Authors: Daniel Otero, Rafael Mateus
Abstract: Sewerage infrastructure is among the most expensive modern investments requiring time-intensive manual inspections by qualified personnel. Our study addresses the need for automated solutions without relying on large amounts of labeled data. We propose a novel application of Self-Supervised Learning (SSL) for sewer inspection that offers a scalable and cost-effective solution for defect detection. We achieve competitive results with a model that is at least 5 times smaller than other approaches found in the literature and obtain competitive performance with 10\% of the available data when training with a larger architecture. Our findings highlight the potential of SSL to revolutionize sewer maintenance in resource-limited settings.
Authors: Yiming Zhao, Taein Kwon, Paul Streli, Marc Pollefeys, Christian Holz
Abstract: Estimating touch contact and pressure in egocentric vision is a central task for downstream applications in Augmented Reality, Virtual Reality, as well as many robotic applications, because it provides precise physical insights into hand-object interaction and object manipulation. However, existing contact pressure datasets lack egocentric views and hand poses, which are essential for accurate estimation during in-situ operation, both for AR/VR interaction and robotic manipulation. In this paper, we introduce EgoPressure,a novel dataset of touch contact and pressure interaction from an egocentric perspective, complemented with hand pose meshes and fine-grained pressure intensities for each contact. The hand poses in our dataset are optimized using our proposed multi-view sequence-based method that processes footage from our capture rig of 8 accurately calibrated RGBD cameras. EgoPressure comprises 5.0 hours of touch contact and pressure interaction from 21 participants captured by a moving egocentric camera and 7 stationary Kinect cameras, which provided RGB images and depth maps at 30 Hz. In addition, we provide baselines for estimating pressure with different modalities, which will enable future developments and benchmarking on the dataset. Overall, we demonstrate that pressure and hand poses are complementary, which supports our intention to better facilitate the physical understanding of hand-object interactions in AR/VR and robotics research.
Authors: Yichun Li, Shuanglin Li, Syed Mohsen Naqvi
Abstract: Mental disorders are among the foremost contributors to the global healthcare challenge. Research indicates that timely diagnosis and intervention are vital in treating various mental disorders. However, the early somatization symptoms of certain mental disorders may not be immediately evident, often resulting in their oversight and misdiagnosis. Additionally, the traditional diagnosis methods incur high time and cost. Deep learning methods based on fMRI and EEG have improved the efficiency of the mental disorder detection process. However, the cost of the equipment and trained staff are generally huge. Moreover, most systems are only trained for a specific mental disorder and are not general-purpose. Recently, physiological studies have shown that there are some speech and facial-related symptoms in a few mental disorders (e.g., depression and ADHD). In this paper, we focus on the emotional expression features of mental disorders and introduce a multimodal mental disorder diagnosis system based on audio-visual information input. Our proposed system is based on spatial-temporal attention networks and innovative uses a less computationally intensive pre-train audio recognition network to fine-tune the video recognition module for better results. We also apply the unified system for multiple mental disorders (ADHD and depression) for the first time. The proposed system achieves over 80\% accuracy on the real multimodal ADHD dataset and achieves state-of-the-art results on the depression dataset AVEC 2014.
Authors: Abdullah Arafat Miah, Kaan Icer, Resit Sendag, Yu Bi
Abstract: Backdoor attacks pose a significant threat when using third-party data for deep learning development. In these attacks, data can be manipulated to cause a trained model to behave improperly when a specific trigger pattern is applied, providing the adversary with unauthorized advantages. While most existing works focus on designing trigger patterns in both visible and invisible to poison the victim class, they typically result in a single targeted class upon the success of the backdoor attack, meaning that the victim class can only be converted to another class based on the adversary predefined value. In this paper, we address this issue by introducing a novel sample-specific multi-targeted backdoor attack, namely NoiseAttack. Specifically, we adopt White Gaussian Noise (WGN) with various Power Spectral Densities (PSD) as our underlying triggers, coupled with a unique training strategy to execute the backdoor attack. This work is the first of its kind to launch a vision backdoor attack with the intent to generate multiple targeted classes with minimal input configuration. Furthermore, our extensive experimental results demonstrate that NoiseAttack can achieve a high attack success rate against popular network architectures and datasets, as well as bypass state-of-the-art backdoor detection methods. Our source code and experiments are available at https://github.com/SiSL-URI/NoiseAttack/tree/main.
Authors: Saeid Asgari Taghanaki, Joseph Lambourne, Alana Mongkhounsavath
Abstract: Large foundation models have revolutionized the field, yet challenges remain in optimizing multi-modal models for specialized visual tasks. We propose a novel, generalizable methodology to identify preferred image distributions for black-box Vision-Language Models (VLMs) by measuring output consistency across varied input prompts. Applying this to different rendering types of 3D objects, we demonstrate its efficacy across various domains requiring precise interpretation of complex structures, with a focus on Computer-Aided Design (CAD) as an exemplar field. We further refine VLM outputs using in-context learning with human feedback, significantly enhancing explanation quality. To address the lack of benchmarks in specialized domains, we introduce CAD-VQA, a new dataset for evaluating VLMs on CAD-related visual question answering tasks. Our evaluation of state-of-the-art VLMs on CAD-VQA establishes baseline performance levels, providing a framework for advancing VLM capabilities in complex visual reasoning tasks across various fields requiring expert-level visual interpretation. We release the dataset and evaluation codes at \url{https://github.com/asgsaeid/cad_vqa}.
Authors: Yichun Li, Yuxing Yang, Syed Nohsen Naqvi
Abstract: Attention Deficit Hyperactivity Disorder (ADHD) causes significant impairment in various domains. Early diagnosis of ADHD and treatment could significantly improve the quality of life and functioning. Recently, machine learning methods have improved the accuracy and efficiency of the ADHD diagnosis process. However, the cost of the equipment and trained staff required by the existing methods are generally huge. Therefore, we introduce the video-based frame-level action recognition network to ADHD diagnosis for the first time. We also record a real multi-modal ADHD dataset and extract three action classes from the video modality for ADHD diagnosis. The whole process data have been reported to CNTW-NHS Foundation Trust, which would be reviewed by medical consultants/professionals and will be made public in due course.
Authors: Yichun Li, Syes Mohsen Naqvi, Rajesh Nair
Abstract: Demand for ADHD diagnosis and treatment is increasing significantly and the existing services are unable to meet the demand in a timely manner. In this work, we introduce a novel action recognition method for ADHD diagnosis by identifying and analysing raw video recordings. Our main contributions include 1) designing and implementing a test focusing on the attention and hyperactivity/impulsivity of participants, recorded through three cameras; 2) implementing a novel machine learning ADHD diagnosis system based on action recognition neural networks for the first time; 3) proposing classification criteria to provide diagnosis results and analysis of ADHD action characteristics.
Authors: Sanjita Prajapati, Tanu Singh, Chinmay Hegde, Pranamesh Chakraborty
Abstract: Recent developments in vision language models (VLM) have shown great potential for diverse applications related to image understanding. In this study, we have explored state-of-the-art VLM models for vision-based transportation engineering tasks such as image classification and object detection. The image classification task involves congestion detection and crack identification, whereas, for object detection, helmet violations were identified. We have applied open-source models such as CLIP, BLIP, OWL-ViT, Llava-Next, and closed-source GPT-4o to evaluate the performance of these state-of-the-art VLM models to harness the capabilities of language understanding for vision-based transportation tasks. These tasks were performed by applying zero-shot prompting to the VLM models, as zero-shot prompting involves performing tasks without any training on those tasks. It eliminates the need for annotated datasets or fine-tuning for specific tasks. Though these models gave comparative results with benchmark Convolutional Neural Networks (CNN) models in the image classification tasks, for object localization tasks, it still needs improvement. Therefore, this study provides a comprehensive evaluation of the state-of-the-art VLM models highlighting the advantages and limitations of the models, which can be taken as the baseline for future improvement and wide-scale implementation.
Authors: Lewis Mason, Mark Martinez
Abstract: K-Origins is a neural network layer designed to improve image-based network performances when learning colour, or intensities, is beneficial. Over 250 encoder-decoder convolutional networks are trained and tested on 16-bit synthetic data, demonstrating that K-Origins improves semantic segmentation accuracy in two scenarios: object detection with low signal-to-noise ratios, and segmenting multiple objects that are identical in shape but vary in colour. K-Origins generates output features from the input features, $\textbf{X}$, by the equation $\textbf{Y}_k = \textbf{X}-\textbf{J}\cdot w_k$ for each trainable parameter $w_k$, where $\textbf{J}$ is a matrix of ones. Additionally, networks with varying receptive fields were trained to determine optimal network depths based on the dimensions of target classes, suggesting that receptive field lengths should exceed object sizes. By ensuring a sufficient receptive field length and incorporating K-Origins, we can achieve better semantic network performance.
Authors: Suhang You, Sanyukta Adap, Siddhesh Thakur, Bhakti Baheti, Spyridon Bakas
Abstract: Time to biochemical recurrence in prostate cancer is essential for prognostic monitoring of the progression of patients after prostatectomy, which assesses the efficacy of the surgery. In this work, we proposed to leverage multiple instance learning through a two-stage ``thinking fast \& slow'' strategy for the time to recurrence (TTR) prediction. The first (``thinking fast'') stage finds the most relevant WSI area for biochemical recurrence and the second (``thinking slow'') stage leverages higher resolution patches to predict TTR. Our approach reveals a mean C-index ($Ci$) of 0.733 ($\theta=0.059$) on our internal validation and $Ci=0.603$ on the LEOPARD challenge validation set. Post hoc attention visualization shows that the most attentive area contributes to the TTR prediction.
Authors: Gonglin Chen, Jinsen Wu, Haiwei Chen, Wenbin Teng, Zhiyuan Gao, Andrew Feng, Rongjun Qin, Yajie Zhao
Abstract: Establishing consistent and dense correspondences across multiple images is crucial for Structure from Motion (SfM) systems. Significant view changes, such as air-to-ground with very sparse view overlap, pose an even greater challenge to the correspondence solvers. We present a novel optimization-based approach that significantly enhances existing feature matching methods by introducing geometry cues in addition to color cues. This helps fill gaps when there is less overlap in large-scale scenarios. Our method formulates geometric verification as an optimization problem, guiding feature matching within detector-free methods and using sparse correspondences from detector-based methods as anchor points. By enforcing geometric constraints via the Sampson Distance, our approach ensures that the denser correspondences from detector-free methods are geometrically consistent and more accurate. This hybrid strategy significantly improves correspondence density and accuracy, mitigates multi-view inconsistencies, and leads to notable advancements in camera pose accuracy and point cloud density. It outperforms state-of-the-art feature matching methods on benchmark datasets and enables feature matching in challenging extreme large-scale settings.
Authors: Harish Babu Manogaran, M. Maruf, Arka Daw, Kazi Sajeed Mehrab, Caleb Patrick Charpentier, Josef C. Uyeda, Wasila Dahdul, Matthew J Thompson, Elizabeth G Campolongo, Kaiya L Provost, Paula M. Mabee, Hilmar Lapp, Anuj Karpatne
Abstract: A grand challenge in biology is to discover evolutionary traits - features of organisms common to a group of species with a shared ancestor in the tree of life (also referred to as phylogenetic tree). With the growing availability of image repositories in biology, there is a tremendous opportunity to discover evolutionary traits directly from images in the form of a hierarchy of prototypes. However, current prototype-based methods are mostly designed to operate over a flat structure of classes and face several challenges in discovering hierarchical prototypes, including the issue of learning over-specific features at internal nodes. To overcome these challenges, we introduce the framework of Hierarchy aligned Commonality through Prototypical Networks (HComP-Net). We empirically show that HComP-Net learns prototypes that are accurate, semantically consistent, and generalizable to unseen species in comparison to baselines on birds, butterflies, and fishes datasets. The code and datasets are available at https://github.com/Imageomics/HComPNet.
Authors: Xuelu Feng, Yunsheng Li, Dongdong Chen, Chunming Qiao, Junsong Yuan, Lu Yuan, Gang Hua
Abstract: We introduce pluralistic salient object detection (PSOD), a novel task aimed at generating multiple plausible salient segmentation results for a given input image. Unlike conventional SOD methods that produce a single segmentation mask for salient objects, this new setting recognizes the inherent complexity of real-world images, comprising multiple objects, and the ambiguity in defining salient objects due to different user intentions. To study this task, we present two new SOD datasets "DUTS-MM" and "DUS-MQ", along with newly designed evaluation metrics. DUTS-MM builds upon the DUTS dataset but enriches the ground-truth mask annotations from three aspects which 1) improves the mask quality especially for boundary and fine-grained structures; 2) alleviates the annotation inconsistency issue; and 3) provides multiple ground-truth masks for images with saliency ambiguity. DUTS-MQ consists of approximately 100K image-mask pairs with human-annotated preference scores, enabling the learning of real human preferences in measuring mask quality. Building upon these two datasets, we propose a simple yet effective pluralistic SOD baseline based on a Mixture-of-Experts (MOE) design. Equipped with two prediction heads, it simultaneously predicts multiple masks using different query prompts and predicts human preference scores for each mask candidate. Extensive experiments and analyses underscore the significance of our proposed datasets and affirm the effectiveness of our PSOD framework.
Authors: Siyi Chen, Minkyu Choi, Zesen Zhao, Kuan Han, Qing Qu, Zhongming Liu
Abstract: Taking inspiration from physical motion, we present a new self-supervised dynamics learning strategy for videos: Video Time-Differentiation for Instance Discrimination (ViDiDi). ViDiDi is a simple and data-efficient strategy, readily applicable to existing self-supervised video representation learning frameworks based on instance discrimination. At its core, ViDiDi observes different aspects of a video through various orders of temporal derivatives of its frame sequence. These derivatives, along with the original frames, support the Taylor series expansion of the underlying continuous dynamics at discrete times, where higher-order derivatives emphasize higher-order motion features. ViDiDi learns a single neural network that encodes a video and its temporal derivatives into consistent embeddings following a balanced alternating learning algorithm. By learning consistent representations for original frames and derivatives, the encoder is steered to emphasize motion features over static backgrounds and uncover the hidden dynamics in original frames. Hence, video representations are better separated by dynamic features. We integrate ViDiDi into existing instance discrimination frameworks (VICReg, BYOL, and SimCLR) for pretraining on UCF101 or Kinetics and test on standard benchmarks including video retrieval, action recognition, and action detection. The performances are enhanced by a significant margin without the need for large models or extensive datasets.
Authors: Siyi Chen, Huijie Zhang, Minzhe Guo, Yifu Lu, Peng Wang, Qing Qu
Abstract: Recently, diffusion models have emerged as a powerful class of generative models. Despite their success, there is still limited understanding of their semantic spaces. This makes it challenging to achieve precise and disentangled image generation without additional training, especially in an unsupervised way. In this work, we improve the understanding of their semantic spaces from intriguing observations: among a certain range of noise levels, (1) the learned posterior mean predictor (PMP) in the diffusion model is locally linear, and (2) the singular vectors of its Jacobian lie in low-dimensional semantic subspaces. We provide a solid theoretical basis to justify the linearity and low-rankness in the PMP. These insights allow us to propose an unsupervised, single-step, training-free LOw-rank COntrollable image editing (LOCO Edit) method for precise local editing in diffusion models. LOCO Edit identified editing directions with nice properties: homogeneity, transferability, composability, and linearity. These properties of LOCO Edit benefit greatly from the low-dimensional semantic subspace. Our method can further be extended to unsupervised or text-supervised editing in various text-to-image diffusion models (T-LOCO Edit). Finally, extensive empirical experiments demonstrate the effectiveness and efficiency of LOCO Edit. The codes will be released at https://github.com/ChicyChen/LOCO-Edit.
Authors: Jie Fu (University of the Arts London, Creative Computing Institute, London, United Kingdom), Shun Fu (Bloks Technology Company, Shanghai, China), Mick Grierson (University of the Arts London, Creative Computing Institute, London, United Kingdom)
Abstract: With the rapid development of VR technology, the demand for high-quality 3D models is increasing. Traditional methods struggle with efficiency and quality in large-scale customization. This paper introduces a deep-learning framework that generates high-precision 3D coral models from a single image. Using the Coral dataset, the framework extracts geometric and texture features, performs 3D reconstruction, and optimizes design and material blending. Advanced optimization and polygon count control ensure shape accuracy, detail retention, and flexible output for various complexities, catering to high-quality rendering and real-time interaction needs.The project incorporates Explainable AI (XAI) to transform AI-generated models into interactive "artworks," best viewed in VR and XR. This enhances model interpretability and human-machine collaboration. Real-time feedback in VR interactions displays information like coral species and habitat, enriching user experience. The generated models surpass traditional methods in detail, visual quality, and efficiency. This research offers an intelligent approach to 3D content creation for VR, lowering production barriers, and promoting widespread VR applications. Additionally, integrating XAI provides new insights into AI-generated visual content and advances research in 3D vision interpretability.
Authors: Huasong Han, Kaixuan Zhou, Xiaoxiao Long, Yusen Wang, Chunxia Xiao
Abstract: We propose GGS, a Generalizable Gaussian Splatting method for Autonomous Driving which can achieve realistic rendering under large viewpoint changes. Previous generalizable 3D gaussian splatting methods are limited to rendering novel views that are very close to the original pair of images, which cannot handle large differences in viewpoint. Especially in autonomous driving scenarios, images are typically collected from a single lane. The limited training perspective makes rendering images of a different lane very challenging. To further improve the rendering capability of GGS under large viewpoint changes, we introduces a novel virtual lane generation module into GSS method to enables high-quality lane switching even without a multi-lane dataset. Besides, we design a diffusion loss to supervise the generation of virtual lane image to further address the problem of lack of data in the virtual lanes. Finally, we also propose a depth refinement module to optimize depth estimation in the GSS model. Extensive validation of our method, compared to existing approaches, demonstrates state-of-the-art performance.
