-creating behavior is studied across different setups.
Authors: Mahmud A. Mohamad, Gamal Elghazaly, Arthur Hubert, Raphael Frank
Abstract: This paper presents DENSER, an efficient and effective approach leveraging 3D Gaussian splatting (3DGS) for the reconstruction of dynamic urban environments. While several methods for photorealistic scene representations, both implicitly using neural radiance fields (NeRF) and explicitly using 3DGS have shown promising results in scene reconstruction of relatively complex dynamic scenes, modeling the dynamic appearance of foreground objects tend to be challenging, limiting the applicability of these methods to capture subtleties and details of the scenes, especially far dynamic objects. To this end, we propose DENSER, a framework that significantly enhances the representation of dynamic objects and accurately models the appearance of dynamic objects in the driving scene. Instead of directly using Spherical Harmonics (SH) to model the appearance of dynamic objects, we introduce and integrate a new method aiming at dynamically estimating SH bases using wavelets, resulting in better representation of dynamic objects appearance in both space and time. Besides object appearance, DENSER enhances object shape representation through densification of its point cloud across multiple scene frames, resulting in faster convergence of model training. Extensive evaluations on KITTI dataset show that the proposed approach significantly outperforms state-of-the-art methods by a wide margin. Source codes and models will be uploaded to this repository https://github.com/sntubix/denser
Authors: Anqi Shi, Yuze Cai, Xiangyu Chen, Jian Pu, Zeyu Fu, Hong Lu
Abstract: High-definition (HD) maps are essential for autonomous driving systems. Traditionally, an expensive and labor-intensive pipeline is implemented to construct HD maps, which is limited in scalability. In recent years, crowdsourcing and online mapping have emerged as two alternative methods, but they have limitations respectively. In this paper, we provide a novel methodology, namely global map construction, to perform direct generation of vectorized global maps, combining the benefits of crowdsourcing and online mapping. We introduce GlobalMapNet, the first online framework for vectorized global HD map construction, which updates and utilizes a global map on the ego vehicle. To generate the global map from scratch, we propose GlobalMapBuilder to match and merge local maps continuously. We design a new algorithm, Map NMS, to remove duplicate map elements and produce a clean map. We also propose GlobalMapFusion to aggregate historical map information, improving consistency of prediction. We examine GlobalMapNet on two widely recognized datasets, Argoverse2 and nuScenes, showing that our framework is capable of generating globally consistent results.
Authors: Meng Chen, Jiawei Tu, Chao Qi, Yonghao Dang, Feng Zhou, Wei Wei, Jianqin Yin
Abstract: The deployment of embodied navigation agents in safety-critical environments raises concerns about their vulnerability to adversarial attacks on deep neural networks. However, current attack methods often lack practicality due to challenges in transitioning from the digital to the physical world, while existing physical attacks for object detection fail to achieve both multi-view effectiveness and naturalness. To address this, we propose a practical attack method for embodied navigation by attaching adversarial patches with learnable textures and opacity to objects. Specifically, to ensure effectiveness across varying viewpoints, we employ a multi-view optimization strategy based on object-aware sampling, which uses feedback from the navigation model to optimize the patch's texture. To make the patch inconspicuous to human observers, we introduce a two-stage opacity optimization mechanism, where opacity is refined after texture optimization. Experimental results show our adversarial patches reduce navigation success rates by about 40%, outperforming previous methods in practicality, effectiveness, and naturalness. Code is available at: [https://github.com/chen37058/Physical-Attacks-in-Embodied-Navigation].
URLs: https://github.com/chen37058/Physical-Attacks-in-Embodied-Navigation].
Authors: Yuchen Guo, Ruoxiang Xu, Rongcheng Li, Zhenghao Wu, Weifeng Su
Abstract: Multi-modality image fusion aims to integrate complementary data information from different imaging modalities into a single image. Existing methods often generate either blurry fused images that lose fine-grained semantic information or unnatural fused images that appear perceptually cropped from the inputs. In this work, we propose a novel two-phase discriminative autoencoder framework, termed DAE-Fuse, that generates sharp and natural fused images. In the adversarial feature extraction phase, we introduce two discriminative blocks into the encoder-decoder architecture, providing an additional adversarial loss to better guide feature extraction by reconstructing the source images. While the two discriminative blocks are adapted in the attention-guided cross-modality fusion phase to distinguish the structural differences between the fused output and the source inputs, injecting more naturalness into the results. Extensive experiments on public infrared-visible, medical image fusion, and downstream object detection datasets demonstrate our method's superiority and generalizability in both quantitative and qualitative evaluations.
Authors: Weijing Tao, Xiaofeng Yang, Miaomiao Cui, Guosheng Lin
Abstract: This work presents MotionCom, a training-free motion-aware diffusion based image composition, enabling automatic and seamless integration of target objects into new scenes with dynamically coherent results without finetuning or optimization. Traditional approaches in this area suffer from two significant limitations: they require manual planning for object placement and often generate static compositions lacking motion realism. MotionCom addresses these issues by utilizing a Large Vision Language Model (LVLM) for intelligent planning, and a Video Diffusion prior for motion-infused image synthesis, streamlining the composition process. Our multi-modal Chain-of-Thought (CoT) prompting with LVLM automates the strategic placement planning of foreground objects, considering their potential motion and interaction within the scenes. Complementing this, we propose a novel method MotionPaint to distill motion-aware information from pretrained video diffusion models in the generation phase, ensuring that these objects are not only seamlessly integrated but also endowed with realistic motion. Extensive quantitative and qualitative results highlight MotionCom's superiority, showcasing its efficiency in streamlining the planning process and its capability to produce compositions that authentically depict motion and interaction.
Authors: Kun Fang, Qinghua Tao, Zuopeng Yang, Xiaolin Huang, Jie Yang
Abstract: Out-of-Distribution (OoD) detection determines whether the given samples are from the training distribution of the classifier-under-protection, i.e., the In-Distribution (InD), or from a different OoD. Latest researches introduce diffusion models pre-trained on InD data to advocate OoD detection by transferring an OoD image into a generated one that is close to InD, so that one could capture the distribution disparities between original and generated images to detect OoD data. Existing diffusion-based detectors adopt perceptual metrics on the two images to measure such disparities, but ignore a fundamental fact: Perceptual metrics are devised essentially for human-perceived similarities of low-level image patterns, e.g., textures and colors, and are not advisable in evaluating distribution disparities, since images with different low-level patterns could possibly come from the same distribution. To address this issue, we formulate a diffusion-based detection framework that considers the distribution similarity between a tested image and its generated counterpart via a novel proper similarity metric in the informative feature space and probability space learned by the classifier-under-protection. An anomaly-removal strategy is further presented to enlarge such distribution disparities by removing abnormal OoD information in the feature space to facilitate the detection. Extensive empirical results unveil the insufficiency of perceptual metrics and the effectiveness of our distribution similarity framework with new state-of-the-art detection performance.
Authors: Huy-Dung Nguyen, Anass Bairouk, Mirjana Maras, Wei Xiao, Tsun-Hsuan Wang, Patrick Chareyre, Ramin Hasani, Marc Blanchon, Daniela Rus
Abstract: Autonomous driving holds great potential to transform road safety and traffic efficiency by minimizing human error and reducing congestion. A key challenge in realizing this potential is the accurate estimation of steering angles, which is essential for effective vehicle navigation and control. Recent breakthroughs in deep learning have made it possible to estimate steering angles directly from raw camera inputs. However, the limited available navigation data can hinder optimal feature learning, impacting the system's performance in complex driving scenarios. In this paper, we propose a shared encoder trained on multiple computer vision tasks critical for urban navigation, such as depth, pose, and 3D scene flow estimation, as well as semantic, instance, panoptic, and motion segmentation. By incorporating diverse visual information used by humans during navigation, this unified encoder might enhance steering angle estimation. To achieve effective multi-task learning within a single encoder, we introduce a multi-scale feature network for pose estimation to improve depth learning. Additionally, we employ knowledge distillation from a multi-backbone model pretrained on these navigation tasks to stabilize training and boost performance. Our findings demonstrate that a shared backbone trained on diverse visual tasks is capable of providing overall perception capabilities. While our performance in steering angle estimation is comparable to existing methods, the integration of human-like perception through multi-task learning holds significant potential for advancing autonomous driving systems. More details and the pretrained model are available at https://hi-computervision.github.io/uni-encoder/.
Authors: Yi-Hsin Li, Sebastian Knorr, M{\aa}rten Sj\"ostr\"om, Thomas Sikora
Abstract: Kernel image regression methods have shown to provide excellent efficiency in many image processing task, such as image and light-field compression, Gaussian Splatting, denoising and super-resolution. The estimation of parameters for these methods frequently employ gradient descent iterative optimization, which poses significant computational burden for many applications. In this paper, we introduce a novel adaptive segmentation-based initialization method targeted for optimizing Steered-Mixture-of Experts (SMoE) gating networks and Radial-Basis-Function (RBF) networks with steering kernels. The novel initialization method allocates kernels into pre-calculated image segments. The optimal number of kernels, kernel positions, and steering parameters are derived per segment in an iterative optimization and kernel sparsification procedure. The kernel information from "local" segments is then transferred into a "global" initialization, ready for use in iterative optimization of SMoE, RBF, and related kernel image regression methods. Results show that drastic objective and subjective quality improvements are achievable compared to widely used regular grid initialization, "state-of-the-art" K-Means initialization and previously introduced segmentation-based initialization methods, while also drastically improving the sparsity of the regression models. For same quality, the novel initialization results in models with around 50% reduction of kernels. In addition, a significant reduction of convergence time is achieved, with overall run-time savings of up to 50%. The segmentation-based initialization strategy itself admits heavy parallel computation; in theory, it may be divided into as many tasks as there are segments in the images. By accessing only four parallel GPUs, run-time savings of already 50% for initialization are achievable.
Authors: Thomas Fraunholz, Dennis Rall, Tim K\"ohler, Alfons Schuster, Monika Mayer, Lars Larsen
Abstract: In the realm of industrial manufacturing, Artificial Intelligence (AI) is playing an increasing role, from automating existing processes to aiding in the development of new materials and techniques. However, a significant challenge arises in smaller, experimental processes characterized by limited training data availability, questioning the possibility to train AI models in such small data contexts. In this work, we explore the potential of Transfer Learning to address this challenge, specifically investigating the minimum amount of data required to develop a functional AI model. For this purpose, we consider the use case of quality control of Carbon Fiber Reinforced Polymer (CFRP) tape laying in aerospace manufacturing using optical sensors. We investigate the behavior of different open-source computer vision models with a continuous reduction of the training data. Our results show that the amount of data required to successfully train an AI model can be drastically reduced, and the use of smaller models does not necessarily lead to a loss of performance.
Authors: Peng Li, Wangguandong Zheng, Yuan Liu, Tao Yu, Yangguang Li, Xingqun Qi, Mengfei Li, Xiaowei Chi, Siyu Xia, Wei Xue, Wenhan Luo, Qifeng Liu, Yike Guo
Abstract: Detailed and photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, full-body reconstruction from a monocular RGB image remains challenging due to the ill-posed nature of the problem and sophisticated clothing topology with self-occlusions. In this paper, we propose PSHuman, a novel framework that explicitly reconstructs human meshes utilizing priors from the multiview diffusion model. It is found that directly applying multiview diffusion on single-view human images leads to severe geometric distortions, especially on generated faces. To address it, we propose a cross-scale diffusion that models the joint probability distribution of global full-body shape and local facial characteristics, enabling detailed and identity-preserved novel-view generation without any geometric distortion. Moreover, to enhance cross-view body shape consistency of varied human poses, we condition the generative model on parametric models like SMPL-X, which provide body priors and prevent unnatural views inconsistent with human anatomy. Leveraging the generated multi-view normal and color images, we present SMPLX-initialized explicit human carving to recover realistic textured human meshes efficiently. Extensive experimental results and quantitative evaluations on CAPE and THuman2.1 datasets demonstrate PSHumans superiority in geometry details, texture fidelity, and generalization capability.
Authors: Shadab Ahamed
Abstract: Automated segmentation of cancerous lesions in PET/CT scans is a crucial first step in quantitative image analysis. However, training deep learning models for segmentation with high accuracy is particularly challenging due to the variations in lesion size, shape, and radiotracer uptake. These lesions can appear in different parts of the body, often near healthy organs that also exhibit considerable uptake, making the task even more complex. As a result, creating an effective segmentation model for routine PET/CT image analysis is challenging. In this study, we utilized a 3D Residual UNet model and employed the Generalized Dice Focal Loss function to train the model on the AutoPET Challenge 2024 dataset. We conducted a 5-fold cross-validation and used an average ensembling technique using the models from the five folds. In the preliminary test phase for Task-1, the average ensemble achieved a mean Dice Similarity Coefficient (DSC) of 0.6687, mean false negative volume (FNV) of 10.9522 ml and mean false positive volume (FPV) 2.9684 ml. More details about the algorithm can be found on our GitHub repository: https://github.com/ahxmeds/autosegnet2024.git. The training code has been shared via the repository: https://github.com/ahxmeds/autopet2024.git.
URLs: https://github.com/ahxmeds/autosegnet2024.git., https://github.com/ahxmeds/autopet2024.git.
Authors: Vedasri Nakka, Andreas Fischer, Rolf Ingold, Lars Vogtlin
Abstract: This thesis investigates the effectiveness of SimCLR, a contrastive learning technique, in Greek letter recognition, focusing on the impact of various augmentation techniques. We pretrain the SimCLR backbone using the Alpub dataset (pretraining dataset) and fine-tune it on a smaller ICDAR dataset (finetuning dataset) to compare SimCLR's performance against traditional baseline models, which use cross-entropy and triplet loss functions. Additionally, we explore the role of different data augmentation strategies, essential for the SimCLR training process. Methodologically, we examine three primary approaches: (1) a baseline model using cross-entropy loss, (2) a triplet embedding model with a classification layer, and (3) a SimCLR pretrained model with a classification layer. Initially, we train the baseline, triplet, and SimCLR models using 93 augmentations on ResNet-18 and ResNet-50 networks with the ICDAR dataset. From these, the top four augmentations are selected using a statistical t-test. Pretraining of SimCLR is conducted on the Alpub dataset, followed by fine-tuning on the ICDAR dataset. The triplet loss model undergoes a similar process, being pretrained on the top four augmentations before fine-tuning on ICDAR. Our experiments show that SimCLR does not outperform the baselines in letter recognition tasks. The baseline model with cross-entropy loss demonstrates better performance than both SimCLR and the triplet loss model. This study provides a detailed evaluation of contrastive learning for letter recognition, highlighting SimCLR's limitations while emphasizing the strengths of traditional supervised learning models in this task. We believe SimCLR's cropping strategies may cause a semantic shift in the input image, reducing training effectiveness despite the large pretraining dataset. Our code is available at https://github.com/DIVA-DIA/MT_augmentation_and_contrastive_learning/.
URLs: https://github.com/DIVA-DIA/MT_augmentation_and_contrastive_learning/.
Authors: Gonzalo Garrido-Lopez, Luis F. Gomez, Julian Fierrez, Aythami Morales, Ruben Tolosana, Javier Rueda, Enrique Navarro
Abstract: Sprinting is a determinant ability, especially in team sports. The kinematics of the sprint have been studied in the past using different methods specially developed considering human biomechanics and, among those methods, markerless systems stand out as very cost-effective. On the other hand, we have now multiple general methods for pixel and body tracking based on recent machine learning breakthroughs with excellent performance in body tracking, but these excellent trackers do not generally consider realistic human biomechanics. This investigation first adapts two of these general trackers (MoveNet and CoTracker) for realistic biomechanical analysis and then evaluate them in comparison to manual tracking (with key points manually marked using the software Kinovea). Our best resulting markerless body tracker particularly adapted for sprint biomechanics is termed VideoRun2D. The experimental development and assessment of VideoRun2D is reported on forty sprints recorded with a video camera from 5 different subjects, focusing our analysis in 3 key angles in sprint biomechanics: inclination of the trunk, flex extension of the hip and the knee. The CoTracker method showed huge differences compared to the manual labeling approach. However, the angle curves were correctly estimated by the MoveNet method, finding errors between 3.2{\deg} and 5.5{\deg}. In conclusion, our proposed VideoRun2D based on MoveNet core seems to be a helpful tool for evaluating sprint kinematics in some scenarios. On the other hand, the observed precision of this first version of VideoRun2D as a markerless sprint analysis system may not be yet enough for highly demanding applications. Future research lines towards that purpose are also discussed at the end: better tracking post-processing and user- and time-dependent adaptation.
Authors: Lena Wild, Ludvig Ericson, Rafael Valencia, Patric Jensfelt
Abstract: Acquisition and maintenance are central problems in deploying high-definition (HD) maps for autonomous driving, with two lines of research prevalent in current literature: Online HD map generation and HD map change detection. However, the generated map's quality is currently insufficient for safe deployment, and many change detection approaches fail to precisely localize and extract the changed map elements, hence lacking explainability and hindering a potential fleet-based cooperative HD map update. In this paper, we propose the novel task of explainable element-based HD map change detection and update. In extending recent approaches that use online mapping techniques informed with an outdated map prior for HD map updating, we present ExelMap, an explainable element-based map updating strategy that specifically identifies changed map elements. In this context, we discuss how currently used metrics fail to capture change detection performance, while allowing for unfair comparison between prior-less and prior-informed map generation methods. Finally, we present an experimental study on real-world changes related to pedestrian crossings of the Argoverse 2 Map Change Dataset. To the best of our knowledge, this is the first comprehensive problem investigation of real-world end-to-end element-based HD map change detection and update, and ExelMap the first proposed solution.
Authors: Ba\c{s}ak Melis \"Ocal, Maxim Tatarchenko, Sezer Karaoglu, Theo Gevers
Abstract: Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and generalizability to real-world data are still limited. To tackle this problem, we propose a self-supervised framework, namely RealDiff, that formulates point cloud completion as a conditional generation problem directly on real-world measurements. To better deal with noisy observations without resorting to training on synthetic data, we leverage additional geometric cues. Specifically, RealDiff simulates a diffusion process at the missing object parts while conditioning the generation on the partial input to address the multimodal nature of the task. We further regularize the training by matching object silhouettes and depth maps, predicted by our method, with the externally estimated ones. Experimental results show that our method consistently outperforms state-of-the-art methods in real-world point cloud completion.
Authors: Weihao Ye, Qiong Wu, Wenhao Lin, Yiyi Zhou
Abstract: Recent progress in Multimodal Large Language Models(MLLMs) often use large image tokens to compensate the visual shortcoming of MLLMs, which not only exhibits obvious redundancy but also greatly exacerbates the already high computation. Token pruning is an effective solution for speeding up MLLMs, but when and how to drop tokens still remains a challenge. In this paper, we propose a novel and training-free approach for the effective visual token pruning of MLLMs, termed FitPrune, which can quickly produce a complete pruning recipe for MLLMs according to a pre-defined budget. Specifically, FitPrune considers token pruning as a statistical problem of MLLM and its objective is to find out an optimal pruning scheme that can minimize the divergence of the attention distributions before and after pruning. In practice, FitPrune can be quickly accomplished based on the attention statistics from a small batch of inference data, avoiding the expensive trials of MLLMs. According to the pruning recipe, an MLLM can directly remove the redundant visual tokens of different examples during inference. To validate FitPrune, we apply it to a set of recent MLLMs, including LLaVA-1.5, LLaVA-HR and LLaVA-NEXT, and conduct extensive experiments on a set of benchmarks. The experimental results show that our FitPrune can not only reduce the computational complexity to a large extent, while retaining high performance, e.g., -54.9% FLOPs for LLaVA-NEXT with only 0.5% accuracy drop. Notably, the pruning recipe can be obtained in about 5 minutes. Our code is available at https://github.com/ywh187/FitPrune.
Authors: Vittorio Casula, Lorenzo Berlincioni, Luca Cultrera, Federico Becattini, Chiara Pero, Carmen Bisogni, Marco Bertini, Alberto Del Bimbo
Abstract: In the rapidly evolving field of online fashion shopping, the need for more personalized and interactive image retrieval systems has become paramount. Existing methods often struggle with precisely manipulating specific garment attributes without inadvertently affecting others. To address this challenge, we propose GAMMA (Garment Attribute Manipulation with Multi-level Attention), a novel framework that integrates attribute-disentangled representations with a multi-stage attention-based architecture. GAMMA enables targeted manipulation of fashion image attributes, allowing users to refine their searches with high accuracy. By leveraging a dual-encoder Transformer and memory block, our model achieves state-of-the-art performance on popular datasets like Shopping100k and DeepFashion.
Authors: Federico Becattini, Luca Cultrera, Lorenzo Berlincioni, Claudio Ferrari, Andrea Leonardo, Alberto Del Bimbo
Abstract: Traditional approaches for analyzing RGB frames are capable of providing a fine-grained understanding of a face from different angles by inferring emotions, poses, shapes, landmarks. However, when it comes to subtle movements standard RGB cameras might fall behind due to their latency, making it hard to detect micro-movements that carry highly informative cues to infer the true emotions of a subject. To address this issue, the usage of event cameras to analyze faces is gaining increasing interest. Nonetheless, all the expertise matured for RGB processing is not directly transferrable to neuromorphic data due to a strong domain shift and intrinsic differences in how data is represented. The lack of labeled data can be considered one of the main causes of this gap, yet gathering data is harder in the event domain since it cannot be crawled from the web and labeling frames should take into account event aggregation rates and the fact that static parts might not be visible in certain frames. In this paper, we first present FACEMORPHIC, a multimodal temporally synchronized face dataset comprising both RGB videos and event streams. The data is labeled at a video level with facial Action Units and also contains streams collected with a variety of applications in mind, ranging from 3D shape estimation to lip-reading. We then show how temporal synchronization can allow effective neuromorphic face analysis without the need to manually annotate videos: we instead leverage cross-modal supervision bridging the domain gap by representing face shapes in a 3D space.
Authors: Merve Rabia Bar{\i}n, G\"orkay Aydemir, Fatma G\"uney
Abstract: Extracting a Bird's Eye View (BEV) representation from multiple camera images offers a cost-effective, scalable alternative to LIDAR-based solutions in autonomous driving. However, the performance of the existing BEV methods drops significantly under various corruptions such as brightness and weather changes or camera failures. To improve the robustness of BEV perception, we propose to adapt a large vision foundational model, DINOv2, to BEV estimation using Low Rank Adaptation (LoRA). Our approach builds on the strong representation space of DINOv2 by adapting it to the BEV task in a state-of-the-art framework, SimpleBEV. Our experiments show increased robustness of BEV perception under various corruptions, with increasing gains from scaling up the model and the input resolution. We also showcase the effectiveness of the adapted representations in terms of fewer learnable parameters and faster convergence during training.
Authors: Joshua Knights, Sebasti\'an Barbas Laina, Peyman Moghadam, Stefan Leutenegger
Abstract: This paper proposes SOLVR, a unified pipeline for learning based LiDAR-Visual re-localisation which performs place recognition and 6-DoF registration across sensor modalities. We propose a strategy to align the input sensor modalities by leveraging stereo image streams to produce metric depth predictions with pose information, followed by fusing multiple scene views from a local window using a probabilistic occupancy framework to expand the limited field-of-view of the camera. Additionally, SOLVR adopts a flexible definition of what constitutes positive examples for different training losses, allowing us to simultaneously optimise place recognition and registration performance. Furthermore, we replace RANSAC with a registration function that weights a simple least-squares fitting with the estimated inlier likelihood of sparse keypoint correspondences, improving performance in scenarios with a low inlier ratio between the query and retrieved place. Our experiments on the KITTI and KITTI360 datasets show that SOLVR achieves state-of-the-art performance for LiDAR-Visual place recognition and registration, particularly improving registration accuracy over larger distances between the query and retrieved place.
Authors: Minghan Chen, Guikun Chen, Wenguan Wang, Yi Yang
Abstract: DETR introduces a simplified one-stage framework for scene graph generation (SGG). However, DETR-based SGG models face two challenges: i) Sparse supervision, as each image typically contains fewer than 10 relation annotations, while the models employ over 100 relation queries. This sparsity arises because each ground truth relation is assigned to only one single query during training. ii) False negative samples, since one ground truth relation may have multiple queries with similar matching scores. These suboptimally matched queries are simply treated as negative samples, causing the loss of valuable supervisory signals. As a response, we devise Hydra-SGG, a one-stage SGG method that adopts a new Hybrid Relation Assignment. This assignment combines a One-to-One Relation Assignment with a newly introduced IoU-based One-to-Many Relation Assignment. Specifically, each ground truth is assigned to multiple relation queries with high IoU subject-object boxes. This Hybrid Relation Assignment increases the number of positive training samples, alleviating sparse supervision. Moreover, we, for the first time, empirically show that self-attention over relation queries helps reduce duplicated relation predictions. We, therefore, propose Hydra Branch, a parameter-sharing auxiliary decoder without a self-attention layer. This design promotes One-to-Many Relation Assignment by enabling different queries to predict the same relation. Hydra-SGG achieves state-of-the-art performance with 10.6 mR@20 and 16.0 mR@50 on VG150, while only requiring 12 training epochs. It also sets a new state-of-the-art on Open Images V6 and and GQA.
Authors: Wentao Wang, Xili Wang
Abstract: Large-scale semantic segmentation networks often achieve high performance, while their application can be challenging when faced with limited sample sizes and computational resources. In scenarios with restricted network size and computational complexity, models encounter significant challenges in capturing long-range dependencies and recovering detailed information in images. We propose a lightweight bilateral semantic segmentation network called bilateral attention fusion network (BAFNet) to efficiently segment high-resolution urban remote sensing images. The model consists of two paths, namely dependency path and remote-local path. The dependency path utilizes large kernel attention to acquire long-range dependencies in the image. Besides, multi-scale local attention and efficient remote attention are designed to construct remote-local path. Finally, a feature aggregation module is designed to effectively utilize the different features of the two paths. Our proposed method was tested on public high-resolution urban remote sensing datasets Vaihingen and Potsdam, with mIoU reaching 83.20% and 86.53%, respectively. As a lightweight semantic segmentation model, BAFNet not only outperforms advanced lightweight models in accuracy but also demonstrates comparable performance to non-lightweight state-of-the-art methods on two datasets, despite a tenfold variance in floating-point operations and a fifteenfold difference in network parameters.
Authors: Roni Blushtein-Livnon, Tal Svoray, Michael Dorman
Abstract: This study introduces a laboratory experiment designed to assess the influence of annotation strategies, levels of imbalanced data, and prior experience, on the performance of human annotators. The experiment focuses on labeling aerial imagery, using ArcGIS Pro tools, to detect and segment small-scale photovoltaic solar panels, selected as a case study for rectangular objects. The experiment is conducted using images with a pixel size of 0.15\textbf{$m$}, involving both expert and non-expert participants, across different setup strategies and target-background ratio datasets. Our findings indicate that human annotators generally perform more effectively in object detection than in segmentation tasks. A marked tendency to commit more Type II errors (False Negatives, i.e., undetected objects) than Type I errors (False Positives, i.e. falsely detecting objects that do not exist) was observed across all experimental setups and conditions, suggesting a consistent bias in detection and segmentation processes. Performance was better in tasks with higher target-background ratios (i.e., more objects per unit area). Prior experience did not significantly impact performance and may, in some cases, even lead to overestimation in segmentation. These results provide evidence that human annotators are relatively cautious and tend to identify objects only when they are confident about them, prioritizing underestimation over overestimation. Annotators' performance is also influenced by object scarcity, showing a decline in areas with extremely imbalanced datasets and a low ratio of target-to-background. These findings may enhance annotation strategies for remote sensing research while efficient human annotators are crucial in an era characterized by growing demands for high-quality training data to improve segmentation and detection models.
Authors: Neil De La Fuente, Mireia Maj\'o, Irina Luzko, Henry C\'ordova, Gloria Fern\'andez-Esparrach, Jorge Bernal
Abstract: Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities. By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18\% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6\% increase in global accuracy and precision.
Authors: Mikhail Goncharov, Valentin Samokhin, Eugenia Soboleva, Roman Sokolov, Boris Shirokikh, Mikhail Belyaev, Anvar Kurmukov, Ivan Oseledets
Abstract: We propose a self-supervised model producing 3D anatomical positional embeddings (APE) of individual medical image voxels. APE encodes voxels' anatomical closeness, i.e., voxels of the same organ or nearby organs always have closer positional embeddings than the voxels of more distant body parts. In contrast to the existing models of anatomical positional embeddings, our method is able to efficiently produce a map of voxel-wise embeddings for a whole volumetric input image, which makes it an optimal choice for different downstream applications. We train our APE model on 8400 publicly available CT images of abdomen and chest regions. We demonstrate its superior performance compared with the existing models on anatomical landmark retrieval and weakly-supervised few-shot localization of 13 abdominal organs. As a practical application, we show how to cheaply train APE to crop raw CT images to different anatomical regions of interest with 0.99 recall, while reducing the image volume by 10-100 times. The code and the pre-trained APE model are available at https://github.com/mishgon/ape .
Authors: Blaine Hoak, Patrick McDaniel
Abstract: The influence of textures on machine learning models has been an ongoing investigation, specifically in texture bias/learning, interpretability, and robustness. However, due to the lack of large and diverse texture data available, the findings in these works have been limited, as more comprehensive evaluations have not been feasible. Image generative models are able to provide data creation at scale, but utilizing these models for texture synthesis has been unexplored and poses additional challenges both in creating accurate texture images and validating those images. In this work, we introduce an extensible methodology and corresponding new dataset for generating high-quality, diverse texture images capable of supporting a broad set of texture-based tasks. Our pipeline consists of: (1) developing prompts from a range of descriptors to serve as input to text-to-image models, (2) adopting and adapting Stable Diffusion pipelines to generate and filter the corresponding images, and (3) further filtering down to the highest quality images. Through this, we create the Prompted Textures Dataset (PTD), a dataset of 362,880 texture images that span 56 textures. During the process of generating images, we find that NSFW safety filters in image generation pipelines are highly sensitive to texture (and flag up to 60\% of our texture images), uncovering a potential bias in these models and presenting unique challenges when working with texture data. Through both standard metrics and a human evaluation, we find that our dataset is high quality and diverse.
Authors: Euntae Choi, Vincent Carpentier, Seunghun Shin, Sungjoo Yoo
Abstract: Relighting, which synthesizes a novel view under a given lighting condition (unseen in training time), is a must feature for immersive photo-realistic experience. However, real-time relighting is challenging due to high computation cost of the rendering equation which requires shape and material decomposition and visibility test to model shadow. Additionally, for indirect illumination, additional computation of rendering equation on each secondary surface point (where reflection occurs) is required rendering real-time relighting challenging. We propose a novel method that executes a CNN renderer to compute primary surface points and rendering parameters, required for direct illumination. We also present a lightweight hash grid-based renderer, for indirect illumination, which is recursively executed to perform the secondary ray tracing process. Both renderers are trained in a distillation from a pre-trained teacher model and provide real-time physically-based rendering under unseen lighting condition at a negligible loss of rendering quality.
Authors: Yuchen Guo, Weifeng Su
Abstract: Although multi-modality medical image segmentation holds significant potential for enhancing the diagnosis and understanding of complex diseases by integrating diverse imaging modalities, existing methods predominantly rely on feature-level fusion strategies. We argue the current feature-level fusion strategy is prone to semantic inconsistencies and misalignments across various imaging modalities because it merges features at intermediate layers in a neural network without evaluative control. To mitigate this, we introduce a novel image-level fusion based multi-modality medical image segmentation method, Fuse4Seg, which is a bi-level learning framework designed to model the intertwined dependencies between medical image segmentation and medical image fusion. The image-level fusion process is seamlessly employed to guide and enhance the segmentation results through a layered optimization approach. Besides, the knowledge gained from the segmentation module can effectively enhance the fusion module. This ensures that the resultant fused image is a coherent representation that accurately amalgamates information from all modalities. Moreover, we construct a BraTS-Fuse benchmark based on BraTS dataset, which includes 2040 paired original images, multi-modal fusion images, and ground truth. This benchmark not only serves image-level medical segmentation but is also the largest dataset for medical image fusion to date. Extensive experiments on several public datasets and our benchmark demonstrate the superiority of our approach over prior state-of-the-art (SOTA) methodologies.
Authors: {\L}ukasz Struski, Jacek Tabor
Abstract: Understanding the decisions made by image classification networks is a critical area of research in deep learning. This task is traditionally divided into two distinct approaches: post-hoc methods and intrinsic methods. Post-hoc methods, such as GradCam, aim to interpret the decisions of pre-trained models by identifying regions of the image where the network focuses its attention. However, these methods provide only a high-level overview, making it difficult to fully understand the network's decision-making process. Conversely, intrinsic methods, like prototypical parts models, offer a more detailed understanding of network predictions but are constrained by specific architectures, training methods, and datasets. In this paper, we introduce InfoDisent, a hybrid model that combines the advantages of both approaches. By utilizing an information bottleneck, InfoDisent disentangles the information in the final layer of a pre-trained deep network, enabling the breakdown of classification decisions into basic, understandable atomic components. Unlike standard prototypical parts approaches, InfoDisent can interpret the decisions of pre-trained classification networks and be used for making classification decisions, similar to intrinsic models. We validate the effectiveness of InfoDisent on benchmark datasets such as ImageNet, CUB-200-2011, Stanford Cars, and Stanford Dogs for both convolutional and transformer backbones.
Authors: Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sj\"olund, Thomas B. Sch\"on
Abstract: Diffusion models have achieved remarkable progress in generative modelling, particularly in enhancing image quality to conform to human preferences. Recently, these models have also been applied to low-level computer vision for photo-realistic image restoration (IR) in tasks such as image denoising, deblurring, dehazing, etc. In this review paper, we introduce key constructions in diffusion models and survey contemporary techniques that make use of diffusion models in solving general IR tasks. Furthermore, we point out the main challenges and limitations of existing diffusion-based IR frameworks and provide potential directions for future work.
Authors: T\'eo Guichoux, Laure Soulier, Nicolas Obin, Catherine Pelachaud
Abstract: Co-speech gestures are fundamental for communication. The advent of recent deep learning techniques has facilitated the creation of lifelike, synchronous co-speech gestures for Embodied Conversational Agents. "In-the-wild" datasets, aggregating video content from platforms like YouTube via human pose detection technologies, provide a feasible solution by offering 2D skeletal sequences aligned with speech. Concurrent developments in lifting models enable the conversion of these 2D sequences into 3D gesture databases. However, it is important to note that the 3D poses estimated from the 2D extracted poses are, in essence, approximations of the ground-truth, which remains in the 2D domain. This distinction raises questions about the impact of gesture representation dimensionality on the quality of generated motions - a topic that, to our knowledge, remains largely unexplored. Our study examines the effect of using either 2D or 3D joint coordinates as training data on the performance of speech-to-gesture deep generative models. We employ a lifting model for converting generated 2D pose sequences into 3D and assess how gestures created directly in 3D stack up against those initially generated in 2D and then converted to 3D. We perform an objective evaluation using widely used metrics in the gesture generation field as well as a user study to qualitatively evaluate the different approaches.
Authors: Amin Karimi Monsefi, Mengxi Zhou, Nastaran Karimi Monsefi, Ser-Nam Lim, Wei-Lun Chao, Rajiv Ramnath
Abstract: We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-defined frequencies in the input image and employs a reconstruction loss to pre-train the model. While achieving promising results, such an implementation has two fundamental limitations as identified in our paper. First, using pre-defined frequencies overlooks the variability of image frequency responses. Second, pre-trained with frequency-filtered images, the resulting model needs relatively more data to adapt to naturally looking images during fine-tuning. To address these drawbacks, we propose FOurier transform compression with seLf-Knowledge distillation (FOLK), integrating two dedicated ideas. First, inspired by image compression, we adaptively select the masked-out frequencies based on image frequency responses, creating more suitable SSL tasks for pre-training. Second, we employ a two-branch framework empowered by knowledge distillation, enabling the model to take both the filtered and original images as input, largely reducing the burden of downstream tasks. Our experimental results demonstrate the effectiveness of FOLK in achieving competitive performance to many state-of-the-art SSL methods across various downstream tasks, including image classification, few-shot learning, and semantic segmentation.
Authors: M\'elanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia, Galvin Khara, Ben Glocker
Abstract: Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive pairs. Positive contrastive pairs should preserve semantic meaning while discarding unwanted variations related to the data acquisition domain. Traditional contrastive pipelines attempt to simulate domain shifts through pre-defined generic image transformations. However, these do not always mimic realistic and relevant domain variations for medical imaging such as scanner differences. To tackle this issue, we herein introduce counterfactual contrastive learning, a novel framework leveraging recent advances in causal image synthesis to create contrastive positive pairs that faithfully capture relevant domain variations. Our method, evaluated across five datasets encompassing both chest radiography and mammography data, for two established contrastive objectives (SimCLR and DINO-v2), outperforms standard contrastive learning in terms of robustness to acquisition shift. Notably, counterfactual contrastive learning achieves superior downstream performance on both in-distribution and on external datasets, especially for images acquired with scanners under-represented in the training set. Further experiments show that the proposed framework extends beyond acquisition shifts, with models trained with counterfactual contrastive learning substantially improving subgroup performance across biological sex.
Authors: Filippo Botti, Alex Ergasti, Leonardo Rossi, Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi, Andrea Prati
Abstract: The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or diffusion-based models to perform this task, despite the heavy computational burden that they require. In particular, transformers use self- and cross-attention layers which have large memory footprint, while diffusion models require high inference time. To overcome the above, this paper explores a novel design of Mamba, an emergent State-Space Model (SSM), called Mamba-ST, to perform style transfer. To do so, we adapt Mamba linear equation to simulate the behavior of cross-attention layers, which are able to combine two separate embeddings into a single output, but drastically reducing memory usage and time complexity. We modified the Mamba's inner equations so to accept inputs from, and combine, two separate data streams. To the best of our knowledge, this is the first attempt to adapt the equations of SSMs to a vision task like style transfer without requiring any other module like cross-attention or custom normalization layers. An extensive set of experiments demonstrates the superiority and efficiency of our method in performing style transfer compared to transformers and diffusion models. Results show improved quality in terms of both ArtFID and FID metrics. Code is available at https://github.com/FilippoBotti/MambaST.
Authors: Hanbo Bi, Yingchao Feng, Wenhui Diao, Peijin Wang, Yongqiang Mao, Kun Fu, Hongqi Wang, Xian Sun
Abstract: For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed feature encoders tend to be class-agnostic, inevitably activating objects that are irrelevant to the target class. In contrast, humans can effortlessly focus on specific objects in the line of sight. This paper mimics the visual perception pattern of human beings and proposes a novel and powerful prompt-driven scheme, called ``Prompt and Transfer" (PAT), which constructs a dynamic class-aware prompting paradigm to tune the encoder for focusing on the interested object (target class) in the current task. Three key points are elaborated to enhance the prompting: 1) Cross-modal linguistic information is introduced to initialize prompts for each task. 2) Semantic Prompt Transfer (SPT) that precisely transfers the class-specific semantics within the images to prompts. 3) Part Mask Generator (PMG) that works in conjunction with SPT to adaptively generate different but complementary part prompts for different individuals. Surprisingly, PAT achieves competitive performance on 4 different tasks including standard FSS, Cross-domain FSS (e.g., CV, medical, and remote sensing domains), Weak-label FSS, and Zero-shot Segmentation, setting new state-of-the-arts on 11 benchmarks.
Authors: Qianying Liu, Paul Henderson, Xiao Gu, Hang Dai, Fani Deligianni
Abstract: Semi-supervised medical image segmentation has shown promise in training models with limited labeled data and abundant unlabeled data. However, state-of-the-art methods ignore a potentially valuable source of unsupervised semantic information -- spatial registration transforms between image volumes. To address this, we propose CCT-R, a contrastive cross-teaching framework incorporating registration information. To leverage the semantic information available in registrations between volume pairs, CCT-R incorporates two proposed modules: Registration Supervision Loss (RSL) and Registration-Enhanced Positive Sampling (REPS). The RSL leverages segmentation knowledge derived from transforms between labeled and unlabeled volume pairs, providing an additional source of pseudo-labels. REPS enhances contrastive learning by identifying anatomically-corresponding positives across volumes using registration transforms. Experimental results on two challenging medical segmentation benchmarks demonstrate the effectiveness and superiority of CCT-R across various semi-supervised settings, with as few as one labeled case. Our code is available at https://github.com/kathyliu579/ContrastiveCross-teachingWithRegistration.
URLs: https://github.com/kathyliu579/ContrastiveCross-teachingWithRegistration.
Authors: Toan Nguyen, Huy Nguyen, Huy Ung, Hieu Ung, Binh Nguyen
Abstract: Accurate insect pest recognition plays a critical role in agriculture. It is a challenging problem due to the intricate characteristics of insects. In this paper, we present DeWi, novel learning assistance for insect pest classification. With a one-stage and alternating training strategy, DeWi simultaneously improves several Convolutional Neural Networks in two perspectives: discrimination (by optimizing a triplet margin loss in a supervised training manner) and generalization (via data augmentation). From that, DeWi can learn discriminative and in-depth features of insect pests (deep) yet still generalize well to a large number of insect categories (wide). Experimental results show that DeWi achieves the highest performances on two insect pest classification benchmarks (76.44\% accuracy on the IP102 dataset and 99.79\% accuracy on the D0 dataset, respectively). In addition, extensive evaluations and ablation studies are conducted to thoroughly investigate our DeWi and demonstrate its superiority. Our source code is available at https://github.com/toannguyen1904/DeWi.
Authors: Lehong Wu, Lilang Lin, Jiahang Zhang, Yiyang Ma, Jiaying Liu
Abstract: Self-supervised learning has proved effective for skeleton-based human action understanding. However, previous works either rely on contrastive learning that suffers false negative problems or are based on reconstruction that learns too much unessential low-level clues, leading to limited representations for downstream tasks. Recently, great advances have been made in generative learning, which is naturally a challenging yet meaningful pretext task to model the general underlying data distributions. However, the representation learning capacity of generative models is under-explored, especially for the skeletons with spacial sparsity and temporal redundancy. To this end, we propose Masked Conditional Diffusion (MacDiff) as a unified framework for human skeleton modeling. For the first time, we leverage diffusion models as effective skeleton representation learners. Specifically, we train a diffusion decoder conditioned on the representations extracted by a semantic encoder. Random masking is applied to encoder inputs to introduce a information bottleneck and remove redundancy of skeletons. Furthermore, we theoretically demonstrate that our generative objective involves the contrastive learning objective which aligns the masked and noisy views. Meanwhile, it also enforces the representation to complement for the noisy view, leading to better generalization performance. MacDiff achieves state-of-the-art performance on representation learning benchmarks while maintaining the competence for generative tasks. Moreover, we leverage the diffusion model for data augmentation, significantly enhancing the fine-tuning performance in scenarios with scarce labeled data. Our project is available at https://lehongwu.github.io/ECCV24MacDiff/.
Authors: Qi Qian, Haiyang Xu, Ming Yan, Juhua Hu
Abstract: Diffusion models demonstrate impressive image generation performance with text guidance. Inspired by the learning process of diffusion, existing images can be edited according to text by DDIM inversion. However, the vanilla DDIM inversion is not optimized for classifier-free guidance and the accumulated error will result in the undesired performance. While many algorithms are developed to improve the framework of DDIM inversion for editing, in this work, we investigate the approximation error in DDIM inversion and propose to disentangle the guidance scale for the source and target branches to reduce the error while keeping the original framework. Moreover, a better guidance scale (i.e., 0.5) than default settings can be derived theoretically. Experiments on PIE-Bench show that our proposal can improve the performance of DDIM inversion dramatically without sacrificing efficiency.
Authors: Simone Maurizio La Cava, Sara Concas, Ruben Tolosana, Roberto Casula, Giulia Orr\`u, Martin Drahansky, Julian Fierrez, Gian Luca Marcialis
Abstract: 3D face reconstruction (3DFR) algorithms are based on specific assumptions tailored to distinct application scenarios. These assumptions limit their use when acquisition conditions, such as the subject's distance from the camera or the camera's characteristics, are different than expected, as typically happens in video surveillance. Additionally, 3DFR algorithms follow various strategies to address the reconstruction of a 3D shape from 2D data, such as statistical model fitting, photometric stereo, or deep learning. In the present study, we explore the application of three 3DFR algorithms representative of the SOTA, employing each one as the template set generator for a face verification system. The scores provided by each system are combined by score-level fusion. We show that the complementarity induced by different 3DFR algorithms improves performance when tests are conducted at never-seen-before distances from the camera and camera characteristics (cross-distance and cross-camera settings), thus encouraging further investigations on multiple 3DFR-based approaches.
Authors: Kaleb Newman, Shijie Wang, Yuan Zang, David Heffren, Chen Sun
Abstract: For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a whole apple into a sliced apple). Our paper aims to investigate if VLMs pre-trained on web-scale data learn to encode object states, which can be extracted with zero-shot text prompts. We curate an object state recognition dataset ChangeIt-Frames, and evaluate nine open-source VLMs, including models trained with contrastive and generative objectives. We observe that while these state-of-the-art vision-language models can reliably perform object recognition, they consistently fail to accurately distinguish the objects' physical states. Through extensive experiments, we identify three areas for improvements for VLMs to better encode object states, namely the quality of object localization, the architecture to bind concepts to objects, and the objective to learn discriminative visual and language encoders on object states. Data and code are released.
Authors: Zihan Huang, Tao Wu, Wang Lin, Shengyu Zhang, Jingyuan Chen, Fei Wu
Abstract: With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning. However, existing research has primarily focused on text-based algebra problems, neglecting the study of geometry due to the lack of high-quality geometric datasets. To address this gap, this paper introduces AutoGeo, a novel approach for automatically generating mathematical geometric images to fulfill the demand for large-scale and diverse geometric datasets. AutoGeo facilitates the creation of AutoGeo-100k, an extensive repository comprising 100k high-quality geometry image-text pairs. By leveraging precisely defined geometric clauses, AutoGeo-100k contains a wide variety of geometric shapes, including lines, polygons, circles, and complex spatial relationships, etc. Furthermore, this paper demonstrates the efficacy of AutoGeo-100k in enhancing the performance of multimodal large language models through fine-tuning. Experimental results indicate significant improvements in the model's ability in handling geometric images, as evidenced by enhanced accuracy in tasks such as geometric captioning and mathematical reasoning. This research not only fills a critical gap in the availability of geometric datasets but also paves the way for the advancement of sophisticated AI-driven tools in education and research. Project page: https://autogeo-official.github.io/.
Authors: Youzhu Jin, Yichen Zhang
Abstract: Multimodal large language models (MLLMs) have achieved significant success in the general field of image processing. Their emerging task generalization and freeform conversational capabilities can greatly facilitate medical diagnostic assistance, helping patients better understand their conditions and enhancing doctor-patient trust. Computed Tomography (CT) is a non-invasive imaging technique used to capture the internal mechanisms of a patient's condition and is widely utilized. However, in past research, the complex textural features of this imaging data have made accurate interpretation by algorithms challenging, impeding the performance of general LLMs in diagnostic assistance. To address this, we developed OrthoDoc, a MLLM designed for CT diagnostics. OrthoDoc is trained on 120,000 CT images and diagnostic reports and includes a Retrieval-Augmented Generation (RAG) module capable of effectively mitigating model hallucinations. This module is informed by extensive medical literature, textbooks, and explanatory data. Thus, OrthoDoc not only processes complex CT images but also stores, understands, and reasons over medical knowledge and language. In extensive experiments, OrthoDoc outperforms commercial models led by GPT-4, demonstrating superior diagnostic capabilities and accuracy. Specifically, OrthoDoc significantly surpasses existing models in the diagnosis of common orthopedic conditions such as fractures, arthritis, and tumors. Additionally, OrthoDoc exhibits robust generalization and stability when handling rare and complex cases.
Authors: Masoud Tafavvoghi, Anders Sildnes, Mehrdad Rakaee, Nikita Shvetsov, Lars Ailo Bongo, Lill-Tove Rasmussen Busund, Kajsa M{\o}llersen
Abstract: Classifying breast cancer molecular subtypes is crucial for tailoring treatment strategies. While immunohistochemistry (IHC) and gene expression profiling are standard methods for molecular subtyping, IHC can be subjective, and gene profiling is costly and not widely accessible in many regions. Previous approaches have highlighted the potential application of deep learning models on H&E-stained whole slide images (WSI) for molecular subtyping, but these efforts vary in their methods, datasets, and reported performance. In this work, we investigated whether H&E-stained WSIs could be solely leveraged to predict breast cancer molecular subtypes (luminal A, B, HER2-enriched, and Basal). We used 1,433 WSIs of breast cancer in a two-step pipeline: first, classifying tumor and non-tumor tiles to use only the tumor regions for molecular subtyping; and second, employing a One-vs-Rest (OvR) strategy to train four binary OvR classifiers and aggregating their results using an eXtreme Gradient Boosting (XGBoost) model. The pipeline was tested on 221 hold-out WSIs, achieving an overall macro F1 score of 0.95 for tumor detection and 0.73 for molecular subtyping. Our findings suggest that, with further validation, supervised deep learning models could serve as supportive tools for molecular subtyping in breast cancer. Our codes are made available to facilitate ongoing research and development.
Authors: Tianyi Chen, Xiaoyi Qu, David Aponte, Colby Banbury, Jongwoo Ko, Tianyu Ding, Yong Ma, Vladimir Lyapunov, Ilya Zharkov, Luming Liang
Abstract: Structured pruning is one of the most popular approaches to effectively compress the heavy deep neural networks (DNNs) into compact sub-networks while retaining performance. The existing methods suffer from multi-stage procedures along with significant engineering efforts and human expertise. The Only-Train-Once (OTO) series has been recently proposed to resolve the many pain points by streamlining the workflow by automatically conducting (i) search space generation, (ii) structured sparse optimization, and (iii) sub-network construction. However, the built-in sparse optimizers in the OTO series, i.e., the Half-Space Projected Gradient (HSPG) family, have limitations that require hyper-parameter tuning and the implicit controls of the sparsity exploration, consequently requires intervening by human expertise. To address such limitations, we propose a Hybrid Efficient Structured Sparse Optimizer (HESSO). HESSO could automatically and efficiently train a DNN to produce a high-performing subnetwork. Meanwhile, it is almost tuning-free and enjoys user-friendly integration for generic training applications. To address another common issue of irreversible performance collapse observed in pruning DNNs, we further propose a Corrective Redundant Identification Cycle (CRIC) for reliably identifying indispensable structures. We numerically demonstrate the efficacy of HESSO and its enhanced version HESSO-CRIC on a variety of applications ranging from computer vision to natural language processing, including large language model. The numerical results showcase that HESSO can achieve competitive even superior performance to varying state-of-the-arts and support most DNN architectures. Meanwhile, CRIC can effectively prevent the irreversible performance collapse and further enhance the performance of HESSO on certain applications. The code is available at https://github.com/microsoft/only_train_once.
Authors: Zhenyu Ning, Jieru Zhao, Qihao Jin, Wenchao Ding, Minyi Guo
Abstract: Multimodal Large Language Models (MLLMs) are distinguished by their multimodal comprehensive ability and widely used in many real-world applications including GPT-4o, autonomous driving and robotics. Despite their impressive performance, the multimodal inputs always incur long context. The inference under long context requires caching massive Key and Value states (KV cache) of previous tokens, which introduces high latency and excessive memory consumption. Due to this reason, it is challenging to deploy streaming inference of MLLMs on edge devices, which largely constrains the power and usage of MLLMs in real-world applications. In this paper, we introduce Inf-MLLM, an efficient inference framework for MLLMs, which enable streaming inference of MLLM on a single GPU with infinite context. Inf-MLLM is based on our key observation of the attention pattern in both LLMs and MLLMs called "attention saddles". Thanks to the newly discovered attention pattern, Inf-MLLM maintains a size-constrained KV cache by dynamically caching recent tokens and relevant tokens. Furthermore, Inf-MLLM proposes attention bias, a novel approach to enable MLLMs to capture long-term dependency. We show that Inf-MLLM enables multiple LLMs and MLLMs to achieve stable performance over 4M-token long texts and multi-round conversations with 1-hour-long videos on a single GPU. In addition, Inf-MLLM exhibits superior streaming reasoning quality than existing methods such as StreamingLLM and 2x speedup than H2O.
Authors: Altaf Allah Abbassi, Houssem Ben Braiek, Foutse Khomh, Thomas Reid
Abstract: The industry increasingly relies on deep learning (DL) technology for manufacturing inspections, which are challenging to automate with rule-based machine vision algorithms. DL-powered inspection systems derive defect patterns from labeled images, combining human-like agility with the consistency of a computerized system. However, finite labeled datasets often fail to encompass all natural variations necessitating Continuous Training (CT) to regularly adjust their models with recent data. Effective CT requires fresh labeled samples from the original distribution; otherwise, selfgenerated labels can lead to silent performance degradation. To mitigate this risk, we develop a robust CT-based maintenance approach that updates DL models using reliable data selections through a two-stage filtering process. The initial stage filters out low-confidence predictions, as the model inherently discredits them. The second stage uses variational auto-encoders and histograms to generate image embeddings that capture latent and pixel characteristics, then rejects the inputs of substantially shifted embeddings as drifted data with erroneous overconfidence. Then, a fine-tuning of the original DL model is executed on the filtered inputs while validating on a mixture of recent production and original datasets. This strategy mitigates catastrophic forgetting and ensures the model adapts effectively to new operational conditions. Evaluations on industrial inspection systems for popsicle stick prints and glass bottles using critical real-world datasets showed less than 9% of erroneous self-labeled data are retained after filtering and used for fine-tuning, improving model performance on production data by up to 14% without compromising its results on original validation data.
Authors: Alexandre Filiot, Paul Jacob, Alice Mac Kain, Charlie Saillard
Abstract: Gathering histopathology slides from over 100 publicly available cohorts, we compile a diverse dataset of 460 million pathology tiles covering more than 30 cancer sites. Using this dataset, we train a large self-supervised vision transformer using DINOv2 and publicly release one iteration of this model for further experimentation, coined Phikon-v2. While trained on publicly available histology slides, Phikon-v2 surpasses our previously released model (Phikon) and performs on par with other histopathology foundation models (FM) trained on proprietary data. Our benchmarks include eight slide-level tasks with results reported on external validation cohorts avoiding any data contamination between pre-training and evaluation datasets. Our downstream training procedure follows a simple yet robust ensembling strategy yielding a +1.75 AUC increase across tasks and models compared to one-shot retraining (p<0.001). We compare Phikon (ViT-B) and Phikon-v2 (ViT-L) against 14 different histology feature extractors, making our evaluation the most comprehensive to date. Our result support evidences that DINOv2 handles joint model and data scaling better than iBOT. Also, we show that recent scaling efforts are overall beneficial to downstream performance in the context of biomarker prediction with GigaPath and H-Optimus-0 (two ViT-g with 1.1B parameters each) standing out. However, the statistical margins between the latest top-performing FMs remain mostly non-significant; some even underperform on specific indications or tasks such as MSI prediction - deposed by a 13x smaller model developed internally. While latest foundation models may exhibit limitations for clinical deployment, they nonetheless offer excellent grounds for the development of more specialized and cost-efficient histology encoders fueling AI-guided diagnostic tools.
Authors: Yaopeng Peng, Zhi Chen, Andreas Wahle, Tomas Kovarnik, Milan Sonk, Danny Z. Chen
Abstract: The key manifestation of coronary artery disease (CAD) is development of fibroatheromatous plaque, the cap of which may rupture and subsequently lead to coronary artery blocking and heart attack. As such, quantitative analysis of coronary plaque, its plaque cap, and consequently the cap's likelihood to rupture are of critical importance when assessing a risk of cardiovascular events. This paper reports a new deep learning based approach, called FiAt-Net, for detecting angular extent of fibroatheroma (FA) and segmenting its cap in 3D intravascular optical coherence tomography (IVOCT) images. IVOCT 2D image frames are first associated with distinct clusters and data from each cluster are used for model training. As plaque is typically focal and thus unevenly distributed, a binary partitioning method is employed to identify FA plaque areas to focus on to mitigate the data imbalance issue. Additional image representations (called auxiliary images) are generated to capture IVOCT intensity changes to help distinguish FA and non-FA areas on the coronary wall. Information in varying scales is derived from the original IVOCT and auxiliary images, and a multi-head self-attention mechanism is employed to fuse such information. Our FiAt-Net achieved high performance on a 3D IVOCT coronary image dataset, demonstrating its effectiveness in accurately detecting FA cap in IVOCT images.