Authors: Tuyen Tran, Thao Minh Le, Hung Tran, Truyen Tran
Abstract: Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their ability to exploit the complementary advantages across modalities. Recent studies focus on combining these two modalities using simple feature fusion techniques. However, due to the inherent disparities in representation between these input modalities, designing a unified neural network architecture to effectively leverage their complementary information remains a significant challenge. To address this, we propose a comprehensive multimodal framework for robust video-based human activity recognition. Our key contribution is the introduction of a novel compositional query machine, called COMPUTER ($\textbf{COMP}ositional h\textbf{U}man-cen\textbf{T}ric qu\textbf{ER}y$ machine), a generic neural architecture that models the interactions between a human of interest and its surroundings in both space and time. Thanks to its versatile design, COMPUTER can be leveraged to distill distinctive representations for various input modalities. Additionally, we introduce a consistency loss that enforces agreement in prediction between modalities, exploiting the complementary information from multimodal inputs for robust human movement recognition. Through extensive experiments on action localization and group activity recognition tasks, our approach demonstrates superior performance when compared with state-of-the-art methods. Our code is available at: https://github.com/tranxuantuyen/COMPUTER.
Authors: Xiongkun Linghu, Jiangyong Huang, Xuesong Niu, Xiaojian Ma, Baoxiong Jia, Siyuan Huang
Abstract: Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding are limited in data modality, diversity, scale, and task scope. To address these limitations, we propose Multi-modal Situated Question Answering (MSQA), a large-scale multi-modal situated reasoning dataset, scalably collected leveraging 3D scene graphs and vision-language models (VLMs) across a diverse range of real-world 3D scenes. MSQA includes 251K situated question-answering pairs across 9 distinct question categories, covering complex scenarios within 3D scenes. We introduce a novel interleaved multi-modal input setting in our benchmark to provide text, image, and point cloud for situation and question description, resolving ambiguity in previous single-modality convention (e.g., text). Additionally, we devise the Multi-modal Situated Next-step Navigation (MSNN) benchmark to evaluate models' situated reasoning for navigation. Comprehensive evaluations on MSQA and MSNN highlight the limitations of existing vision-language models and underscore the importance of handling multi-modal interleaved inputs and situation modeling. Experiments on data scaling and cross-domain transfer further demonstrate the efficacy of leveraging MSQA as a pre-training dataset for developing more powerful situated reasoning models.
Authors: Jiaqi Li, Pingfan Jia, Jiaxing Chen, Jiaxi Liu, Lei He
Abstract: In recent years, significant academic advancements have been made in the field of autonomous vehicles, with Local maps emerging as a crucial component of autonomous driving technology. Local maps not only provide intricate details of road networks but also serve as fundamental inputs for critical tasks such as vehicle localization, navigation, and decision-making. Given the characteristics of SD map (Standard Definition Map), which include low cost, ease of acquisition, and high versatility, perception methods that integrate SD map as prior information have demonstrated significant potential in the field of Local map perception. The purpose of this paper is to provide researchers with a comprehensive overview and summary of the latest advancements in the integration of SD map as prior information for Local map perception methods. This review begins by introducing the task definition and general pipeline of local map perception methods that incorporate SD maps as prior information, along with relevant public datasets. And then it focuses on the representation and encoding methods of multi-source information, as well as the methods for fusing multi-source information. In response to this burgeoning trend, this article presents a comprehensive and meticulous overview of the diverse research efforts in this particular field. Finally, the article addresses pertinent issues and future challenges with the aim of guiding researchers in understanding the current trends and methodologies prevalent in the field.
Authors: Weiwei Tian, Xinyu Huang, Junlin Hou, Caiyue Ren, Longquan Jiang, Rui-Wei Zhao, Gang Jin, Yuejie Zhang, Daoying Geng
Abstract: Owing to a large amount of multi-modal data in modern medical systems, such as medical images and reports, Medical Vision-Language Pre-training (Med-VLP) has demonstrated incredible achievements in coarse-grained downstream tasks (i.e., medical classification, retrieval, and visual question answering). However, the problem of transferring knowledge learned from Med-VLP to fine-grained multi-organ segmentation tasks has barely been investigated. Multi-organ segmentation is challenging mainly due to the lack of large-scale fully annotated datasets and the wide variation in the shape and size of the same organ between individuals with different diseases. In this paper, we propose a novel pre-training & fine-tuning framework for Multi-Organ Segmentation by harnessing Medical repOrt Supervision (MOSMOS). Specifically, we first introduce global contrastive learning to maximally align the medical image-report pairs in the pre-training stage. To remedy the granularity discrepancy, we further leverage multi-label recognition to implicitly learn the semantic correspondence between image pixels and organ tags. More importantly, our pre-trained models can be transferred to any segmentation model by introducing the pixel-tag attention maps. Different network settings, i.e., 2D U-Net and 3D UNETR, are utilized to validate the generalization. We have extensively evaluated our approach using different diseases and modalities on BTCV, AMOS, MMWHS, and BRATS datasets. Experimental results in various settings demonstrate the effectiveness of our framework. This framework can serve as the foundation to facilitate future research on automatic annotation tasks under the supervision of medical reports.
Authors: Aishwarya Agarwal, Srikrishna Karanam, Balaji Vasan Srinivasan
Abstract: We consider the problem of independently, in a disentangled fashion, controlling the outputs of text-to-image diffusion models with color and style attributes of a user-supplied reference image. We present the first training-free, test-time-only method to disentangle and condition text-to-image models on color and style attributes from reference image. To realize this, we propose two key innovations. Our first contribution is to transform the latent codes at inference time using feature transformations that make the covariance matrix of current generation follow that of the reference image, helping meaningfully transfer color. Next, we observe that there exists a natural disentanglement between color and style in the LAB image space, which we exploit to transform the self-attention feature maps of the image being generated with respect to those of the reference computed from its L channel. Both these operations happen purely at test time and can be done independently or merged. This results in a flexible method where color and style information can come from the same reference image or two different sources, and a new generation can seamlessly fuse them in either scenario.
Authors: Yilong Chen, Zongyi Xu, Xiaoshui Huang, Shanshan Zhao, Xinqi Jiang, Xinyu Gao, Xinbo Gao
Abstract: Compared to single-modal knowledge distillation, cross-modal knowledge distillation faces more severe challenges due to domain gaps between modalities. Although various methods have proposed various solutions to overcome these challenges, there is still limited research on how domain gaps affect cross-modal knowledge distillation. This paper provides an in-depth analysis and evaluation of this issue. We first introduce the Non-Target Divergence Hypothesis (NTDH) to reveal the impact of domain gaps on cross-modal knowledge distillation. Our key finding is that domain gaps between modalities lead to distribution differences in non-target classes, and the smaller these differences, the better the performance of cross-modal knowledge distillation. Subsequently, based on Vapnik-Chervonenkis (VC) theory, we derive the upper and lower bounds of the approximation error for cross-modal knowledge distillation, thereby theoretically validating the NTDH. Finally, experiments on five cross-modal datasets further confirm the validity, generalisability, and applicability of the NTDH.
Authors: Hoang Khanh Lam, Kahandakanaththage Maduni Pramuditha Perera
Abstract: A solution was made available for Korean Food lovers who have dietary restrictions to identify the Korean food before consuming. Just by uploading a clear photo of the dish, people can get to know what they are eating. Image processing techniques together with machine learning helped to come up with this solution.
Authors: Stefano Esposito, Anpei Chen, Christian Reiser, Samuel Rota Bul\`o, Lorenzo Porzi, Katja Schwarz, Christian Richardt, Michael Zollh\"ofer, Peter Kontschieder, Andreas Geiger
Abstract: High-quality real-time view synthesis methods are based on volume rendering, splatting, or surface rendering. While surface-based methods generally are the fastest, they cannot faithfully model fuzzy geometry like hair. In turn, alpha-blending techniques excel at representing fuzzy materials but require an unbounded number of samples per ray (P1). Further overheads are induced by empty space skipping in volume rendering (P2) and sorting input primitives in splatting (P3). These problems are exacerbated on low-performance graphics hardware, e.g. on mobile devices. We present a novel representation for real-time view synthesis where the (P1) number of sampling locations is small and bounded, (P2) sampling locations are efficiently found via rasterization, and (P3) rendering is sorting-free. We achieve this by representing objects as semi-transparent multi-layer meshes, rendered in fixed layer order from outermost to innermost. We model mesh layers as SDF shells with optimal spacing learned during training. After baking, we fit UV textures to the corresponding meshes. We show that our method can represent challenging fuzzy objects while achieving higher frame rates than volume-based and splatting-based methods on low-end and mobile devices.
Authors: Yunfeng Diao, Baiqi Wu, Ruixuan Zhang, Ajian Liu, Xingxing Wei, Meng Wang, He Wang
Abstract: Skeletal sequences, as well-structured representations of human behaviors, are crucial in Human Activity Recognition (HAR). The transferability of adversarial skeletal sequences enables attacks in real-world HAR scenarios, such as autonomous driving, intelligent surveillance, and human-computer interactions. However, existing Skeleton-based HAR (S-HAR) attacks exhibit weak adversarial transferability and, therefore, cannot be considered true transfer-based S-HAR attacks. More importantly, the reason for this failure remains unclear. In this paper, we study this phenomenon through the lens of loss surface, and find that its sharpness contributes to the poor transferability in S-HAR. Inspired by this observation, we assume and empirically validate that smoothening the rugged loss landscape could potentially improve adversarial transferability in S-HAR. To this end, we propose the first Transfer-based Attack on Skeletal Action Recognition, TASAR. TASAR explores the smoothed model posterior without re-training the pre-trained surrogates, which is achieved by a new post-train Dual Bayesian optimization strategy. Furthermore, unlike previous transfer-based attacks that treat each frame independently and overlook temporal coherence within sequences, TASAR incorporates motion dynamics into the Bayesian attack gradient, effectively disrupting the spatial-temporal coherence of S-HARs. To exhaustively evaluate the effectiveness of existing methods and our method, we build the first large-scale robust S-HAR benchmark, comprising 7 S-HAR models, 10 attack methods, 3 S-HAR datasets and 2 defense models. Extensive results demonstrate the superiority of TASAR. Our benchmark enables easy comparisons for future studies, with the code available in the supplementary material.
Authors: Cho-Ying Wu, Yiqi Zhong, Junying Wang, Ulrich Neumann
Abstract: Indoor robots rely on depth to perform tasks like navigation or obstacle detection, and single-image depth estimation is widely used to assist perception. Most indoor single-image depth prediction focuses less on model generalizability to unseen datasets, concerned with in-the-wild robustness for system deployment. This work leverages gradient-based meta-learning to gain higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied meta-learning of image classification associated with explicit class labels, no explicit task boundaries exist for continuous depth values tied to highly varying indoor environments regarding object arrangement and scene composition. We propose fine-grained task that treats each RGB-D mini-batch as a task in our meta-learning formulation. We first show that our method on limited data induces a much better prior (max 27.8% in RMSE). Then, finetuning on meta-learned initialization consistently outperforms baselines without the meta approach. Aiming at generalization, we propose zero-shot cross-dataset protocols and validate higher generalizability induced by our meta-initialization, as a simple and useful plugin to many existing depth estimation methods. The work at the intersection of depth and meta-learning potentially drives both research to step closer to practical robotic and machine perception usage.
Authors: Duy Le Dinh Anh, Kim Hoang Tran, Ngan Hoang Le
Abstract: While Multi-Object Tracking (MOT) has made substantial advancements, it is limited by heavy reliance on prior knowledge and limited to predefined categories. In contrast, Generic Multiple Object Tracking (GMOT), tracking multiple objects with similar appearance, requires less prior information about the targets but faces challenges with variants like viewpoint, lighting, occlusion, and resolution. Our contributions commence with the introduction of the \textbf{\text{Refer-GMOT dataset}} a collection of videos, each accompanied by fine-grained textual descriptions of their attributes. Subsequently, we introduce a novel text prompt-based open-vocabulary GMOT framework, called \textbf{\text{TP-GMOT}}, which can track never-seen object categories with zero training examples. Within \text{TP-GMOT} framework, we introduce two novel components: (i) {\textbf{\text{TP-OD}}, an object detection by a textual prompt}, for accurately detecting unseen objects with specific characteristics. (ii) Motion-Appearance Cost SORT \textbf{\text{MAC-SORT}}, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking multiple generic objects with high similarity. Our contributions are benchmarked on the \text{Refer-GMOT} dataset for GMOT task. Additionally, to assess the generalizability of the proposed \text{TP-GMOT} framework and the effectiveness of \text{MAC-SORT} tracker, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models will be publicly available at: https://fsoft-aic.github.io/TP-GMOT
Authors: Jialong Li, Zhicheng Zhang, Yunwei Chen, Qiqi Lu, Ye Wu, Xiaoming Liu, QianJin Feng, Yanqiu Feng, Xinyuan Zhang
Abstract: Diffusion tensor imaging (DTI) holds significant importance in clinical diagnosis and neuroscience research. However, conventional model-based fitting methods often suffer from sensitivity to noise, leading to decreased accuracy in estimating DTI parameters. While traditional data-driven deep learning methods have shown potential in terms of accuracy and efficiency, their limited generalization to out-of-training-distribution data impedes their broader application due to the diverse scan protocols used across centers, scanners, and studies. This work aims to tackle these challenges and promote the use of DTI by introducing a data-driven optimization-based method termed DoDTI. DoDTI combines the weighted linear least squares fitting algorithm and regularization by denoising technique. The former fits DW images from diverse acquisition settings into diffusion tensor field, while the latter applies a deep learning-based denoiser to regularize the diffusion tensor field instead of the DW images, which is free from the limitation of fixed-channel assignment of the network. The optimization object is solved using the alternating direction method of multipliers and then unrolled to construct a deep neural network, leveraging a data-driven strategy to learn network parameters. Extensive validation experiments are conducted utilizing both internally simulated datasets and externally obtained in-vivo datasets. The results, encompassing both qualitative and quantitative analyses, showcase that the proposed method attains state-of-the-art performance in DTI parameter estimation. Notably, it demonstrates superior generalization, accuracy, and efficiency, rendering it highly reliable for widespread application in the field.
Authors: Li Liu, Ruijie Zhu, Jiacheng Deng, Ziyang Song, Wenfei Yang, Tianzhu Zhang
Abstract: Monocular depth estimation aims to infer a dense depth map from a single image, which is a fundamental and prevalent task in computer vision. Many previous works have shown impressive depth estimation results through carefully designed network structures, but they usually ignore the planar information and therefore perform poorly in low-texture areas of indoor scenes. In this paper, we propose Plane2Depth, which adaptively utilizes plane information to improve depth prediction within a hierarchical framework. Specifically, in the proposed plane guided depth generator (PGDG), we design a set of plane queries as prototypes to softly model planes in the scene and predict per-pixel plane coefficients. Then the predicted plane coefficients can be converted into metric depth values with the pinhole camera model. In the proposed adaptive plane query aggregation (APGA) module, we introduce a novel feature interaction approach to improve the aggregation of multi-scale plane features in a top-down manner. Extensive experiments show that our method can achieve outstanding performance, especially in low-texture or repetitive areas. Furthermore, under the same backbone network, our method outperforms the state-of-the-art methods on the NYU-Depth-v2 dataset, achieves competitive results with state-of-the-art methods KITTI dataset and can be generalized to unseen scenes effectively.
Authors: Jinhao Chai, Shiyi Mu, Shugong Xu
Abstract: Understanding other drivers' intentions is crucial for safe driving. The role of taillights in conveying these intentions is underemphasized in current autonomous driving systems. Accurately identifying taillight signals is essential for predicting vehicle behavior and preventing collisions. Open-source taillight datasets are scarce, often small and inconsistently annotated. To address this gap, we introduce a new large-scale taillight dataset called TLD. Sourced globally, our dataset covers diverse traffic scenarios. To our knowledge, TLD is the first dataset to separately annotate brake lights and turn signals in real driving scenarios. We collected 17.78 hours of driving videos from the internet. This dataset consists of 152k labeled image frames sampled at a rate of 2 Hz, along with 1.5 million unlabeled frames interspersed throughout. Additionally, we have developed a two-stage vehicle light detection model consisting of two primary modules: a vehicle detector and a taillight classifier. Initially, YOLOv10 and DeepSORT captured consecutive vehicle images over time. Subsequently, the two classifiers work simultaneously to determine the states of the brake lights and turn signals. A post-processing procedure is then used to eliminate noise caused by misidentifications and provide the taillight states of the vehicle within a given time frame. Our method shows exceptional performance on our dataset, establishing a benchmark for vehicle taillight detection. The dataset is available at https://huggingface.co/datasets/ChaiJohn/TLD/tree/main
URLs: https://huggingface.co/datasets/ChaiJohn/TLD/tree/main
Authors: Sumin Son, Hyesong Choi, Dongbo Min
Abstract: Masked Image Modeling (MIM) techniques have redefined the landscape of computer vision, enabling pre-trained models to achieve exceptional performance across a broad spectrum of tasks. Despite their success, the full potential of MIM-based methods in dense prediction tasks, particularly in depth estimation, remains untapped. Existing MIM approaches primarily rely on single-image inputs, which makes it challenging to capture the crucial structured information, leading to suboptimal performance in tasks requiring fine-grained feature representation. To address these limitations, we propose SG-MIM, a novel Structured knowledge Guided Masked Image Modeling framework designed to enhance dense prediction tasks by utilizing structured knowledge alongside images. SG-MIM employs a lightweight relational guidance framework, allowing it to guide structured knowledge individually at the feature level rather than naively combining at the pixel level within the same architecture, as is common in traditional multi-modal pre-training methods. This approach enables the model to efficiently capture essential information while minimizing discrepancies between pre-training and downstream tasks. Furthermore, SG-MIM employs a selective masking strategy to incorporate structured knowledge, maximizing the synergy between general representation learning and structured knowledge-specific learning. Our method requires no additional annotations, making it a versatile and efficient solution for a wide range of applications. Our evaluations on the KITTI, NYU-v2, and ADE20k datasets demonstrate SG-MIM's superiority in monocular depth estimation and semantic segmentation.