Authors: Eleonora Lopez, Aurelio Uncini, Danilo Comminiello
Abstract: Emotion recognition is relevant in various domains, ranging from healthcare to human-computer interaction. Physiological signals, being beyond voluntary control, offer reliable information for this purpose, unlike speech and facial expressions which can be controlled at will. They reflect genuine emotional responses, devoid of conscious manipulation, thereby enhancing the credibility of emotion recognition systems. Nonetheless, multimodal emotion recognition with deep learning models remains a relatively unexplored field. In this paper, we introduce a fully hypercomplex network with a hierarchical learning structure to fully capture correlations. Specifically, at the encoder level, the model learns intra-modal relations among the different channels of each input signal. Then, a hypercomplex fusion module learns inter-modal relations among the embeddings of the different modalities. The main novelty is in exploiting intra-modal relations by endowing the encoders with parameterized hypercomplex convolutions (PHCs) that thanks to hypercomplex algebra can capture inter-channel interactions within single modalities. Instead, the fusion module comprises parameterized hypercomplex multiplications (PHMs) that can model inter-modal correlations. The proposed architecture surpasses state-of-the-art models on the MAHNOB-HCI dataset for emotion recognition, specifically in classifying valence and arousal from electroencephalograms (EEGs) and peripheral physiological signals. The code of this study is available at https://github.com/ispamm/MHyEEG.
Authors: Yaopeng Peng, Milan Sonka, Danny Z. Chen
Abstract: This paper introduces Spectral U-Net, a novel deep learning network based on spectral decomposition, by exploiting Dual Tree Complex Wavelet Transform (DTCWT) for down-sampling and inverse Dual Tree Complex Wavelet Transform (iDTCWT) for up-sampling. We devise the corresponding Wave-Block and iWave-Block, integrated into the U-Net architecture, aiming at mitigating information loss during down-sampling and enhancing detail reconstruction during up-sampling. In the encoder, we first decompose the feature map into high and low-frequency components using DTCWT, enabling down-sampling while mitigating information loss. In the decoder, we utilize iDTCWT to reconstruct higher-resolution feature maps from down-sampled features. Evaluations on the Retina Fluid, Brain Tumor, and Liver Tumor segmentation datasets with the nnU-Net framework demonstrate the superiority of the proposed Spectral U-Net.
Authors: Chengxi Ye, Grace Chu, Yanfeng Liu, Yichi Zhang, Lukasz Lew, Andrew Howard
Abstract: The discontinuous operations inherent in quantization and sparsification introduce obstacles to backpropagation. This is particularly challenging when training deep neural networks in ultra-low precision and sparse regimes. We propose a novel, robust, and universal solution: a denoising affine transform that stabilizes training under these challenging conditions. By formulating quantization and sparsification as perturbations during training, we derive a perturbation-resilient approach based on ridge regression. Our solution employs a piecewise constant backbone model to ensure a performance lower bound and features an inherent noise reduction mechanism to mitigate perturbation-induced corruption. This formulation allows existing models to be trained at arbitrarily low precision and sparsity levels with off-the-shelf recipes. Furthermore, our method provides a novel perspective on training temporal binary neural networks, contributing to ongoing efforts to narrow the gap between artificial and biological neural networks.
Authors: Kento Tomita, Koki Ho
Abstract: Onboard terrain sensing and mapping for safe planetary landings often suffer from missed hazardous features, e.g., small rocks, due to the large observational range and the limited resolution of the obtained terrain data. To this end, this paper develops a novel real-time stochastic terrain mapping algorithm that accounts for topographic uncertainty between the sampled points, or the uncertainty due to the sparse 3D terrain measurements. We introduce a Gaussian digital elevation map that is efficiently constructed using the combination of Delauney triangulation and local Gaussian process regression. The geometric investigation of the lander-terrain interaction is exploited to efficiently evaluate the marginally conservative local slope and roughness while avoiding the costly computation of the local plane. The conservativeness is proved in the paper. The developed real-time uncertainty quantification pipeline enables stochastic landing safety evaluation under challenging operational conditions, such as a large observational range or limited sensor capability, which is a critical stepping stone for the development of predictive guidance algorithms for safe autonomous planetary landing. Detailed reviews on background and related works are also presented.
Authors: Yahan Tu, Rui Hu, Jitao Sang
Abstract: Hallucination poses a significant challenge for multimodal large language models (MLLMs). However, existing benchmarks for evaluating hallucinations are static, which can lead to potential data contamination. This paper introduces ODE, an open-set, dynamic protocol for evaluating object existence hallucinations in MLLMs. Our framework employs graph structures to model associations between real-word concepts and generates novel samples for both general and domain-specific scenarios. The dynamic combination of concepts, along with various combination principles, ensures a broad sample distribution. Experimental results show that MLLMs exhibit higher hallucination rates with ODE-generated samples, effectively avoiding data contamination. Moreover, these samples can also be used for fine-tuning to improve MLLM performance on existing benchmarks.
Authors: Sunwoo Kim, Yongjun Ahn, Daeyoung Park, Byonghyo Shim
Abstract: Recent advances in sensing and computer vision (CV) technologies have opened the door for the application of deep learning (DL)-based CV technologies in the realm of 6G wireless communications. For the successful application of this emerging technology, it is crucial to have a qualified vision dataset tailored for wireless applications (e.g., RGB images containing wireless devices such as laptops and cell phones). An aim of this paper is to propose a large-scale vision dataset referred to as Vision Objects for Millimeter and Terahertz Communications (VOMTC). The VOMTC dataset consists of 20,232 pairs of RGB and depth images obtained from a camera attached to the base station (BS), with each pair labeled with three representative object categories (person, cell phone, and laptop) and bounding boxes of the objects. Through experimental studies of the VOMTC datasets, we show that the beamforming technique exploiting the VOMTC-trained object detector outperforms conventional beamforming techniques.
Authors: Seunghwan Kim, Seungkyu Lee
Abstract: Variational autoencoder (VAE) is an established generative model but is notorious for its blurriness. In this work, we investigate the blurry output problem of VAE and resolve it, exploiting the variance of Gaussian decoder and $\beta$ of beta-VAE. Specifically, we reveal that the indistinguishability of decoder variance and $\beta$ hinders appropriate analysis of the model by random likelihood value, and limits performance improvement by omitting the gain from $\beta$. To address the problem, we propose Beta-Sigma VAE (BS-VAE) that explicitly separates $\beta$ and decoder variance $\sigma^2_x$ in the model. Our method demonstrates not only superior performance in natural image synthesis but also controllable parameters and predictable analysis compared to conventional VAE. In our experimental evaluation, we employ the analysis of rate-distortion curve and proxy metrics on computer vision datasets. The code is available on https://github.com/overnap/BS-VAE
Authors: Tobit Klug, Kun Wang, Stefan Ruschke, Reinhard Heckel
Abstract: A major challenge of the long measurement times in magnetic resonance imaging (MRI), an important medical imaging technology, is that patients may move during data acquisition. This leads to severe motion artifacts in the reconstructed images and volumes. In this paper, we propose a deep learning-based test-time-training method for accurate motion estimation. The key idea is that a neural network trained for motion-free reconstruction has a small loss if there is no motion, thus optimizing over motion parameters passed through the reconstruction network enables accurate estimation of motion. The estimated motion parameters enable to correct for the motion and to reconstruct accurate motion-corrected images. Our method uses 2D reconstruction networks to estimate rigid motion in 3D, and constitutes the first deep learning based method for 3D rigid motion estimation towards 3D-motion-corrected MRI. We show that our method can provably reconstruct motion parameters for a simple signal and neural network model. We demonstrate the effectiveness of our method for both retrospectively simulated motion and prospectively collected real motion-corrupted data.
Authors: Mohammed Munzer Dwedari, William Consagra, Philip M\"uller, \"Ozg\"un Turgut, Daniel Rueckert, Yogesh Rathi
Abstract: The Orientation Distribution Function (ODF) characterizes key brain microstructural properties and plays an important role in understanding brain structural connectivity. Recent works introduced Implicit Neural Representation (INR) based approaches to form a spatially aware continuous estimate of the ODF field and demonstrated promising results in key tasks of interest when compared to conventional discrete approaches. However, traditional INR methods face difficulties when scaling to large-scale images, such as modern ultra-high-resolution MRI scans, posing challenges in learning fine structures as well as inefficiencies in training and inference speed. In this work, we propose HashEnc, a grid-hash-encoding-based estimation of the ODF field and demonstrate its effectiveness in retaining structural and textural features. We show that HashEnc achieves a 10% enhancement in image quality while requiring 3x less computational resources than current methods. Our code can be found at https://github.com/MunzerDw/NODF-HashEnc.
Authors: Maximilian Rokuss, Balint Kovacs, Yannick Kirchhoff, Shuhan Xiao, Constantin Ulrich, Klaus H. Maier-Hein, Fabian Isensee
Abstract: Automated lesion segmentation in PET/CT scans is crucial for improving clinical workflows and advancing cancer diagnostics. However, the task is challenging due to physiological variability, different tracers used in PET imaging, and diverse imaging protocols across medical centers. To address this, the autoPET series was created to challenge researchers to develop algorithms that generalize across diverse PET/CT environments. This paper presents our solution for the autoPET III challenge, targeting multitracer, multicenter generalization using the nnU-Net framework with the ResEncL architecture. Key techniques include misalignment data augmentation and multi-modal pretraining across CT, MR, and PET datasets to provide an initial anatomical understanding. We incorporate organ supervision as a multitask approach, enabling the model to distinguish between physiological uptake and tracer-specific patterns, which is particularly beneficial in cases where no lesions are present. Compared to the default nnU-Net, which achieved a Dice score of 57.61, or the larger ResEncL (65.31) our model significantly improved performance with a Dice score of 68.40, alongside a reduction in false positive (FPvol: 7.82) and false negative (FNvol: 10.35) volumes. These results underscore the effectiveness of combining advanced network design, augmentation, pretraining, and multitask learning for PET/CT lesion segmentation. Code is publicly available at https://github.com/MIC-DKFZ/autopet-3-submission.
Authors: Yuheng Qiu, Yutian Chen, Zihao Zhang, Wenshan Wang, Sebastian Scherer
Abstract: We propose the MAC-VO, a novel learning-based stereo VO that leverages the learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization. Compared to traditional geometric methods prioritizing texture-affluent features like edges, our keypoint selector employs the learned uncertainty to filter out the low-quality features based on global inconsistency. In contrast to the learning-based algorithms that model the scale-agnostic diagonal weight matrix for covariance, we design a metrics-aware covariance model to capture the spatial error during keypoint registration and the correlations between different axes. Integrating this covariance model into pose graph optimization enhances the robustness and reliability of pose estimation, particularly in challenging environments with varying illumination, feature density, and motion patterns. On public benchmark datasets, MAC-VO outperforms existing VO algorithms and even some SLAM algorithms in challenging environments. The covariance map also provides valuable information about the reliability of the estimated poses, which can benefit decision-making for autonomous systems.
Authors: Mobina Mansoori, Sajjad Shahabodini, Jamshid Abouei, Konstantinos N. Plataniotis, Arash Mohammadi
Abstract: Early diagnosis and treatment of polyps during colonoscopy are essential for reducing the incidence and mortality of Colorectal Cancer (CRC). However, the variability in polyp characteristics and the presence of artifacts in colonoscopy images and videos pose significant challenges for accurate and efficient polyp detection and segmentation. This paper presents a novel approach to polyp segmentation by integrating the Segment Anything Model (SAM 2) with the YOLOv8 model. Our method leverages YOLOv8's bounding box predictions to autonomously generate input prompts for SAM 2, thereby reducing the need for manual annotations. We conducted exhaustive tests on five benchmark colonoscopy image datasets and two colonoscopy video datasets, demonstrating that our method exceeds state-of-the-art models in both image and video segmentation tasks. Notably, our approach achieves high segmentation accuracy using only bounding box annotations, significantly reducing annotation time and effort. This advancement holds promise for enhancing the efficiency and scalability of polyp detection in clinical settings https://github.com/sajjad-sh33/YOLO_SAM2.
Authors: Brighton Ancelin, Yenho Chen, Peimeng Guan, Chiraag Kaushik, Belen Martin-Urcelay, Alex Saad-Falcon, Nakul Singh
Abstract: Learning semantically meaningful image transformations (i.e. rotation, thickness, blur) directly from examples can be a challenging task. Recently, the Manifold Autoencoder (MAE) proposed using a set of Lie group operators to learn image transformations directly from examples. However, this approach has limitations, as the learned operators are not guaranteed to be disentangled and the training routine is prohibitively expensive when scaling up the model. To address these limitations, we propose MANGO (transformation Manifolds with Grouped Operators) for learning disentangled operators that describe image transformations in distinct latent subspaces. Moreover, our approach allows practitioners the ability to define which transformations they aim to model, thus improving the semantic meaning of the learned operators. Through our experiments, we demonstrate that MANGO enables composition of image transformations and introduces a one-phase training routine that leads to a 100x speedup over prior works.
Authors: Ka Nam Canaan Law, Mingshuo Yu, Lianglei Zhang, Yiyi Zhang, Peng Xu, Jerry Gao, Jun Liu
Abstract: The quality control of printed circuit boards (PCBs) is paramount in advancing electronic device technology. While numerous machine learning methodologies have been utilized to augment defect detection efficiency and accuracy, previous studies have predominantly focused on optimizing individual models for specific defect types, often overlooking the potential synergies between different approaches. This paper introduces a comprehensive inspection framework leveraging an ensemble learning strategy to address this gap. Initially, we utilize four distinct PCB defect detection models utilizing state-of-the-art methods: EfficientDet, MobileNet SSDv2, Faster RCNN, and YOLOv5. Each method is capable of identifying PCB defects independently. Subsequently, we integrate these models into an ensemble learning framework to enhance detection performance. A comparative analysis reveals that our ensemble learning framework significantly outperforms individual methods, achieving a 95% accuracy in detecting diverse PCB defects. These findings underscore the efficacy of our proposed ensemble learning framework in enhancing PCB quality control processes.
Authors: Sahil Kuchlous, Marvin Li, Jeffrey G. Wang
Abstract: With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models: embedding spaces. First, because traditional classifier-based fairness definitions require true labels not present in generative modeling, we propose statistical group fairness criteria based on a model's internal representation of the world. Using these definitions, we demonstrate theoretically and empirically that an unbiased text embedding space for input prompts is a necessary condition for representationally balanced diffusion models, meaning the distribution of generated images satisfy diversity requirements with respect to protected attributes. Next, we investigate the impact of biased embeddings on evaluating the alignment between generated images and prompts, a process which is commonly used to assess diffusion models. We find that biased multimodal embeddings like CLIP can result in lower alignment scores for representationally balanced TTI models, thus rewarding unfair behavior. Finally, we develop a theoretical framework through which biases in alignment evaluation can be studied and propose bias mitigation methods. By specifically adapting the perspective of embedding spaces, we establish new fairness conditions for diffusion model development and evaluation.
Authors: Ang Nan Gu, Michael Tsang, Hooman Vaseli, Teresa Tsang, Purang Abolmaesumi
Abstract: The fundamental problem with ultrasound-guided diagnosis is that the acquired images are often 2-D cross-sections of a 3-D anatomy, potentially missing important anatomical details. This limitation leads to challenges in ultrasound echocardiography, such as poor visualization of heart valves or foreshortening of ventricles. Clinicians must interpret these images with inherent uncertainty, a nuance absent in machine learning's one-hot labels. We propose Re-Training for Uncertainty (RT4U), a data-centric method to introduce uncertainty to weakly informative inputs in the training set. This simple approach can be incorporated to existing state-of-the-art aortic stenosis classification methods to further improve their accuracy. When combined with conformal prediction techniques, RT4U can yield adaptively sized prediction sets which are guaranteed to contain the ground truth class to a high accuracy. We validate the effectiveness of RT4U on three diverse datasets: a public (TMED-2) and a private AS dataset, along with a CIFAR-10-derived toy dataset. Results show improvement on all the datasets.
Authors: Dylan Sam, Devin Willmott, Joao D. Semedo, J. Zico Kolter
Abstract: Vision-language models (VLMs) such as CLIP are trained via contrastive learning between text and image pairs, resulting in aligned image and text embeddings that are useful for many downstream tasks. A notable drawback of CLIP, however, is that the resulting embedding space seems to lack some of the structure of their purely text-based alternatives. For instance, while text embeddings have been long noted to satisfy \emph{analogies} in embedding space using vector arithmetic, CLIP has no such property. In this paper, we propose an approach to natively train CLIP in a contrastive manner to reason about differences in embedding space. We finetune CLIP so that the differences in image embedding space correspond to \emph{text descriptions of the image differences}, which we synthetically generate with large language models on image-caption paired datasets. We first demonstrate that our approach yields significantly improved capabilities in ranking images by a certain attribute (e.g., elephants are larger than cats), which is useful in retrieval or constructing attribute-based classifiers, and improved zeroshot classification performance on many downstream image classification tasks. In addition, our approach enables a new mechanism for inference that we refer to as comparative prompting, where we leverage prior knowledge of text descriptions of differences between classes of interest, achieving even larger performance gains in classification. Finally, we illustrate that the resulting embeddings obey a larger degree of geometric properties in embedding space, such as in text-to-image generation.
Authors: Shih-Wei Guo, Tsu-Ching Hsiao, Yu-Lun Liu, Chun-Yi Lee
Abstract: In this paper, we propose a novel coarse-to-fine continuous pose diffusion method to enhance the precision of pick-and-place operations within robotic manipulation tasks. Leveraging the capabilities of diffusion networks, we facilitate the accurate perception of object poses. This accurate perception enhances both pick-and-place success rates and overall manipulation precision. Our methodology utilizes a top-down RGB image projected from an RGB-D camera and adopts a coarse-to-fine architecture. This architecture enables efficient learning of coarse and fine models. A distinguishing feature of our approach is its focus on continuous pose estimation, which enables more precise object manipulation, particularly concerning rotational angles. In addition, we employ pose and color augmentation techniques to enable effective training with limited data. Through extensive experiments in simulated and real-world scenarios, as well as an ablation study, we comprehensively evaluate our proposed methodology. Taken together, the findings validate its effectiveness in achieving high-precision pick-and-place tasks.
Authors: Weifeng Wei, Heng Chen, Pengxiang Su
Abstract: Magnetic Resonance Imaging (MRI) requires a trade-off between resolution, signal-to-noise ratio, and scan time, making high-resolution (HR) acquisition challenging. Therefore, super-resolution for MR image is a feasible solution. However, most existing methods face challenges in accurately learning a continuous volumetric representation from low-resolution image or require HR image for supervision. To solve these challenges, we propose a novel method for MR image super-resolution based on two-factor representation. Specifically, we factorize intensity signals into a linear combination of learnable basis and coefficient factors, enabling efficient continuous volumetric representation from low-resolution MR image. Besides, we introduce a coordinate-based encoding to capture structural relationships between sparse voxels, facilitating smooth completion in unobserved regions. Experiments on BraTS 2019 and MSSEG 2016 datasets demonstrate that our method achieves state-of-the-art performance, providing superior visual fidelity and robustness, particularly in large up-sampling scale MR image super-resolution.
Authors: Liu Li, Hanchun Wang, Matthew Baugh, Qiang Ma, Weitong Zhang, Cheng Ouyang, Daniel Rueckert, Bernhard Kainz
Abstract: Although existing medical image segmentation methods provide impressive pixel-wise accuracy, they often neglect topological correctness, making their segmentations unusable for many downstream tasks. One option is to retrain such models whilst including a topology-driven loss component. However, this is computationally expensive and often impractical. A better solution would be to have a versatile plug-and-play topology refinement method that is compatible with any domain-specific segmentation pipeline. Directly training a post-processing model to mitigate topological errors often fails as such models tend to be biased towards the topological errors of a target segmentation network. The diversity of these errors is confined to the information provided by a labelled training set, which is especially problematic for small datasets. Our method solves this problem by training a model-agnostic topology refinement network with synthetic segmentations that cover a wide variety of topological errors. Inspired by the Stone-Weierstrass theorem, we synthesize topology-perturbation masks with randomly sampled coefficients of orthogonal polynomial bases, which ensures a complete and unbiased representation. Practically, we verified the efficiency and effectiveness of our methods as being compatible with multiple families of polynomial bases, and show evidence that our universal plug-and-play topology refinement network outperforms both existing topology-driven learning-based and post-processing methods. We also show that combining our method with learning-based models provides an effortless add-on, which can further improve the performance of existing approaches.
Authors: Frauke Wilm, Mathias \"Ottl, Marc Aubreville, Katharina Breininger
Abstract: Recent advances in computer-aided diagnosis for histopathology have been largely driven by the use of deep learning models for automated image analysis. While these networks can perform on par with medical experts, their performance can be impeded by out-of-distribution data. The Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation (COSAS) challenge aimed to address the task of cross-domain adenocarcinoma segmentation in the presence of morphological and scanner-induced domain shifts. In this paper, we present a U-Net-based segmentation framework designed to tackle this challenge. Our approach achieved segmentation scores of 0.8020 for the cross-organ track and 0.8527 for the cross-scanner track on the final challenge test sets, ranking it the best-performing submission.
Authors: Stanley Lewis, Tom Gao, Odest Chadwicke Jenkins
Abstract: Articulated objects and their representations pose a difficult problem for robots. These objects require not only representations of geometry and texture, but also of the various connections and joint parameters that make up each articulation. We propose a method that learns a common Neural Radiance Field (NeRF) representation across a small number of collected scenes. This representation is combined with a parts-based image segmentation to produce an implicit space part localization, from which the connectivity and joint parameters of the articulated object can be estimated, thus enabling configuration-conditioned rendering.
Authors: Ningfei Wang, Shaoyuan Xie, Takami Sato, Yunpeng Luo, Kaidi Xu, Qi Alfred Chen
Abstract: Traffic Sign Recognition (TSR) is crucial for safe and correct driving automation. Recent works revealed a general vulnerability of TSR models to physical-world adversarial attacks, which can be low-cost, highly deployable, and capable of causing severe attack effects such as hiding a critical traffic sign or spoofing a fake one. However, so far existing works generally only considered evaluating the attack effects on academic TSR models, leaving the impacts of such attacks on real-world commercial TSR systems largely unclear. In this paper, we conduct the first large-scale measurement of physical-world adversarial attacks against commercial TSR systems. Our testing results reveal that it is possible for existing attack works from academia to have highly reliable (100\%) attack success against certain commercial TSR system functionality, but such attack capabilities are not generalizable, leading to much lower-than-expected attack success rates overall. We find that one potential major factor is a spatial memorization design that commonly exists in today's commercial TSR systems. We design new attack success metrics that can mathematically model the impacts of such design on the TSR system-level attack success, and use them to revisit existing attacks. Through these efforts, we uncover 7 novel observations, some of which directly challenge the observations or claims in prior works due to the introduction of the new metrics.
Authors: Bharat Joshi, Ioannis Rekleitis
Abstract: This paper presents an extension to visual inertial odometry (VIO) by introducing tightly-coupled fusion of magnetometer measurements. A sliding window of keyframes is optimized by minimizing re-projection errors, relative inertial errors, and relative magnetometer orientation errors. The results of IMU orientation propagation are used to efficiently transform magnetometer measurements between frames producing relative orientation constraints between consecutive frames. The soft and hard iron effects are calibrated using an ellipsoid fitting algorithm. The introduction of magnetometer data results in significant reductions in the orientation error and also in recovery of the true yaw orientation with respect to the magnetic north. The proposed framework operates in all environments with slow-varying magnetic fields, mainly outdoors and underwater. We have focused our work on the underwater domain, especially in underwater caves, as the narrow passage and turbulent flow make it difficult to perform loop closures and reset the localization drift. The underwater caves present challenges to VIO due to the absence of ambient light and the confined nature of the environment, while also being a crucial source of fresh water and providing valuable historical records. Experimental results from underwater caves demonstrate the improvements in accuracy and robustness introduced by the proposed VIO extension.
Authors: Neeloy Chakraborty, Yixiao Fang, Andre Schreiber, Tianchen Ji, Zhe Huang, Aganze Mihigo, Cassidy Wall, Abdulrahman Almana, Katherine Driggs-Campbell
Abstract: Teleoperation is an important technology to enable supervisors to control agricultural robots remotely. However, environmental factors in dense crop rows and limitations in network infrastructure hinder the reliability of data streamed to teleoperators. These issues result in delayed and variable frame rate video feeds that often deviate significantly from the robot's actual viewpoint. We propose a modular learning-based vision pipeline to generate delay-compensated images in real-time for supervisors. Our extensive offline evaluations demonstrate that our method generates more accurate images compared to state-of-the-art approaches in our setting. Additionally, we are one of the few works to evaluate a delay-compensation method in outdoor field environments with complex terrain on data from a real robot in real-time. Additional videos are provided at https://sites.google.com/illinois.edu/comp-teleop.
Authors: Alexander Koch, Orhun Utku Aydin, Adam Hilbert, Jana Rieger, Satoru Tanioka, Fujimaro Ishida, Dietmar Frey
Abstract: Cerebrovascular disease often requires multiple imaging modalities for accurate diagnosis, treatment, and monitoring. Computed Tomography Angiography (CTA) and Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) are two common non-invasive angiography techniques, each with distinct strengths in accessibility, safety, and diagnostic accuracy. While CTA is more widely used in acute stroke due to its faster acquisition times and higher diagnostic accuracy, TOF-MRA is preferred for its safety, as it avoids radiation exposure and contrast agent-related health risks. Despite the predominant role of CTA in clinical workflows, there is a scarcity of open-source CTA data, limiting the research and development of AI models for tasks such as large vessel occlusion detection and aneurysm segmentation. This study explores diffusion-based image-to-image translation models to generate synthetic CTA images from TOF-MRA input. We demonstrate the modality conversion from TOF-MRA to CTA and show that diffusion models outperform a traditional U-Net-based approach. Our work compares different state-of-the-art diffusion architectures and samplers, offering recommendations for optimal model performance in this cross-modality translation task.
Authors: Balint Kovacs, Shuhan Xiao, Maximilian Rokuss, Constantin Ulrich, Fabian Isensee, Klaus H. Maier-Hein
Abstract: The third autoPET challenge introduced a new data-centric task this year, shifting the focus from model development to improving metastatic lesion segmentation on PET/CT images through data quality and handling strategies. In response, we developed targeted methods to enhance segmentation performance tailored to the characteristics of PET/CT imaging. Our approach encompasses two key elements. First, to address potential alignment errors between CT and PET modalities as well as the prevalence of punctate lesions, we modified the baseline data augmentation scheme and extended it with misalignment augmentation. This adaptation aims to improve segmentation accuracy, particularly for tiny metastatic lesions. Second, to tackle the variability in image dimensions significantly affecting the prediction time, we implemented a dynamic ensembling and test-time augmentation (TTA) strategy. This method optimizes the use of ensembling and TTA within a 5-minute prediction time limit, effectively leveraging the generalization potential for both small and large images. Both of our solutions are designed to be robust across different tracers and institutional settings, offering a general, yet imaging-specific approach to the multi-tracer and multi-institutional challenges of the competition. We made the challenge repository with our modifications publicly available at \url{https://github.com/MIC-DKFZ/miccai2024_autopet3_datacentric}.
URLs: https://github.com/MIC-DKFZ/miccai2024_autopet3_datacentric
Authors: Yufan Zhang, Kailun Yang, Ze Wang, Kaiwei Wang
Abstract: This paper presents P2U-SLAM, a visual Simultaneous Localization And Mapping (SLAM) system with a wide Field of View (FoV) camera, which utilizes pose uncertainty and point uncertainty. While the wide FoV enables considerable repetitive observations of historical map points for matching cross-view features, the data properties of the historical map points and the poses of historical keyframes have changed during the optimization process. The neglect of data property changes triggers the absence of a partial information matrix in optimization and leads to the risk of long-term positioning performance degradation. The purpose of our research is to reduce the risk of the wide field of view visual input to the SLAM system. Based on the conditional probability model, this work reveals the definite impact of the above data properties changes on the optimization process, concretizes it as point uncertainty and pose uncertainty, and gives a specific mathematical form. P2U-SLAM respectively embeds point uncertainty and pose uncertainty into the tracking module and local mapping, and updates these uncertainties after each optimization operation including local mapping, map merging, and loop closing. We present an exhaustive evaluation in 27 sequences from two popular public datasets with wide-FoV visual input. P2U-SLAM shows excellent performance compared with other state-of-the-art methods. The source code will be made publicly available at https://github.com/BambValley/P2U-SLAM.
Authors: Mohammad Nomaan Qureshi, Sparsh Garg, Francisco Yandun, David Held, George Kantor, Abhishesh Silwal
Abstract: Sim2Real transfer, particularly for manipulation policies relying on RGB images, remains a critical challenge in robotics due to the significant domain shift between synthetic and real-world visual data. In this paper, we propose SplatSim, a novel framework that leverages Gaussian Splatting as the primary rendering primitive to reduce the Sim2Real gap for RGB-based manipulation policies. By replacing traditional mesh representations with Gaussian Splats in simulators, SplatSim produces highly photorealistic synthetic data while maintaining the scalability and cost-efficiency of simulation. We demonstrate the effectiveness of our framework by training manipulation policies within SplatSim}and deploying them in the real world in a zero-shot manner, achieving an average success rate of 86.25%, compared to 97.5% for policies trained on real-world data.
Authors: Zhixi Cai, Cristian Rojas Cardenas, Kevin Leo, Chenyuan Zhang, Kal Backman, Hanbing Li, Boying Li, Mahsa Ghorbanali, Stavya Datta, Lizhen Qu, Julian Gutierrez Santiago, Alexey Ignatiev, Yuan-Fang Li, Mor Vered, Peter J Stuckey, Maria Garcia de la Banda, Hamid Rezatofighi
Abstract: This paper addresses the problem of autonomous UAV search missions, where a UAV must locate specific Entities of Interest (EOIs) within a time limit, based on brief descriptions in large, hazard-prone environments with keep-out zones. The UAV must perceive, reason, and make decisions with limited and uncertain information. We propose NEUSIS, a compositional neuro-symbolic system designed for interpretable UAV search and navigation in realistic scenarios. NEUSIS integrates neuro-symbolic visual perception, reasoning, and grounding (GRiD) to process raw sensory inputs, maintains a probabilistic world model for environment representation, and uses a hierarchical planning component (SNaC) for efficient path planning. Experimental results from simulated urban search missions using AirSim and Unreal Engine show that NEUSIS outperforms a state-of-the-art (SOTA) vision-language model and a SOTA search planning model in success rate, search efficiency, and 3D localization. These results demonstrate the effectiveness of our compositional neuro-symbolic approach in handling complex, real-world scenarios, making it a promising solution for autonomous UAV systems in search missions.
Authors: Jakub Gregorek, Lazaros Nalpantidis
Abstract: Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods still assumes depth values covering all areas of the scene. To address this limitation, we introduce SteeredMarigold, a training-free, zero-shot depth completion method capable of producing metric dense depth, even for largely incomplete depth maps. SteeredMarigold achieves this by using the available sparse depth points as conditions to steer a denoising diffusion probabilistic model. Our method outperforms relevant top-performing methods on the NYUv2 dataset, in tests where no depth was provided for a large area, achieving state-of-art performance and exhibiting remarkable robustness against depth map incompleteness. Our code will be publicly available.
Authors: Saif Khalid, Hatem A. Rashwan, Saddam Abdulwahab, Mohamed Abdel-Nasser, Facundo Manuel Quiroga, Domenec Puig
Abstract: The performance of diagnostic Computer-Aided Design (CAD) systems for retinal diseases depends on the quality of the retinal images being screened. Thus, many studies have been developed to evaluate and assess the quality of such retinal images. However, most of them did not investigate the relationship between the accuracy of the developed models and the quality of the visualization of interpretability methods for distinguishing between gradable and non-gradable retinal images. Consequently, this paper presents a novel framework called FGR-Net to automatically assess and interpret underlying fundus image quality by merging an autoencoder network with a classifier network. The FGR-Net model also provides an interpretable quality assessment through visualizations. In particular, FGR-Net uses a deep autoencoder to reconstruct the input image in order to extract the visual characteristics of the input fundus images based on self-supervised learning. The extracted features by the autoencoder are then fed into a deep classifier network to distinguish between gradable and ungradable fundus images. FGR-Net is evaluated with different interpretability methods, which indicates that the autoencoder is a key factor in forcing the classifier to focus on the relevant structures of the fundus images, such as the fovea, optic disk, and prominent blood vessels. Additionally, the interpretability methods can provide visual feedback for ophthalmologists to understand how our model evaluates the quality of fundus images. The experimental results showed the superiority of FGR-Net over the state-of-the-art quality assessment methods, with an accuracy of 89% and an F1-score of 87%.
Authors: Xi Wang, Xin Liu, Songming Zhu, Zhanwen Li, Lina Gao
Abstract: The recent emergence of Distributed Acoustic Sensing (DAS) technology has facilitated the effective capture of traffic-induced seismic data. The traffic-induced seismic wave is a prominent contributor to urban vibrations and contain crucial information to advance urban exploration and governance. However, identifying vehicular movements within massive noisy data poses a significant challenge. In this study, we introduce a real-time semi-supervised vehicle monitoring framework tailored to urban settings. It requires only a small fraction of manual labels for initial training and exploits unlabeled data for model improvement. Additionally, the framework can autonomously adapt to newly collected unlabeled data. Before DAS data undergo object detection as two-dimensional images to preserve spatial information, we leveraged comprehensive one-dimensional signal preprocessing to mitigate noise. Furthermore, we propose a novel prior loss that incorporates the shapes of vehicular traces to track a single vehicle with varying speeds. To evaluate our model, we conducted experiments with seismic data from the Stanford 2 DAS Array. The results showed that our model outperformed the baseline model Efficient Teacher and its supervised counterpart, YOLO (You Only Look Once), in both accuracy and robustness. With only 35 labeled images, our model surpassed YOLO's mAP 0.5:0.95 criterion by 18% and showed a 7% increase over Efficient Teacher. We conducted comparative experiments with multiple update strategies for self-updating and identified an optimal approach. This approach surpasses the performance of non-overfitting training conducted with all data in a single pass.
Authors: Xiaolong Mao, Hui Yuan, Tian Guo, Shiqi Jiang, Raouf Hamzaoui, Sam Kwong
Abstract: We propose an end-to-end attribute compression method for dense point clouds. The proposed method combines a frequency sampling module, an adaptive scale feature extraction module with geometry assistance, and a global hyperprior entropy model. The frequency sampling module uses a Hamming window and the Fast Fourier Transform to extract high-frequency components of the point cloud. The difference between the original point cloud and the sampled point cloud is divided into multiple sub-point clouds. These sub-point clouds are then partitioned using an octree, providing a structured input for feature extraction. The feature extraction module integrates adaptive convolutional layers and uses offset-attention to capture both local and global features. Then, a geometry-assisted attribute feature refinement module is used to refine the extracted attribute features. Finally, a global hyperprior model is introduced for entropy encoding. This model propagates hyperprior parameters from the deepest (base) layer to the other layers, further enhancing the encoding efficiency. At the decoder, a mirrored network is used to progressively restore features and reconstruct the color attribute through transposed convolutional layers. The proposed method encodes base layer information at a low bitrate and progressively adds enhancement layer information to improve reconstruction accuracy. Compared to the latest G-PCC test model (TMC13v23) under the MPEG common test conditions (CTCs), the proposed method achieved an average Bjontegaard delta bitrate reduction of 24.58% for the Y component (21.23% for YUV combined) on the MPEG Category Solid dataset and 22.48% for the Y component (17.19% for YUV combined) on the MPEG Category Dense dataset. This is the first instance of a learning-based codec outperforming the G-PCC standard on these datasets under the MPEG CTCs.
Authors: Songning Lai, Tianlang Xue, Hongru Xiao, Lijie Hu, Jiemin Wu, Ninghui Feng, Runwei Guan, Haicheng Liao, Zhenning Li, Yutao Yue
Abstract: Recent advancements in autonomous driving have seen a paradigm shift towards end-to-end learning paradigms, which map sensory inputs directly to driving actions, thereby enhancing the robustness and adaptability of autonomous vehicles. However, these models often sacrifice interpretability, posing significant challenges to trust, safety, and regulatory compliance. To address these issues, we introduce DRIVE -- Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Driving, a comprehensive framework designed to improve the dependability and stability of explanations in end-to-end unsupervised autonomous driving models. Our work specifically targets the inherent instability problems observed in the Driving through the Concept Gridlock (DCG) model, which undermine the trustworthiness of its explanations and decision-making processes. We define four key attributes of DRIVE: consistent interpretability, stable interpretability, consistent output, and stable output. These attributes collectively ensure that explanations remain reliable and robust across different scenarios and perturbations. Through extensive empirical evaluations, we demonstrate the effectiveness of our framework in enhancing the stability and dependability of explanations, thereby addressing the limitations of current models. Our contributions include an in-depth analysis of the dependability issues within the DCG model, a rigorous definition of DRIVE with its fundamental properties, a framework to implement DRIVE, and novel metrics for evaluating the dependability of concept-based explainable autonomous driving models. These advancements lay the groundwork for the development of more reliable and trusted autonomous driving systems, paving the way for their broader acceptance and deployment in real-world applications.
Authors: Euntae Choi, Sungjoo Yoo
Abstract: We propose two novel ideas (adoption of deferred rendering and mesh-based representation) to improve the quality of 3D Gaussian splatting (3DGS) based inverse rendering. We first report a problem incurred by hidden Gaussians, where Gaussians beneath the surface adversely affect the pixel color in the volume rendering adopted by the existing methods. In order to resolve the problem, we propose applying deferred rendering and report new problems incurred in a naive application of deferred rendering to the existing 3DGS-based inverse rendering. In an effort to improve the quality of 3DGS-based inverse rendering under deferred rendering, we propose a novel two-step training approach which (1) exploits mesh extraction and utilizes a hybrid mesh-3DGS representation and (2) applies novel regularization methods to better exploit the mesh. Our experiments show that, under relighting, the proposed method offers significantly better rendering quality than the existing 3DGS-based inverse rendering methods. Compared with the SOTA voxel grid-based inverse rendering method, it gives better rendering quality while offering real-time rendering.
Authors: Aaron Mark Thomas, Sharu Theresa Jose
Abstract: This paper presents a novel hybrid quantum generative model, the VAE-QWGAN, which combines the strengths of a classical Variational AutoEncoder (VAE) with a hybrid Quantum Wasserstein Generative Adversarial Network (QWGAN). The VAE-QWGAN integrates the VAE decoder and QGAN generator into a single quantum model with shared parameters, utilizing the VAE's encoder for latent vector sampling during training. To generate new data from the trained model at inference, input latent vectors are sampled from a Gaussian Mixture Model (GMM), learnt on the training latent vectors. This, in turn, enhances the diversity and quality of generated images. We evaluate the model's performance on MNIST/Fashion-MNIST datasets, and demonstrate improved quality and diversity of generated images compared to existing approaches.
Authors: Yifan Xu, Ziming Luo, Qianwei Wang, Vineet Kamat, Carol Menassa
Abstract: Current open-vocabulary scene graph generation algorithms highly rely on both 3D scene point cloud data and posed RGB-D images and thus have limited applications in scenarios where RGB-D images or camera poses are not readily available. To solve this problem, we propose Point2Graph, a novel end-to-end point cloud-based 3D open-vocabulary scene graph generation framework in which the requirement of posed RGB-D image series is eliminated. This hierarchical framework contains room and object detection/segmentation and open-vocabulary classification. For the room layer, we leverage the advantage of merging the geometry-based border detection algorithm with the learning-based region detection to segment rooms and create a "Snap-Lookup" framework for open-vocabulary room classification. In addition, we create an end-to-end pipeline for the object layer to detect and classify 3D objects based solely on 3D point cloud data. Our evaluation results show that our framework can outperform the current state-of-the-art (SOTA) open-vocabulary object and room segmentation and classification algorithm on widely used real-scene datasets.
Authors: Jingpei Lu, Zekai Liang, Tristin Xie, Florian Ritcher, Shan Lin, Sainan Liu, Michael C. Yip
Abstract: Camera-to-robot calibration is crucial for vision-based robot control and requires effort to make it accurate. Recent advancements in markerless pose estimation methods have eliminated the need for time-consuming physical setups for camera-to-robot calibration. While the existing markerless pose estimation methods have demonstrated impressive accuracy without the need for cumbersome setups, they rely on the assumption that all the robot joints are visible within the camera's field of view. However, in practice, robots usually move in and out of view, and some portion of the robot may stay out-of-frame during the whole manipulation task due to real-world constraints, leading to a lack of sufficient visual features and subsequent failure of these approaches. To address this challenge and enhance the applicability to vision-based robot control, we propose a novel framework capable of estimating the robot pose with partially visible robot manipulators. Our approach leverages the Vision-Language Models for fine-grained robot components detection, and integrates it into a keypoint-based pose estimation network, which enables more robust performance in varied operational conditions. The framework is evaluated on both public robot datasets and self-collected partial-view datasets to demonstrate our robustness and generalizability. As a result, this method is effective for robot pose estimation in a wider range of real-world manipulation scenarios.
Authors: Yong He, Hongshan Yu, Xiaoyan Liu, Zhengeng Yang, Wei Sun, Saeed Anwar, Ajmal Mian
Abstract: 3D segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving and robotics. It has received significant attention from the computer vision, graphics and machine learning communities. Conventional methods for 3D segmentation, based on hand-crafted features and machine learning classifiers, lack generalization ability. Driven by their success in 2D computer vision, deep learning techniques have recently become the tool of choice for 3D segmentation tasks. This has led to an influx of many methods in the literature that have been evaluated on different benchmark datasets. Whereas survey papers on RGB-D and point cloud segmentation exist, there is a lack of a recent in-depth survey that covers all 3D data modalities and application domains. This paper fills the gap and comprehensively surveys the recent progress in deep learning-based 3D segmentation techniques. We cover over 220 works from the last six years, analyze their strengths and limitations, and discuss their competitive results on benchmark datasets. The survey provides a summary of the most commonly used pipelines and finally highlights promising research directions for the future.
Authors: Wenhao Li, Mengyuan Liu, Hong Liu, Tianyu Guo, Ti Wang, Hao Tang, Nicu Sebe
Abstract: Modern multi-layer perceptron (MLP) models have shown competitive results in learning visual representations without self-attention. However, existing MLP models are not good at capturing local details and lack prior knowledge of human body configurations, which limits their modeling power for skeletal representation learning. To address these issues, we propose a simple yet effective graph-reinforced MLP-Like architecture, named GraphMLP, that combines MLPs and graph convolutional networks (GCNs) in a global-local-graphical unified architecture for 3D human pose estimation. GraphMLP incorporates the graph structure of human bodies into an MLP model to meet the domain-specific demand of the 3D human pose, while allowing for both local and global spatial interactions. Furthermore, we propose to flexibly and efficiently extend the GraphMLP to the video domain and show that complex temporal dynamics can be effectively modeled in a simple way with negligible computational cost gains in the sequence length. To the best of our knowledge, this is the first MLP-Like architecture for 3D human pose estimation in a single frame and a video sequence. Extensive experiments show that the proposed GraphMLP achieves state-of-the-art performance on two datasets, i.e., Human3.6M and MPI-INF-3DHP. Code and models are available at https://github.com/Vegetebird/GraphMLP.
Authors: Xingping Dong, Tianran Ouyang, Shengcai Liao, Bo Du, Ling Shao
Abstract: Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been proposed for FSL, which includes only a few labeled samples and numbers of unlabeled samples in base classes. However, existing methods under this setting require class-aware sample selection from the unlabeled set, which violates the assumption of unlabeled set. In this paper, we propose a practical semi-supervised meta-training setting with truly unlabeled data to facilitate the applications of FSL in realistic scenarios. To better utilize both the labeled and truly unlabeled data, we propose a simple and effective meta-training framework, called pseudo-labeling based meta-learning (PLML). Firstly, we train a classifier via common semi-supervised learning (SSL) and use it to obtain the pseudo-labels of unlabeled data. Then we build few-shot tasks from labeled and pseudo-labeled data and design a novel finetuning method with feature smoothing and noise suppression to better learn the FSL model from noise labels. Surprisingly, through extensive experiments across two FSL datasets, we find that this simple meta-training framework effectively prevents the performance degradation of various FSL models under limited labeled data, and also significantly outperforms the state-of-the-art SSMT models. Besides, benefiting from meta-training, our method also improves two representative SSL algorithms as well.
Authors: Yiheng Han, Irvin Haozhe Zhan, Long Zeng, Yu-Ping Wang, Ran Yi, Minjing Yu, Matthieu Gaetan Lin, Jenny Sheng, Yong-Jin Liu
Abstract: Some robust point cloud registration approaches with controllable pose refinement magnitude, such as ICP and its variants, are commonly used to improve 6D pose estimation accuracy. However, the effectiveness of these methods gradually diminishes with the advancement of deep learning techniques and the enhancement of initial pose accuracy, primarily due to their lack of specific design for pose refinement. In this paper, we propose Point Cloud Completion and Keypoint Refinement with Fusion Data (PCKRF), a new pose refinement pipeline for 6D pose estimation. The pipeline consists of two steps. First, it completes the input point clouds via a novel pose-sensitive point completion network. The network uses both local and global features with pose information during point completion. Then, it registers the completed object point cloud with the corresponding target point cloud by our proposed Color supported Iterative KeyPoint (CIKP) method. The CIKP method introduces color information into registration and registers a point cloud around each keypoint to increase stability. The PCKRF pipeline can be integrated with existing popular 6D pose estimation methods, such as the full flow bidirectional fusion network, to further improve their pose estimation accuracy. Experiments demonstrate that our method exhibits superior stability compared to existing approaches when optimizing initial poses with relatively high precision. Notably, the results indicate that our method effectively complements most existing pose estimation techniques, leading to improved performance in most cases. Furthermore, our method achieves promising results even in challenging scenarios involving textureless and symmetrical objects. Our source code is available at https://github.com/zhanhz/KRF.
Authors: Matthew Kowal, Mennatullah Siam, Md Amirul Islam, Neil D. B. Bruce, Richard P. Wildes, Konstantinos G. Derpanis
Abstract: There is limited understanding of the information captured by deep spatiotemporal models in their intermediate representations. For example, while evidence suggests that action recognition algorithms are heavily influenced by visual appearance in single frames, no quantitative methodology exists for evaluating such static bias in the latent representation compared to bias toward dynamics. We tackle this challenge by proposing an approach for quantifying the static and dynamic biases of any spatiotemporal model, and apply our approach to three tasks, action recognition, automatic video object segmentation (AVOS) and video instance segmentation (VIS). Our key findings are: (i) Most examined models are biased toward static information. (ii) Some datasets that are assumed to be biased toward dynamics are actually biased toward static information. (iii) Individual channels in an architecture can be biased toward static, dynamic or a combination of the two. (iv) Most models converge to their culminating biases in the first half of training. We then explore how these biases affect performance on dynamically biased datasets. For action recognition, we propose StaticDropout, a semantically guided dropout that debiases a model from static information toward dynamics. For AVOS, we design a better combination of fusion and cross connection layers compared with previous architectures.
Authors: Lei Qi, Dongjia Zhao, Yinghuan Shi, Xin Geng
Abstract: Despite the significant success of deep learning in computer vision tasks, cross-domain tasks still present a challenge in which the model's performance will degrade when the training set and the test set follow different distributions. Most existing methods employ adversarial learning or instance normalization for achieving data augmentation to solve this task. In contrast, considering that the batch normalization (BN) layer may not be robust for unseen domains and there exist the differences between local patches of an image, we propose a novel method called patch-aware batch normalization (PBN). To be specific, we first split feature maps of a batch into non-overlapping patches along the spatial dimension, and then independently normalize each patch to jointly optimize the shared BN parameter at each iteration. By exploiting the differences between local patches of an image, our proposed PBN can effectively enhance the robustness of the model's parameters. Besides, considering the statistics from each patch may be inaccurate due to their smaller size compared to the global feature maps, we incorporate the globally accumulated statistics with the statistics from each batch to obtain the final statistics for normalizing each patch. Since the proposed PBN can replace the typical BN, it can be integrated into most existing state-of-the-art methods. Extensive experiments and analysis demonstrate the effectiveness of our PBN in multiple computer vision tasks, including classification, object detection, instance retrieval, and semantic segmentation.
Authors: Yi Li, Hualiang Wang, Yiqun Duan, Jiheng Zhang, Xiaomeng Li
Abstract: Contrastive language-image pre-training (CLIP) is a powerful vision-language model that has shown great benefits for various tasks. However, we have identified some issues with its explainability, which undermine its credibility and limit the capacity for related tasks. Specifically, we find that CLIP tends to focus on background regions rather than foregrounds, with noisy activations at irrelevant positions on the visualization results. These phenomena conflict with conventional explainability methods based on the class attention map (CAM), where the raw model can highlight the local foreground regions using global supervision without alignment. To address these problems, we take a closer look at its architecture and features. Based on thorough analyses, we find the raw self-attentions link to inconsistent semantic regions, resulting in the opposite visualization. Besides, the noisy activations are owing to redundant features among categories. Building on these insights, we propose the CLIP Surgery for reliable CAM, a method that allows surgery-like modifications to the inference architecture and features, without further fine-tuning as classical CAM methods. This approach significantly improves the explainability of CLIP, surpassing existing methods by large margins. Besides, it enables multimodal visualization and extends the capacity of raw CLIP on open-vocabulary tasks without extra alignment. The code is available at https://github.com/xmed-lab/CLIP_Surgery.
Authors: Seulki Park, Daeho Um, Hajung Yoon, Sanghyuk Chun, Sangdoo Yun
Abstract: With the extensive use of vision-language models in various downstream tasks, evaluating their robustness is crucial. In this paper, we propose a benchmark for assessing the robustness of vision-language models. We believe that a robust model should properly understand both linguistic and visual semantics and be resilient to explicit variations. In pursuit of this goal, we create new variants of texts and images in the MS-COCO test set and re-evaluate the state-of-the-art (SOTA) models with the new data. Specifically, we alter the meaning of text by replacing a word, and generate visually altered images that maintain some visual context while introducing noticeable pixel changes through image mixing techniques.Our evaluations on the proposed benchmark reveal substantial performance degradation in many SOTA models (e.g., Image-to-Text Recall@1: 81.9\% $\rightarrow$ 48.4\% in BLIP, 66.1\% $\rightarrow$ 37.6\% in VSE$\infty$), with the models often favoring the altered texts/images over the original ones. This indicates the current vision-language models struggle with subtle changes and often fail to understand the overall context of texts and images. Based on these findings, we propose semantic contrastive loss and visual contrastive loss to learn more robust embedding. Datasets and code are available at {\url{https://github.com/pseulki/rococo}}.
Authors: Hanqing Sun, Yanwei Pang, Jiale Cao, Jin Xie, Xuelong Li
Abstract: Transformers have shown promising progress in various visual object detection tasks, including monocular 2D/3D detection and surround-view 3D detection. More importantly, the attention mechanism in the Transformer model and the 3D information extraction in binocular stereo are both similarity-based. However, directly applying existing Transformer-based detectors to binocular stereo 3D object detection leads to slow convergence and significant precision drops. We argue that a key cause of that defect is that existing Transformers ignore the binocular-stereo-specific image correspondence information. In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information. To achieve this goal, we present TS3D, a Transformer-based Stereo-aware 3D object detector. In the TS3D, a Disparity-Aware Positional Encoding (DAPE) module is proposed to embed the image correspondence information into stereo features. The correspondence is encoded as normalized sub-pixel-level disparity and is used in conjunction with sinusoidal 2D positional encoding to provide the 3D location information of the scene. To enrich multi-scale stereo features, we propose a Stereo Preserving Feature Pyramid Network (SPFPN). The SPFPN is designed to preserve the correspondence information while fusing intra-scale and aggregating cross-scale stereo features. Our proposed TS3D achieves a 41.29% Moderate Car detection average precision on the KITTI test set and takes 88 ms to detect objects from each binocular image pair. It is competitive with advanced counterparts in terms of both precision and inference speed.
Authors: Teerapong Panboonyuen, Naphat Nithisopa, Panin Pienroj, Laphonchai Jirachuphun, Chaiwasut Watthanasirikrit, Naruepon Pornwiriyakul
Abstract: Evaluating car damages from misfortune is critical to the car insurance industry. However, the accuracy is still insufficient for real-world applications since the deep learning network is not designed for car damage images as inputs, and its segmented masks are still very coarse. This paper presents MARS (Mask Attention Refinement with Sequential quadtree nodes) for car damage instance segmentation. Our MARS represents self-attention mechanisms to draw global dependencies between the sequential quadtree nodes layer and quadtree transformer to recalibrate channel weights and predict highly accurate instance masks. Our extensive experiments demonstrate that MARS outperforms state-of-the-art (SOTA) instance segmentation methods on three popular benchmarks such as Mask R-CNN [9], PointRend [13], and Mask Transfiner [12], by a large margin of +1.3 maskAP-based R50-FPN backbone and +2.3 maskAP-based R101-FPN backbone on Thai car-damage dataset. Our demos are available at https://github.com/kaopanboonyuen/MARS.
Authors: Shunxin Wang, Raymond Veldhuis, Christoph Brune, Nicola Strisciuglio
Abstract: The performance of computer vision models are susceptible to unexpected changes in input images caused by sensor errors or extreme imaging environments, known as common corruptions (e.g. noise, blur, illumination changes). These corruptions can significantly hinder the reliability of these models when deployed in real-world scenarios, yet they are often overlooked when testing model generalization and robustness. In this survey, we present a comprehensive overview of methods that improve the robustness of computer vision models against common corruptions. We categorize methods into three groups based on the model components and training methods they target: data augmentation, learning strategies, and network components. We release a unified benchmark framework (available at \url{https://github.com/nis-research/CorruptionBenchCV}) to compare robustness performance across several datasets, and we address the inconsistencies of evaluation practices in the literature. Our experimental analysis highlights the base corruption robustness of popular vision backbones, revealing that corruption robustness does not necessarily scale with model size and data size. Large models gain negligible robustness improvements, considering the increased computational requirements. To achieve generalizable and robust computer vision models, we foresee the need of developing new learning strategies that efficiently exploit limited data and mitigate unreliable learning behaviors.
Authors: Junhao Dong, Zhu Meng, Delong Liu, Jiaxuan Liu, Zhicheng Zhao, Fei Su
Abstract: Semi-supervised semantic segmentation has attracted increasing attention in computer vision, aiming to leverage unlabeled data through latent supervision. To achieve this goal, prototype-based classification has been introduced and achieved lots of success. However, the current approaches isolate prototype generation from the main training framework, presenting a non-end-to-end workflow. Furthermore, most methods directly perform the K-Means clustering on features to generate prototypes, resulting in their proximity to category semantic centers, while overlooking the clear delineation of class boundaries. To address the above problems, we propose a novel end-to-end boundary-refined prototype generation (BRPG) method. Specifically, we perform online clustering on sampled features to incorporate the prototype generation into the whole training framework. In addition, to enhance the classification boundaries, we sample and cluster high- and low-confidence features separately based on confidence estimation, facilitating the generation of prototypes closer to the class boundaries. Moreover, an adaptive prototype optimization strategy is proposed to increase the number of prototypes for categories with scattered feature distributions, which further refines the class boundaries. Extensive experiments demonstrate the remarkable robustness and scalability of our method across diverse datasets, segmentation networks, and semi-supervised frameworks, outperforming the state-of-the-art approaches on three benchmark datasets: PASCAL VOC 2012, Cityscapes and MS COCO. The code is available at https://github.com/djh-dzxw/BRPG.