Authors: Wen Li, Muyuan Fang, Cheng Zou, Biao Gong, Ruobing Zheng, Meng Wang, Jingdong Chen, Ming Yang
Abstract: Despite the burst of innovative methods for controlling the diffusion process, effectively controlling image styles in text-to-image generation remains a challenging task. Many adapter-based methods impose image representation conditions on the denoising process to accomplish image control. However these conditions are not aligned with the word embedding space, leading to interference between image and text control conditions and the potential loss of semantic information from the text prompt. Addressing this issue involves two key challenges. Firstly, how to inject the style representation without compromising the effectiveness of text representation in control. Secondly, how to obtain the accurate style representation from a single reference image. To tackle these challenges, we introduce StyleTokenizer, a zero-shot style control image generation method that aligns style representation with text representation using a style tokenizer. This alignment effectively minimizes the impact on the effectiveness of text prompts. Furthermore, we collect a well-labeled style dataset named Style30k to train a style feature extractor capable of accurately representing style while excluding other content information. Experimental results demonstrate that our method fully grasps the style characteristics of the reference image, generating appealing images that are consistent with both the target image style and text prompt. The code and dataset are available at https://github.com/alipay/style-tokenizer.
Authors: Soomin Kim, Hyesong Choi, Jihye Ahn, Dongbo Min
Abstract: Unlike other vision tasks where Transformer-based approaches are becoming increasingly common, stereo depth estimation is still dominated by convolution-based approaches. This is mainly due to the limited availability of real-world ground truth for stereo matching, which is a limiting factor in improving the performance of Transformer-based stereo approaches. In this paper, we propose UniTT-Stereo, a method to maximize the potential of Transformer-based stereo architectures by unifying self-supervised learning used for pre-training with stereo matching framework based on supervised learning. To be specific, we explore the effectiveness of reconstructing features of masked portions in an input image and at the same time predicting corresponding points in another image from the perspective of locality inductive bias, which is crucial in training models with limited training data. Moreover, to address these challenging tasks of reconstruction-and-prediction, we present a new strategy to vary a masking ratio when training the stereo model with stereo-tailored losses. State-of-the-art performance of UniTT-Stereo is validated on various benchmarks such as ETH3D, KITTI 2012, and KITTI 2015 datasets. Lastly, to investigate the advantages of the proposed approach, we provide a frequency analysis of feature maps and the analysis of locality inductive bias based on attention maps.
Authors: Weichao Pan, Xu Wang, Wenqing Huan
Abstract: Unmanned Aerial Vehicle (UAV)-based Road Damage Detection (RDD) is important for daily maintenance and safety in cities, especially in terms of significantly reducing labor costs. However, current UAV-based RDD research is still faces many challenges. For example, the damage with irregular size and direction, the masking of damage by the background, and the difficulty of distinguishing damage from the background significantly affect the ability of UAV to detect road damage in daily inspection. To solve these problems and improve the performance of UAV in real-time road damage detection, we design and propose three corresponding modules: a feature extraction module that flexibly adapts to shape and background; a module that fuses multiscale perception and adapts to shape and background ; an efficient downsampling module. Based on these modules, we designed a multi-scale, adaptive road damage detection model with the ability to automatically remove background interference, called Dynamic Scale-Aware Fusion Detection Model (RT-DSAFDet). Experimental results on the UAV-PDD2023 public dataset show that our model RT-DSAFDet achieves a mAP50 of 54.2%, which is 11.1% higher than that of YOLOv10-m, an efficient variant of the latest real-time object detection model YOLOv10, while the amount of parameters is reduced to 1.8M and FLOPs to 4.6G, with a decreased by 88% and 93%, respectively. Furthermore, on the large generalized object detection public dataset MS COCO2017 also shows the superiority of our model with mAP50-95 is the same as YOLOv9-t, but with 0.5% higher mAP50, 10% less parameters volume, and 40% less FLOPs.
Authors: Kangkai Zhang, Shiming Ge, Ruixin Shi, Dan Zeng
Abstract: Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a low-resolution student model by aligning cross-resolution representations. However, these approaches still face limitations in adapting to the situation where the recognized objects exhibit significant representation discrepancies between training and testing images. In this study, we propose a cross-resolution relational contrastive distillation approach to facilitate low-resolution object recognition. Our approach enables the student model to mimic the behavior of a well-trained teacher model which delivers high accuracy in identifying high-resolution objects. To extract sufficient knowledge, the student learning is supervised with contrastive relational distillation loss, which preserves the similarities in various relational structures in contrastive representation space. In this manner, the capability of recovering missing details of familiar low-resolution objects can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution object classification and low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.
Authors: Paul Johannes Claasen, Johan Pieter de Villiers
Abstract: A novel MOT algorithm, IMM Joint Homography State Estimation (IMM-JHSE), is proposed. By jointly modelling the camera projection matrix as part of track state vectors, IMM-JHSE removes the explicit influence of camera motion compensation techniques on predicted track position states, which was prevalent in previous approaches. Expanding upon this, static and dynamic camera motion models are combined through the use of an IMM filter. A simple bounding box motion model is used to predict bounding box positions to incorporate image plane information. In addition to applying an IMM to camera motion, a non-standard IMM approach is applied where bounding-box-based BIoU scores are mixed with ground-plane-based Mahalanobis distances in an IMM-like fashion to perform association only. Finally, IMM-JHSE makes use of dynamic process and measurement noise estimation techniques. IMM-JHSE improves upon related techniques on the DanceTrack and KITTI-car datasets, increasing HOTA by 2.64 and 2.11, respectively, while offering competitive performance on the MOT17, MOT20 and KITTI-pedestrian datasets.
Authors: Florian Blume, Runfeng Qu, Pia Bideau, Martin Maier, Rasha Abdel Rahman, Olaf Hellwich
Abstract: Facial expression perception in humans inherently relies on prior knowledge and contextual cues, contributing to efficient and flexible processing. For instance, multi-modal emotional context (such as voice color, affective text, body pose, etc.) can prompt people to perceive emotional expressions in objectively neutral faces. Drawing inspiration from this, we introduce a novel approach for facial expression classification that goes beyond simple classification tasks. Our model accurately classifies a perceived face and synthesizes the corresponding mental representation perceived by a human when observing a face in context. With this, our model offers visual insights into its internal decision-making process. We achieve this by learning two independent representations of content and context using a VAE-GAN architecture. Subsequently, we propose a novel attention mechanism for context-dependent feature adaptation. The adapted representation is used for classification and to generate a context-augmented expression. We evaluate synthesized expressions in a human study, showing that our model effectively produces approximations of human mental representations. We achieve State-of-the-Art classification accuracies of 81.01% on the RAVDESS dataset and 79.34% on the MEAD dataset. We make our code publicly available.
Authors: Tiantian Zhang, Zhangjun Zhou, Jialun Pei
Abstract: Segment Anything Model (SAM) has demonstrated powerful zero-shot segmentation performance in natural scenes. The recently released Segment Anything Model 2 (SAM2) has further heightened researchers' expectations towards image segmentation capabilities. To evaluate the performance of SAM2 on class-agnostic instance-level segmentation tasks, we adopt different prompt strategies for SAM2 to cope with instance-level tasks for three relevant scenarios: Salient Instance Segmentation (SIS), Camouflaged Instance Segmentation (CIS), and Shadow Instance Detection (SID). In addition, to further explore the effectiveness of SAM2 in segmenting granular object structures, we also conduct detailed tests on the high-resolution Dichotomous Image Segmentation (DIS) benchmark to assess the fine-grained segmentation capability. Qualitative and quantitative experimental results indicate that the performance of SAM2 varies significantly across different scenarios. Besides, SAM2 is not particularly sensitive to segmenting high-resolution fine details. We hope this technique report can drive the emergence of SAM2-based adapters, aiming to enhance the performance ceiling of large vision models on class-agnostic instance segmentation tasks.
Authors: Taesung Kwon, Jong Chul Ye
Abstract: Recently, diffusion model-based inverse problem solvers (DIS) have emerged as state-of-the-art approaches for addressing inverse problems, including image super-resolution, deblurring, inpainting, etc. However, their application to video inverse problems arising from spatio-temporal degradation remains largely unexplored due to the challenges in training video diffusion models. To address this issue, here we introduce an innovative video inverse solver that leverages only image diffusion models. Specifically, by drawing inspiration from the success of the recent decomposed diffusion sampler (DDS), our method treats the time dimension of a video as the batch dimension of image diffusion models and solves spatio-temporal optimization problems within denoised spatio-temporal batches derived from each image diffusion model. Moreover, we introduce a batch-consistent diffusion sampling strategy that encourages consistency across batches by synchronizing the stochastic noise components in image diffusion models. Our approach synergistically combines batch-consistent sampling with simultaneous optimization of denoised spatio-temporal batches at each reverse diffusion step, resulting in a novel and efficient diffusion sampling strategy for video inverse problems. Experimental results demonstrate that our method effectively addresses various spatio-temporal degradations in video inverse problems, achieving state-of-the-art reconstructions. Project page: https://solving-video-inverse.github.io/main/
Authors: Luqing Luo, Shichu Sun, Jiangang Yang, Linfang Zheng, Jinwei Du, Jian Liu
Abstract: Monocular object pose estimation, as a pivotal task in computer vision and robotics, heavily depends on accurate 2D-3D correspondences, which often demand costly CAD models that may not be readily available. Object 3D reconstruction methods offer an alternative, among which recent advancements in 3D Gaussian Splatting (3DGS) afford a compelling potential. Yet its performance still suffers and tends to overfit with fewer input views. Embracing this challenge, we introduce SGPose, a novel framework for sparse view object pose estimation using Gaussian-based methods. Given as few as ten views, SGPose generates a geometric-aware representation by starting with a random cuboid initialization, eschewing reliance on Structure-from-Motion (SfM) pipeline-derived geometry as required by traditional 3DGS methods. SGPose removes the dependence on CAD models by regressing dense 2D-3D correspondences between images and the reconstructed model from sparse input and random initialization, while the geometric-consistent depth supervision and online synthetic view warping are key to the success. Experiments on typical benchmarks, especially on the Occlusion LM-O dataset, demonstrate that SGPose outperforms existing methods even under sparse view constraints, under-scoring its potential in real-world applications.
Authors: N. T. Diba, N. Akter, S. A. H. Chowdhury, J. E. Giti
Abstract: A person's Body Mass Index, or BMI, is the most widely used parameter for assessing their health. BMI is a crucial predictor of potential diseases that may arise at higher body fat levels because it is correlated with body fat. Conversely, a community's or an individual's nutritional status can be determined using the BMI. Although deep learning models are used in several studies to estimate BMI from face photos and other data, no previous research established a clear connection between deep learning techniques for handwriting analysis and BMI prediction. This article addresses this research gap with a deep learning approach to estimating BMI from handwritten characters by developing a convolutional neural network (CNN). A dataset containing samples from 48 people in lowercase English scripts is successfully captured for the BMI prediction task. The proposed CNN-based approach reports a commendable accuracy of 99.92%. Performance comparison with other popular CNN architectures reveals that AlexNet and InceptionV3 achieve the second and third-best performance, with the accuracy of 99.69% and 99.53%, respectively.
Authors: Wenwu Guo, Jinlin Wu, Zhen Chen, Qingxiang Zhao, Miao Xu, Zhen Lei, Hongbin Liu
Abstract: Vision-based surgical navigation has received increasing attention due to its non-invasive, cost-effective, and flexible advantages. In particular, a critical element of the vision-based navigation system is tracking surgical instruments. Compared with 2D instrument tracking methods, 3D instrument tracking has broader value in clinical practice, but is also more challenging due to weak texture, occlusion, and lack of Computer-Aided Design (CAD) models for 3D registration. To solve these challenges, we propose the SurgTrack, a two-stage 3D instrument tracking method for CAD-free and robust real-world applications. In the first registration stage, we incorporate an Instrument Signed Distance Field (SDF) modeling the 3D representation of instruments, achieving CAD-freed 3D registration. Due to this, we can obtain the location and orientation of instruments in the 3D space by matching the video stream with the registered SDF model. In the second tracking stage, we devise a posture graph optimization module, leveraging the historical tracking results of the posture memory pool to optimize the tracking results and improve the occlusion robustness. Furthermore, we collect the Instrument3D dataset to comprehensively evaluate the 3D tracking of surgical instruments. The extensive experiments validate the superiority and scalability of our SurgTrack, by outperforming the state-of-the-arts with a remarkable improvement. The code and dataset are available at https://github.com/wenwucode/SurgTrack.
Authors: Weiwei Tian, Xinyu Huang, Tianhao Cheng, Wen He, Jinwu Fang, Rui Feng, Daoying Geng, Xiaobo Zhang
Abstract: Pediatric pneumonia is the leading cause of death among children under five years worldwide, imposing a substantial burden on affected families. Currently, there are three significant hurdles in diagnosing and treating pediatric pneumonia. Firstly, pediatric pneumonia shares similar symptoms with other respiratory diseases, making rapid and accurate differential diagnosis challenging. Secondly, primary hospitals often lack sufficient medical resources and experienced doctors. Lastly, providing personalized diagnostic reports and treatment recommendations is labor-intensive and time-consuming. To tackle these challenges, we proposed a Medical Multimodal Large Language Model for Pediatric Pneumonia (P2Med-MLLM). It was capable of handling diverse clinical tasks, such as generating free-text radiology reports and medical records within a unified framework. Specifically, P2Med-MLLM can process both pure text and image-text data, trained on an extensive and large-scale dataset (P2Med-MD), including real clinical information from 163,999 outpatient and 8,684 inpatient cases. This dataset comprised 2D chest X-ray images, 3D chest CT images, corresponding radiology reports, and outpatient and inpatient records. We designed a three-stage training strategy to enable P2Med-MLLM to comprehend medical knowledge and follow instructions for various clinical tasks. To rigorously evaluate P2Med-MLLM's performance, we developed P2Med-MBench, a benchmark consisting of 642 meticulously verified samples by pediatric pulmonology specialists, covering six clinical decision-support tasks and a balanced variety of diseases. The automated scoring results demonstrated the superiority of P2Med-MLLM. This work plays a crucial role in assisting primary care doctors with prompt disease diagnosis and treatment planning, reducing severe symptom mortality rates, and optimizing the allocation of medical resources.
Authors: Lingling Zhang, Muye Huang, QianYing Wang, Yaxian Wang, Wenjun Wu, Jun Liu
Abstract: Chart Question Answering (CQA) aims at answering questions based on the visual chart content, which plays an important role in chart sumarization, business data analysis, and data report generation. CQA is a challenging multi-modal task because of the strong context dependence and complex reasoning requirement. The former refers to answering this question strictly based on the analysis of the visual content or internal data of the given chart, while the latter emphasizes the various logical and numerical reasoning involved in answer prediction process. In this paper, we pay more attention on the complex reasoning in CQA task, and propose a novel Graph-of-Thought (GoT) guided compositional reasoning model called GoT-CQA to overcome this problem. At first, we transform the chart-oriented question into a directed acyclic GoT composed of multiple operator nodes, including localization, numerical and logical operator. It intuitively reflects the human brain's solution process to this question. After that, we design an efficient auto-compositional reasoning framework guided by the GoT, to excute the multi-step reasoning operations in various types of questions. Comprehensive experiments on ChartQA and PlotQA-D datasets show that GoT-CQA achieves outstanding performance, especially in complex human-written and reasoning questions, comparing with the latest popular baselines.
Authors: Melih Catal, Manuel G\"unther
Abstract: Machine learning models are vulnerable to adversarial attacks. Several tools have been developed to research these vulnerabilities, but they often lack comprehensive features and flexibility. We introduce AdvSecureNet, a PyTorch based toolkit for adversarial machine learning that is the first to natively support multi-GPU setups for attacks, defenses, and evaluation. It is the first toolkit that supports both CLI and API interfaces and external YAML configuration files to enhance versatility and reproducibility. The toolkit includes multiple attacks, defenses and evaluation metrics. Rigiorous software engineering practices are followed to ensure high code quality and maintainability. The project is available as an open-source project on GitHub at https://github.com/melihcatal/advsecurenet and installable via PyPI.
Authors: Jianwen Jiang, Chao Liang, Jiaqi Yang, Gaojie Lin, Tianyun Zhong, Yanbo Zheng
Abstract: With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to the limited control of audio signals in driving human motion, existing methods often add auxiliary spatial signals to stabilize movements, which may compromise the naturalness and freedom of motion. In this paper, we propose an end-to-end audio-only conditioned video diffusion model named Loopy. Specifically, we designed an inter- and intra-clip temporal module and an audio-to-latents module, enabling the model to leverage long-term motion information from the data to learn natural motion patterns and improving audio-portrait movement correlation. This method removes the need for manually specified spatial motion templates used in existing methods to constrain motion during inference. Extensive experiments show that Loopy outperforms recent audio-driven portrait diffusion models, delivering more lifelike and high-quality results across various scenarios.