Authors: Mainak Singha, Harsh Pal, Ankit Jha, Biplab Banerjee
Abstract: Although deep learning models have shown impressive performance on supervised learning tasks, they often struggle to generalize well when the training (source) and test (target) domains differ. Unsupervised domain adaptation (DA) has emerged as a popular solution to this problem. However, current DA techniques rely on visual backbones, which may lack semantic richness. Despite the potential of large-scale vision-language foundation models like CLIP, their effectiveness for DA has yet to be fully explored. To address this gap, we introduce \textsc{AD-CLIP}, a domain-agnostic prompt learning strategy for CLIP that aims to solve the DA problem in the prompt space. We leverage the frozen vision backbone of CLIP to extract both image style (domain) and content information, which we apply to learn prompt tokens. Our prompts are designed to be domain-invariant and class-generalizable, by conditioning prompt learning on image style and content features simultaneously. We use standard supervised contrastive learning in the source domain, while proposing an entropy minimization strategy to align domains in the embedding space given the target domain data. We also consider a scenario where only target domain samples are available during testing, without any source domain data, and propose a cross-domain style mapping network to hallucinate domain-agnostic tokens. Our extensive experiments on three benchmark DA datasets demonstrate the effectiveness of \textsc{AD-CLIP} compared to existing literature. Code is available at \url{https://github.com/mainaksingha01/AD-CLIP}
Authors: Thi Minh Anh Pham, An Duc Nguyen, Cephas Svosve, Vasileios Argyriou, Georgios Tzimiropoulos
Abstract: Large pre-trained vision-language models such as CLIP have demonstrated great potential in zero-shot transferability to downstream tasks. However, to attain optimal performance, the manual selection of prompts is necessary to improve alignment between the downstream image distribution and the textual class descriptions. This manual prompt engineering is the major challenge for deploying such models in practice since it requires domain expertise and is extremely time-consuming. To avoid non-trivial prompt engineering, recent work Context Optimization (CoOp) introduced the concept of prompt learning to the vision domain using learnable textual tokens. While CoOp can achieve substantial improvements over manual prompts, its learned context is worse generalizable to wider unseen classes within the same dataset. In this work, we present Prompt Learning with Reparameterization Encoder (PRE) - a simple and efficient method that enhances the generalization ability of the learnable prompt to unseen classes while maintaining the capacity to learn Base classes. Instead of directly optimizing the prompts, PRE employs a prompt encoder to reparameterize the input prompt embeddings, enhancing the exploration of task-specific knowledge from few-shot samples. Experiments and extensive ablation studies on 8 benchmarks demonstrate that our approach is an efficient method for prompt learning. Specifically, PRE achieves a notable enhancement of 5.60% in average accuracy on New classes and 3% in Harmonic mean compared to CoOp in the 16-shot setting, all achieved within a good training time.
Authors: Hao Shi, Chengshan Pang, Jiaming Zhang, Kailun Yang, Yuhao Wu, Huajian Ni, Yining Lin, Rainer Stiefelhagen, Kaiwei Wang
Abstract: Roadside camera-driven 3D object detection is a crucial task in intelligent transportation systems, which extends the perception range beyond the limitations of vision-centric vehicles and enhances road safety. While previous studies have limitations in using only depth or height information, we find both depth and height matter and they are in fact complementary. The depth feature encompasses precise geometric cues, whereas the height feature is primarily focused on distinguishing between various categories of height intervals, essentially providing semantic context. This insight motivates the development of Complementary-BEV (CoBEV), a novel end-to-end monocular 3D object detection framework that integrates depth and height to construct robust BEV representations. In essence, CoBEV estimates each pixel's depth and height distribution and lifts the camera features into 3D space for lateral fusion using the newly proposed two-stage complementary feature selection (CFS) module. A BEV feature distillation framework is also seamlessly integrated to further enhance the detection accuracy from the prior knowledge of the fusion-modal CoBEV teacher. We conduct extensive experiments on the public 3D detection benchmarks of roadside camera-based DAIR-V2X-I and Rope3D, as well as the private Supremind-Road dataset, demonstrating that CoBEV not only achieves the accuracy of the new state-of-the-art, but also significantly advances the robustness of previous methods in challenging long-distance scenarios and noisy camera disturbance, and enhances generalization by a large margin in heterologous settings with drastic changes in scene and camera parameters. For the first time, the vehicle AP score of a camera model reaches 80% on DAIR-V2X-I in terms of easy mode. The source code will be made publicly available at https://github.com/MasterHow/CoBEV.
Authors: Zhen Xing, Qijun Feng, Haoran Chen, Qi Dai, Han Hu, Hang Xu, Zuxuan Wu, Yu-Gang Jiang
Abstract: The recent wave of AI-generated content (AIGC) has witnessed substantial success in computer vision, with the diffusion model playing a crucial role in this achievement. Due to their impressive generative capabilities, diffusion models are gradually superseding methods based on GANs and auto-regressive Transformers, demonstrating exceptional performance not only in image generation and editing, but also in the realm of video-related research. However, existing surveys mainly focus on diffusion models in the context of image generation, with few up-to-date reviews on their application in the video domain. To address this gap, this paper presents a comprehensive review of video diffusion models in the AIGC era. Specifically, we begin with a concise introduction to the fundamentals and evolution of diffusion models. Subsequently, we present an overview of research on diffusion models in the video domain, categorizing the work into three key areas: video generation, video editing, and other video understanding tasks. We conduct a thorough review of the literature in these three key areas, including further categorization and practical contributions in the field. Finally, we discuss the challenges faced by research in this domain and outline potential future developmental trends. A comprehensive list of video diffusion models studied in this survey is available at https://github.com/ChenHsing/Awesome-Video-Diffusion-Models.
URLs: https://github.com/ChenHsing/Awesome-Video-Diffusion-Models.
Authors: Haoyu Wang, Sizheng Guo, Jin Ye, Zhongying Deng, Junlong Cheng, Tianbin Li, Jianpin Chen, Yanzhou Su, Ziyan Huang, Yiqing Shen, Bin Fu, Shaoting Zhang, Junjun He, Yu Qiao
Abstract: Existing volumetric medical image segmentation models are typically task-specific, excelling at specific target but struggling to generalize across anatomical structures or modalities. This limitation restricts their broader clinical use. In this paper, we introduce SAM-Med3D for general-purpose segmentation on volumetric medical images. Given only a few 3D prompt points, SAM-Med3D can accurately segment diverse anatomical structures and lesions across various modalities. To achieve this, we gather and process a large-scale 3D medical image dataset, SA-Med3D-140K, from a blend of public sources and licensed private datasets. This dataset includes 22K 3D images and 143K corresponding 3D masks. Then SAM-Med3D, a promptable segmentation model characterized by the fully learnable 3D structure, is trained on this dataset using a two-stage procedure and exhibits impressive performance on both seen and unseen segmentation targets. We comprehensively evaluate SAM-Med3D on 16 datasets covering diverse medical scenarios, including different anatomical structures, modalities, targets, and zero-shot transferability to new/unseen tasks. The evaluation shows the efficiency and efficacy of SAM-Med3D, as well as its promising application to diverse downstream tasks as a pre-trained model. Our approach demonstrates that substantial medical resources can be utilized to develop a general-purpose medical AI for various potential applications. Our dataset, code, and models are available at https://github.com/uni-medical/SAM-Med3D.
Authors: Zhanwen Liu, Nan Yang, Yang Wang, Yuke Li, Xiangmo Zhao, Fei-Yue Wang
Abstract: Traffic object detection under variable illumination is challenging due to the information loss caused by the limited dynamic range of conventional frame-based cameras. To address this issue, we introduce bio-inspired event cameras and propose a novel Structure-aware Fusion Network (SFNet) that extracts sharp and complete object structures from the event stream to compensate for the lost information in images through cross-modality fusion, enabling the network to obtain illumination-robust representations for traffic object detection. Specifically, to mitigate the sparsity or blurriness issues arising from diverse motion states of traffic objects in fixed-interval event sampling methods, we propose the Reliable Structure Generation Network (RSGNet) to generate Speed Invariant Frames (SIF), ensuring the integrity and sharpness of object structures. Next, we design a novel Adaptive Feature Complement Module (AFCM) which guides the adaptive fusion of two modality features to compensate for the information loss in the images by perceiving the global lightness distribution of the images, thereby generating illumination-robust representations. Finally, considering the lack of large-scale and high-quality annotations in the existing event-based object detection datasets, we build a DSEC-Det dataset, which consists of 53 sequences with 63,931 images and more than 208,000 labels for 8 classes. Extensive experimental results demonstrate that our proposed SFNet can overcome the perceptual boundaries of conventional cameras and outperform the frame-based method by 8.0% in mAP50 and 5.9% in mAP50:95. Our code and dataset will be available at https://github.com/YN-Yang/SFNet.
Authors: Mohammed Baharoon, Waseem Qureshi, Jiahong Ouyang, Yanwu Xu, Abdulrhman Aljouie, Wei Peng
Abstract: The integration of deep learning systems into healthcare has been hindered by the resource-intensive process of data annotation and the inability of these systems to generalize to different data distributions. Foundation models, which are models pre-trained on large datasets, have emerged as a solution to reduce reliance on annotated data and enhance model generalizability and robustness. DINOv2 is an open-source foundation model pre-trained with self-supervised learning on 142 million curated natural images that exhibits promising capabilities across various vision tasks. Nevertheless, a critical question remains unanswered regarding DINOv2's adaptability to radiological imaging, and whether its features are sufficiently general to benefit radiology image analysis. Therefore, this study comprehensively evaluates the performance DINOv2 for radiology, conducting over 200 evaluations across diverse modalities (X-ray, CT, and MRI). To measure the effectiveness and generalizability of DINOv2's feature representations, we analyze the model across medical image analysis tasks including disease classification and organ segmentation on both 2D and 3D images, and under different settings like kNN, few-shot learning, linear-probing, end-to-end fine-tuning, and parameter-efficient fine-tuning. Comparative analyses with established supervised, self-supervised, and weakly-supervised models reveal DINOv2's superior performance and cross-task generalizability. The findings contribute insights to potential avenues for optimizing pre-training strategies for medical imaging and enhancing the broader understanding of DINOv2's role in bridging the gap between natural and radiological image analysis. Our code is available at https://github.com/MohammedSB/DINOv2ForRadiology
Authors: Cong Wang, Jiaxi Gu, Panwen Hu, Songcen Xu, Hang Xu, Xiaodan Liang
Abstract: Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation models. Nevertheless, these methods often result in either low fidelity or flickering over time due to their limitation to shallow image guidance and poor temporal consistency. To tackle these problems, we propose a high-fidelity image-to-video generation method by devising a frame retention branch based on a pre-trained video diffusion model, named DreamVideo. Instead of integrating the reference image into the diffusion process at a semantic level, our DreamVideo perceives the reference image via convolution layers and concatenates the features with the noisy latents as model input. By this means, the details of the reference image can be preserved to the greatest extent. In addition, by incorporating double-condition classifier-free guidance, a single image can be directed to videos of different actions by providing varying prompt texts. This has significant implications for controllable video generation and holds broad application prospects. We conduct comprehensive experiments on the public dataset, and both quantitative and qualitative results indicate that our method outperforms the state-of-the-art method. Especially for fidelity, our model has a powerful image retention ability and delivers the best results in UCF101 compared to other image-to-video models to our best knowledge. Also, precise control can be achieved by giving different text prompts. Further details and comprehensive results of our model will be presented in https://anonymous0769.github.io/DreamVideo/.
Authors: Kaichen Zhou, Jia-Wang Bian, Qian Xie, Jian-Qing Zheng, Niki Trigoni, Andrew Markham
Abstract: Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper, we present Manydepth2, a Motion-Guided Cost Volume Depth Net, to achieve precise depth estimation for both dynamic objects and static backgrounds, all while maintaining computational efficiency. To tackle the challenges posed by dynamic content, we incorporate optical flow and coarse monocular depth to create a novel static reference frame. This frame is then utilized to build a motion-guided cost volume in collaboration with the target frame. Additionally, to enhance the accuracy and resilience of the network structure, we introduce an attention-based depth net architecture to effectively integrate information from feature maps with varying resolutions. Compared to methods with similar computational costs, Manydepth2 achieves a significant reduction of approximately five percent in root-mean-square error for self-supervised monocular depth estimation on the KITTI-2015 dataset. The code could be found: https://github.com/kaichen-z/Manydepth2
Authors: Mia Gaia Polansky, Charles Herrmann, Junhwa Hur, Deqing Sun, Dor Verbin, Todd Zickler
Abstract: We present a lightweight network that infers grouping and boundaries, including curves, corners and junctions. It operates in a bottom-up fashion, analogous to classical methods for sub-pixel edge localization and edge-linking, but with a higher-dimensional representation of local boundary structure, and notions of local scale and spatial consistency that are learned instead of designed. Our network uses a mechanism that we call boundary attention: a geometry-aware local attention operation that, when applied densely and repeatedly, progressively refines a pixel-resolution field of variables that specify the boundary structure in every overlapping patch within an image. Unlike many edge detectors that produce rasterized binary edge maps, our model provides a rich, unrasterized representation of the geometric structure in every local region. We find that its intentional geometric bias allows it to be trained on simple synthetic shapes and then generalize to extracting boundaries from noisy low-light photographs.
Authors: Fuchen Long, Zhaofan Qiu, Ting Yao, Tao Mei
Abstract: The recent innovations and breakthroughs in diffusion models have significantly expanded the possibilities of generating high-quality videos for the given prompts. Most existing works tackle the single-scene scenario with only one video event occurring in a single background. Extending to generate multi-scene videos nevertheless is not trivial and necessitates to nicely manage the logic in between while preserving the consistent visual appearance of key content across video scenes. In this paper, we propose a novel framework, namely VideoStudio, for consistent-content and multi-scene video generation. Technically, VideoStudio leverages Large Language Models (LLM) to convert the input prompt into comprehensive multi-scene script that benefits from the logical knowledge learnt by LLM. The script for each scene includes a prompt describing the event, the foreground/background entities, as well as camera movement. VideoStudio identifies the common entities throughout the script and asks LLM to detail each entity. The resultant entity description is then fed into a text-to-image model to generate a reference image for each entity. Finally, VideoStudio outputs a multi-scene video by generating each scene video via a diffusion process that takes the reference images, the descriptive prompt of the event and camera movement into account. The diffusion model incorporates the reference images as the condition and alignment to strengthen the content consistency of multi-scene videos. Extensive experiments demonstrate that VideoStudio outperforms the SOTA video generation models in terms of visual quality, content consistency, and user preference. Source code is available at \url{https://github.com/FuchenUSTC/VideoStudio}.
Authors: Haobo Yuan, Xiangtai Li, Chong Zhou, Yining Li, Kai Chen, Chen Change Loy
Abstract: The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, whereas CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a unified framework. Specifically, we introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM's knowledge into the CLIP via distillation and learnable transformer adapters, while the latter transfers CLIP knowledge into SAM, enhancing its recognition capabilities. Extensive experiments on various datasets and detectors show the effectiveness of Open-Vocabulary SAM in both segmentation and recognition tasks, significantly outperforming the na\"{i}ve baselines of simply combining SAM and CLIP. Furthermore, aided with image classification data training, our method can segment and recognize approximately 22,000 classes.
Authors: Casimir Feldmann, Niall Siegenheim, Nikolas Hars, Lovro Rabuzin, Mert Ertugrul, Luca Wolfart, Marc Pollefeys, Zuria Bauer, Martin R. Oswald
Abstract: The capabilities of monocular depth estimation (MDE) models are limited by the availability of sufficient and diverse datasets. In the case of MDE models for autonomous driving, this issue is exacerbated by the linearity of the captured data trajectories. We propose a NeRF-based data augmentation pipeline to introduce synthetic data with more diverse viewing directions into training datasets and demonstrate the benefits of our approach to model performance and robustness. Our data augmentation pipeline, which we call \textit{NeRFmentation}, trains NeRFs on each scene in a dataset, filters out subpar NeRFs based on relevant metrics, and uses them to generate synthetic RGB-D images captured from new viewing directions. In this work, we apply our technique in conjunction with three state-of-the-art MDE architectures on the popular autonomous driving dataset, KITTI, augmenting its training set of the Eigen split. We evaluate the resulting performance gain on the original test set, a separate popular driving dataset, and our own synthetic test set.
Authors: Abdul-Hakeem Omotayo, Ashery Mbilinyi, Lukman Ismaila, Houcemeddine Turki, Mahmoud Abdien, Karim Gamal, Idriss Tondji, Yvan Pimi, Naome A. Etori, Marwa M. Matar, Clifford Broni-Bediako, Abigail Oppong, Mai Gamal, Eman Ehab, Gbetondji Dovonon, Zainab Akinjobi, Daniel Ajisafe, Oluwabukola G. Adegboro, Mennatullah Siam
Abstract: Despite significant efforts to democratize artificial intelligence (AI), computer vision which is a sub-field of AI, still lags in Africa. A significant factor to this, is the limited access to computing resources, datasets, and collaborations. As a result, Africa's contribution to top-tier publications in this field has only been 0.06% over the past decade. Towards improving the computer vision field and making it more accessible and inclusive, this study analyzes 63,000 Scopus-indexed computer vision publications from Africa. We utilize large language models to automatically parse their abstracts, to identify and categorize topics and datasets. This resulted in listing more than 100 African datasets. Our objective is to provide a comprehensive taxonomy of dataset categories to facilitate better understanding and utilization of these resources. We also analyze collaboration trends of researchers within and outside the continent. Additionally, we conduct a large-scale questionnaire among African computer vision researchers to identify the structural barriers they believe require urgent attention. In conclusion, our study offers a comprehensive overview of the current state of computer vision research in Africa, to empower marginalized communities to participate in the design and development of computer vision systems.
Authors: Zhaohu Xing, Tian Ye, Yijun Yang, Guang Liu, Lei Zhu
Abstract: The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and widespread adoption in this task. Mamba, as a State Space Model (SSM), recently emerged as a notable manner for long-range dependencies in sequential modeling, excelling in natural language processing filed with its remarkable memory efficiency and computational speed. Inspired by its success, we introduce SegMamba, a novel 3D medical image \textbf{Seg}mentation \textbf{Mamba} model, designed to effectively capture long-range dependencies within whole volume features at every scale. Our SegMamba, in contrast to Transformer-based methods, excels in whole volume feature modeling from a state space model standpoint, maintaining superior processing speed, even with volume features at a resolution of {$64\times 64\times 64$}. Comprehensive experiments on the BraTS2023 dataset demonstrate the effectiveness and efficiency of our SegMamba. The code for SegMamba is available at: https://github.com/ge-xing/SegMamba
Authors: Fangcen Liu, Chenqiang Gao, Yaming Zhang, Junjie Guo, Jinhao Wang, Deyu Meng
Abstract: In recent years, the foundation models have swept the computer vision field and facilitated the development of various tasks within different modalities. However, it remains an open question on how to design an infrared foundation model. In this paper, we propose InfMAE, a foundation model in infrared modality. We release an infrared dataset, called Inf30 to address the problem of lacking large-scale data for self-supervised learning in the infrared vision community. Besides, we design an information-aware masking strategy, which is suitable for infrared images. This masking strategy allows for a greater emphasis on the regions with richer information in infrared images during the self-supervised learning process, which is conducive to learning the generalized representation. In addition, we adopt a multi-scale encoder to enhance the performance of the pre-trained encoders in downstream tasks. Finally, based on the fact that infrared images do not have a lot of details and texture information, we design an infrared decoder module, which further improves the performance of downstream tasks. Extensive experiments show that our proposed method InfMAE outperforms other supervised methods and self-supervised learning methods in three downstream tasks.
Authors: Yaning Zhang, Zitong Yu, Tianyi Wang, Xiaobin Huang, Linlin Shen, Zan Gao, Jianfeng Ren
Abstract: The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative cross appearance-edge learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an appearance-edge cross-attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at \url{https://github.com/Jenine-321/GenFace
Authors: Soroush Seifi, Daniel Olmeda Reino, Fabien Despinoy, Rahaf Aljundi
Abstract: Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent works attempt to achieve zeroshot semantic segmentation while requiring either large-scale training or additional image/pixel level annotations. In this work, we generate free annotations for any semantic segmentation dataset using existing foundation models. We use CLIP to detect objects and SAM to generate high quality object masks. Next, we build a lightweight module on top of a self-supervised vision encoder, DinoV2, to align the patch features with a pretrained text encoder for zeroshot semantic segmentation. Our approach can bring language-based semantics to any pretrained vision encoder with minimal training, uses foundation models as the sole source of supervision and generalizes from little training data with no annotation.
Authors: Fadillah Adamsyah Maani, Numan Saeed, Aleksandr Matsun, Mohammad Yaqub
Abstract: Deep learning (DL) models have been advancing automatic medical image analysis on various modalities, including echocardiography, by offering a comprehensive end-to-end training pipeline. This approach enables DL models to regress ejection fraction (EF) directly from 2D+time echocardiograms, resulting in superior performance. However, the end-to-end training pipeline makes the learned representations less explainable. The representations may also fail to capture the continuous relation among echocardiogram clips, indicating the existence of spurious correlations, which can negatively affect the generalization. To mitigate this issue, we propose CoReEcho, a novel training framework emphasizing continuous representations tailored for direct EF regression. Our extensive experiments demonstrate that CoReEcho: 1) outperforms the current state-of-the-art (SOTA) on the largest echocardiography dataset (EchoNet-Dynamic) with MAE of 3.90 & R2 of 82.44, and 2) provides robust and generalizable features that transfer more effectively in related downstream tasks. The code is publicly available at https://github.com/fadamsyah/CoReEcho.
Authors: Jiabin Liang, Lanqing Zhang, Zhuoran Zhao, Xiangyu Xu
Abstract: The conventional mesh-based Level of Detail (LoD) technique, exemplified by applications such as Google Earth and many game engines, exhibits the capability to holistically represent a large scene even the Earth, and achieves rendering with a space complexity of O(log n). This constrained data requirement not only enhances rendering efficiency but also facilitates dynamic data fetching, thereby enabling a seamless 3D navigation experience for users. In this work, we extend this proven LoD technique to Neural Radiance Fields (NeRF) by introducing an octree structure to represent the scenes in different scales. This innovative approach provides a mathematically simple and elegant representation with a rendering space complexity of O(log n), aligned with the efficiency of mesh-based LoD techniques. We also present a novel training strategy that maintains a complexity of O(n). This strategy allows for parallel training with minimal overhead, ensuring the scalability and efficiency of our proposed method. Our contribution is not only in extending the capabilities of existing techniques but also in establishing a foundation for scalable and efficient large-scale scene representation using NeRF and octree structures.
Authors: Sihan Ma, Qiong Cao, Jing Zhang, Dacheng Tao
Abstract: This paper addresses the problem of generating 3D interactive human motion from text. Given a textual description depicting the actions of different body parts in contact with static objects, we synthesize sequences of 3D body poses that are visually natural and physically plausible. Yet, this task poses a significant challenge due to the inadequate consideration of interactions by physical contacts in both motion and textual descriptions, leading to unnatural and implausible sequences. To tackle this challenge, we create a novel dataset named RICH-CAT, representing "Contact-Aware Texts" constructed from the RICH dataset. RICH-CAT comprises high-quality motion, accurate human-object contact labels, and detailed textual descriptions, encompassing over 8,500 motion-text pairs across 26 indoor/outdoor actions. Leveraging RICH-CAT, we propose a novel approach named CATMO for text-driven interactive human motion synthesis that explicitly integrates human body contacts as evidence. We employ two VQ-VAE models to encode motion and body contact sequences into distinct yet complementary latent spaces and an intertwined GPT for generating human motions and contacts in a mutually conditioned manner. Additionally, we introduce a pre-trained text encoder to learn textual embeddings that better discriminate among various contact types, allowing for more precise control over synthesized motions and contacts. Our experiments demonstrate the superior performance of our approach compared to existing text-to-motion methods, producing stable, contact-aware motion sequences. Code and data will be available for research purposes at https://xymsh.github.io/RICH-CAT/
Authors: Aryan Satpathy, Nilaksh Singh, Dhruva Rajwade, Somesh Kumar
Abstract: Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world problems. However, SSL methods have recently been shown to be vulnerable to backdoor attacks, where the learned model can be exploited by adversaries to manipulate the learned representations, either through tampering the training data distribution, or via modifying the model itself. This work aims to address defending against backdoor attacks in SSL, where the adversary has access to a realistic fraction of the SSL training data, and no access to the model. We use novel methods that are computationally efficient as well as generalizable across different problem settings. We also investigate the adversarial robustness of SSL models when trained with our method, and show insights into increased robustness in SSL via frequency domain augmentations. We demonstrate the effectiveness of our method on a variety of SSL benchmarks, and show that our method is able to mitigate backdoor attacks while maintaining high performance on downstream tasks. Code for our work is available at github.com/Aryan-Satpathy/Backdoor
Authors: Gianluca Barone, Aashrit Cunchala, Rudy Nunez
Abstract: Standard classification theory assumes that the distribution of images in the test and training sets are identical. Unfortunately, real-life scenarios typically feature unseen data (''out-of-distribution data") which is different from data in the training distribution(''in-distribution"). This issue is most prevalent in social justice problems where data from under-represented groups may appear in the test data without representing an equal proportion of the training data. This may result in a model returning confidently wrong decisions and predictions. We are interested in the following question: Can the performance of a neural network improve on facial images of out-of-distribution data when it is trained simultaneously on multiple datasets of in-distribution data? We approach this problem by incorporating the Outlier Exposure model and investigate how the model's performance changes when other datasets of facial images were implemented. We observe that the accuracy and other metrics of the model can be increased by applying Outlier Exposure, incorporating a trainable weight parameter to increase the machine's emphasis on outlier images, and by re-weighting the importance of different class labels. We also experimented with whether sorting the images and determining outliers via image features would have more of an effect on the metrics than sorting by average pixel value, and found no conclusive results. Our goal was to make models not only more accurate but also more fair by scanning a more expanded range of images. We also tested the datasets in reverse order to see whether a more fair dataset with balanced features has an effect on the model's accuracy. Utilizing Python and the Pytorch package, we found that models that utilizing outlier exposure could make models more fair.
Authors: Zifu Wan, Pingping Zhang, Yuhao Wang, Silong Yong, Simon Stepputtis, Katia Sycara, Yaqi Xie
Abstract: Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environments. Leveraging additional modalities (X-modality) like thermal and depth alongside traditional RGB provides complementary information, enabling more robust and reliable prediction. In this work, we introduce Sigma, a Siamese Mamba network for multi-modal semantic segmentation utilizing the advanced Mamba. Unlike conventional methods that rely on CNNs, with their limited local receptive fields, or Vision Transformers (ViTs), which offer global receptive fields at the cost of quadratic complexity, our model achieves global receptive fields with linear complexity. By employing a Siamese encoder and innovating a Mamba-based fusion mechanism, we effectively select essential information from different modalities. A decoder is then developed to enhance the channel-wise modeling ability of the model. Our proposed method is rigorously evaluated on both RGB-Thermal and RGB-Depth semantic segmentation tasks, demonstrating its superiority and marking the first successful application of State Space Models (SSMs) in multi-modal perception tasks. Code is available at https://github.com/zifuwan/Sigma.
Authors: Haibo Jin, Haoxuan Che, Hao Chen
Abstract: Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection faces three problems: 1) The selected confident pseudo-labels often contain data bias, which may hurt model performance; 2) It is not easy to decide a proper threshold for sample selection as the localization task can be sensitive to noisy pseudo-labels; 3) coordinate regression does not output confidence, making selection-based self-training infeasible. To address the above issues, we propose Self-Training for Landmark Detection (STLD), a method that does not require explicit pseudo-label selection. Instead, STLD constructs a task curriculum to deal with confirmation bias, which progressively transitions from more confident to less confident tasks over the rounds of self-training. Pseudo pretraining and shrink regression are two essential components for such a curriculum, where the former is the first task of the curriculum for providing a better model initialization and the latter is further added in the later rounds to directly leverage the pseudo-labels in a coarse-to-fine manner. Experiments on three facial and one medical landmark detection benchmark show that STLD outperforms the existing methods consistently in both semi- and omni-supervised settings. The code is available at https://github.com/jhb86253817/STLD.
Authors: Xinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan, Yanjiao Chen, Xiaoyu Ji, Wenyuan Xu
Abstract: Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexually explicit scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block sexually explicit content (e.g., naked) but may still be vulnerable to adversarial prompts -- inputs that appear innocent but are ill-intended. In this paper, we present SafeGen, a framework to mitigate sexual content generation by text-to-image models in a text-agnostic manner. The key idea is to eliminate explicit visual representations from the model regardless of the text input. In this way, the text-to-image model is resistant to adversarial prompts since such unsafe visual representations are obstructed from within. Extensive experiments conducted on four datasets and large-scale user studies demonstrate SafeGen's effectiveness in mitigating sexually explicit content generation while preserving the high-fidelity of benign images. SafeGen outperforms eight state-of-the-art baseline methods and achieves 99.4% sexual content removal performance. Furthermore, our constructed benchmark of adversarial prompts provides a basis for future development and evaluation of anti-NSFW-generation methods.
Authors: Tal Hakim
Abstract: The application of machine-learning solutions to movement assessment from skeleton videos has attracted significant research attention in recent years. This advancement has made rehabilitation at home more accessible, utilizing movement assessment algorithms that can operate on affordable equipment for human pose detection and analysis from 2D or 3D videos. While the primary objective of automatic assessment tasks is to score movements, the automatic generation of feedback highlighting key movement issues has the potential to significantly enhance and accelerate the rehabilitation process. While numerous research works exist in the field of automatic movement assessment, only a handful address feedback generation. In this study, we propose terminology and criteria for the classification, evaluation, and comparison of feedback generation solutions. We discuss the challenges associated with each feedback generation approach and use our proposed criteria to classify existing solutions. To our knowledge, this is the first work that formulates feedback generation in skeletal movement assessment.