Authors: Junyi Ma, Xieyuanli Chen, Wentao Bao, Jingyi Xu, Hesheng Wang
Abstract: Understanding human intentions and actions through egocentric videos is important on the path to embodied artificial intelligence. As a branch of egocentric vision techniques, hand trajectory prediction plays a vital role in comprehending human motion patterns, benefiting downstream tasks in extended reality and robot manipulation. However, capturing high-level human intentions consistent with reasonable temporal causality is challenging when only egocentric videos are available. This difficulty is exacerbated under camera egomotion interference and the absence of affordance labels to explicitly guide the optimization of hand waypoint distribution. In this work, we propose a novel hand trajectory prediction method dubbed MADiff, which forecasts future hand waypoints with diffusion models. The devised denoising operation in the latent space is achieved by our proposed motion-aware Mamba, where the camera wearer's egomotion is integrated to achieve motion-driven selective scan (MDSS). To discern the relationship between hands and scenarios without explicit affordance supervision, we leverage a foundation model that fuses visual and language features to capture high-level semantics from video clips. Comprehensive experiments conducted on five public datasets with the existing and our proposed new evaluation metrics demonstrate that MADiff predicts comparably reasonable hand trajectories compared to the state-of-the-art baselines, and achieves real-time performance. We will release our code and pretrained models of MADiff at the project page: https://irmvlab.github.io/madiff.github.io.
Authors: Cornelius B\"urkle, Fabian Oboril, Kay-Ulrich Scholl
Abstract: The automotive industry is currently expanding digital display options with every new model that comes onto the market. This entails not just an expansion in dimensions, resolution, and customization choices, but also the capability to employ novel display effects like overlays while assembling the content of the display cluster. Unfortunately, this raises the need for appropriate monitoring systems that can detect rendering errors and apply appropriate countermeasures when required. Classical solutions such as Cyclic Redundancy Checks (CRC) will soon be no longer viable as any sort of alpha blending, warping of scaling of content can cause unwanted CRC violations. Therefore, we propose a novel monitoring approach to verify correctness of displayed content using telltales (e.g. warning signs) as example. It uses a learning-based approach to separate "good" telltales, i.e. those that a human driver will understand correctly, and "corrupted" telltales, i.e. those that will not be visible or perceived correctly. As a result, it possesses inherent resilience against individual pixel errors and implicitly supports changing backgrounds, overlay or scaling effects. This is underlined by our experimental study where all "corrupted" test patterns were correctly classified, while no false alarms were triggered.
Authors: Kyungmin Jo, Jaegul Choo
Abstract: The emergence of diffusion models has enabled the generation of diverse high-quality images solely from text, prompting subsequent efforts to enhance the controllability of these models. Despite the improvement in controllability, pose control remains limited to specific objects (e.g., humans) or poses (e.g., frontal view) due to the fact that pose is generally controlled via camera parameters (e.g., rotation angle) or keypoints (e.g., eyes, nose). Specifically, camera parameters-conditional pose control models generate unrealistic images depending on the object, owing to the small size of 3D datasets for training. Also, keypoint-based approaches encounter challenges in acquiring reliable keypoints for various objects (e.g., church) or poses (e.g., back view). To address these limitations, we propose depth-based pose control, as depth maps are easily obtainable from a single depth estimation model regardless of objects and poses, unlike camera parameters and keypoints. However, depth-based pose control confronts issues of shape dependency, as depth maps influence not only the pose but also the shape of the generated images. To tackle this issue, we propose Skip-and-Play (SnP), designed via analysis of the impact of three components of depth-conditional ControlNet on the pose and the shape of the generated images. To be specific, based on the analysis, we selectively skip parts of the components to mitigate shape dependency on the depth map while preserving the pose. Through various experiments, we demonstrate the superiority of SnP over baselines and showcase the ability of SnP to generate images of diverse objects and poses. Remarkably, SnP exhibits the ability to generate images even when the objects in the condition (e.g., a horse) and the prompt (e.g., a hedgehog) differ from each other.
Authors: Jun Ling, Yiwen Wang, Han Xue, Rong Xie, Li Song
Abstract: While previous audio-driven talking head generation (THG) methods generate head poses from driving audio, the generated poses or lips cannot match the audio well or are not editable. In this study, we propose \textbf{PoseTalk}, a THG system that can freely generate lip-synchronized talking head videos with free head poses conditioned on text prompts and audio. The core insight of our method is using head pose to connect visual, linguistic, and audio signals. First, we propose to generate poses from both audio and text prompts, where the audio offers short-term variations and rhythm correspondence of the head movements and the text prompts describe the long-term semantics of head motions. To achieve this goal, we devise a Pose Latent Diffusion (PLD) model to generate motion latent from text prompts and audio cues in a pose latent space. Second, we observe a loss-imbalance problem: the loss for the lip region contributes less than 4\% of the total reconstruction loss caused by both pose and lip, making optimization lean towards head movements rather than lip shapes. To address this issue, we propose a refinement-based learning strategy to synthesize natural talking videos using two cascaded networks, i.e., CoarseNet, and RefineNet. The CoarseNet estimates coarse motions to produce animated images in novel poses and the RefineNet focuses on learning finer lip motions by progressively estimating lip motions from low-to-high resolutions, yielding improved lip-synchronization performance. Experiments demonstrate our pose prediction strategy achieves better pose diversity and realness compared to text-only or audio-only, and our video generator model outperforms state-of-the-art methods in synthesizing talking videos with natural head motions. Project: https://junleen.github.io/projects/posetalk.
Authors: Kaiqing Lin, Yuzhen Lin, Weixiang Li, Taiping Yao, Bin Li
Abstract: The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen datasets or created by emerging generative models remains constrained. In this paper, inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel approach that repurposes a well-trained VLM for general deepfake detection. Motivated by the model reprogramming paradigm that manipulates the model prediction via data perturbations, our method can reprogram a pretrained VLM model (e.g., CLIP) solely based on manipulating its input without tuning the inner parameters. Furthermore, we insert a pseudo-word guided by facial identity into the text prompt. Extensive experiments on several popular benchmarks demonstrate that (1) the cross-dataset and cross-manipulation performances of deepfake detection can be significantly and consistently improved (e.g., over 88% AUC in cross-dataset setting from FF++ to WildDeepfake) using a pre-trained CLIP model with our proposed reprogramming method; (2) our superior performances are at less cost of trainable parameters, making it a promising approach for real-world applications.
Authors: Daniel Busch, Ido Freeman, Richard Meyes, Tobias Meisen
Abstract: Bird's Eye View (BEV) map prediction is essential for downstream autonomous driving tasks like trajectory prediction. In the past, this was accomplished through the use of a sophisticated sensor configuration that captured a surround view from multiple cameras. However, in large-scale production, cost efficiency is an optimization goal, so that using fewer cameras becomes more relevant. But the consequence of fewer input images correlates with a performance drop. This raises the problem of developing a BEV perception model that provides a sufficient performance on a low-cost sensor setup. Although, primarily relevant for inference time on production cars, this cost restriction is less problematic on a test vehicle during training. Therefore, the objective of our approach is to reduce the aforementioned performance drop as much as possible using a modern multi-camera surround view model reduced for single-camera inference. The approach includes three features, a modern masking technique, a cyclic Learning Rate (LR) schedule, and a feature reconstruction loss for supervising the transition from six-camera inputs to one-camera input during training. Our method outperforms versions trained strictly with one camera or strictly with six-camera surround view for single-camera inference resulting in reduced hallucination and better quality of the BEV map.
Authors: Konstantina Nikolaidou, George Retsinas, Giorgos Sfikas, Marcus Liwicki
Abstract: The evaluation of generative models for natural image tasks has been extensively studied. Similar protocols and metrics are used in cases with unique particularities, such as Handwriting Generation, even if they might not be completely appropriate. In this work, we introduce three measures tailored for HTG evaluation, $ \text{HTG}_{\text{HTR}} $, $ \text{HTG}_{\text{style}} $, and $ \text{HTG}_{\text{OOV}} $, and argue that they are more expedient to evaluate the quality of generated handwritten images. The metrics rely on the recognition error/accuracy of Handwriting Text Recognition and Writer Identification models and emphasize writing style, textual content, and diversity as the main aspects that adhere to the content of handwritten images. We conduct comprehensive experiments on the IAM handwriting database, showcasing that widely used metrics such as FID fail to properly quantify the diversity and the practical utility of generated handwriting samples. Our findings show that our metrics are richer in information and underscore the necessity of standardized evaluation protocols in HTG. The proposed metrics provide a more robust and informative protocol for assessing HTG quality, contributing to improved performance in HTR. Code for the evaluation protocol is available at: https://github.com/koninik/HTG_evaluation.
Authors: Minhee Cho, Hyesong Choi, Hayeon Jo, Dongbo Min
Abstract: Unsupervised Domain Adaptation (UDA) endeavors to bridge the gap between a model trained on a labeled source domain and its deployment in an unlabeled target domain. However, current high-performance models demand significant resources, resulting in prohibitive deployment costs and highlighting the need for small yet effective models. For UDA of lightweight models, Knowledge Distillation (KD) in a Teacher-Student framework can be a common approach, but we find that domain shift in UDA leads to a significant increase in non-salient parameters in the teacher model, degrading model's generalization ability and transferring misleading information to the student model. Interestingly, we observed that this phenomenon occurs considerably less in the student model. Driven by this insight, we introduce Collaborative Learning, a method that updates the teacher's non-salient parameters using the student model and at the same time enhance the student's performance using the updated teacher model. Experiments across various tasks and datasets show consistent performance improvements for both student and teacher models. For example, in semantic segmentation, CLDA achieves an improvement of +0.7% mIoU for teacher and +1.4% mIoU for student compared to the baseline model in the GTA to Cityscapes. In the Synthia to Cityscapes, it achieves an improvement of +0.8% mIoU for teacher and +2.0% mIoU for student.
Authors: Jiarui Sun, M. Ugur Akcal, Wei Zhang, Girish Chowdhary
Abstract: In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency, primarily due to the complexity of extracting informative state representations from high-dimensional data. Previous methods such as contrastive-based approaches have made strides in improving sample efficiency but fall short in modeling the nuanced evolution of states. To address this, we introduce MOOSS, a novel framework that leverages a temporal contrastive objective with the help of graph-based spatial-temporal masking to explicitly model state evolution in visual RL. Specifically, we propose a self-supervised dual-component strategy that integrates (1) a graph construction of pixel-based observations for spatial-temporal masking, coupled with (2) a multi-level contrastive learning mechanism that enriches state representations by emphasizing temporal continuity and change of states. MOOSS advances the understanding of state dynamics by disrupting and learning from spatial-temporal correlations, which facilitates policy learning. Our comprehensive evaluation on multiple continuous and discrete control benchmarks shows that MOOSS outperforms previous state-of-the-art visual RL methods in terms of sample efficiency, demonstrating the effectiveness of our method. Our code is released at https://github.com/jsun57/MOOSS.
Authors: Wenjun Huang, Yang Ni, Arghavan Rezvani, SungHeon Jeong, Hanning Chen, Yezi Liu, Fei Wen, Mohsen Imani
Abstract: Human pose estimation (HPE) is crucial for various applications. However, deploying HPE algorithms in surveillance contexts raises significant privacy concerns due to the potential leakage of sensitive personal information (SPI) such as facial features, and ethnicity. Existing privacy-enhancing methods often compromise either privacy or performance, or they require costly additional modalities. We propose a novel privacy-enhancing system that generates privacy-enhanced portraits while maintaining high HPE performance. Our key innovations include the reversible recovery of SPI for authorized personnel and the preservation of contextual information. By jointly optimizing a privacy-enhancing module, a privacy recovery module, and a pose estimator, our system ensures robust privacy protection, efficient SPI recovery, and high-performance HPE. Experimental results demonstrate the system's robust performance in privacy enhancement, SPI recovery, and HPE.
Authors: Ashish Tiwari, Mihir Sutariya, Shanmuganathan Raman
Abstract: Photometric stereo is a powerful method for obtaining per-pixel surface normals from differently illuminated images of an object. While several methods address photometric stereo with different image (or light) counts ranging from one to two to a hundred, very few focus on learning optimal lighting configuration. Finding an optimal configuration is challenging due to the vast number of possible lighting directions. Moreover, exhaustively sampling all possibilities is impractical due to time and resource constraints. Photometric stereo methods have demonstrated promising performance on existing datasets, which feature limited light directions sparsely sampled from the light space. Therefore, can we optimally utilize these datasets for illumination planning? In this work, we introduce LIPIDS - Learning-based Illumination Planning In Discretized light Space to achieve minimal and optimal lighting configurations for photometric stereo under arbitrary light distribution. We propose a Light Sampling Network (LSNet) that optimizes lighting direction for a fixed number of lights by minimizing the normal loss through a normal regression network. The learned light configurations can directly estimate surface normals during inference, even using an off-the-shelf photometric stereo method. Extensive qualitative and quantitative analyses on synthetic and real-world datasets show that photometric stereo under learned lighting configurations through LIPIDS either surpasses or is nearly comparable to existing illumination planning methods across different photometric stereo backbones.
Authors: Huawei Sun, Zixu Wang, Hao Feng, Julius Ott, Lorenzo Servadei, Robert Wille
Abstract: Depth estimation plays a pivotal role in autonomous driving, facilitating a comprehensive understanding of the vehicle's 3D surroundings. Radar, with its robustness to adverse weather conditions and capability to measure distances, has drawn significant interest for radar-camera depth estimation. However, existing algorithms process the inherently noisy and sparse radar data by projecting 3D points onto the image plane for pixel-level feature extraction, overlooking the valuable geometric information contained within the radar point cloud. To address this gap, we propose GET-UP, leveraging attention-enhanced Graph Neural Networks (GNN) to exchange and aggregate both 2D and 3D information from radar data. This approach effectively enriches the feature representation by incorporating spatial relationships compared to traditional methods that rely only on 2D feature extraction. Furthermore, we incorporate a point cloud upsampling task to densify the radar point cloud, rectify point positions, and derive additional 3D features under the guidance of lidar data. Finally, we fuse radar and camera features during the decoding phase for depth estimation. We benchmark our proposed GET-UP on the nuScenes dataset, achieving state-of-the-art performance with a 15.3% and 14.7% improvement in MAE and RMSE over the previously best-performing model.
Authors: Umaima Rahman, Raza Imam, Dwarikanath Mahapatra, Boulbaba Ben Amor
Abstract: In medical image classification, supervised learning is challenging due to the lack of labeled medical images. Contrary to the traditional \textit{modus operandi} of pre-training followed by fine-tuning, this work leverages the visual-textual alignment within Vision-Language models (\texttt{VLMs}) to facilitate the unsupervised learning. Specifically, we propose \underline{Med}ical \underline{Un}supervised \underline{A}daptation (\texttt{MedUnA}), constituting two-stage training: Adapter Pre-training, and Unsupervised Learning. In the first stage, we use descriptions generated by a Large Language Model (\texttt{LLM}) corresponding to class labels, which are passed through the text encoder \texttt{BioBERT}. The resulting text embeddings are then aligned with the class labels by training a lightweight \texttt{adapter}. We choose \texttt{\texttt{LLMs}} because of their capability to generate detailed, contextually relevant descriptions to obtain enhanced text embeddings. In the second stage, the trained \texttt{adapter} is integrated with the visual encoder of \texttt{MedCLIP}. This stage employs a contrastive entropy-based loss and prompt tuning to align visual embeddings. We incorporate self-entropy minimization into the overall training objective to ensure more confident embeddings, which are crucial for effective unsupervised learning and alignment. We evaluate the performance of \texttt{MedUnA} on three different kinds of data modalities - chest X-rays, eye fundus and skin lesion images. The results demonstrate significant accuracy gain on average compared to the baselines across different datasets, highlighting the efficacy of our approach.
Authors: Shuang Song, Luca Morelli, Xinyi Wu, Rongjun Qin, Hessah Albanwan, Fabio Remondino
Abstract: A critical step in the digital surface models(DSM) generation is feature matching. Off-track (or multi-date) satellite stereo images, in particular, can challenge the performance of feature matching due to spectral distortions between images, long baseline, and wide intersection angles. Feature matching methods have evolved over the years from handcrafted methods (e.g., SIFT) to learning-based methods (e.g., SuperPoint and SuperGlue). In this paper, we compare the performance of different features, also known as feature extraction and matching methods, applied to satellite imagery. A wide range of stereo pairs(~500) covering two separate study sites are used. SIFT, as a widely used classic feature extraction and matching algorithm, is compared with seven deep-learning matching methods: SuperGlue, LightGlue, LoFTR, ASpanFormer, DKM, GIM-LightGlue, and GIM-DKM. Results demonstrate that traditional matching methods are still competitive in this age of deep learning, although for particular scenarios learning-based methods are very promising.
Authors: Xing Lan, Jian Xue, Ji Qi, Dongmei Jiang, Ke Lu, Tat-Seng Chua
Abstract: Facial expression recognition (FER) is a critical task in multimedia with significant implications across various domains. However, analyzing the causes of facial expressions is essential for accurately recognizing them. Current approaches, such as those based on facial action units (AUs), typically provide AU names and intensities but lack insight into the interactions and relationships between AUs and the overall expression. In this paper, we propose a novel method called ExpLLM, which leverages large language models to generate an accurate chain of thought (CoT) for facial expression recognition. Specifically, we have designed the CoT mechanism from three key perspectives: key observations, overall emotional interpretation, and conclusion. The key observations describe the AU's name, intensity, and associated emotions. The overall emotional interpretation provides an analysis based on multiple AUs and their interactions, identifying the dominant emotions and their relationships. Finally, the conclusion presents the final expression label derived from the preceding analysis. Furthermore, we also introduce the Exp-CoT Engine, designed to construct this expression CoT and generate instruction-description data for training our ExpLLM. Extensive experiments on the RAF-DB and AffectNet datasets demonstrate that ExpLLM outperforms current state-of-the-art FER methods. ExpLLM also surpasses the latest GPT-4o in expression CoT generation, particularly in recognizing micro-expressions where GPT-4o frequently fails.
Authors: Hayeon Jo, Hyesong Choi, Minhee Cho, Dongbo Min
Abstract: Transfer learning based on full fine-tuning (FFT) of the pre-trained encoder and task-specific decoder becomes increasingly complex as deep models grow exponentially. Parameter efficient fine-tuning (PEFT) approaches using adapters consisting of small learnable layers have emerged as an alternative to FFT, achieving comparable performance while maintaining high training efficiency. However, the inflexibility of the adapter with respect to input instances limits its capability of learning task-specific information in diverse downstream tasks. In this paper, we propose a novel PEFT approach, input-Conditioned transFormer, termed iConFormer, that leverages a dynamic adapter conditioned on the input instances. To secure flexible learning ability on input instances in various downstream tasks, we introduce an input-Conditioned Network (iCoN) in the dynamic adapter that enables instance-level feature transformation. To be specific, iCoN generates channel-wise convolutional kernels for each feature and transform it using adaptive convolution process to effectively capture task-specific and fine-grained details tailor to downstream tasks. Experimental results demonstrate that by tuning just 1.6% to 2.8% of the Transformer backbone parameters, iConFormer achieves performance comparable to FFT in monocular depth estimation and semantic segmentation, while outperforming it in image classification and instance segmentation. Also, the proposed method consistently outperforms recent PEFT methods for all the tasks mentioned above.
Authors: Jihye Ahn, Hyesong Choi, Soomin Kim, Dongbo Min
Abstract: In stereo matching, CNNs have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still lags behind CNN-based stereo models due to the inherent data scarcity issue in the stereo matching task. In this paper, we propose Masked Image Modeling Distilled Stereo matching model, termed MaDis-Stereo, that enhances locality inductive bias by leveraging Masked Image Modeling (MIM) in training Transformer-based stereo model. Given randomly masked stereo images as inputs, our method attempts to conduct both image reconstruction and depth prediction tasks. While this strategy is beneficial to resolving the data scarcity issue, the dual challenge of reconstructing masked tokens and subsequently performing stereo matching poses significant challenges, particularly in terms of training stability. To address this, we propose to use an auxiliary network (teacher), updated via Exponential Moving Average (EMA), along with the original stereo model (student), where teacher predictions serve as pseudo supervisory signals to effectively distill knowledge into the student model. State-of-the-arts performance is achieved with the proposed method on several stereo matching such as ETH3D and KITTI 2015. Additionally, to demonstrate that our model effectively leverages locality inductive bias, we provide the attention distance measurement.
Authors: Zhibin Liu, Haoye Dong, Aviral Chharia, Hefeng Wu
Abstract: Generating lifelike 3D humans from a single RGB image remains a challenging task in computer vision, as it requires accurate modeling of geometry, high-quality texture, and plausible unseen parts. Existing methods typically use multi-view diffusion models for 3D generation, but they often face inconsistent view issues, which hinder high-quality 3D human generation. To address this, we propose Human-VDM, a novel method for generating 3D human from a single RGB image using Video Diffusion Models. Human-VDM provides temporally consistent views for 3D human generation using Gaussian Splatting. It consists of three modules: a view-consistent human video diffusion module, a video augmentation module, and a Gaussian Splatting module. First, a single image is fed into a human video diffusion module to generate a coherent human video. Next, the video augmentation module applies super-resolution and video interpolation to enhance the textures and geometric smoothness of the generated video. Finally, the 3D Human Gaussian Splatting module learns lifelike humans under the guidance of these high-resolution and view-consistent images. Experiments demonstrate that Human-VDM achieves high-quality 3D human from a single image, outperforming state-of-the-art methods in both generation quality and quantity. Project page: https://human-vdm.github.io/Human-VDM/
Authors: June Moh Goo, Xenios Milidonis, Alessandro Artusi, Jan Boehm, Carlo Ciliberto
Abstract: Detecting and segmenting cracks in infrastructure, such as roads and buildings, is crucial for safety and cost-effective maintenance. In spite of the potential of deep learning, there are challenges in achieving precise results and handling diverse crack types. With the proposed dataset and model, we aim to enhance crack detection and infrastructure maintenance. We introduce Hybrid-Segmentor, an encoder-decoder based approach that is capable of extracting both fine-grained local and global crack features. This allows the model to improve its generalization capabilities in distinguish various type of shapes, surfaces and sizes of cracks. To keep the computational performances low for practical purposes, while maintaining the high the generalization capabilities of the model, we incorporate a self-attention model at the encoder level, while reducing the complexity of the decoder component. The proposed model outperforms existing benchmark models across 5 quantitative metrics (accuracy 0.971, precision 0.804, recall 0.744, F1-score 0.770, and IoU score 0.630), achieving state-of-the-art status.
Authors: Andrea Atzori, Pietro Cosseddu, Gianni Fenu, Mirko Marras
Abstract: Over the recent years, the advancements in deep face recognition have fueled an increasing demand for large and diverse datasets. Nevertheless, the authentic data acquired to create those datasets is typically sourced from the web, which, in many cases, can lead to significant privacy issues due to the lack of explicit user consent. Furthermore, obtaining a demographically balanced, large dataset is even more difficult because of the natural imbalance in the distribution of images from different demographic groups. In this paper, we investigate the impact of demographically balanced authentic and synthetic data, both individually and in combination, on the accuracy and fairness of face recognition models. Initially, several generative methods were used to balance the demographic representations of the corresponding synthetic datasets. Then a state-of-the-art face encoder was trained and evaluated using (combinations of) synthetic and authentic images. Our findings emphasized two main points: (i) the increased effectiveness of training data generated by diffusion-based models in enhancing accuracy, whether used alone or combined with subsets of authentic data, and (ii) the minimal impact of incorporating balanced data from pre-trained generative methods on fairness (in nearly all tested scenarios using combined datasets, fairness scores remained either unchanged or worsened, even when compared to unbalanced authentic datasets). Source code and data are available at \url{https://cutt.ly/AeQy1K5G} for reproducibility.
URLs: https://cutt.ly/AeQy1K5G
Authors: Guangtao Zheng, Wenqian Ye, Aidong Zhang
Abstract: Few-shot image classifiers are designed to recognize and classify new data with minimal supervision and limited data but often show reliance on spurious correlations between classes and spurious attributes, known as spurious bias. Spurious correlations commonly hold in certain samples and few-shot classifiers can suffer from spurious bias induced from them. There is an absence of an automatic benchmarking system to assess the robustness of few-shot classifiers against spurious bias. In this paper, we propose a systematic and rigorous benchmark framework, termed FewSTAB, to fairly demonstrate and quantify varied degrees of robustness of few-shot classifiers to spurious bias. FewSTAB creates few-shot evaluation tasks with biased attributes so that using them for predictions can demonstrate poor performance. To construct these tasks, we propose attribute-based sample selection strategies based on a pre-trained vision-language model, eliminating the need for manual dataset curation. This allows FewSTAB to automatically benchmark spurious bias using any existing test data. FewSTAB offers evaluation results in a new dimension along with a new design guideline for building robust classifiers. Moreover, it can benchmark spurious bias in varied degrees and enable designs for varied degrees of robustness. Its effectiveness is demonstrated through experiments on ten few-shot learning methods across three datasets. We hope our framework can inspire new designs of robust few-shot classifiers. Our code is available at https://github.com/gtzheng/FewSTAB.
Authors: Junyoung Park, Eun Hyun Seo, Sunjun Kim, SangHak Yi, Kun Ho Lee, Sungho Won
Abstract: Drawing tests like the Rey Complex Figure Test (RCFT) are widely used to assess cognitive functions such as visuospatial skills and memory, making them valuable tools for detecting mild cognitive impairment (MCI). Despite their utility, existing predictive models based on these tests often suffer from limitations like small sample sizes and lack of external validation, which undermine their reliability. We developed a multi-stream deep learning framework that integrates two distinct processing streams: a multi-head self-attention based spatial stream using raw RCFT images and a scoring stream employing a previously developed automated scoring system. Our model was trained on data from 1,740 subjects in the Korean cohort and validated on an external hospital dataset of 222 subjects from Korea. The proposed multi-stream model demonstrated superior performance over baseline models (AUC = 0.872, Accuracy = 0.781) in external validation. The integration of both spatial and scoring streams enables the model to capture intricate visual details from the raw images while also incorporating structured scoring data, which together enhance its ability to detect subtle cognitive impairments. This dual approach not only improves predictive accuracy but also increases the robustness of the model, making it more reliable in diverse clinical settings. Our model has practical implications for clinical settings, where it could serve as a cost-effective tool for early MCI screening.
Authors: Owais Iqbal, Omprakash Chakraborty, Aftab Hussain, Rameswar Panda, Abir Das
Abstract: Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreover, handling spatio-temporal data using deep $3$D transformers for this can introduce significant computational complexity. In this paper, our objective is to address video action recognition in a semi-supervised setting by leveraging only a handful of labeled videos along with a collection of unlabeled videos in a compute efficient manner. Specifically, we rearrange multiple frames from the input videos in row-column form to construct super images. Subsequently, we capitalize on the vast pool of unlabeled samples and employ contrastive learning on the encoded super images. Our proposed approach employs two pathways to generate representations for temporally augmented super images originating from the same video. Specifically, we utilize a 2D image-transformer to generate representations and apply a contrastive loss function to minimize the similarity between representations from different videos while maximizing the representations of identical videos. Our method demonstrates superior performance compared to existing state-of-the-art approaches for semi-supervised action recognition across various benchmark datasets, all while significantly reducing computational costs.
Authors: Yuhang Lu, Yichen Yao, Jiadong Tu, Jiangnan Shao, Yuexin Ma, Xinge Zhu
Abstract: Large Vision-Language Models (LVLMs) have recently garnered significant attention, with many efforts aimed at harnessing their general knowledge to enhance the interpretability and robustness of autonomous driving models. However, LVLMs typically rely on large, general-purpose datasets and lack the specialized expertise required for professional and safe driving. Existing vision-language driving datasets focus primarily on scene understanding and decision-making, without providing explicit guidance on traffic rules and driving skills, which are critical aspects directly related to driving safety. To bridge this gap, we propose IDKB, a large-scale dataset containing over one million data items collected from various countries, including driving handbooks, theory test data, and simulated road test data. Much like the process of obtaining a driver's license, IDKB encompasses nearly all the explicit knowledge needed for driving from theory to practice. In particular, we conducted comprehensive tests on 15 LVLMs using IDKB to assess their reliability in the context of autonomous driving and provided extensive analysis. We also fine-tuned popular models, achieving notable performance improvements, which further validate the significance of our dataset. The project page can be found at: \url{https://4dvlab.github.io/project_page/idkb.html}
Authors: Jiaxin Guo, Jiangliu Wang, Ruofeng Wei, Di Kang, Qi Dou, Yun-hui Liu
Abstract: Visualizing surgical scenes is crucial for revealing internal anatomical structures during minimally invasive procedures. Novel View Synthesis is a vital technique that offers geometry and appearance reconstruction, enhancing understanding, planning, and decision-making in surgical scenes. Despite the impressive achievements of Neural Radiance Field (NeRF), its direct application to surgical scenes produces unsatisfying results due to two challenges: endoscopic sparse views and significant photometric inconsistencies. In this paper, we propose uncertainty-aware conditional NeRF for novel view synthesis to tackle the severe shape-radiance ambiguity from sparse surgical views. The core of UC-NeRF is to incorporate the multi-view uncertainty estimation to condition the neural radiance field for modeling the severe photometric inconsistencies adaptively. Specifically, our UC-NeRF first builds a consistency learner in the form of multi-view stereo network, to establish the geometric correspondence from sparse views and generate uncertainty estimation and feature priors. In neural rendering, we design a base-adaptive NeRF network to exploit the uncertainty estimation for explicitly handling the photometric inconsistencies. Furthermore, an uncertainty-guided geometry distillation is employed to enhance geometry learning. Experiments on the SCARED and Hamlyn datasets demonstrate our superior performance in rendering appearance and geometry, consistently outperforming the current state-of-the-art approaches. Our code will be released at \url{https://github.com/wrld/UC-NeRF}.
Authors: Xinyu Liu, Yingqing He, Lanqing Guo, Xiang Li, Bu Jin, Peng Li, Yan Li, Chi-Min Chan, Qifeng Chen, Wei Xue, Wenhan Luo, Qingfeng Liu, Yike Guo
Abstract: The potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural artifacts especially when scaling to 4K resolution and higher. We figure out that the problem is caused by that, a single prompt for the generation of multiple scales provides insufficient efficacy. In response, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts offer both global and local guidance. Specifically, the global guidance comes from the user input that describes the overall content, while the local guidance utilizes patch-wise descriptions from MLLMs to elaborately guide the regional structure and texture generation. Furthermore, during the inverse denoising process, the generated noise is decomposed into low- and high-frequency spatial components. These components are conditioned on multiple prompt levels, including detailed patch-wise descriptions and broader image-level prompts, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality.
Authors: Xiangyuan Xue, Zeyu Lu, Di Huang, Wanli Ouyang, Lei Bai
Abstract: Much previous AI research has focused on developing monolithic models to maximize their intelligence and capability, with the primary goal of enhancing performance on specific tasks. In contrast, this paper explores an alternative approach: collaborative AI systems that use workflows to integrate models, data sources, and pipelines to solve complex and diverse tasks. We introduce GenAgent, an LLM-based framework that automatically generates complex workflows, offering greater flexibility and scalability compared to monolithic models. The core innovation of GenAgent lies in representing workflows with code, alongside constructing workflows with collaborative agents in a step-by-step manner. We implement GenAgent on the ComfyUI platform and propose a new benchmark, OpenComfy. The results demonstrate that GenAgent outperforms baseline approaches in both run-level and task-level evaluations, showing its capability to generate complex workflows with superior effectiveness and stability.
Authors: Samer Francy, Raghubir Singh
Abstract: This work evaluates the compression techniques on ConvNeXt models in image classification tasks using the CIFAR-10 dataset. Structured pruning, unstructured pruning, and dynamic quantization methods are evaluated to reduce model size and computational complexity while maintaining accuracy. The experiments, conducted on cloud-based platforms and edge device, assess the performance of these techniques. Results show significant reductions in model size, with up to 75% reduction achieved using structured pruning techniques. Additionally, dynamic quantization achieves a reduction of up to 95% in the number of parameters. Fine-tuned models exhibit improved compression performance, indicating the benefits of pre-training in conjunction with compression techniques. Unstructured pruning methods reveal trends in accuracy and compression, with limited reductions in computational complexity. The combination of OTOV3 pruning and dynamic quantization further enhances compression performance, resulting 89.7% reduction in size, 95% reduction with number of parameters and MACs, and 3.8% increase with accuracy. The deployment of the final compressed model on edge device demonstrates high accuracy 92.5% and low inference time 20 ms, validating the effectiveness of compression techniques for real-world edge computing applications.
Authors: Dexin Duan, Peilin liu, Fei Wen
Abstract: On-device computing, or edge computing, is becoming increasingly important for remote sensing, particularly in applications like deep network-based perception on on-orbit satellites and unmanned aerial vehicles (UAVs). In these scenarios, two brain-like capabilities are crucial for remote sensing models: (1) high energy efficiency, allowing the model to operate on edge devices with limited computing resources, and (2) online adaptation, enabling the model to quickly adapt to environmental variations, weather changes, and sensor drift. This work addresses these needs by proposing an online adaptation framework based on spiking neural networks (SNNs) for remote sensing. Starting with a pretrained SNN model, we design an efficient, unsupervised online adaptation algorithm, which adopts an approximation of the BPTT algorithm and only involves forward-in-time computation that significantly reduces the computational complexity of SNN adaptation learning. Besides, we propose an adaptive activation scaling scheme to boost online SNN adaptation performance, particularly in low time-steps. Furthermore, for the more challenging remote sensing detection task, we propose a confidence-based instance weighting scheme, which substantially improves adaptation performance in the detection task. To our knowledge, this work is the first to address the online adaptation of SNNs. Extensive experiments on seven benchmark datasets across classification, segmentation, and detection tasks demonstrate that our proposed method significantly outperforms existing domain adaptation and domain generalization approaches under varying weather conditions. The proposed method enables energy-efficient and fast online adaptation on edge devices, and has much potential in applications such as remote perception on on-orbit satellites and UAV.
Authors: Maytus Piriyajitakonkij, Sirawaj Itthipuripat, Ian Ballard, Ioannis Pappas
Abstract: In visual decision making, high-level features, such as object categories, have a strong influence on choice. However, the impact of low-level features on behavior is less understood partly due to the high correlation between high- and low-level features in the stimuli presented (e.g., objects of the same category are more likely to share low-level features). To disentangle these effects, we propose a method that de-correlates low- and high-level visual properties in a novel set of stimuli. Our method uses two Convolutional Neural Networks (CNNs) as candidate models of the ventral visual stream: the CORnet-S that has high neural predictivity in high-level, IT-like responses and the VGG-16 that has high neural predictivity in low-level responses. Triplets (root, image1, image2) of stimuli are parametrized by the level of low- and high-level similarity of images extracted from the different layers. These stimuli are then used in a decision-making task where participants are tasked to choose the most similar-to-the-root image. We found that different networks show differing abilities to predict the effects of low-versus-high-level similarity: while CORnet-S outperforms VGG-16 in explaining human choices based on high-level similarity, VGG-16 outperforms CORnet-S in explaining human choices based on low-level similarity. Using Brain-Score, we observed that the behavioral prediction abilities of different layers of these networks qualitatively corresponded to their ability to explain neural activity at different levels of the visual hierarchy. In summary, our algorithm for stimulus set generation enables the study of how different representations in the visual stream affect high-level cognitive behaviors.
Authors: Ali Lotfi, Ian McQuillan
Abstract: This paper presents two novel theorems that address two open problems in stochastic Lindenmayer-system (L-system) inference, specifically focusing on the construction of an optimal stochastic L-system capable of generating a given sequence of strings. The first theorem delineates a method for crafting a stochastic L-system that maximizes the likelihood of producing a given sequence of words through a singular derivation. Furthermore, the second theorem determines the stochastic L-systems with the highest probability of producing a given sequence of words with multiple possible derivations. From these, we introduce an algorithm to infer an optimal stochastic L-system from a given sequence. This algorithm incorporates sophisticated optimization techniques, such as interior point methods, ensuring production of a stochastically optimal stochastic L-system suitable for generating the given sequence. This allows for the use of using stochastic L-systems as model for machine learning using only positive data for training.