Authors: Xiao Zhou, Xiaoman Zhang, Chaoyi Wu, Ya Zhang, Weidi Xie, Yanfeng Wang
Abstract: In this paper, we consider the problem of visual representation learning for computational pathology, by exploiting large-scale image-text pairs gathered from public resources, along with the domain-specific knowledge in pathology. Specifically, we make the following contributions: (i) We curate a pathology knowledge tree that consists of 50,470 informative attributes for 4,718 diseases requiring pathology diagnosis from 32 human tissues. To our knowledge, this is the first comprehensive structured pathology knowledge base; (ii) We develop a knowledge-enhanced visual-language pretraining approach, where we first project pathology-specific knowledge into latent embedding space via a language model, and use it to guide the visual representation learning; (iii) We conduct thorough experiments to validate the effectiveness of our proposed components, demonstrating significant performance improvement on various downstream tasks, including cross-modal retrieval, zero-shot classification on pathology patches, and zero-shot tumor subtyping on whole slide images (WSIs).
Authors: Ankit Vani, Bac Nguyen, Samuel Lavoie, Ranjay Krishna, Aaron Courville
Abstract: Selective attention helps us focus on task-relevant aspects in the constant flood of our sensory input. This constraint in our perception allows us to robustly generalize under distractions and to new compositions of perceivable concepts. Transformers employ a similar notion of attention in their architecture, but representation learning models with transformer backbones like CLIP and DINO often fail to demonstrate robustness and compositionality. We highlight a missing architectural prior: unlike human perception, transformer encodings do not separately attend over individual concepts. In response, we propose SPARO, a read-out mechanism that partitions encodings into separately-attended slots, each produced by a single attention head. Using SPARO with CLIP imparts an inductive bias that the vision and text modalities are different views of a shared compositional world with the same corresponding concepts. Using SPARO, we demonstrate improvements on downstream recognition, robustness, retrieval, and compositionality benchmarks with CLIP (up to +14% for ImageNet, +4% for SugarCrepe), and on nearest neighbors and linear probe for ImageNet with DINO (+3% each). We also showcase a powerful ability to intervene and select individual SPARO concepts to further improve downstream task performance (up from +4% to +9% for SugarCrepe) and use this ability to study the robustness of SPARO's representation structure. Finally, we provide insights through ablation experiments and visualization of learned concepts.
Authors: Panagiotis Sapoutzoglou, George Giapitzakis, George Terzakis, Maria Pateraki
Abstract: We present a generic algorithm for scoring pose estimation methods that rely on single image semantic analysis. The algorithm employs a lightweight putative shape representation using a combination of multiple Gaussian Processes. Each Gaussian Process (GP) yields distance normal distributions from multiple reference points in the object's coordinate system to its surface, thus providing a geometric evaluation framework for scoring predicted poses. Our confidence measure comprises the average mixture probability of pixel back-projections onto the shape template. In the reported experiments, we compare the accuracy of our GP based representation of objects versus the actual geometric models and demonstrate the ability of our method to capture the influence of outliers as opposed to the corresponding intrinsic measures that ship with the segmentation and pose estimation methods.
Authors: Zelong Zeng, Kaname Tomite
Abstract: In anomaly segmentation for complex driving scenes, state-of-the-art approaches utilize anomaly scoring functions to calculate anomaly scores. For these functions, accurately predicting the logits of inlier classes for each pixel is crucial for precisely inferring the anomaly score. However, in real-world driving scenarios, the diversity of scenes often results in distorted manifolds of pixel embeddings in the space. This effect is not conducive to directly using the pixel embeddings for the logit prediction during inference, a concern overlooked by existing methods. To address this problem, we propose a novel method called Random Walk on Pixel Manifolds (RWPM). RWPM utilizes random walks to reveal the intrinsic relationships among pixels to refine the pixel embeddings. The refined pixel embeddings alleviate the distortion of manifolds, improving the accuracy of anomaly scores. Our extensive experiments show that RWPM consistently improve the performance of the existing anomaly segmentation methods and achieve the best results. Code is available at: \url{https://github.com/ZelongZeng/RWPM}.
Authors: Yujun Shi, Jun Hao Liew, Hanshu Yan, Vincent Y. F. Tan, Jiashi Feng
Abstract: Accuracy and speed are critical in image editing tasks. Pan et al. introduced a drag-based image editing framework that achieves pixel-level control using Generative Adversarial Networks (GANs). A flurry of subsequent studies enhanced this framework's generality by leveraging large-scale diffusion models. However, these methods often suffer from inordinately long processing times (exceeding 1 minute per edit) and low success rates. Addressing these issues head on, we present LightningDrag, a rapid approach enabling high quality drag-based image editing in ~1 second. Unlike most previous methods, we redefine drag-based editing as a conditional generation task, eliminating the need for time-consuming latent optimization or gradient-based guidance during inference. In addition, the design of our pipeline allows us to train our model on large-scale paired video frames, which contain rich motion information such as object translations, changing poses and orientations, zooming in and out, etc. By learning from videos, our approach can significantly outperform previous methods in terms of accuracy and consistency. Despite being trained solely on videos, our model generalizes well to perform local shape deformations not presented in the training data (e.g., lengthening of hair, twisting rainbows, etc.). Extensive qualitative and quantitative evaluations on benchmark datasets corroborate the superiority of our approach. The code and model will be released at https://github.com/magic-research/LightningDrag.
Authors: Yuliang Xiu, Yufei Ye, Zhen Liu, Dimitrios Tzionas, Michael J. Black
Abstract: Generating personalized 3D avatars is crucial for AR/VR. However, recent text-to-3D methods that generate avatars for celebrities or fictional characters, struggle with everyday people. Methods for faithful reconstruction typically require full-body images in controlled settings. What if a user could just upload their personal "OOTD" (Outfit Of The Day) photo collection and get a faithful avatar in return? The challenge is that such casual photo collections contain diverse poses, challenging viewpoints, cropped views, and occlusion (albeit with a consistent outfit, accessories and hairstyle). We address this novel "Album2Human" task by developing PuzzleAvatar, a novel model that generates a faithful 3D avatar (in a canonical pose) from a personal OOTD album, while bypassing the challenging estimation of body and camera pose. To this end, we fine-tune a foundational vision-language model (VLM) on such photos, encoding the appearance, identity, garments, hairstyles, and accessories of a person into (separate) learned tokens and instilling these cues into the VLM. In effect, we exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar. Importantly, we can customize avatars by simply inter-changing tokens. As a benchmark for this new task, we collect a new dataset, called PuzzleIOI, with 41 subjects in a total of nearly 1K OOTD configurations, in challenging partial photos with paired ground-truth 3D bodies. Evaluation shows that PuzzleAvatar not only has high reconstruction accuracy, outperforming TeCH and MVDreamBooth, but also a unique scalability to album photos, and strong robustness. Our code and data are publicly available for research purpose at https://puzzleavatar.is.tue.mpg.de/
Authors: Yang Chen, Tian He, Junfeng Fu, Ling Wang, Jingcai Guo, Ting Hu, Hong Cheng
Abstract: Skeleton-based action representation learning aims to interpret and understand human behaviors by encoding the skeleton sequences, which can be categorized into two primary training paradigms: supervised learning and self-supervised learning. However, the former one-hot classification requires labor-intensive predefined action categories annotations, while the latter involves skeleton transformations (e.g., cropping) in the pretext tasks that may impair the skeleton structure. To address these challenges, we introduce a novel skeleton-based training framework (C$^2$VL) based on Cross-modal Contrastive learning that uses the progressive distillation to learn task-agnostic human skeleton action representation from the Vision-Language knowledge prompts. Specifically, we establish the vision-language action concept space through vision-language knowledge prompts generated by pre-trained large multimodal models (LMMs), which enrich the fine-grained details that the skeleton action space lacks. Moreover, we propose the intra-modal self-similarity and inter-modal cross-consistency softened targets in the cross-modal representation learning process to progressively control and guide the degree of pulling vision-language knowledge prompts and corresponding skeletons closer. These soft instance discrimination and self-knowledge distillation strategies contribute to the learning of better skeleton-based action representations from the noisy skeleton-vision-language pairs. During the inference phase, our method requires only the skeleton data as the input for action recognition and no longer for vision-language prompts. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that our method outperforms the previous methods and achieves state-of-the-art results. Code is available at: https://github.com/cseeyangchen/C2VL.
Authors: Yun Peng, Xiao Lin, Nachuan Ma, Jiayuan Du, Chuangwei Liu, Chengju Liu, Qijun Chen
Abstract: Visual anomaly detection is vital in real-world applications, such as industrial defect detection and medical diagnosis. However, most existing methods focus on local structural anomalies and fail to detect higher-level functional anomalies under logical conditions. Although recent studies have explored logical anomaly detection, they can only address simple anomalies like missing or addition and show poor generalizability due to being heavily data-driven. To fill this gap, we propose SAM-LAD, a zero-shot, plug-and-play framework for logical anomaly detection in any scene. First, we obtain a query image's feature map using a pre-trained backbone. Simultaneously, we retrieve the reference images and their corresponding feature maps via the nearest neighbor search of the query image. Then, we introduce the Segment Anything Model (SAM) to obtain object masks of the query and reference images. Each object mask is multiplied with the entire image's feature map to obtain object feature maps. Next, an Object Matching Model (OMM) is proposed to match objects in the query and reference images. To facilitate object matching, we further propose a Dynamic Channel Graph Attention (DCGA) module, treating each object as a keypoint and converting its feature maps into feature vectors. Finally, based on the object matching relations, an Anomaly Measurement Model (AMM) is proposed to detect objects with logical anomalies. Structural anomalies in the objects can also be detected. We validate our proposed SAM-LAD using various benchmarks, including industrial datasets (MVTec Loco AD, MVTec AD), and the logical dataset (DigitAnatomy). Extensive experimental results demonstrate that SAM-LAD outperforms existing SoTA methods, particularly in detecting logical anomalies.
Authors: Qilong Zhangli, Jindong Jiang, Di Liu, Licheng Yu, Xiaoliang Dai, Ankit Ramchandani, Guan Pang, Dimitris N. Metaxas, Praveen Krishnan
Abstract: While diffusion models have significantly advanced the quality of image generation their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene text generation are typically limited by their reliance on an intermediate layout output. This dependency often results in a constrained diversity of text styles and fonts an inherent limitation stemming from the deterministic nature of the layout generation phase. To address these challenges this paper introduces SceneTextGen a novel diffusion-based model specifically designed to circumvent the need for a predefined layout stage. By doing so SceneTextGen facilitates a more natural and varied representation of text. The novelty of SceneTextGen lies in its integration of three key components: a character-level encoder for capturing detailed typographic properties coupled with a character-level instance segmentation model and a word-level spotting model to address the issues of unwanted text generation and minor character inaccuracies. We validate the performance of our method by demonstrating improved character recognition rates on generated images across different public visual text datasets in comparison to both standard diffusion based methods and text specific methods.
Authors: Shiqi Liu, Wenhan Cao, Chang Liu, Tianyi Zhang, Shengbo Eben Li
Abstract: Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, are inevitable due to complex traffic scenarios. Recent tracking methods are based on filtering algorithms that overlook these outliers, leading to reduced tracking accuracy or even loss of the objects trajectory. To handle this challenge, we adopt a probabilistic perspective, regarding the generation of outliers as misspecification between the actual distribution of measurement data and the nominal measurement model used for filtering. We further demonstrate that, by designing a convolutional operation, we can mitigate this misspecification. Incorporating this operation into the widely used unscented Kalman filter (UKF) in commonly adopted tracking algorithms, we derive a variant of the UKF that is robust to outliers, called the convolutional UKF (ConvUKF). We show that ConvUKF maintains the Gaussian conjugate property, thus allowing for real-time tracking. We also prove that ConvUKF has a bounded tracking error in the presence of outliers, which implies robust stability. The experimental results on the KITTI and nuScenes datasets show improved accuracy compared to representative baseline algorithms for MOT tasks.
Authors: Utsab Saha, Sawradip Saha, Shaikh Anowarul Fattah, Mohammad Saquib
Abstract: The identification and restoration of ancient watermarks have long been a major topic in codicology and history. Classifying historical documents based on watermarks is challenging due to their diversity, noisy samples, multiple representation modes, and minor distinctions between classes and intra-class variations. This paper proposes a modified U-net-based conditional generative adversarial network (GAN) named Npix2Cpix to translate noisy raw historical watermarked images into clean, handwriting-free watermarked images by performing image translation from degraded (noisy) pixels to clean pixels. Using image-to-image translation and adversarial learning, the network creates clutter-free images for watermark restoration and categorization. The generator and discriminator of the proposed GAN are trained using two separate loss functions, each based on the distance between images, to learn the mapping from the input noisy image to the output clean image. After using the proposed GAN to pre-process noisy watermarked images, Siamese-based one-shot learning is employed for watermark classification. Experimental results on a large-scale historical watermark dataset demonstrate that cleaning the noisy watermarked images can help to achieve high one-shot classification accuracy. The qualitative and quantitative evaluation of the retrieved watermarked image highlights the effectiveness of the proposed approach.
Authors: Sergey Linok, Tatiana Zemskova, Svetlana Ladanova, Roman Titkov, Dmitry Yudin, Maxim Monastyrny, Aleksei Valenkov
Abstract: Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object grounding with simple (bare) queries, but cannot cope with ambiguous descriptions that demand an understanding of object relations. To tackle this problem, we propose a modular approach called BBQ (Beyond Bare Queries), which constructs 3D scene graph representation with metric and semantic edges and utilizes a large language model as a human-to-agent interface through our deductive scene reasoning algorithm. BBQ employs robust DINO-powered associations to construct 3D object-centric map and an advanced raycasting algorithm with a 2D vision-language model to describe them as graph nodes. On the Replica and ScanNet datasets, we have demonstrated that BBQ takes a leading place in open-vocabulary 3D semantic segmentation compared to other zero-shot methods. Also, we show that leveraging spatial relations is especially effective for scenes containing multiple entities of the same semantic class. On challenging Sr3D+, Nr3D and ScanRefer benchmarks, our deductive approach demonstrates a significant improvement, enabling objects grounding by complex queries compared to other state-of-the-art methods. The combination of our design choices and software implementation has resulted in significant data processing speed in experiments on the robot on-board computer. This promising performance enables the application of our approach in intelligent robotics projects. We made the code publicly available at https://linukc.github.io/BeyondBareQueries/.
Authors: Hashmat Shadab Malik, Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar, Fahad Shahbaz Khan, Salman Khan
Abstract: Vision State Space Models (VSSMs), a novel architecture that combines the strengths of recurrent neural networks and latent variable models, have demonstrated remarkable performance in visual perception tasks by efficiently capturing long-range dependencies and modeling complex visual dynamics. However, their robustness under natural and adversarial perturbations remains a critical concern. In this work, we present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios, including occlusions, image structure, common corruptions, and adversarial attacks, and compare their performance to well-established architectures such as transformers and Convolutional Neural Networks. Furthermore, we investigate the resilience of VSSMs to object-background compositional changes on sophisticated benchmarks designed to test model performance in complex visual scenes. We also assess their robustness on object detection and segmentation tasks using corrupted datasets that mimic real-world scenarios. To gain a deeper understanding of VSSMs' adversarial robustness, we conduct a frequency-based analysis of adversarial attacks, evaluating their performance against low-frequency and high-frequency perturbations. Our findings highlight the strengths and limitations of VSSMs in handling complex visual corruptions, offering valuable insights for future research. Our code and models will be available at https://github.com/HashmatShadab/MambaRobustness.
Authors: Mehar Khurana, Neehar Peri, James Hays, Deva Ramanan
Abstract: State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. Contemporary methods adapt best-practices for self-supervised learning from the image domain to point clouds (such as contrastive learning). However, publicly available 3D datasets are considerably smaller and less diverse than those used for image-based self-supervised learning, limiting their effectiveness. We do note, however, that such data is naturally collected in a multimodal fashion, often paired with images. Rather than pre-training with only self-supervised objectives, we argue that it is better to bootstrap point cloud representations using image-based foundation models trained on internet-scale image data. Specifically, we propose a shelf-supervised approach (e.g. supervised with off-the-shelf image foundation models) for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. Pre-training 3D detectors with such pseudo-labels yields significantly better semi-supervised detection accuracy than prior self-supervised pretext tasks. Importantly, we show that image-based shelf-supervision is helpful for training LiDAR-only and multi-modal (RGB + LiDAR) detectors. We demonstrate the effectiveness of our approach on nuScenes and WOD, significantly improving over prior work in limited data settings. Our code is available at https://github.com/meharkhurana03/cm3d
Authors: Rishabh Mondal, Shataxi Dubey, Vannsh Jani, Shrimay Shah, Suraj Jaiswal, Zeel B Patel, Nipun Batra
Abstract: Air pollution kills 7 million people annually. The brick manufacturing industry accounts for 8%-14% of air pollution in the densely populated Indo-Gangetic plain. Due to the unorganized nature of brick kilns, policy violation detection, such as proximity to human habitats, remains challenging. While previous studies have utilized computer vision-based machine learning methods for brick kiln detection from satellite imagery, they utilize proprietary satellite data and rarely focus on compliance with government policies. In this research, we introduce a scalable framework for brick kiln detection and automatic compliance monitoring. We use Google Maps Static API to download the satellite imagery followed by the YOLOv8x model for detection. We identified and hand-verified 19579 new brick kilns across 9 states within the Indo-Gangetic plain. Furthermore, we automate and test the compliance to the policies affecting human habitats, rivers and hospitals. Our results show that a substantial number of brick kilns do not meet the compliance requirements. Our framework offers a valuable tool for governments worldwide to automate and enforce policy regulations for brick kilns, addressing critical environmental and public health concerns.
Authors: Qianhui Wan, Zecheng Zhang, Liheng Jiang, Zhaoqi Wang, Yan Zhou
Abstract: Image anomaly detection is a popular research direction, with many methods emerging in recent years due to rapid advancements in computing. The use of artificial intelligence for image anomaly detection has been widely studied. By analyzing images of athlete posture and movement, it is possible to predict injury status and suggest necessary adjustments. Most existing methods rely on convolutional networks to extract information from irrelevant pixel data, limiting model accuracy. This paper introduces a network combining Residual Network (ResNet) and Bidirectional Gated Recurrent Unit (BiGRU), which can predict potential injury types and provide early warnings by analyzing changes in muscle and bone poses from video images. To address the high complexity of this network, the Sparrow search algorithm was used for optimization. Experiments conducted on four datasets demonstrated that our model has the smallest error in image anomaly detection compared to other models, showing strong adaptability. This provides a new approach for anomaly detection and predictive analysis in images, contributing to the sustainable development of human health and performance.
Authors: Sihan Ma, Jing Zhang, Qiong Cao, Dacheng Tao
Abstract: Pose estimation aims to accurately identify anatomical keypoints in humans and animals using monocular images, which is crucial for various applications such as human-machine interaction, embodied AI, and autonomous driving. While current models show promising results, they are typically trained and tested on clean data, potentially overlooking the corruption during real-world deployment and thus posing safety risks in practical scenarios. To address this issue, we introduce PoseBench, a comprehensive benchmark designed to evaluate the robustness of pose estimation models against real-world corruption. We evaluated 60 representative models, including top-down, bottom-up, heatmap-based, regression-based, and classification-based methods, across three datasets for human and animal pose estimation. Our evaluation involves 10 types of corruption in four categories: 1) blur and noise, 2) compression and color loss, 3) severe lighting, and 4) masks. Our findings reveal that state-of-the-art models are vulnerable to common real-world corruptions and exhibit distinct behaviors when tackling human and animal pose estimation tasks. To improve model robustness, we delve into various design considerations, including input resolution, pre-training datasets, backbone capacity, post-processing, and data augmentations. We hope that our benchmark will serve as a foundation for advancing research in robust pose estimation. The benchmark and source code will be released at https://xymsh.github.io/PoseBench
Authors: Guido Di Federico, Louis J. Durlofsky
Abstract: Geological parameterization entails the representation of a geomodel using a small set of latent variables and a mapping from these variables to grid-block properties such as porosity and permeability. Parameterization is useful for data assimilation (history matching), as it maintains geological realism while reducing the number of variables to be determined. Diffusion models are a new class of generative deep-learning procedures that have been shown to outperform previous methods, such as generative adversarial networks, for image generation tasks. Diffusion models are trained to "denoise", which enables them to generate new geological realizations from input fields characterized by random noise. Latent diffusion models, which are the specific variant considered in this study, provide dimension reduction through use of a low-dimensional latent variable. The model developed in this work includes a variational autoencoder for dimension reduction and a U-net for the denoising process. Our application involves conditional 2D three-facies (channel-levee-mud) systems. The latent diffusion model is shown to provide realizations that are visually consistent with samples from geomodeling software. Quantitative metrics involving spatial and flow-response statistics are evaluated, and general agreement between the diffusion-generated models and reference realizations is observed. Stability tests are performed to assess the smoothness of the parameterization method. The latent diffusion model is then used for ensemble-based data assimilation. Two synthetic "true" models are considered. Significant uncertainty reduction, posterior P$_{10}$-P$_{90}$ forecasts that generally bracket observed data, and consistent posterior geomodels, are achieved in both cases.
Authors: Sedigheh Eslami, Gerard de Melo
Abstract: Contrastive Language--Image Pre-training (CLIP) has manifested remarkable improvements in zero-shot classification and cross-modal vision-language tasks. Yet, from a geometrical point of view, the CLIP embedding space has been found to have a pronounced modality gap. This gap renders the embedding space overly sparse and disconnected, with different modalities being densely distributed in distinct subregions of the hypersphere. In this work, we aim at answering three main questions: 1. Does sharing the parameter space between the multi-modal encoders reduce the modality gap? 2. Can the gap be mitigated by pushing apart the uni-modal embeddings via intra-modality separation? 3. How do these gap reduction approaches affect the downstream performance? We design AlignCLIP, in order to answer these questions and through extensive experiments, we show that AlignCLIP achieves noticeable enhancements in the cross-modal alignment of the embeddings, and thereby, reduces the modality gap, while improving the performance across several zero-shot and fine-tuning downstream evaluations.
Authors: Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, Guangjun Yu, Xiang Wan, Benyou Wang
Abstract: The rapid development of multimodal large language models (MLLMs), such as GPT-4V, has led to significant advancements. However, these models still face challenges in medical multimodal capabilities due to limitations in the quantity and quality of medical vision-text data, stemming from data privacy concerns and high annotation costs. While pioneering approaches utilize PubMed's large-scale, de-identified medical image-text pairs to address these limitations, they still fall short due to inherent data noise. To tackle this, we refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) in an 'unblinded' capacity to denoise and reformat the data, resulting in the creation of the PubMedVision dataset with 1.3 million medical VQA samples. Our validation demonstrates that: (1) PubMedVision can significantly enhance the medical multimodal capabilities of current MLLMs, showing significant improvement in benchmarks including the MMMU Health & Medicine track; (2) manual checks by medical experts and empirical results validate the superior data quality of our dataset compared to other data construction methods. Using PubMedVision, we train a 34B medical MLLM HuatuoGPT-Vision, which shows superior performance in medical multimodal scenarios among open-source MLLMs.
Authors: Qiang Zheng, Yafei Qi, Chen Wang, Chao Zhang, Jian Sun
Abstract: In the domain of point cloud analysis, despite the significant capabilities of Graph Neural Networks (GNNs) in managing complex 3D datasets, existing approaches encounter challenges like high computational costs and scalability issues with extensive scenarios. These limitations restrict the practical deployment of GNNs, notably in resource-constrained environments. To address these issues, this study introduce Point<\b> Vi<\b>sion G<\b>NN (PointViG), an efficient framework for point cloud analysis. PointViG incorporates a lightweight graph convolutional module to efficiently aggregate local features and mitigate over-smoothing. For large-scale point cloud scenes, we propose an adaptive dilated graph convolution technique that searches for sparse neighboring nodes within a dilated neighborhood based on semantic correlation, thereby expanding the receptive field and ensuring computational efficiency. Experiments demonstrate that PointViG achieves performance comparable to state-of-the-art models while balancing performance and complexity. On the ModelNet40 classification task, PointViG achieved 94.3% accuracy with 1.5M parameters. For the S3DIS segmentation task, it achieved an mIoU of 71.7% with 5.3M parameters. These results underscore the potential and efficiency of PointViG in point cloud analysis.
Authors: Md Farhan Ishmam, Ishmam Tashdeed, Talukder Asir Saadat, Md Hamjajul Ashmafee, Abu Raihan Mostofa Kamal, Md. Azam Hossain
Abstract: Can Visual Question Answering (VQA) systems perform just as well when deployed in the real world? Or are they susceptible to realistic corruption effects e.g. image blur, which can be detrimental in sensitive applications, such as medical VQA? While linguistic or textual robustness has been thoroughly explored in the VQA literature, there has yet to be any significant work on the visual robustness of VQA models. We propose the first large-scale benchmark comprising 213,000 augmented images, challenging the visual robustness of multiple VQA models and assessing the strength of realistic visual corruptions. Additionally, we have designed several robustness evaluation metrics that can be aggregated into a unified metric and tailored to fit a variety of use cases. Our experiments reveal several insights into the relationships between model size, performance, and robustness with the visual corruptions. Our benchmark highlights the need for a balanced approach in model development that considers model performance without compromising the robustness.
Authors: Li Li, Hubert P. H. Shum, Toby P. Breckon
Abstract: 3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and two effective RAPiD-Seg variants, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets.
Authors: Rafay Mohiuddin, Sai Manoj Prakhya, Fiona Collins, Ziyuan Liu, Andr\'e Borrmann
Abstract: In this paper, we present a novel, scalable approach for constructing open set, instance-level 3D scene representations, advancing open world understanding of 3D environments. Existing methods require pre-constructed 3D scenes and face scalability issues due to per-point feature vector learning, limiting their efficacy with complex queries. Our method overcomes these limitations by incrementally building instance-level 3D scene representations using 2D foundation models, efficiently aggregating instance-level details such as masks, feature vectors, names, and captions. We introduce fusion schemes for feature vectors to enhance their contextual knowledge and performance on complex queries. Additionally, we explore large language models for robust automatic annotation and spatial reasoning tasks. We evaluate our proposed approach on multiple scenes from ScanNet and Replica datasets demonstrating zero-shot generalization capabilities, exceeding current state-of-the-art methods in open world 3D scene understanding.
Authors: Yiyang Jiang, Wengyu Zhang, Xulu Zhang, Xiaoyong Wei, Chang Wen Chen, Qing Li
Abstract: In this paper, we investigate the feasibility of leveraging large language models (LLMs) for integrating general knowledge and incorporating pseudo-events as priors for temporal content distribution in video moment retrieval (VMR) models. The motivation behind this study arises from the limitations of using LLMs as decoders for generating discrete textual descriptions, which hinders their direct application to continuous outputs like salience scores and inter-frame embeddings that capture inter-frame relations. To overcome these limitations, we propose utilizing LLM encoders instead of decoders. Through a feasibility study, we demonstrate that LLM encoders effectively refine inter-concept relations in multimodal embeddings, even without being trained on textual embeddings. We also show that the refinement capability of LLM encoders can be transferred to other embeddings, such as BLIP and T5, as long as these embeddings exhibit similar inter-concept similarity patterns to CLIP embeddings. We present a general framework for integrating LLM encoders into existing VMR architectures, specifically within the fusion module. Through experimental validation, we demonstrate the effectiveness of our proposed methods by achieving state-of-the-art performance in VMR. The source code can be accessed at https://github.com/fletcherjiang/LLMEPET.