Authors: Georg Stemmer, Jose A. Lopez, Juan A. Del Hoyo Ontiveros, Arvind Raju, Tara Thimmanaik, Sovan Biswas
Abstract: In this work we explore the application of AI to robotic welding. Robotic welding is a widely used technology in many industries, but robots currently do not have the capability to detect welding defects which get introduced due to various reasons in the welding process. We describe how deep-learning methods can be applied to detect weld defects in real-time by recording the welding process with microphones and a camera. Our findings are based on a large database with more than 4000 welding samples we collected which covers different weld types, materials and various defect categories. All deep learning models are trained in an unsupervised fashion because the space of possible defects is large and the defects in our data may contain biases. We demonstrate that a reliable real-time detection of most categories of weld defects is feasible both from audio and video, with improvements achieved by combining both modalities. Specifically, the multi-modal approach achieves an average Area-under-ROC-Curve (AUC) of 0.92 over all eleven defect types in our data. We conclude the paper with an analysis of the results by defect type and a discussion of future work.
Authors: Zijian Chen, Jueqi Wang, Archana Venkataraman
Abstract: We propose an image-conditioned diffusion model to estimate high angular resolution diffusion weighted imaging (DWI) from a low angular resolution acquisition. Our model, which we call QID$^2$, takes as input a set of low angular resolution DWI data and uses this information to estimate the DWI data associated with a target gradient direction. We leverage a U-Net architecture with cross-attention to preserve the positional information of the reference images, further guiding the target image generation. We train and evaluate QID$^2$ on single-shell DWI samples curated from the Human Connectome Project (HCP) dataset. Specifically, we sub-sample the HCP gradient directions to produce low angular resolution DWI data and train QID$^2$ to reconstruct the missing high angular resolution samples. We compare QID$^2$ with two state-of-the-art GAN models. Our results demonstrate that QID$^2$ not only achieves higher-quality generated images, but it consistently outperforms the GAN models in downstream tensor estimation across multiple metrics. Taken together, this study highlights the potential of diffusion models, and QID$^2$ in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications.
Authors: Lina Mar\'ia Amaya-Mej\'ia, Mohamed Ghita, Jan Dentler, Miguel Olivares-Mendez, Carol Martinez
Abstract: On-orbit servicing (OOS) activities will power the next big step for sustainable exploration and commercialization of space. Developing robotic capabilities for autonomous OOS operations is a priority for the space industry. Visual Servoing (VS) enables robots to achieve the precise manoeuvres needed for critical OOS missions by utilizing visual information for motion control. This article presents an overview of existing VS approaches for autonomous OOS operations with space manipulator systems (SMS). We divide the approaches according to their contribution to the typical phases of a robotic OOS mission: a) Recognition, b) Approach, and c) Contact. We also present a discussion on the reviewed VS approaches, identifying current trends. Finally, we highlight the challenges and areas for future research on VS techniques for robotic OOS.
Authors: Sourav Raxit, Simant Bahadur Singh, Abdullah Al Redwan Newaz
Abstract: By harnessing fiducial markers as visual landmarks in the environment, Unmanned Aerial Vehicles (UAVs) can rapidly build precise maps and navigate spaces safely and efficiently, unlocking their potential for fluent collaboration and coexistence with humans. Existing fiducial marker methods rely on handcrafted feature extraction, which sacrifices accuracy. On the other hand, deep learning pipelines for marker detection fail to meet real-time runtime constraints crucial for navigation applications. In this work, we propose YoloTag \textemdash a real-time fiducial marker-based localization system. YoloTag uses a lightweight YOLO v8 object detector to accurately detect fiducial markers in images while meeting the runtime constraints needed for navigation. The detected markers are then used by an efficient perspective-n-point algorithm to estimate UAV states. However, this localization system introduces noise, causing instability in trajectory tracking. To suppress noise, we design a higher-order Butterworth filter that effectively eliminates noise through frequency domain analysis. We evaluate our algorithm through real-robot experiments in an indoor environment, comparing the trajectory tracking performance of our method against other approaches in terms of several distance metrics.
Authors: Deepak Raina, Mythra V. Balakuntala, Byung Wook Kim, Juan Wachs, Richard Voyles
Abstract: Ultrasound is widely employed for clinical intervention and diagnosis, due to its advantages of offering non-invasive, radiation-free, and real-time imaging. However, the accessibility of this dexterous procedure is limited due to the substantial training and expertise required of operators. The robotic ultrasound (RUS) offers a viable solution to address this limitation; nonetheless, achieving human-level proficiency remains challenging. Learning from demonstrations (LfD) methods have been explored in RUS, which learns the policy prior from a dataset of offline demonstrations to encode the mental model of the expert sonographer. However, active engagement of experts, i.e. Coaching, during the training of RUS has not been explored thus far. Coaching is known for enhancing efficiency and performance in human training. This paper proposes a coaching framework for RUS to amplify its performance. The framework combines DRL (self-supervised practice) with sparse expert's feedback through coaching. The DRL employs an off-policy Soft Actor-Critic (SAC) network, with a reward based on image quality rating. The coaching by experts is modeled as a Partially Observable Markov Decision Process (POMDP), which updates the policy parameters based on the correction by the expert. The validation study on phantoms showed that coaching increases the learning rate by $25\%$ and the number of high-quality image acquisition by $74.5\%$.
Authors: Jie Su, Fang Cai, Shu-Kuo Zhao, Xin-Yi Wang, Tian-Yi Qian, Da-Hui Wang, Bo Hong
Abstract: Uncovering the fundamental neural correlates of biological intelligence, developing mathematical models, and conducting computational simulations are critical for advancing new paradigms in artificial intelligence (AI). In this study, we implemented a comprehensive visual decision-making model that spans from visual input to behavioral output, using a neural dynamics modeling approach. Drawing inspiration from the key components of the dorsal visual pathway in primates, our model not only aligns closely with human behavior but also reflects neural activities in primates, and achieving accuracy comparable to convolutional neural networks (CNNs). Moreover, magnetic resonance imaging (MRI) identified key neuroimaging features such as structural connections and functional connectivity that are associated with performance in perceptual decision-making tasks. A neuroimaging-informed fine-tuning approach was introduced and applied to the model, leading to performance improvements that paralleled the behavioral variations observed among subjects. Compared to classical deep learning models, our model more accurately replicates the behavioral performance of biological intelligence, relying on the structural characteristics of biological neural networks rather than extensive training data, and demonstrating enhanced resilience to perturbation.
Authors: Brayan Monroy, Jorge Bacca
Abstract: In this paper, we introduce an efficient algorithm for generating specific Hadamard rows, addressing the memory demands of pre-computing the entire matrix. Leveraging Sylvester's recursive construction, our method generates the required $i$-th row on demand, significantly reducing computational resources. The algorithm uses the Kronecker product to construct the desired row from the binary representation of the index, without creating the full matrix. This approach is particularly useful for single-pixel imaging systems that need only one row at a time.
Authors: Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu
Abstract: Recent empirical studies have demonstrated that diffusion models can effectively learn the image distribution and generate new samples. Remarkably, these models can achieve this even with a small number of training samples despite a large image dimension, circumventing the curse of dimensionality. In this work, we provide theoretical insights into this phenomenon by leveraging key empirical observations: (i) the low intrinsic dimensionality of image data, (ii) a union of manifold structure of image data, and (iii) the low-rank property of the denoising autoencoder in trained diffusion models. These observations motivate us to assume the underlying data distribution of image data as a mixture of low-rank Gaussians and to parameterize the denoising autoencoder as a low-rank model according to the score function of the assumed distribution. With these setups, we rigorously show that optimizing the training loss of diffusion models is equivalent to solving the canonical subspace clustering problem over the training samples. Based on this equivalence, we further show that the minimal number of samples required to learn the underlying distribution scales linearly with the intrinsic dimensions under the above data and model assumptions. This insight sheds light on why diffusion models can break the curse of dimensionality and exhibit the phase transition in learning distributions. Moreover, we empirically establish a correspondence between the subspaces and the semantic representations of image data, facilitating image editing. We validate these results with corroborated experimental results on both simulated distributions and image datasets.
Authors: John Li, Shehab Sarar Ahmed, Deepak Nair
Abstract: Despite the growing adoption of video processing via Internet of Things (IoT) devices due to their cost-effectiveness, transmitting captured data to nearby servers poses challenges due to varying timing constraints and scarcity of network bandwidth. Existing video compression methods face difficulties in recovering compressed data when incomplete data is provided. Here, we introduce \emph{\project}, a deep-learning based solution that utilizes previously received data to predict the missing segments of a frame, enabling the reconstruction of a frame from partially received data.
Authors: Anqi Liu, Shiyi Mu, Shugong Xu
Abstract: Autonomous driving algorithms usually employ sRGB images as model input due to their compatibility with the human visual system. However, visually pleasing sRGB images are possibly sub-optimal for downstream tasks when compared to RAW images. The availability of RAW images is constrained by the difficulties in collecting real-world driving data and the associated challenges of annotation. To address this limitation and support research in RAW-domain driving perception, we design a novel and ultra-lightweight RAW reconstruction method. The proposed model introduces a learnable color correction matrix (CCM), which uses only a single convolutional layer to approximate the complex inverse image signal processor (ISP). Experimental results demonstrate that simulated RAW (simRAW) images generated by our method provide performance improvements equivalent to those produced by more complex inverse ISP methods when pretraining RAW-domain object detectors, which highlights the effectiveness and practicality of our approach.
Authors: Vighnesh Birodkar, Gabriel Barcik, James Lyon, Sergey Ioffe, David Minnen, Joshua V. Dillon
Abstract: For learned image representations, basic autoencoders often produce blurry results. Reconstruction quality can be improved by incorporating additional penalties such as adversarial (GAN) and perceptual losses. Arguably, these approaches lack a principled interpretation. Concurrently, in generative settings diffusion has demonstrated a remarkable ability to create crisp, high quality results and has solid theoretical underpinnings (from variational inference to direct study as the Fisher Divergence). Our work combines autoencoder representation learning with diffusion and is, to our knowledge, the first to demonstrate the efficacy of jointly learning a continuous encoder and decoder under a diffusion-based loss. We demonstrate that this approach yields better reconstruction quality as compared to GAN-based autoencoders while being easier to tune. We also show that the resulting representation is easier to model with a latent diffusion model as compared to the representation obtained from a state-of-the-art GAN-based loss. Since our decoder is stochastic, it can generate details not encoded in the otherwise deterministic latent representation; we therefore name our approach "Sample what you can't compress", or SWYCC for short.
Authors: Ryotaro Shimizu, Yu Wang, Masanari Kimura, Yuki Hirakawa, Takashi Wada, Yuki Saito, Julian McAuley
Abstract: In this work, we propose a fashion item recommendation model that incorporates hyperbolic geometry into user and item representations. Using hyperbolic space, our model aims to capture implicit hierarchies among items based on their visual data and users' purchase history. During training, we apply a multi-task learning framework that considers both hyperbolic and Euclidean distances in the loss function. Our experiments on three data sets show that our model performs better than previous models trained in Euclidean space only, confirming the effectiveness of our model. Our ablation studies show that multi-task learning plays a key role, and removing the Euclidean loss substantially deteriorates the model performance.
Authors: Xudong Ma, Yuqi Zhang, Chenchong Wang, Ming Wang, Mingxin Huang, Wei Xu
Abstract: The intricate microstructure serves as the cornerstone for the composition/processing-structure-property (CPSP) connection in multiphase alloys. Traditional alloy design methods often overlook microstructural details, which diminishes the reliability and effectiveness of the outcomes. This study introduces an improved alloy design algorithm that integrates authentic microstructural information to establish precise CPSP relationships. The approach utilizes a deep-learning framework based on a variational autoencoder to map real microstructural data to a latent space, enabling the prediction of composition, processing steps, and material properties from the latent space vector. By integrating this deep learning model with a specific sampling strategy in the latent space, a novel, microstructure-centered algorithm for multiphase alloy design is developed. This algorithm is demonstrated through the design of a unified dual-phase steel, and the results are assessed at three performance levels. Moreover, an exploration into the latent vector space of the model highlights its seamless interpolation ability and its rich material information content. Notably, the current configuration of the latent space is particularly advantageous for alloy design, offering an exhaustive representation of microstructure, composition, processing, and property variations essential for multiphase alloys.
Authors: Ivan Pereira-S\'anchez, Eloi Sans, Julia Navarro, Joan Duran
Abstract: The objective of pansharpening and hypersharpening is to accurately combine a high-resolution panchromatic (PAN) image with a low-resolution multispectral (MS) or hyperspectral (HS) image, respectively. Unfolding fusion methods integrate the powerful representation capabilities of deep learning with the robustness of model-based approaches. These techniques involve unrolling the steps of the optimization scheme derived from the minimization of an energy into a deep learning framework, resulting in efficient and highly interpretable architectures. In this paper, we propose a model-based deep unfolded method for satellite image fusion. Our approach is based on a variational formulation that incorporates the classic observation model for MS/HS data, a high-frequency injection constraint based on the PAN image, and an arbitrary convex prior. For the unfolding stage, we introduce upsampling and downsampling layers that use geometric information encoded in the PAN image through residual networks. The backbone of our method is a multi-head attention residual network (MARNet), which replaces the proximity operator in the optimization scheme and combines multiple head attentions with residual learning to exploit image self-similarities via nonlocal operators defined in terms of patches. Additionally, we incorporate a post-processing module based on the MARNet architecture to further enhance the quality of the fused images. Experimental results on PRISMA, Quickbird, and WorldView2 datasets demonstrate the superior performance of our method and its ability to generalize across different sensor configurations and varying spatial and spectral resolutions. The source code will be available at https://github.com/TAMI-UIB/MARNet.
Authors: Mazen Soufi, Yoshito Otake, Makoto Iwasa, Keisuke Uemura, Tomoki Hakotani, Masahiro Hashimoto, Yoshitake Yamada, Minoru Yamada, Yoichi Yokoyama, Masahiro Jinzaki, Suzushi Kusano, Masaki Takao, Seiji Okada, Nobuhiko Sugano, Yoshinobu Sato
Abstract: Deep learning-based image segmentation has allowed for the fully automated, accurate, and rapid analysis of musculoskeletal (MSK) structures from medical images. However, current approaches were either applied only to 2D cross-sectional images, addressed few structures, or were validated on small datasets, which limit the application in large-scale databases. This study aimed to validate an improved deep learning model for volumetric MSK segmentation of the hip and thigh with uncertainty estimation from clinical computed tomography (CT) images. Databases of CT images from multiple manufacturers/scanners, disease status, and patient positioning were used. The segmentation accuracy, and accuracy in estimating the structures volume and density, i.e., mean HU, were evaluated. An approach for segmentation failure detection based on predictive uncertainty was also investigated. The model has shown an overall improvement with respect to all segmentation accuracy and structure volume/density evaluation metrics. The predictive uncertainty yielded large areas under the receiver operating characteristic (AUROC) curves (AUROCs>=.95) in detecting inaccurate and failed segmentations. The high segmentation and muscle volume/density estimation accuracy, along with the high accuracy in failure detection based on the predictive uncertainty, exhibited the model's reliability for analyzing individual MSK structures in large-scale CT databases.
Authors: Jeff Mitchell, Jes\'us Mart\'inez del Rinc\'on, Niall McLaughlin
Abstract: While deep neural networks can achieve state-of-the-art performance in many tasks, these models are more fragile than they appear. They are prone to learning spurious correlations in their training data, leading to surprising failure cases. In this paper, we propose a new approach that addresses the issue of spurious correlations: UnLearning from Experience (ULE). Our method is based on using two classification models trained in parallel: student and teacher models. Both models receive the same batches of training data. The student model is trained with no constraints and pursues the spurious correlations in the data. The teacher model is trained to solve the same classification problem while avoiding the mistakes of the student model. As training is done in parallel, the better the student model learns the spurious correlations, the more robust the teacher model becomes. The teacher model uses the gradient of the student's output with respect to its input to unlearn mistakes made by the student. We show that our method is effective on the Waterbirds, CelebA, Spawrious and UrbanCars datasets.
Authors: Xiang Yue, Tianyu Zheng, Yuansheng Ni, Yubo Wang, Kai Zhang, Shengbang Tong, Yuxuan Sun, Ming Yin, Botao Yu, Ge Zhang, Huan Sun, Yu Su, Wenhu Chen, Graham Neubig
Abstract: This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. MMMU-Pro rigorously assesses multimodal models' true understanding and reasoning capabilities through a three-step process based on MMMU: (1) filtering out questions answerable by text-only models, (2) augmenting candidate options, and (3) introducing a vision-only input setting where questions are embedded within images. This setting challenges AI to truly "see" and "read" simultaneously, testing a fundamental human cognitive skill of seamlessly integrating visual and textual information. Results show that model performance is substantially lower on MMMU-Pro than on MMMU, ranging from 16.8% to 26.9% across models. We explore the impact of OCR prompts and Chain of Thought (CoT) reasoning, finding that OCR prompts have minimal effect while CoT generally improves performance. MMMU-Pro provides a more rigorous evaluation tool, closely mimicking real-world scenarios and offering valuable directions for future research in multimodal AI.
Authors: Antonia Alomar, Ricardo Rubio, Laura Salort, Gerard Albaiges, Antoni Pay\`a, Gemma Piella, Federico Sukno
Abstract: Craniofacial anomalies indicate early developmental disturbances and are usually linked to many genetic syndromes. Early diagnosis is critical, yet ultrasound (US) examinations often fail to identify these features. This study presents an AI-driven tool to assist clinicians in standardizing fetal facial axes/planes in 3D US, reducing sonographer workload and facilitating the facial evaluation. Our network, structured into three blocks-feature extractor, rotation and translation regression, and spatial transformer-processes three orthogonal 2D slices to estimate the necessary transformations for standardizing the facial planes in the 3D US. These transformations are applied to the original 3D US using a differentiable module (the spatial transformer block), yielding a standardized 3D US and the corresponding 2D facial standard planes. The dataset used consists of 1180 fetal facial 3D US images acquired between weeks 20 and 35 of gestation. Results show that our network considerably reduces inter-observer rotation variability in the test set, with a mean geodesic angle difference of 14.12$^{\circ}$ $\pm$ 18.27$^{\circ}$ and an Euclidean angle error of 7.45$^{\circ}$ $\pm$ 14.88$^{\circ}$. These findings demonstrate the network's ability to effectively standardize facial axes, crucial for consistent fetal facial assessments. In conclusion, the proposed network demonstrates potential for improving the consistency and accuracy of fetal facial assessments in clinical settings, facilitating early evaluation of craniofacial anomalies.
Authors: Leanne Nortje
Abstract: This dissertation examines visually grounded speech (VGS) models that learn from unlabelled speech paired with images. It focuses on applications for low-resource languages and understanding human language acquisition. We introduce a task called visually prompted keyword localisation to detect and localise keywords in speech using images. We demonstrate the effectiveness of VGS models in few-shot learning scenarios for low-resource languages like Yoruba. Additionally, we examine the mutual exclusivity bias in VGS models. Our monolingual VGS model exhibits this bias, but we found that multilingualism does not affect the bias in this VGS model similarly to what is observed in children.
Authors: Jonathan Zalach, Inbal Gazy, Assaf Avinoam, Ron Sinai, Eran Shmuel, Inbar Gilboa, Christine Swisher, Naim Matasci, Reva Basho, David B. Agus
Abstract: The rapidly evolving field of digital oncopathology faces significant challenges, including the need to address diverse and complex clinical questions, often involving rare conditions, with limited availability of labeled data. These limitations hinder the development of robust AI-driven tools in the biomedical space, where accuracy in probabilistic determinations is of utmost importance. To address this, digital pathology foundation models have begun to emerge, typically developed with the size and diversity of the pre-training dataset and model parameters in mind. Here, we present CanvOI, a ViT-g/10-based foundation model designed to enhance the capabilities of digital pathology by addressing these challenges through a different approach. Considering the unique nature of oncologic histopathological images and the requirements from the embeddings to provide meaningful representations for Multiple Instance Learning (MIL) downstream models, we chose to modify the input image characteristics. By introducing larger tile sizes (380 x 380 pixels) and smaller patch sizes (10 x 10 pixels), we were able to optimize the model's performance, pushing computational resources in a new direction and achieving state-of-the-art performance on cancer-related benchmarks. CanvOI demonstrated a 1.5-7.4% improvement in averaged AUC compared to other leading foundation models built for digital pathology. Moreover, our results demonstrate that CanvOI significantly outperformed the other models, with the performance gap widening substantially when trained on just 10% of the initial cohort. This work highlights an alternative approach that, if integrated with traditional development approaches, has the potential to advance Oncology Intelligence (OI), overcome some of the current barriers and ultimately improve the clinical outcome of cancer patients.
Authors: Xidong Wang, Dingjie Song, Shunian Chen, Chen Zhang, Benyou Wang
Abstract: Expanding the long-context capabilities of Multi-modal Large Language Models~(MLLMs) is crucial for video understanding, high-resolution image understanding, and multi-modal agents. This involves a series of systematic optimizations, including model architecture, data construction and training strategy, particularly addressing challenges such as \textit{degraded performance with more images} and \textit{high computational costs}. In this paper, we adapt the model architecture to a hybrid of Mamba and Transformer blocks, approach data construction with both temporal and spatial dependencies among multiple images and employ a progressive training strategy. The released model \textbf{LongLLaVA}~(\textbf{Long}-Context \textbf{L}arge \textbf{L}anguage \textbf{a}nd \textbf{V}ision \textbf{A}ssistant) is the first hybrid MLLM, which achieved a better balance between efficiency and effectiveness. LongLLaVA not only achieves competitive results across various benchmarks, but also maintains high throughput and low memory consumption. Especially, it could process nearly a thousand images on a single A100 80GB GPU, showing promising application prospects for a wide range of tasks.
Authors: Xiongkun Linghu, Yan Bai, Yihang Lou, Shengsen Wu, Jinze Li, Jianzhong He, Tao Bai
Abstract: Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like machine learning. State-of-the-art solutions involve learning to find a good metric and representation space to compute the distance between samples. Despite the promising accuracy performance, how to model uncertainty for metric-based FSC methods effectively is still a challenge. To model uncertainty, We place a distribution over class probability based on the theory of evidence. As a result, uncertainty modeling and metric learning can be decoupled. To reduce the uncertainty of classification, we propose a Bayesian evidence fusion theorem. Given observed samples, the network learns to get posterior distribution parameters given the prior parameters produced by the pre-trained network. Detailed gradient analysis shows that our method provides a smooth optimization target and can capture the uncertainty. The proposed method is agnostic to metric learning strategies and can be implemented as a plug-and-play module. We integrate our method into several newest FSC methods and demonstrate the improved accuracy and uncertainty quantification on standard FSC benchmarks.
Authors: Dimitrios Kollias, Andreas Psaroudakis, Anastasios Arsenos, Paraskevi Theofilou, Chunchang Shao, Guanyu Hu, Ioannis Patras
Abstract: This paper presents MMA-MRNNet, a novel deep learning architecture for dynamic multi-output Facial Expression Intensity Estimation (FEIE) from video data. Traditional approaches to this task often rely on complex 3-D CNNs, which require extensive pre-training and assume that facial expressions are uniformly distributed across all frames of a video. These methods struggle to handle videos of varying lengths, often resorting to ad-hoc strategies that either discard valuable information or introduce bias. MMA-MRNNet addresses these challenges through a two-stage process. First, the Multiple Models of Affect (MMA) extractor component is a Multi-Task Learning CNN that concurrently estimates valence-arousal, recognizes basic facial expressions, and detects action units in each frame. These representations are then processed by a Masked RNN component, which captures temporal dependencies and dynamically updates weights according to the true length of the input video, ensuring that only the most relevant features are used for the final prediction. The proposed unimodal non-ensemble learning MMA-MRNNet was evaluated on the Hume-Reaction dataset and demonstrated significantly superior performance, surpassing state-of-the-art methods by a wide margin, regardless of whether they were unimodal, multimodal, or ensemble approaches. Finally, we demonstrated the effectiveness of the MMA component of our proposed method across multiple in-the-wild datasets, where it consistently outperformed all state-of-the-art methods across various metrics.
Authors: Milad Moradi, Ke Yan, David Colwell, Matthias Samwald, Rhona Asgari
Abstract: In recent years, deep neural networks have been widely used for building high-performance Artificial Intelligence (AI) systems for computer vision applications. Object detection is a fundamental task in computer vision, which has been greatly progressed through developing large and intricate AI models. However, the lack of transparency is a big challenge that may not allow the widespread adoption of these models. Explainable artificial intelligence is a field of research where methods are developed to help users understand the behavior, decision logics, and vulnerabilities of AI systems. Previously, few explanation methods were developed for object detection based on random masking. However, random masks may raise some issues regarding the actual importance of pixels within an image. In this paper, we design and implement a black-box explanation method named Black-box Object Detection Explanation by Masking (BODEM) through adopting a hierarchical random masking approach for object detection systems. We propose a hierarchical random masking framework in which coarse-grained masks are used in lower levels to find salient regions within an image, and fine-grained mask are used to refine the salient regions in higher levels. Experimentations on various object detection datasets and models showed that BODEM can effectively explain the behavior of object detectors. Moreover, our method outperformed Detector Randomized Input Sampling for Explanation (D-RISE) and Local Interpretable Model-agnostic Explanations (LIME) with respect to different quantitative measures of explanation effectiveness. The experimental results demonstrate that BODEM can be an effective method for explaining and validating object detection systems in black-box testing scenarios.
Authors: Ziwei Wang, Timothy Molloy, Pieter van Goor, Robert Mahony
Abstract: Event-based cameras are popular for tracking fast-moving objects due to their high temporal resolution, low latency, and high dynamic range. In this paper, we propose a novel algorithm for tracking event blobs using raw events asynchronously in real time. We introduce the concept of an event blob as a spatio-temporal likelihood of event occurrence where the conditional spatial likelihood is blob-like. Many real-world objects such as car headlights or any quickly moving foreground objects generate event blob data. The proposed algorithm uses a nearest neighbour classifier with a dynamic threshold criteria for data association coupled with an extended Kalman filter to track the event blob state. Our algorithm achieves highly accurate blob tracking, velocity estimation, and shape estimation even under challenging lighting conditions and high-speed motions (> 11000 pixels/s). The microsecond time resolution achieved means that the filter output can be used to derive secondary information such as time-to-contact or range estimation, that will enable applications to real-world problems such as collision avoidance in autonomous driving.
Authors: Sushmanth reddy, Jyothi Swaroop Reddy
Abstract: Eye tracking has been a pivotal tool in diverse fields such as vision research, language analysis, and usability assessment. The majority of prior investigations, however, have concentrated on expansive desktop displays employing specialized, costly eye tracking hardware that lacks scalability. Remarkably little insight exists into ocular movement patterns on smartphones, despite their widespread adoption and significant usage. In this manuscript, we present an open-source implementation of a smartphone-based gaze tracker that emulates the methodology proposed by a GooglePaper (whose source code remains proprietary). Our focus is on attaining accuracy comparable to that attained through the GooglePaper's methodology, without the necessity for supplementary hardware. Through the integration of machine learning techniques, we unveil an accurate eye tracking solution that is native to smartphones. Our approach demonstrates precision akin to the state-of-the-art mobile eye trackers, which are characterized by a cost that is two orders of magnitude higher. Leveraging the vast MIT GazeCapture dataset, which is available through registration on the dataset's website, we successfully replicate crucial findings from previous studies concerning ocular motion behavior in oculomotor tasks and saliency analyses during natural image observation. Furthermore, we emphasize the applicability of smartphone-based gaze tracking in discerning reading comprehension challenges. Our findings exhibit the inherent potential to amplify eye movement research by significant proportions, accommodating participation from thousands of subjects with explicit consent. This scalability not only fosters advancements in vision research, but also extends its benefits to domains such as accessibility enhancement and healthcare applications.
Authors: Henik Riedel, Robert Steven Lorenzen, Clemens H\"ubler
Abstract: As infrastructure ages, the need for efficient monitoring methods becomes increasingly critical. Bridge Weigh-In-Motion (BWIM) systems are crucial for cost-efficient load and thus residual service life determination of road and railway infrastructure. However, conventional BWIM systems require additional sensors for axle detection, which have to be installed in potentially inaccessible locations or in locations that interfere with bridge operation. This study addresses this challenge by replacing dedicated axle detectors with a novel approach to real-time detection of train axles using sensors arbitrarily placed on bridges. The proposed Virtual Axle Detector with Enhanced Receptive Field (VADER) has been validated on a single-track railway bridge, demonstrating that it achieves to detect 99.9% of axles with a spatial error of 3.69cm using only acceleration measurements. Using raw data as input outperforms the state-of-the-art spectrogram-based method in both speed and memory usage by 99%, making real-time application feasible for the first time. Additionally, we introduce the Maximum Receptive Field (MRF) rule, a novel approach to optimise hyperparameters of Convolutional Neural Networks (CNNs) based on the size of objects, which in this case relates to the fundamental frequency of a bridge. The MRF rule effectively narrows the hyperparameter search space, potentially replacing the need for extensive hyperparameter tuning. Since the MRF rule is theoretically applicable to all unstructured data, it could have implications for a wide range of deep learning problems from earthquake prediction to object recognition.
Authors: Shanmin Yang, Hui Guo, Shu Hu, Bin Zhu, Ying Fu, Siwei Lyu, Xi Wu, Xin Wang
Abstract: Deepfake technology poses a significant threat to security and social trust. Although existing detection methods have shown high performance in identifying forgeries within datasets that use the same deepfake techniques for both training and testing, they suffer from sharp performance degradation when faced with cross-dataset scenarios where unseen deepfake techniques are tested. To address this challenge, we propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF). Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. Specifically, it adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination. Moreover, it optimizes these two kinds of information to be independent with a de-correlation learning module, thereby enhancing the model's robustness against various irrelevant information changes and generalization ability to unseen forgery methods. Our extensive experimental evaluation and comparison with existing state-of-the-art detection methods validate the effectiveness and superiority of the DID framework on cross-dataset deepfake detection.
Authors: Maximilian Krahn, Michele Sasdelli, Fengyi Yang, Vladislav Golyanik, Juho Kannala, Tat-Jun Chin, Tolga Birdal
Abstract: We present, QP-SBGD, a novel layer-wise stochastic optimiser tailored towards training neural networks with binary weights, known as binary neural networks (BNNs), on quantum hardware. BNNs reduce the computational requirements and energy consumption of deep learning models with minimal loss in accuracy. However, training them in practice remains to be an open challenge. Most known BNN-optimisers either rely on projected updates or binarise weights post-training. Instead, QP-SBGD approximately maps the gradient onto binary variables, by solving a quadratic constrained binary optimisation. Under practically reasonable assumptions, we show that this update rule converges with a rate of $\mathcal{O}(1 / \sqrt{T})$. Moreover, we show how the $\mathcal{NP}$-hard projection can be effectively executed on an adiabatic quantum annealer, harnessing recent advancements in quantum computation. We also introduce a projected version of this update rule and prove that if a fixed point exists in the binary variable space, the modified updates will converge to it. Last but not least, our algorithm is implemented layer-wise, making it suitable to train larger networks on resource-limited quantum hardware. Through extensive evaluations, we show that QP-SBGD outperforms or is on par with competitive and well-established baselines such as BinaryConnect, signSGD and ProxQuant when optimising the Rosenbrock function, training BNNs as well as binary graph neural networks.
Authors: Supreeth Mysore Venkatesh, Antonio Macaluso, Marlon Nuske, Matthias Klusch, Andreas Dengel
Abstract: We present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixel-wise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology of the D-Wave Advantage device, offering superior scalability over existing quantum approaches and outperforming several tested state-of-the-art classical methods. Empirical evaluations on synthetic datasets have shown that Q-Seg has better runtime performance than the state-of-the-art classical optimizer Gurobi. The method has also been tested on earth observation image segmentation, a critical area with noisy and unreliable annotations. In the era of noisy intermediate-scale quantum, Q-Seg emerges as a reliable contender for real-world applications in comparison to advanced techniques like Segment Anything. Consequently, Q-Seg offers a promising solution using available quantum hardware, especially in situations constrained by limited labeled data and the need for efficient computational runtime.
Authors: Shanle Yao, Babak Rahimi Ardabili, Armin Danesh Pazho, Ghazal Alinezhad Noghre, Christopher Neff, Lauren Bourque, Hamed Tabkhi
Abstract: This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera networks, leveraging recent advancements in AI for easy adoption. Prioritizing privacy and ethical standards, pose based data is used for downstream AI tasks such as anomaly detection. Cloud-based infrastructure and mobile app are deployed, enabling real-time alerts within communities. The SVS employs innovative data representation and visualization techniques, such as the Occupancy Indicator, Statistical Anomaly Detection, Bird's Eye View, and Heatmaps, to understand pedestrian behaviors and enhance public safety. Evaluation of the SVS demonstrates its capacity to convert complex computer vision outputs into actionable insights for stakeholders, community partners, law enforcement, urban planners, and social scientists. This article presents a comprehensive real-world deployment and evaluation of the SVS, implemented in a community college environment across 16 cameras. The system integrates AI-driven visual processing, supported by statistical analysis, database management, cloud communication, and user notifications. Additionally, the article evaluates the end-to-end latency from the moment an AI algorithm detects anomalous behavior in real-time at the camera level to the time stakeholders receive a notification. The results demonstrate the system's robustness, effectively managing 16 CCTV cameras with a consistent throughput of 16.5 frames per second (FPS) over a 21-hour period and an average end-to-end latency of 26.76 seconds between anomaly detection and alert issuance.
Authors: Lei Zhang, Fangxun Shu, Tianyang Liu, Sucheng Ren, Hao Jiang, Cihang Xie
Abstract: The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which can adversely affect the model performance. This highlights the critical role of data filtering, not only to enhance training efficiency but also to improve overall data quality. Existing methods typically rely on metrics such as CLIP Score and BLIP Score, which are derived from pre-trained models. However, these models are often trained on uncurated, noisy datasets, which can perpetuate errors and misalignments in the filtered dataset. We present a novel algorithm that incorporates human knowledge on image-text alignment to guide filtering vast corpus of web-crawled image-text datasets into a compact and high-quality form. To systemically capture human preferences on image-text alignments, we collect a diverse image-text dataset where each image is associated with multiple captions from various sources, and establish a comprehensive set of both subjective and objective criteria for critically guiding the alignment assessment from labelers. Additionally, we train a reward model on these human-preference annotations to internalize the nuanced human understanding of image-text alignment. The resulting reward model thus can act as a human-like referee to filter image-text pairs. Extensive experiments demonstrate that we can maintain, sometimes even improve, model performance while compressing the image-text datasets up to ~90%. An impressive example is that, by aggressively reducing the total training sample from 130M to only 15.5M, our BLIP-B/16 models consistently show an average improvement of 2.9% on retrieval tasks and 11.5% on captioning tasks compared to full-size-dataset counterparts.