Authors: Mingze Xu, Mingfei Gao, Zhe Gan, Hong-You Chen, Zhengfeng Lai, Haiming Gang, Kai Kang, Afshin Dehghan
Abstract: We propose SlowFast-LLaVA (or SF-LLaVA for short), a training-free video large language model (LLM) that can jointly capture detailed spatial semantics and long-range temporal context without exceeding the token budget of commonly used LLMs. This is realized by using a two-stream SlowFast design of inputs for Video LLMs to aggregate features from sampled frames in an effective way. Specifically, the Slow pathway extracts features at a low frame rate while keeping as much spatial detail as possible (e.g., with 12x24 tokens), and the Fast pathway operates on a high frame rate but uses a larger spatial pooling stride (e.g., downsampling 6x) to focus on the motion cues. As a result, this design allows us to adequately capture both spatial and temporal features that are beneficial for detailed video understanding. Experimental results show that SF-LLaVA outperforms existing training-free methods on a wide range of video tasks. On some benchmarks, it achieves comparable or even better performance compared to state-of-the-art Video LLMs that are fine-tuned on video datasets. Code has been made available at: https://github.com/apple/ml-slowfast-llava.
Authors: Zijian Zhu, Ali Zia, Xuesong Li, Bingbing Dan, Yuebo Ma, Enhai Liu, Rujin Zhao
Abstract: Stripe-like space target detection (SSTD) plays a key role in enhancing space situational awareness and assessing spacecraft behaviour. This domain faces three challenges: the lack of publicly available datasets, interference from stray light and stars, and the variability of stripe-like targets, which makes manual labeling both inaccurate and labor-intensive. In response, we introduces `AstroStripeSet', a pioneering dataset designed for SSTD, aiming to bridge the gap in academic resources and advance research in SSTD. Furthermore, we propose a novel teacher-student label evolution framework with single-point weak supervision, providing a new solution to the challenges of manual labeling. This framework starts with generating initial pseudo-labels using the zero-shot capabilities of the Segment Anything Model (SAM) in a single-point setting. After that, the fine-tuned StripeSAM serves as the teacher and the newly developed StripeNet as the student, consistently improving segmentation performance through label evolution, which iteratively refines these labels. We also introduce `GeoDice', a new loss function customized for the linear characteristics of stripe-like targets. Extensive experiments show that our method matches fully supervised approaches, exhibits strong zero-shot generalization for diverse space-based and ground-based real-world images, and sets a new state-of-the-art (SOTA) benchmark. Our AstroStripeSet dataset and code will be made publicly available.
Authors: Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Tianlu Mao, Zhaoqi Wang
Abstract: Reconstructing textureless areas in MVS poses challenges due to the absence of reliable pixel correspondences within fixed patch. Although certain methods employ patch deformation to expand the receptive field, their patches mistakenly skip depth edges to calculate areas with depth discontinuity, thereby causing ambiguity. Consequently, we introduce Multi-granularity Segmentation Prior Multi-View Stereo (MSP-MVS). Specifically, we first propose multi-granularity segmentation prior by integrating multi-granularity depth edges to restrict patch deformation within homogeneous areas. Moreover, we present anchor equidistribution that bring deformed patches with more uniformly distributed anchors to ensure an adequate coverage of their own homogeneous areas. Furthermore, we introduce iterative local search optimization to represent larger patch with sparse representative candidates, significantly boosting the expressive capacity for each patch. The state-of-the-art results on ETH3D and Tanks & Temples benchmarks demonstrate the effectiveness and robust generalization ability of our proposed method.
Authors: Santosh V. Patapati
Abstract: Major Depressive Disorder (MDD) is a pervasive mental health condition that affects 300 million people worldwide. This work presents a novel, BiLSTM-based tri-modal model-level fusion architecture for the binary classification of depression from clinical interview recordings. The proposed architecture incorporates Mel Frequency Cepstral Coefficients, Facial Action Units, and uses a two-shot learning based GPT-4 model to process text data. This is the first work to incorporate large language models into a multi-modal architecture for this task. It achieves impressive results on the DAIC-WOZ AVEC 2016 Challenge cross-validation split and Leave-One-Subject-Out cross-validation split, surpassing all baseline models and multiple state-of-the-art models. In Leave-One-Subject-Out testing, it achieves an accuracy of 91.01%, an F1-Score of 85.95%, a precision of 80%, and a recall of 92.86%.
Authors: Yash Zambre, Ekdev Rajkitkul, Akshatha Mohan, Joshua Peeples
Abstract: Object detection plays a crucial role in the field of computer vision by autonomously locating and identifying objects of interest. The You Only Look Once (YOLO) model is an effective single-shot detector. However, YOLO faces challenges in cluttered or partially occluded scenes and can struggle with small, low-contrast objects. We propose a new method that integrates spatial transformer networks (STNs) into YOLO to improve performance. The proposed STN-YOLO aims to enhance the model's effectiveness by focusing on important areas of the image and improving the spatial invariance of the model before the detection process. Our proposed method improved object detection performance both qualitatively and quantitatively. We explore the impact of different localization networks within the STN module as well as the robustness of the model across different spatial transformations. We apply the STN-YOLO on benchmark datasets for Agricultural object detection as well as a new dataset from a state-of-the-art plant phenotyping greenhouse facility. Our code and dataset are publicly available.
Authors: Xinlin Ren, Chenjie Cao, Yanwei Fu, Xiangyang Xue
Abstract: Recent advancements in Neural Surface Reconstruction (NSR) have significantly improved multi-view reconstruction when coupled with volume rendering. However, relying solely on photometric consistency in image space falls short of addressing complexities posed by real-world data, including occlusions and non-Lambertian surfaces. To tackle these challenges, we propose an investigation into feature-level consistent loss, aiming to harness valuable feature priors from diverse pretext visual tasks and overcome current limitations. It is crucial to note the existing gap in determining the most effective pretext visual task for enhancing NSR. In this study, we comprehensively explore multi-view feature priors from seven pretext visual tasks, comprising thirteen methods. Our main goal is to strengthen NSR training by considering a wide range of possibilities. Additionally, we examine the impact of varying feature resolutions and evaluate both pixel-wise and patch-wise consistent losses, providing insights into effective strategies for improving NSR performance. By incorporating pre-trained representations from MVSFormer and QuadTree, our approach can generate variations of MVS-NeuS and Match-NeuS, respectively. Our results, analyzed on DTU and EPFL datasets, reveal that feature priors from image matching and multi-view stereo outperform other pretext tasks. Moreover, we discover that extending patch-wise photometric consistency to the feature level surpasses the performance of pixel-wise approaches. These findings underscore the effectiveness of these techniques in enhancing NSR outcomes.
Authors: Muhammad Abdullah Jamal, Omid Mohareri
Abstract: In this paper, we propose a new progressive pre-training method for image understanding tasks which leverages RGB-D datasets. The method utilizes Multi-Modal Contrastive Masked Autoencoder and Denoising techniques. Our proposed approach consists of two stages. In the first stage, we pre-train the model using contrastive learning to learn cross-modal representations. In the second stage, we further pre-train the model using masked autoencoding and denoising/noise prediction used in diffusion models. Masked autoencoding focuses on reconstructing the missing patches in the input modality using local spatial correlations, while denoising learns high frequency components of the input data. Moreover, it incorporates global distillation in the second stage by leveraging the knowledge acquired in stage one. Our approach is scalable, robust and suitable for pre-training RGB-D datasets. Extensive experiments on multiple datasets such as ScanNet, NYUv2 and SUN RGB-D show the efficacy and superior performance of our approach. Specifically, we show an improvement of +1.3% mIoU against Mask3D on ScanNet semantic segmentation. We further demonstrate the effectiveness of our approach in low-data regime by evaluating it for semantic segmentation task against the state-of-the-art methods.
Authors: Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, Chunyuan Li
Abstract: We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the LLaVA-NeXT blog series. Our experimental results demonstrate that LLaVA-OneVision is the first single model that can simultaneously push the performance boundaries of open LMMs in three important computer vision scenarios: single-image, multi-image, and video scenarios. Importantly, the design of LLaVA-OneVision allows strong transfer learning across different modalities/scenarios, yielding new emerging capabilities. In particular, strong video understanding and cross-scenario capabilities are demonstrated through task transfer from images to videos.
Authors: Guru Swaroop Bennabhaktula, Enrique Alegre, Nicola Strisciuglio, George Azzopardi
Abstract: We introduce a novel computational unit, termed PushPull-Conv, in the first layer of a ResNet architecture, inspired by the anti-phase inhibition phenomenon observed in the primary visual cortex. This unit redefines the traditional convolutional layer by implementing a pair of complementary filters: a trainable push kernel and its counterpart, the pull kernel. The push kernel (analogous to traditional convolution) learns to respond to specific stimuli, while the pull kernel reacts to the same stimuli but of opposite contrast. This configuration enhances stimulus selectivity and effectively inhibits response in regions lacking preferred stimuli. This effect is attributed to the push and pull kernels, which produce responses of comparable magnitude in such regions, thereby neutralizing each other. The incorporation of the PushPull-Conv into ResNets significantly increases their robustness to image corruption. Our experiments with benchmark corruption datasets show that the PushPull-Conv can be combined with other data augmentation techniques to further improve model robustness. We set a new robustness benchmark on ResNet50 achieving an $mCE$ of 49.95$\%$ on ImageNet-C when combining PRIME augmentation with PushPull inhibition.
Authors: Bingbing Dan, Meihui Li, Tao Tang, Jing Zhang
Abstract: Infrared small target sequences exhibit strong similarities between frames and contain rich contextual information, which motivates us to achieve sequential infrared small target segmentation (IRSTS) with minimal data. Inspired by the success of Segment Anything Model (SAM) across various downstream tasks, we propose a one-shot and training-free method that perfectly adapts SAM's zero-shot generalization capability to sequential IRSTS. Specifically, we first obtain a confidence map through local feature matching (LFM). The highest point in the confidence map is used as the prompt to replace the manual prompt. Then, to address the over-segmentation issue caused by the domain gap, we design the point prompt-centric focusing (PPCF) module. Subsequently, to prevent miss and false detections, we introduce the triple-level ensemble (TLE) module to produce the final mask. Experiments demonstrate that our method requires only one shot to achieve comparable performance to state-of-the-art IRSTS methods and significantly outperforms other one-shot segmentation methods. Moreover, ablation studies confirm the robustness of our method in the type of annotations and the selection of reference images.
Authors: Qiang Zheng, Chao Zhang, Jian Sun
Abstract: In recent years, point cloud analysis methods based on the Transformer architecture have made significant progress, particularly in the context of multimedia applications such as 3D modeling, virtual reality, and autonomous systems. However, the high computational resource demands of the Transformer architecture hinder its scalability, real-time processing capabilities, and deployment on mobile devices and other platforms with limited computational resources. This limitation remains a significant obstacle to its practical application in scenarios requiring on-device intelligence and multimedia processing. To address this challenge, we propose an efficient point cloud analysis architecture, \textbf{Point} \textbf{M}LP-\textbf{T}ransformer (PointMT). This study tackles the quadratic complexity of the self-attention mechanism by introducing a linear complexity local attention mechanism for effective feature aggregation. Additionally, to counter the Transformer's focus on token differences while neglecting channel differences, we introduce a parameter-free channel temperature adaptation mechanism that adaptively adjusts the attention weight distribution in each channel, enhancing the precision of feature aggregation. To improve the Transformer's slow convergence speed due to the limited scale of point cloud datasets, we propose an MLP-Transformer hybrid module, which significantly enhances the model's convergence speed. Furthermore, to boost the feature representation capability of point tokens, we refine the classification head, enabling point tokens to directly participate in prediction. Experimental results on multiple evaluation benchmarks demonstrate that PointMT achieves performance comparable to state-of-the-art methods while maintaining an optimal balance between performance and accuracy.
Authors: Jakub Kol\'a\v{r}, Radim \v{S}petl\'ik, Ji\v{r}\'i Matas
Abstract: We present a novel method for measuring the rate of periodic phenomena (e.g., rotation, flicker, and vibration), by an event camera, a device asynchronously reporting brightness changes at independently operating pixels with high temporal resolution. The approach assumes that for a periodic phenomenon, a highly similar set of events is generated within a spatio-temporal window at a time difference corresponding to its period. The sets of similar events are detected by a correlation in the spatio-temporal event stream space. The proposed method, EEPPR, is evaluated on a dataset of 12 sequences of periodic phenomena, i.e. flashing light and vibration, and periodic motion, e.g., rotation, ranging from 3.2 Hz to 2 kHz (equivalent to 192 - 120 000 RPM). EEPPR significantly outperforms published methods on this dataset, achieving a mean relative error of 0.1%, setting new state-of-the-art. The dataset and codes are publicly available on GitHub.
Authors: Zhiyuan Li, Heng Wang, Dongnan Liu, Chaoyi Zhang, Ao Ma, Jieting Long, Weidong Cai
Abstract: Large Language Models (LLMs) have showcased exceptional ability in causal reasoning from textual information. However, will these causalities remain straightforward for Vision Large Language Models (VLLMs) when only visual hints are provided? Motivated by this, we propose a novel Multimodal Causal Reasoning benchmark, namely MuCR, to challenge VLLMs to infer semantic cause-and-effect relationship when solely relying on visual cues such as action, appearance, clothing, and environment. Specifically, we introduce a prompt-driven image synthesis approach to create siamese images with embedded semantic causality and visual cues, which can effectively evaluate VLLMs' causal reasoning capabilities. Additionally, we develop tailored metrics from multiple perspectives, including image-level match, phrase-level understanding, and sentence-level explanation, to comprehensively assess VLLMs' comprehension abilities. Our extensive experiments reveal that the current state-of-the-art VLLMs are not as skilled at multimodal causal reasoning as we might have hoped. Furthermore, we perform a comprehensive analysis to understand these models' shortcomings from different views and suggest directions for future research. We hope MuCR can serve as a valuable resource and foundational benchmark in multimodal causal reasoning research. The project is available at: https://github.com/Zhiyuan-Li-John/MuCR
Authors: Chen Feng, Georgios Tzimiropoulos, Ioannis Patras
Abstract: Learning with Noisy labels (LNL) poses a significant challenge for the Machine Learning community. Some of the most widely used approaches that select as clean samples for which the model itself (the in-training model) has high confidence, e.g., `small loss', can suffer from the so called `self-confirmation' bias. This bias arises because the in-training model, is at least partially trained on the noisy labels. Furthermore, in the classification case, an additional challenge arises because some of the label noise is between classes that are visually very similar (`hard noise'). This paper addresses these challenges by proposing a method (\textit{CLIPCleaner}) that leverages CLIP, a powerful Vision-Language (VL) model for constructing a zero-shot classifier for efficient, offline, clean sample selection. This has the advantage that the sample selection is decoupled from the in-training model and that the sample selection is aware of the semantic and visual similarities between the classes due to the way that CLIP is trained. We provide theoretical justifications and empirical evidence to demonstrate the advantages of CLIP for LNL compared to conventional pre-trained models. Compared to current methods that combine iterative sample selection with various techniques, \textit{CLIPCleaner} offers a simple, single-step approach that achieves competitive or superior performance on benchmark datasets. To the best of our knowledge, this is the first time a VL model has been used for sample selection to address the problem of Learning with Noisy Labels (LNL), highlighting their potential in the domain.
Authors: Cong Wang, Jiaxi Gu, Panwen Hu, Haoyu Zhao, Yuanfan Guo, Jianhua Han, Hang Xu, Xiaodan Liang
Abstract: Following the advancements in text-guided image generation technology exemplified by Stable Diffusion, video generation is gaining increased attention in the academic community. However, relying solely on text guidance for video generation has serious limitations, as videos contain much richer content than images, especially in terms of motion. This information can hardly be adequately described with plain text. Fortunately, in computer vision, various visual representations can serve as additional control signals to guide generation. With the help of these signals, video generation can be controlled in finer detail, allowing for greater flexibility for different applications. Integrating various controls, however, is nontrivial. In this paper, we propose a universal framework called EasyControl. By propagating and injecting condition features through condition adapters, our method enables users to control video generation with a single condition map. With our framework, various conditions including raw pixels, depth, HED, etc., can be integrated into different Unet-based pre-trained video diffusion models at a low practical cost. We conduct comprehensive experiments on public datasets, and both quantitative and qualitative results indicate that our method outperforms state-of-the-art methods. EasyControl significantly improves various evaluation metrics across multiple validation datasets compared to previous works. Specifically, for the sketch-to-video generation task, EasyControl achieves an improvement of 152.0 on FVD and 19.9 on IS, respectively, in UCF101 compared with VideoComposer. For fidelity, our model demonstrates powerful image retention ability, resulting in high FVD and IS in UCF101 and MSR-VTT compared to other image-to-video models.
Authors: Haisheng Su, Feixiang Song, Cong Ma, Wei Wu, Junchi Yan
Abstract: Robust object detection and tracking under arbitrary sight of view is challenging yet essential for the development of Autonomous Vehicle technology. With the growing demand of unmanned function vehicles, near-field scene understanding becomes an important research topic in the areas of low-speed autonomous driving. Due to the complexity of driving conditions and diversity of near obstacles such as blind spots and high occlusion, the perception capability of near-field environment is still inferior than its farther counterpart. To further enhance the intelligent ability of unmanned vehicles, in this paper, we construct a multimodal data collection platform based on 3 main types of sensors (Camera, LiDAR and Fisheye), which supports flexible sensor configurations to enable dynamic sight of view for ego vehicle, either global view or local view. Meanwhile, a large-scale multi-sensor dataset is built, named RoboSense, to facilitate near-field scene understanding. RoboSense contains more than 133K synchronized data with 1.4M 3D bounding box and IDs annotated in the full $360^{\circ}$ view, forming 216K trajectories across 7.6K temporal sequences. It has $270\times$ and $18\times$ as many annotations of near-field obstacles within 5$m$ as the previous single-vehicle datasets such as KITTI and nuScenes. Moreover, we define a novel matching criterion for near-field 3D perception and prediction metrics. Based on RoboSense, we formulate 6 popular tasks to facilitate the future development of related research, where the detailed data analysis as well as benchmarks are also provided accordingly.
Authors: Sierra Bonilla, Chiara Di Vece, Rema Daher, Xinwei Ju, Danail Stoyanov, Francisco Vasconcelos, Sophia Bano
Abstract: Three-dimensional (3D) reconstruction from two-dimensional images is an active research field in computer vision, with applications ranging from navigation and object tracking to segmentation and three-dimensional modeling. Traditionally, parametric techniques have been employed for this task. However, recent advancements have seen a shift towards learning-based methods. Given the rapid pace of research and the frequent introduction of new image matching methods, it is essential to evaluate them. In this paper, we present a comprehensive evaluation of various image matching methods using a structure-from-motion pipeline. We assess the performance of these methods on both in-domain and out-of-domain datasets, identifying key limitations in both the methods and benchmarks. We also investigate the impact of edge detection as a pre-processing step. Our analysis reveals that image matching for 3D reconstruction remains an open challenge, necessitating careful selection and tuning of models for specific scenarios, while also highlighting mismatches in how metrics currently represent method performance.
Authors: Emilia Szymanska, Mihai Dusmanu, Jan-Willem Buurlage, Mahdi Rad, Marc Pollefeys
Abstract: Answering questions about the spatial properties of the environment poses challenges for existing language and vision foundation models due to a lack of understanding of the 3D world notably in terms of relationships between objects. To push the field forward, multiple 3D Q&A datasets were proposed which, overall, provide a variety of questions, but they individually focus on particular aspects of 3D reasoning or are limited in terms of data modalities. To address this, we present Space3D-Bench - a collection of 1000 general spatial questions and answers related to scenes of the Replica dataset which offers a variety of data modalities: point clouds, posed RGB-D images, navigation meshes and 3D object detections. To ensure that the questions cover a wide range of 3D objectives, we propose an indoor spatial questions taxonomy inspired by geographic information systems and use it to balance the dataset accordingly. Moreover, we provide an assessment system that grades natural language responses based on predefined ground-truth answers by leveraging a Vision Language Model's comprehension of both text and images to compare the responses with ground-truth textual information or relevant visual data. Finally, we introduce a baseline called RAG3D-Chat integrating the world understanding of foundation models with rich context retrieval, achieving an accuracy of 67% on the proposed dataset.
Authors: Fuchen Zheng, Xuhang Chen, Weihuang Liu, Haolun Li, Yingtie Lei, Jiahui He, Chi-Man Pun, Shounjun Zhou
Abstract: In medical image segmentation, specialized computer vision techniques, notably transformers grounded in attention mechanisms and residual networks employing skip connections, have been instrumental in advancing performance. Nonetheless, previous models often falter when segmenting small, irregularly shaped tumors. To this end, we introduce SMAFormer, an efficient, Transformer-based architecture that fuses multiple attention mechanisms for enhanced segmentation of small tumors and organs. SMAFormer can capture both local and global features for medical image segmentation. The architecture comprises two pivotal components. First, a Synergistic Multi-Attention (SMA) Transformer block is proposed, which has the benefits of Pixel Attention, Channel Attention, and Spatial Attention for feature enrichment. Second, addressing the challenge of information loss incurred during attention mechanism transitions and feature fusion, we design a Feature Fusion Modulator. This module bolsters the integration between the channel and spatial attention by mitigating reshaping-induced information attrition. To evaluate our method, we conduct extensive experiments on various medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, achieving state-of-the-art results. Code and models are available at: \url{https://github.com/CXH-Research/SMAFormer}.
Authors: Xinhe Xu, Zhuoer Wang, Yihan Zhang, Yizhou Liu, Zhaoyue Wang, Zhihao Xu, Muhan Zhao, Huaiying Luo
Abstract: This article compares two style transfer methods in image processing: the traditional method, which synthesizes new images by stitching together small patches from existing images, and a modern machine learning-based approach that uses a segmentation network to isolate foreground objects and apply style transfer solely to the background. The traditional method excels in creating artistic abstractions but can struggle with seamlessness, whereas the machine learning method preserves the integrity of foreground elements while enhancing the background, offering improved aesthetic quality and computational efficiency. Our study indicates that machine learning-based methods are more suited for real-world applications where detail preservation in foreground elements is essential.
Authors: Fangcen Liu, Chenqiang Gao, Fang Chen, Pengcheng Li, Junjie Guo, Deyu Meng
Abstract: Infrared and visible dual-modality tasks such as semantic segmentation and object detection can achieve robust performance even in extreme scenes by fusing complementary information. Most current methods design task-specific frameworks, which are limited in generalization across multiple tasks. In this paper, we propose a fusion-guided infrared and visible general framework, IVGF, which can be easily extended to many high-level vision tasks. Firstly, we adopt the SOTA infrared and visible foundation models to extract the general representations. Then, to enrich the semantics information of these general representations for high-level vision tasks, we design the feature enhancement module and token enhancement module for feature maps and tokens, respectively. Besides, the attention-guided fusion module is proposed for effectively fusing by exploring the complementary information of two modalities. Moreover, we also adopt the cutout&mix augmentation strategy to conduct the data augmentation, which further improves the ability of the model to mine the regional complementary between the two modalities. Extensive experiments show that the IVGF outperforms state-of-the-art dual-modality methods in the semantic segmentation and object detection tasks. The detailed ablation studies demonstrate the effectiveness of each module, and another experiment explores the anti-missing modality ability of the proposed method in the dual-modality semantic segmentation task.
Authors: Xiaolong Wang, Zhi-Qi Cheng, Jue Wang, Xiaojiang Peng
Abstract: Fashion image editing is a crucial tool for designers to convey their creative ideas by visualizing design concepts interactively. Current fashion image editing techniques, though advanced with multimodal prompts and powerful diffusion models, often struggle to accurately identify editing regions and preserve the desired garment texture detail. To address these challenges, we introduce a new multimodal fashion image editing architecture based on latent diffusion models, called Detail-Preserved Diffusion Models (DPDEdit). DPDEdit guides the fashion image generation of diffusion models by integrating text prompts, region masks, human pose images, and garment texture images. To precisely locate the editing region, we first introduce Grounded-SAM to predict the editing region based on the user's textual description, and then combine it with other conditions to perform local editing. To transfer the detail of the given garment texture into the target fashion image, we propose a texture injection and refinement mechanism. Specifically, this mechanism employs a decoupled cross-attention layer to integrate textual descriptions and texture images, and incorporates an auxiliary U-Net to preserve the high-frequency details of generated garment texture. Additionally, we extend the VITON-HD dataset using a multimodal large language model to generate paired samples with texture images and textual descriptions. Extensive experiments show that our DPDEdit outperforms state-of-the-art methods in terms of image fidelity and coherence with the given multimodal inputs.
Authors: Wenlin Li, Yucheng Xu, Xiaoqing Zheng, Suoya Han, Jun Wang, Xiaobo Sun
Abstract: Sparse and noisy images (SNIs), like those in spatial gene expression data, pose significant challenges for effective representation learning and clustering, which are essential for thorough data analysis and interpretation. In response to these challenges, we propose Dual Advancement of Representation Learning and Clustering (DARLC), an innovative framework that leverages contrastive learning to enhance the representations derived from masked image modeling. Simultaneously, DARLC integrates cluster assignments in a cohesive, end-to-end approach. This integrated clustering strategy addresses the "class collision problem" inherent in contrastive learning, thus improving the quality of the resulting representations. To generate more plausible positive views for contrastive learning, we employ a graph attention network-based technique that produces denoised images as augmented data. As such, our framework offers a comprehensive approach that improves the learning of representations by enhancing their local perceptibility, distinctiveness, and the understanding of relational semantics. Furthermore, we utilize a Student's t mixture model to achieve more robust and adaptable clustering of SNIs. Extensive experiments, conducted across 12 different types of datasets consisting of SNIs, demonstrate that DARLC surpasses the state-of-the-art methods in both image clustering and generating image representations that accurately capture gene interactions. Code is available at https://github.com/zipging/DARLC.
Authors: Qiang Zheng, Chao Zhang, Jian Sun
Abstract: Advances in self-supervised learning are essential for enhancing feature extraction and understanding in point cloud processing. This paper introduces PMT-MAE (Point MLP-Transformer Masked Autoencoder), a novel self-supervised learning framework for point cloud classification. PMT-MAE features a dual-branch architecture that integrates Transformer and MLP components to capture rich features. The Transformer branch leverages global self-attention for intricate feature interactions, while the parallel MLP branch processes tokens through shared fully connected layers, offering a complementary feature transformation pathway. A fusion mechanism then combines these features, enhancing the model's capacity to learn comprehensive 3D representations. Guided by the sophisticated teacher model Point-M2AE, PMT-MAE employs a distillation strategy that includes feature distillation during pre-training and logit distillation during fine-tuning, ensuring effective knowledge transfer. On the ModelNet40 classification task, achieving an accuracy of 93.6\% without employing voting strategy, PMT-MAE surpasses the baseline Point-MAE (93.2\%) and the teacher Point-M2AE (93.4\%), underscoring its ability to learn discriminative 3D point cloud representations. Additionally, this framework demonstrates high efficiency, requiring only 40 epochs for both pre-training and fine-tuning. PMT-MAE's effectiveness and efficiency render it well-suited for scenarios with limited computational resources, positioning it as a promising solution for practical point cloud analysis.
Authors: Qiang Zheng, Chao Zhang, Jian Sun
Abstract: The rapid advancement in point cloud processing technologies has significantly increased the demand for efficient and compact models that achieve high-accuracy classification. Knowledge distillation has emerged as a potent model compression technique. However, traditional KD often requires extensive computational resources for forward inference of large teacher models, thereby reducing training efficiency for student models and increasing resource demands. To address these challenges, we introduce an innovative offline recording strategy that avoids the simultaneous loading of both teacher and student models, thereby reducing hardware demands. This approach feeds a multitude of augmented samples into the teacher model, recording both the data augmentation parameters and the corresponding logit outputs. By applying shape-level augmentation operations such as random scaling and translation, while excluding point-level operations like random jittering, the size of the records is significantly reduced. Additionally, to mitigate the issue of small student model over-imitating the teacher model's outputs and converging to suboptimal solutions, we incorporate a negative-weight self-distillation strategy. Experimental results demonstrate that the proposed distillation strategy enables the student model to achieve performance comparable to state-of-the-art models while maintaining lower parameter count. This approach strikes an optimal balance between performance and complexity. This study highlights the potential of our method to optimize knowledge distillation for point cloud classification tasks, particularly in resource-constrained environments, providing a novel solution for efficient point cloud analysis.
Authors: Yubiao Yue, Jun Xue, Haihuang Liang, Zhenzhang Li, Yufeng Wang
Abstract: Due to the lack of effective mpox detection tools, the mpox virus continues to spread worldwide and has once again been declared a public health emergency of international concern by the World Health Organization. Lightweight deep learning model-based detection systems are crucial to alleviate mpox outbreaks since they are suitable for widespread deployment, especially in resource-limited scenarios. However, the key to its successful application depends on ensuring that the model can effectively model local features and long-range dependencies in mpox lesions while maintaining lightweight. Inspired by the success of Mamba in modeling long-range dependencies and its linear complexity, we proposed a lightweight hybrid architecture called MpoxMamba for efficient mpox detection. MpoxMamba utilizes depth-wise separable convolutions to extract local feature representations in mpox skin lesions and greatly enhances the model's ability to model the global contextual information by grouped Mamba modules. Notably, MpoxMamba's parameter size and FLOPs are 0.77M and 0.53G, respectively. Experimental results on two widely recognized benchmark datasets demonstrate that MpoxMamba outperforms state-of-the-art lightweight models and existing mpox detection methods. Importantly, we developed a web-based online application to provide free mpox detection (http://5227i971s5.goho.co:30290). The source codes of MpoxMamba are available at https://github.com/YubiaoYue/MpoxMamba.
URLs: http://5227i971s5.goho.co:30290)., https://github.com/YubiaoYue/MpoxMamba.
Authors: Yudi Dai, Zhiyong Wang, Xiping Lin, Chenglu Wen, Lan Xu, Siqi Shen, Yuexin Ma, Cheng Wang
Abstract: We introduce HiSC4D, a novel Human-centered interaction and 4D Scene Capture method, aimed at accurately and efficiently creating a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, rich human-human interactions, and human-environment interactions. By utilizing body-mounted IMUs and a head-mounted LiDAR, HiSC4D can capture egocentric human motions in unconstrained space without the need for external devices and pre-built maps. This affords great flexibility and accessibility for human-centered interaction and 4D scene capturing in various environments. Taking into account that IMUs can capture human spatially unrestricted poses but are prone to drifting for long-period using, and while LiDAR is stable for global localization but rough for local positions and orientations, HiSC4D employs a joint optimization method, harmonizing all sensors and utilizing environment cues, yielding promising results for long-term capture in large scenes. To promote research of egocentric human interaction in large scenes and facilitate downstream tasks, we also present a dataset, containing 8 sequences in 4 large scenes (200 to 5,000 $m^2$), providing 36k frames of accurate 4D human motions with SMPL annotations and dynamic scenes, 31k frames of cropped human point clouds, and scene mesh of the environment. A variety of scenarios, such as the basketball gym and commercial street, alongside challenging human motions, such as daily greeting, one-on-one basketball playing, and tour guiding, demonstrate the effectiveness and the generalization ability of HiSC4D. The dataset and code will be publicated on www.lidarhumanmotion.net/hisc4d available for research purposes.
Authors: Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang, Le Tian, Xiao Zhou, Jie Zhou
Abstract: In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack transparency about their architectures, while open-source models need more detailed ablations of their training strategies. 2) Pre-training data in open-source works is under-explored, with datasets added empirically, making the process cumbersome. 3) Fine-tuning often focuses on adding datasets, leading to diminishing returns. To address these issues, we propose the following contributions: 1) We trained a robust baseline model using the latest advancements in vision-language models, introducing effective improvements and conducting comprehensive ablation and validation for each technique. 2) Inspired by recent work on large language models, we filtered pre-training data using perplexity, selecting the lowest perplexity data for training. This approach allowed us to train on a curated 1M dataset, achieving competitive performance. 3) During visual instruction tuning, we used model soup on different datasets when adding more datasets yielded marginal improvements. These innovations resulted in a 9B parameter model that performs competitively with state-of-the-art models. Our strategies are efficient and lightweight, making them easily adoptable by the community.
Authors: Ning Gao, Sanping Zhou, Le Wang, Nanning Zheng
Abstract: Semi-supervised learning has emerged as a widely adopted technique in the field of medical image segmentation. The existing works either focuses on the construction of consistency constraints or the generation of pseudo labels to provide high-quality supervisory signals, whose main challenge mainly comes from how to keep the continuous improvement of model capabilities. In this paper, we propose a simple yet effective semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation, whose goal is to generate high-fidelity pseudo labels by learning robust and diverse features in the training process. Specifically, our PMT employs a standard mean teacher to penalize the consistency of the current state and utilizes two sets of MT architectures for co-training. The two sets of MT architectures are individually updated for prolonged periods to maintain stable model diversity established through performance gaps generated by iteration differences. Additionally, a difference-driven alignment regularizer is employed to expedite the alignment of lagging models with the representation capabilities of leading models. Furthermore, a simple yet effective pseudo-label filtering algorithm is employed for facile evaluation of models and selection of high-fidelity pseudo-labels outputted when models are operating at high performance for co-training purposes. Experimental results on two datasets with different modalities, i.e., CT and MRI, demonstrate that our method outperforms the state-of-the-art medical image segmentation approaches across various dimensions. The code is available at https://github.com/Axi404/PMT.
Authors: Dianbo Ma, Kousuke Imamura, Ziyan Gao, Xiangjie Wang, Satoshi Yamane
Abstract: Optical flow estimation is a fundamental and long-standing visual task. In this work, we present a novel method, dubbed HMAFlow, to improve optical flow estimation in challenging scenes, particularly those involving small objects. The proposed model mainly consists of two core components: a Hierarchical Motion Field Alignment (HMA) module and a Correlation Self-Attention (CSA) module. In addition, we rebuild 4D cost volumes by employing a Multi-Scale Correlation Search (MCS) layer and replacing average pooling in common cost volumes with a search strategy utilizing multiple search ranges. Experimental results demonstrate that our model achieves the best generalization performance compared to other state-of-the-art methods. Specifically, compared with RAFT, our method achieves relative error reductions of 14.2% and 3.4% on the clean pass and final pass of the Sintel online benchmark, respectively. On the KITTI test benchmark, HMAFlow surpasses RAFT and GMA in the Fl-all metric by relative margins of 6.8% and 7.7%, respectively. To facilitate future research, our code will be made available at https://github.com/BooTurbo/HMAFlow.
Authors: Lukas Muttenthaler, Klaus Greff, Frieda Born, Bernhard Spitzer, Simon Kornblith, Michael C. Mozer, Klaus-Robert M\"uller, Thomas Unterthiner, Andrew K. Lampinen
Abstract: Deep neural networks have achieved success across a wide range of applications, including as models of human behavior in vision tasks. However, neural network training and human learning differ in fundamental ways, and neural networks often fail to generalize as robustly as humans do, raising questions regarding the similarity of their underlying representations. What is missing for modern learning systems to exhibit more human-like behavior? We highlight a key misalignment between vision models and humans: whereas human conceptual knowledge is hierarchically organized from fine- to coarse-scale distinctions, model representations do not accurately capture all these levels of abstraction. To address this misalignment, we first train a teacher model to imitate human judgments, then transfer human-like structure from its representations into pretrained state-of-the-art vision foundation models. These human-aligned models more accurately approximate human behavior and uncertainty across a wide range of similarity tasks, including a new dataset of human judgments spanning multiple levels of semantic abstractions. They also perform better on a diverse set of machine learning tasks, increasing generalization and out-of-distribution robustness. Thus, infusing neural networks with additional human knowledge yields a best-of-both-worlds representation that is both more consistent with human cognition and more practically useful, thus paving the way toward more robust, interpretable, and human-like artificial intelligence systems.
Authors: Sheng Chen, Zihao Tang, Mariano Cabezas, Xinyi Wang, Arkiev D'Souza, Michael Barnett, Fernando Calamante, Weidong Cai, Chenyu Wang
Abstract: Diffusion-weighted imaging (DWI) is a type of Magnetic Resonance Imaging (MRI) technique sensitised to the diffusivity of water molecules, offering the capability to inspect tissue microstructures and is the only in-vivo method to reconstruct white matter fiber tracts non-invasively. The DWI signal can be analysed with the diffusion tensor imaging (DTI) model to estimate the directionality of water diffusion within voxels. Several scalar metrics, including axial diffusivity (AD), mean diffusivity (MD), radial diffusivity (RD), and fractional anisotropy (FA), can be further derived from DTI to quantitatively summarise the microstructural integrity of brain tissue. These scalar metrics have played an important role in understanding the organisation and health of brain tissue at a microscopic level in clinical studies. However, reliable DTI metrics rely on DWI acquisitions with high gradient directions, which often go beyond the commonly used clinical protocols. To enhance the utility of clinically acquired DWI and save scanning time for robust DTI analysis, this work proposes DirGeo-DTI, a deep learning-based method to estimate reliable DTI metrics even from a set of DWIs acquired with the minimum theoretical number (6) of gradient directions. DirGeo-DTI leverages directional encoding and geometric constraints to facilitate the training process. Two public DWI datasets were used for evaluation, demonstrating the effectiveness of the proposed method. Extensive experimental results show that the proposed method achieves the best performance compared to existing DTI enhancement methods and potentially reveals further clinical insights with routine clinical DWI scans.
Authors: Enming Zhang, Xingyuan Dai, Yisheng Lv, Qinghai Miao
Abstract: Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-and-answer interactions. However, most existing methods rely on computationally expensive visual encoders and large language models (LLMs), making them difficult to deploy in real-world scenarios and real-time applications. Meanwhile, most existing VLMs lack the ability to process multiple images, making it difficult to adapt to multi-camera perception in autonomous driving. To address these issues, we propose a novel framework called MiniDrive, which incorporates our proposed Feature Engineering Mixture of Experts (FE-MoE) module and Dynamic Instruction Adapter (DI-Adapter). The FE-MoE effectively maps 2D features into visual token embeddings before being input into the language model. The DI-Adapter enables the visual token embeddings to dynamically change with the instruction text embeddings, resolving the issue of static visual token embeddings for the same image in previous approaches. Compared to previous works, MiniDrive achieves state-of-the-art performance in terms of parameter size, floating point operations, and response efficiency, with the smallest version containing only 83M parameters.
Authors: Shaode Yu, Ze Chen, Zhimu Yang, Jiacheng Gu, Bizu Feng
Abstract: Score prediction is crucial in realistic image sharpness assessment after informative features are collected. Recently, Kolmogorov-Arnold networks (KANs) have been developed and witnessed remarkable success in data fitting. This study presents Taylor series based KAN (TaylorKAN). Then, different KANs are explored on four realistic image databases (BID2011, CID2013, CLIVE, and KonIQ-10k) for score prediction by using 15 mid-level features and 2048 high-level features. When setting support vector regression as the baseline, experimental results indicate KANs are generally better or competitive, TaylorKAN is the best on three databases using mid-level feature input, while KANs are inferior on CLIVE when high-level features are used. This is the first study that explores KANs for image quality assessment. It sheds lights on how to select and improve KANs on related tasks.
Authors: Haoxuan Wang, Qingdong He, Jinlong Peng, Hao Yang, Mingmin Chi, Yabiao Wang
Abstract: Open-vocabulary detection (OVD) aims to detect objects beyond a predefined set of categories. As a pioneering model incorporating the YOLO series into OVD, YOLO-World is well-suited for scenarios prioritizing speed and efficiency. However, its performance is hindered by its neck feature fusion mechanism, which causes the quadratic complexity and the limited guided receptive fields. To address these limitations, we present Mamba-YOLO-World, a novel YOLO-based OVD model employing the proposed MambaFusion Path Aggregation Network (MambaFusion-PAN) as its neck architecture. Specifically, we introduce an innovative State Space Model-based feature fusion mechanism consisting of a Parallel-Guided Selective Scan algorithm and a Serial-Guided Selective Scan algorithm with linear complexity and globally guided receptive fields. It leverages multi-modal input sequences and mamba hidden states to guide the selective scanning process. Experiments demonstrate that our model outperforms the original YOLO-World on the COCO and LVIS benchmarks in both zero-shot and fine-tuning settings while maintaining comparable parameters and FLOPs. Additionally, it surpasses existing state-of-the-art OVD methods with fewer parameters and FLOPs.
Authors: Clement Fung, Chen Qiu, Aodong Li, Maja Rudolph
Abstract: Anomaly detection is the task of identifying abnormal samples in large unlabeled datasets. While the advent of foundation models has produced powerful zero-shot anomaly detection methods, their deployment in practice is often hindered by the absence of labeled validation data -- without it, their detection performance cannot be evaluated reliably. In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors without labeled validation data. Instead of collecting labeled validation data, we generate synthetic anomalies without any training or fine-tuning, using only a small support set of normal images. Our synthetic anomalies are used to create detection tasks that compose a validation framework for model selection. In an empirical study, we evaluate SWSA with three types of synthetic anomalies and on two selection tasks: model selection of image-based anomaly detectors and prompt selection for CLIP-based anomaly detection. SWSA often selects models and prompts that match selections made with a ground-truth validation set, outperforming baseline selection strategies.
Authors: Holly Dinkel, Julia Di, Jamie Santos, Keenan Albee, Paulo Borges, Marina Moreira, Oleg Alexandrov, Brian Coltin, Trey Smith
Abstract: Assistive free-flyer robots autonomously caring for future crewed outposts -- such as NASA's Astrobee robots on the International Space Station (ISS) -- must be able to detect day-to-day interior changes to track inventory, detect and diagnose faults, and monitor the outpost status. This work presents a framework for multi-agent cooperative mapping and change detection to enable robotic maintenance of space outposts. One agent is used to reconstruct a 3D model of the environment from sequences of images and corresponding depth information. Another agent is used to periodically scan the environment for inconsistencies against the 3D model. Change detection is validated after completing the surveys using real image and pose data collected by Astrobee robots in a ground testing environment and from microgravity aboard the ISS. This work outlines the objectives, requirements, and algorithmic modules for the multi-agent reconstruction system, including recommendations for its use by assistive free-flyers aboard future microgravity outposts.
Authors: Jing Xu
Abstract: Deep learning models have become the dominant method for medical image segmentation. However, they often struggle to be generalisable to unknown tasks involving new anatomical structures, labels, or shapes. In these cases, the model needs to be re-trained for the new tasks, posing a significant challenge for non-machine learning experts and requiring a considerable time investment. Here I developed a general model that can solve unknown medical image segmentation tasks without requiring additional training. Given an example set of images and visual prompts for defining new segmentation tasks, GMISeg (General Medical Image Segmentation) leverages a pre-trained image encoder based on ViT and applies a low-rank fine-tuning strategy to the prompt encoder and mask decoder to fine-tune the model without in an efficient manner. I evaluated the performance of the proposed method on medical image datasets with different imaging modalities and anatomical structures. The proposed method facilitated the deployment of pre-trained AI models to new segmentation works in a user-friendly way.
Authors: Lohith Konathala
Abstract: Uncertainty quantification is vital for safety-critical Deep Learning applications like medical image segmentation. We introduce BA U-Net, an uncertainty-aware model for MRI segmentation that integrates Bayesian Neural Networks with Attention Mechanisms. BA U-Net delivers accurate, interpretable results, crucial for reliable pathology screening. Evaluated on BraTS 2020, this model addresses the critical need for confidence estimation in deep learning-based medical imaging.
Authors: Jing Xu
Abstract: Although transformer is preferred in natural language processing, some studies has only been applied to the field of medical imaging in recent years. For its long-term dependency, the transformer is expected to contribute to unconventional convolution neural net conquer their inherent spatial induction bias. The lately suggested transformer-based segmentation method only uses the transformer as an auxiliary module to help encode the global context into a convolutional representation. How to optimally integrate self-attention with convolution has not been investigated in depth. To solve the problem, this paper proposes MS-Twins (Multi-Scale Twins), which is a powerful segmentation model on account of the bond of self-attention and convolution. MS-Twins can better capture semantic and fine-grained information by combining different scales and cascading features. Compared with the existing network structure, MS-Twins has made progress on the previous method based on the transformer of two in common use data sets, Synapse and ACDC. In particular, the performance of MS-Twins on Synapse is 8% higher than SwinUNet. Even compared with nnUNet, the best entirely convoluted medical image segmentation network, the performance of MS-Twins on Synapse and ACDC still has a bit advantage.
Authors: Sicong Pan, Liren Jin, Xuying Huang, Cyrill Stachniss, Marija Popovi\'c, Maren Bennewitz
Abstract: Object reconstruction is relevant for many autonomous robotic tasks that require interaction with the environment. A key challenge in such scenarios is planning view configurations to collect informative measurements for reconstructing an initially unknown object. One-shot view planning enables efficient data collection by predicting view configurations and planning the globally shortest path connecting all views at once. However, prior knowledge about the object is required to conduct one-shot view planning. In this work, we propose a novel one-shot view planning approach that utilizes the powerful 3D generation capabilities of diffusion models as priors. By incorporating such geometric priors into our pipeline, we achieve effective one-shot view planning starting with only a single RGB image of the object to be reconstructed. Our planning experiments in simulation and real-world setups indicate that our approach balances well between object reconstruction quality and movement cost.
Authors: Luoyu Wang, Yitian Tao, Qing Yang, Yan Liang, Siwei Liu, Hongcheng Shi, Dinggang Shen, Han Zhang
Abstract: Simultaneous functional PET/MR (sf-PET/MR) presents a cutting-edge multimodal neuroimaging technique. It provides an unprecedented opportunity for concurrently monitoring and integrating multifaceted brain networks built by spatiotemporally covaried metabolic activity, neural activity, and cerebral blood flow (perfusion). Albeit high scientific/clinical values, short in hardware accessibility of PET/MR hinders its applications, let alone modern AI-based PET/MR fusion models. Our objective is to develop a clinically feasible AI-based disease diagnosis model trained on comprehensive sf-PET/MR data with the power of, during inferencing, allowing single modality input (e.g., PET only) as well as enforcing multimodal-based accuracy. To this end, we propose MX-ARM, a multimodal MiXture-of-experts Alignment and Reconstruction Model. It is modality detachable and exchangeable, allocating different multi-layer perceptrons dynamically ("mixture of experts") through learnable weights to learn respective representations from different modalities. Such design will not sacrifice model performance in uni-modal situation. To fully exploit the inherent complex and nonlinear relation among modalities while producing fine-grained representations for uni-modal inference, we subsequently add a modal alignment module to line up a dominant modality (e.g., PET) with representations of auxiliary modalities (MR). We further adopt multimodal reconstruction to promote the quality of learned features. Experiments on precious multimodal sf-PET/MR data for Mild Cognitive Impairment diagnosis showcase the efficacy of our model toward clinically feasible precision medicine.
Authors: Elodie Germani (EMPENN, LACODAM), Camille Maumet (EMPENN), Elisa Fromont (LACODAM)
Abstract: We propose a novel approach to improve the reproducibility of neuroimaging results by converting statistic maps across different functional MRI pipelines. We make the assumption that pipelines used to compute fMRI statistic maps can be considered as a style component and we propose to use different generative models, among which, Generative Adversarial Networks (GAN) and Diffusion Models (DM) to convert statistic maps across different pipelines. We explore the performance of multiple GAN frameworks, and design a new DM framework for unsupervised multi-domain styletransfer. We constrain the generation of 3D fMRI statistic maps using the latent space of an auxiliary classifier that distinguishes statistic maps from different pipelines and extend traditional sampling techniques used in DM to improve the transition performance. Our experiments demonstrate that our proposed methods aresuccessful: pipelines can indeed be transferred as a style component, providing animportant source of data augmentation for future medical studies.
Authors: Yushen Xu, Xiaosong Li, Yuchan Jie, Haishu Tan
Abstract: In clinical practice, tri-modal medical image fusion, compared to the existing dual-modal technique, can provide a more comprehensive view of the lesions, aiding physicians in evaluating the disease's shape, location, and biological activity. However, due to the limitations of imaging equipment and considerations for patient safety, the quality of medical images is usually limited, leading to sub-optimal fusion performance, and affecting the depth of image analysis by the physician. Thus, there is an urgent need for a technology that can both enhance image resolution and integrate multi-modal information. Although current image processing methods can effectively address image fusion and super-resolution individually, solving both problems synchronously remains extremely challenging. In this paper, we propose TFS-Diff, a simultaneously realize tri-modal medical image fusion and super-resolution model. Specially, TFS-Diff is based on the diffusion model generation of a random iterative denoising process. We also develop a simple objective function and the proposed fusion super-resolution loss, effectively evaluates the uncertainty in the fusion and ensures the stability of the optimization process. And the channel attention module is proposed to effectively integrate key information from different modalities for clinical diagnosis, avoiding information loss caused by multiple image processing. Extensive experiments on public Harvard datasets show that TFS-Diff significantly surpass the existing state-of-the-art methods in both quantitative and visual evaluations. Code is available at https://github.com/XylonXu01/TFS-Diff}{https://github.com/XylonXu01/TFS-Diff.
URLs: https://github.com/XylonXu01/TFS-Diff, https://github.com/XylonXu01/TFS-Diff.
Authors: Deegan Atha, R. Michael Swan, Abhishek Cauligi, Anne Bettens, Edwin Goh, Dima Kogan, Larry Matthies, Masahiro Ono
Abstract: The ability to determine the pose of a rover in an inertial frame autonomously is a crucial capability necessary for the next generation of surface rover missions on other planetary bodies. Currently, most on-going rover missions utilize ground-in-the-loop interventions to manually correct for drift in the pose estimate and this human supervision bottlenecks the distance over which rovers can operate autonomously and carry out scientific measurements. In this paper, we present ShadowNav, an autonomous approach for global localization on the Moon with an emphasis on driving in darkness and at nighttime. Our approach uses the leading edge of Lunar craters as landmarks and a particle filtering approach is used to associate detected craters with known ones on an offboard map. We discuss the key design decisions in developing the ShadowNav framework for use with a Lunar rover concept equipped with a stereo camera and an external illumination source. Finally, we demonstrate the efficacy of our proposed approach in both a Lunar simulation environment and on data collected during a field test at Cinder Lakes, Arizona.
Authors: Yuhao Zhang, Mihai Bujanca, Mikel Luj\'an
Abstract: Existing SLAM (Simultaneous Localization and Mapping) algorithms have achieved remarkable localization accuracy in dynamic environments by using deep learning techniques to identify dynamic objects. However, they usually require GPUs to operate in real-time. Therefore, this paper proposes an open-source real-time dynamic SLAM system that runs solely on CPU by incorporating a mask prediction mechanism, which allows the deep learning method and the camera tracking to run entirely in parallel at different frequencies. Our SLAM system further introduces a dual-stage optical flow tracking approach and employs a hybrid usage of optical flow and ORB features, enhancing efficiency and robustness by selectively allocating computational resources to input frames. Compared with previous methods, our system maintains high localization accuracy in dynamic environments while achieving a tracking frame rate of 56 FPS on a laptop CPU, proving that deep learning methods are feasible for dynamic SLAM without GPU support. To the best of our knowledge, this is the first SLAM system to achieve this.
Authors: Vittorio Giammarino, James Queeney, Ioannis Ch. Paschalidis
Abstract: We propose C-LAIfO, a computationally efficient algorithm designed for imitation learning from videos in the presence of visual mismatch between agent and expert domains. We analyze the problem of imitation from expert videos with visual discrepancies, and introduce a solution for robust latent space estimation using contrastive learning and data augmentation. Provided a visually robust latent space, our algorithm performs imitation entirely within this space using off-policy adversarial imitation learning. We conduct a thorough ablation study to justify our design and test C-LAIfO on high-dimensional continuous robotic tasks. Additionally, we demonstrate how C-LAIfO can be combined with other reward signals to facilitate learning on a set of challenging hand manipulation tasks with sparse rewards. Our experiments show improved performance compared to baseline methods, highlighting the effectiveness of C-LAIfO. To ensure reproducibility, we open source our code.
Authors: Xiaohua Feng, Chaochao Chen, Yuyuan Li, Li Zhang
Abstract: While generative models have made significant advancements in recent years, they also raise concerns such as privacy breaches and biases. Machine unlearning has emerged as a viable solution, aiming to remove specific training data, e.g., containing private information and bias, from models. In this paper, we study the machine unlearning problem in Image-to-Image (I2I) generative models. Previous studies mainly treat it as a single objective optimization problem, offering a solitary solution, thereby neglecting the varied user expectations towards the trade-off between complete unlearning and model utility. To address this issue, we propose a controllable unlearning framework that uses a control coefficient $\varepsilon$ to control the trade-off. We reformulate the I2I generative model unlearning problem into a $\varepsilon$-constrained optimization problem and solve it with a gradient-based method to find optimal solutions for unlearning boundaries. These boundaries define the valid range for the control coefficient. Within this range, every yielded solution is theoretically guaranteed with Pareto optimality. We also analyze the convergence rate of our framework under various control functions. Extensive experiments on two benchmark datasets across three mainstream I2I models demonstrate the effectiveness of our controllable unlearning framework.
Authors: Ran Yu, Haixin Yu, Shoujie Li, Huang Yan, Ziwu Song, Wenbo Ding
Abstract: Transparent objects are common in daily life, while their optical properties pose challenges for RGB-D cameras to capture accurate depth information. This issue is further amplified when these objects are hand-held, as hand occlusions further complicate depth estimation. For assistant robots, however, accurately perceiving hand-held transparent objects is critical to effective human-robot interaction. This paper presents a Hand-Aware Depth Restoration (HADR) method based on creating an implicit neural representation function from a single RGB-D image. The proposed method utilizes hand posture as an important guidance to leverage semantic and geometric information of hand-object interaction. To train and evaluate the proposed method, we create a high-fidelity synthetic dataset named TransHand-14K with a real-to-sim data generation scheme. Experiments show that our method has better performance and generalization ability compared with existing methods. We further develop a real-world human-to-robot handover system based on HADR, demonstrating its potential in human-robot interaction applications.
Authors: Elona Shatri, George Fazekas
Abstract: Optical Music Recognition (OMR) automates the transcription of musical notation from images into machine-readable formats like MusicXML, MEI, or MIDI, significantly reducing the costs and time of manual transcription. This study explores knowledge discovery in OMR by applying instance segmentation using Mask R-CNN to enhance the detection and delineation of musical symbols in sheet music. Unlike Optical Character Recognition (OCR), OMR must handle the intricate semantics of Common Western Music Notation (CWMN), where symbol meanings depend on shape, position, and context. Our approach leverages instance segmentation to manage the density and overlap of musical symbols, facilitating more precise information retrieval from music scores. Evaluations on the DoReMi and MUSCIMA++ datasets demonstrate substantial improvements, with our method achieving a mean Average Precision (mAP) of up to 59.70\% in dense symbol environments, achieving comparable results to object detection. Furthermore, using traditional computer vision techniques, we add a parallel step for staff detection to infer the pitch for the recognised symbols. This study emphasises the role of pixel-wise segmentation in advancing accurate music symbol recognition, contributing to knowledge discovery in OMR. Our findings indicate that instance segmentation provides more precise representations of musical symbols, particularly in densely populated scores, advancing OMR technology. We make our implementation, pre-processing scripts, trained models, and evaluation results publicly available to support further research and development.
Authors: Mingze Ni, Wei Liu
Abstract: In classification tasks, achieving a harmonious balance between exploration and precision is of paramount importance. To this end, this research introduces two novel deep learning models, SleepNet and DreamNet, to strike this balance. SleepNet seamlessly integrates supervised learning with unsupervised ``sleep" stages using pre-trained encoder models. Dedicated neurons within SleepNet are embedded in these unsupervised features, forming intermittent ``sleep" blocks that facilitate exploratory learning. Building upon the foundation of SleepNet, DreamNet employs full encoder-decoder frameworks to reconstruct the hidden states, mimicking the human "dreaming" process. This reconstruction process enables further exploration and refinement of the learned representations. Moreover, the principle ideas of our SleepNet and DreamNet are generic and can be applied to both computer vision and natural language processing downstream tasks. Through extensive empirical evaluations on diverse image and text datasets, SleepNet and DreanNet have demonstrated superior performance compared to state-of-the-art models, showcasing the strengths of unsupervised exploration and supervised precision afforded by our innovative approaches.
Authors: Andrew Lee, Ian Chuang, Ling-Yuan Chen, Iman Soltani
Abstract: We present InterACT: Inter-dependency aware Action Chunking with Hierarchical Attention Transformers, a novel imitation learning framework for bimanual manipulation that integrates hierarchical attention to capture inter-dependencies between dual-arm joint states and visual inputs. InterACT consists of a Hierarchical Attention Encoder and a Multi-arm Decoder, both designed to enhance information aggregation and coordination. The encoder processes multi-modal inputs through segment-wise and cross-segment attention mechanisms, while the decoder leverages synchronization blocks to refine individual action predictions, providing the counterpart's prediction as context. Our experiments on a variety of simulated and real-world bimanual manipulation tasks demonstrate that InterACT significantly outperforms existing methods. Detailed ablation studies validate the contributions of key components of our work, including the impact of CLS tokens, cross-segment encoders, and synchronization blocks.