Authors: Honghao Fu, Zhiqi Shen, Jing Jih Chin, Hao Wang
Abstract: Analyzing and reconstructing visual stimuli from brain signals effectively advances the understanding of human visual system. However, the EEG signals are complex and contain significant noise. This leads to substantial limitations in existing works of visual stimuli reconstruction from EEG, such as difficulties in aligning EEG embeddings with the fine-grained semantic information and a heavy reliance on additional large self-collected dataset for training. To address these challenges, we propose a novel approach called BrainVis. Firstly, we divide the EEG signals into various units and apply a self-supervised approach on them to obtain EEG time-domain features, in an attempt to ease the training difficulty. Additionally, we also propose to utilize the frequency-domain features to enhance the EEG representations. Then, we simultaneously align EEG time-frequency embeddings with the interpolation of the coarse and fine-grained semantics in the CLIP space, to highlight the primary visual components and reduce the cross-modal alignment difficulty. Finally, we adopt the cascaded diffusion models to reconstruct images. Using only 10\% training data of the previous work, our proposed BrainVis outperforms state of the arts in both semantic fidelity reconstruction and generation quality. The code is available at https://github.com/RomGai/BrainVis.
Authors: Weijian Huang, Cheng Li, Hao Yang, Jiarun Liu, Yong Liang, Hairong Zheng, Shanshan Wang
Abstract: Recently, vision-language representation learning has made remarkable advancements in building up medical foundation models, holding immense potential for transforming the landscape of clinical research and medical care. The underlying hypothesis is that the rich knowledge embedded in radiology reports can effectively assist and guide the learning process, reducing the need for additional labels. However, these reports tend to be complex and sometimes even consist of redundant descriptions that make the representation learning too challenging to capture the key semantic information. This paper develops a novel iterative vision-language representation learning framework by proposing a key semantic knowledge-emphasized report refinement method. Particularly, raw radiology reports are refined to highlight the key information according to a constructed clinical dictionary and two model-optimized knowledge-enhancement metrics. The iterative framework is designed to progressively learn, starting from gaining a general understanding of the patient's condition based on raw reports and gradually refines and extracts critical information essential to the fine-grained analysis tasks. The effectiveness of the proposed framework is validated on various downstream medical image analysis tasks, including disease classification, region-of-interest segmentation, and phrase grounding. Our framework surpasses seven state-of-the-art methods in both fine-tuning and zero-shot settings, demonstrating its encouraging potential for different clinical applications.
Authors: Konstantin A. Maslov, Claudio Persello, Thomas Schellenberger, Alfred Stein
Abstract: Accurate global glacier mapping is critical for understanding climate change impacts. Despite its importance, automated glacier mapping at a global scale remains largely unexplored. Here we address this gap and propose Glacier-VisionTransformer-U-Net (GlaViTU), a convolutional-transformer deep learning model, and five strategies for multitemporal global-scale glacier mapping using open satellite imagery. Assessing the spatial, temporal and cross-sensor generalisation shows that our best strategy achieves intersection over union >0.85 on previously unobserved images in most cases, which drops to >0.75 for debris-rich areas such as High-Mountain Asia and increases to >0.90 for regions dominated by clean ice. A comparative validation against human expert uncertainties in terms of area and distance deviations underscores GlaViTU performance, approaching or matching expert-level delineation. Adding synthetic aperture radar data, namely, backscatter and interferometric coherence, increases the accuracy in all regions where available. The calibrated confidence for glacier extents is reported making the predictions more reliable and interpretable. We also release a benchmark dataset that covers 9% of glaciers worldwide. Our results support efforts towards automated multitemporal and global glacier mapping.
Authors: Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo
Abstract: Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation. Recent diffusion models for video generation have predominantly utilized attention layers to extract temporal features. However, attention layers are limited by their computational costs, which increase quadratically with the sequence length. This limitation presents significant challenges when generating longer video sequences using diffusion models. To overcome this challenge, we propose leveraging state-space models (SSMs) as temporal feature extractors. SSMs (e.g., Mamba) have recently gained attention as promising alternatives due to their linear-time memory consumption relative to sequence length. In line with previous research suggesting that using bidirectional SSMs is effective for understanding spatial features in image generation, we found that bidirectionality is also beneficial for capturing temporal features in video data, rather than relying on traditional unidirectional SSMs. We conducted comprehensive evaluations on multiple long-term video datasets, such as MineRL Navigate, across various model sizes. For sequences up to 256 frames, SSM-based models require less memory to achieve the same FVD as attention-based models. Moreover, SSM-based models often deliver better performance with comparable GPU memory usage. Our codes are available at https://github.com/shim0114/SSM-Meets-Video-Diffusion-Models.
URLs: https://github.com/shim0114/SSM-Meets-Video-Diffusion-Models.
Authors: Haojie Mu, Burhan Ul Tayyab, Nicholas Chua
Abstract: We present SpiralMLP, a novel architecture that introduces a Spiral FC layer as a replacement for the conventional Token Mixing approach. Differing from several existing MLP-based models that primarily emphasize axes, our Spiral FC layer is designed as a deformable convolution layer with spiral-like offsets. We further adapt Spiral FC into two variants: Self-Spiral FC and Cross-Spiral FC, which enable both local and global feature integration seamlessly, eliminating the need for additional processing steps. To thoroughly investigate the effectiveness of the spiral-like offsets and validate our design, we conduct ablation studies and explore optimal configurations. In empirical tests, SpiralMLP reaches state-of-the-art performance, similar to Transformers, CNNs, and other MLPs, benchmarking on ImageNet-1k, COCO and ADE20K. SpiralMLP still maintains linear computational complexity O(HW) and is compatible with varying input image resolutions. Our study reveals that targeting the full receptive field is not essential for achieving high performance, instead, adopting a refined approach offers better results.
Authors: Marah Halawa, Florian Blume, Pia Bideau, Martin Maier, Rasha Abdel Rahman, Olaf Hellwich
Abstract: Human communication is multi-modal; e.g., face-to-face interaction involves auditory signals (speech) and visual signals (face movements and hand gestures). Hence, it is essential to exploit multiple modalities when designing machine learning-based facial expression recognition systems. In addition, given the ever-growing quantities of video data that capture human facial expressions, such systems should utilize raw unlabeled videos without requiring expensive annotations. Therefore, in this work, we employ a multitask multi-modal self-supervised learning method for facial expression recognition from in-the-wild video data. Our model combines three self-supervised objective functions: First, a multi-modal contrastive loss, that pulls diverse data modalities of the same video together in the representation space. Second, a multi-modal clustering loss that preserves the semantic structure of input data in the representation space. Finally, a multi-modal data reconstruction loss. We conduct a comprehensive study on this multimodal multi-task self-supervised learning method on three facial expression recognition benchmarks. To that end, we examine the performance of learning through different combinations of self-supervised tasks on the facial expression recognition downstream task. Our model ConCluGen outperforms several multi-modal self-supervised and fully supervised baselines on the CMU-MOSEI dataset. Our results generally show that multi-modal self-supervision tasks offer large performance gains for challenging tasks such as facial expression recognition, while also reducing the amount of manual annotations required. We release our pre-trained models as well as source code publicly
Authors: Guosheng Lu, Zile Fang, Jiaju Tian, Haowen Huang, Yuelong Xu, Zhuolin Han, Yaoming Kang, Can Feng, Zhigang Zhao
Abstract: Infrared and visible image fusion (IVIF) aims to preserve thermal radiation information from infrared images while integrating texture details from visible images. Thermal radiation information is mainly expressed through image intensities, while texture details are typically expressed through image gradients. However, existing dual-discriminator generative adversarial networks (GANs) often rely on two structurally identical discriminators for learning, which do not fully account for the distinct learning needs of infrared and visible image information. To this end, this paper proposes a novel GAN with a heterogeneous dual-discriminator network and an attention-based fusion strategy (GAN-HA). Specifically, recognizing the intrinsic differences between infrared and visible images, we propose, for the first time, a novel heterogeneous dual-discriminator network to simultaneously capture thermal radiation information and texture details. The two discriminators in this network are structurally different, including a salient discriminator for infrared images and a detailed discriminator for visible images. They are able to learn rich image intensity information and image gradient information, respectively. In addition, a new attention-based fusion strategy is designed in the generator to appropriately emphasize the learned information from different source images, thereby improving the information representation ability of the fusion result. In this way, the fused images generated by GAN-HA can more effectively maintain both the salience of thermal targets and the sharpness of textures. Extensive experiments on various public datasets demonstrate the superiority of GAN-HA over other state-of-the-art (SOTA) algorithms while showcasing its higher potential for practical applications.
Authors: Haoyu Wang, Zhilu Zhang, Donglin Di, Shiliang Zhang, Wangmeng Zuo
Abstract: The goal of image-based virtual try-on is to generate an image of the target person naturally wearing the given clothing. However, existing methods solely focus on the frontal try-on using the frontal clothing. When the views of the clothing and person are significantly inconsistent, particularly when the person's view is non-frontal, the results are unsatisfactory. To address this challenge, we introduce Multi-View Virtual Try-ON (MV-VTON), which aims to reconstruct the dressing results from multiple views using the given clothes. Given that single-view clothes provide insufficient information for MV-VTON, we instead employ two images, i.e., the frontal and back views of the clothing, to encompass the complete view as much as possible. Moreover, we adopt diffusion models that have demonstrated superior abilities to perform our MV-VTON. In particular, we propose a view-adaptive selection method where hard-selection and soft-selection are applied to the global and local clothing feature extraction, respectively. This ensures that the clothing features are roughly fit to the person's view. Subsequently, we suggest joint attention blocks to align and fuse clothing features with person features. Additionally, we collect a MV-VTON dataset MVG, in which each person has multiple photos with diverse views and poses. Experiments show that the proposed method not only achieves state-of-the-art results on MV-VTON task using our MVG dataset, but also has superiority on frontal-view virtual try-on task using VITON-HD and DressCode datasets. Codes and datasets are publicly released at https://github.com/hywang2002/MV-VTON .
Authors: Zhiqiang Shen, Peng Cao, Junming Su, Jinzhu Yang, Osmar R. Zaiane
Abstract: This paper investigates an extremely challenging problem: barely-supervised volumetric medical image segmentation (BSS). A BSS training dataset consists of two parts: 1) a barely-annotated labeled set, where each labeled image contains only a single-slice annotation, and 2) an unlabeled set comprising numerous unlabeled volumetric images. State-of-the-art BSS methods employ a registration-based paradigm, which uses inter-slice image registration to propagate single-slice annotations into volumetric pseudo labels, constructing a completely annotated labeled set, to which a semi-supervised segmentation scheme can be applied. However, the paradigm has a critical limitation: the pseudo-labels generated by image registration are unreliable and noisy. Motivated by this, we propose a new perspective: instead of solving BSS within a semi-supervised learning scheme, this work formulates BSS as an unsupervised domain adaptation problem. To this end, we propose a novel BSS framework, \textbf{B}arely-supervised learning \textbf{via} unsupervised domain \textbf{A}daptation (BvA), as an alternative to the dominant registration paradigm. Specifically, we first design a novel noise-free labeled data construction algorithm (NFC) for slice-to-volume labeled data synthesis. Then, we introduce a frequency and spatial Mix-Up strategy (FSX) to mitigate the domain shifts. Extensive experiments demonstrate that our method provides a promising alternative for BSS. Remarkably, the proposed method, trained on the left atrial segmentation dataset with \textbf{only one} barely-labeled image, achieves a Dice score of 81.20%, outperforming the state-of-the-art by 61.71%. The code is available at https://github.com/Senyh/BvA.
Authors: Sangyeop Yeo, Yoojin Jang, Jaejun Yoo
Abstract: In this paper, we address the challenge of compressing generative adversarial networks (GANs) for deployment in resource-constrained environments by proposing two novel methodologies: Distribution Matching for Efficient compression (DiME) and Network Interactive Compression via Knowledge Exchange and Learning (NICKEL). DiME employs foundation models as embedding kernels for efficient distribution matching, leveraging maximum mean discrepancy to facilitate effective knowledge distillation. Simultaneously, NICKEL employs an interactive compression method that enhances the communication between the student generator and discriminator, achieving a balanced and stable compression process. Our comprehensive evaluation on the StyleGAN2 architecture with the FFHQ dataset shows the effectiveness of our approach, with NICKEL & DiME achieving FID scores of 10.45 and 15.93 at compression rates of 95.73% and 98.92%, respectively. Remarkably, our methods sustain generative quality even at an extreme compression rate of 99.69%, surpassing the previous state-of-the-art performance by a large margin. These findings not only demonstrate our methodologies' capacity to significantly lower GANs' computational demands but also pave the way for deploying high-quality GAN models in settings with limited resources. Our code will be released soon.
Authors: Haruo Fujiwara, Yusuke Mukuta, Tatsuya Harada
Abstract: We propose a simple yet effective pipeline for stylizing a 3D scene, harnessing the power of 2D image diffusion models. Given a NeRF model reconstructed from a set of multi-view images, we perform 3D style transfer by refining the source NeRF model using stylized images generated by a style-aligned image-to-image diffusion model. Given a target style prompt, we first generate perceptually similar multi-view images by leveraging a depth-conditioned diffusion model with an attention-sharing mechanism. Next, based on the stylized multi-view images, we propose to guide the style transfer process with the sliced Wasserstein loss based on the feature maps extracted from a pre-trained CNN model. Our pipeline consists of decoupled steps, allowing users to test various prompt ideas and preview the stylized 3D result before proceeding to the NeRF fine-tuning stage. We demonstrate that our method can transfer diverse artistic styles to real-world 3D scenes with competitive quality. Result videos are also available on our project page: https://haruolabs.github.io/style-n2n/
Authors: Vlad Hosu, Lorenzo Agnolucci, Oliver Wiedemann, Daisuke Iso, Dietmar Saupe
Abstract: We introduce a novel Image Quality Assessment (IQA) dataset comprising 6073 UHD-1 (4K) images, annotated at a fixed width of 3840 pixels. Contrary to existing No-Reference (NR) IQA datasets, ours focuses on highly aesthetic photos of high technical quality, filling a gap in the literature. The images, carefully curated to exclude synthetic content, are sufficiently diverse to train general NR-IQA models. Importantly, the dataset is annotated with perceptual quality ratings obtained through a crowdsourcing study. Ten expert raters, comprising photographers and graphics artists, assessed each image at least twice in multiple sessions spanning several days, resulting in 20 highly reliable ratings per image. Annotators were rigorously selected based on several metrics, including self-consistency, to ensure their reliability. The dataset includes rich metadata with user and machine-generated tags from over 5,000 categories and popularity indicators such as favorites, likes, downloads, and views. With its unique characteristics, such as its focus on high-quality images, reliable crowdsourced annotations, and high annotation resolution, our dataset opens up new opportunities for advancing perceptual image quality assessment research and developing practical NR-IQA models that apply to modern photos. Our dataset is available at https://database.mmsp-kn.de/uhd-iqa-benchmark-database.html
URLs: https://database.mmsp-kn.de/uhd-iqa-benchmark-database.html
Authors: Yuejiao Su, Yi Wang, Lap-Pui Chau
Abstract: Egocentric hand-object segmentation (EgoHOS) is a promising new task aiming at segmenting hands and interacting objects in egocentric images. Although EgoHOS has the potential to enable various applications, current methods struggle to achieve both high performance and end-to-end optimization simultaneously. Moreover, existing approaches fail to fully leverage hand cues to assist the interacting-object segmentation and overlook the coupled relationships between diverse interacting-object categories, resulting in performance deficiencies. To address these limitations, this paper proposes a novel Object-centric Relationship Modeling Network (ORMNet) to fulfill end-to-end and effective EgoHOS by modeling relationships between hands and objects as well as objects and objects. Specifically, a Hand-Object Relation (HOR) module is introduced to capture the correlation between hands and objects, which uses hand features to guide the network to extract more distinguishing interacting-object features. Besides, we find the coupling relations between diverse interacting-object categories and design the Object Relation Decoupling (ORD) strategy to disentangle them, emphasizing learning of the interaction between hands and objects and reducing the confusion of interacting-object classification. In-domain experiments show that ORMNet has notably exceptional segmentation performance compared with state-of-the-art methods, while out-of-domain experiments further exhibit its robust generalization capability. The project is available at https://github.com/yuggiehk/ORMNet/
Authors: Seonghui Min, Hyun-Jic Oh, Won-Ki Jeong
Abstract: In multi-class histopathology nuclei analysis tasks, the lack of training data becomes a main bottleneck for the performance of learning-based methods. To tackle this challenge, previous methods have utilized generative models to increase data by generating synthetic samples. However, existing methods often overlook the importance of considering the context of biological tissues (e.g., shape, spatial layout, and tissue type) in the synthetic data. Moreover, while generative models have shown superior performance in synthesizing realistic histopathology images, none of the existing methods are capable of producing image-label pairs at the same time. In this paper, we introduce a novel framework for co-synthesizing histopathology nuclei images and paired semantic labels using a context-conditioned joint diffusion model. We propose conditioning of a diffusion model using nucleus centroid layouts with structure-related text prompts to incorporate spatial and structural context information into the generation targets. Moreover, we enhance the granularity of our synthesized semantic labels by generating instance-wise nuclei labels using distance maps synthesized concurrently in conjunction with the images and semantic labels. We demonstrate the effectiveness of our framework in generating high-quality samples on multi-institutional, multi-organ, and multi-modality datasets. Our synthetic data consistently outperforms existing augmentation methods in the downstream tasks of nuclei segmentation and classification.
Authors: Pascal Spiegler, Amirhossein Rasoulian, Yiming Xiao
Abstract: Intracranial hemorrhage (ICH) is a life-threatening condition that requires rapid and accurate diagnosis to improve treatment outcomes and patient survival rates. Recent advancements in supervised deep learning have greatly improved the analysis of medical images, but often rely on extensive datasets with high-quality annotations, which are costly, time-consuming, and require medical expertise to prepare. To mitigate the need for large amounts of expert-prepared segmentation data, we have developed a novel weakly supervised ICH segmentation method that utilizes the YOLO object detection model and an uncertainty-rectified Segment Anything Model (SAM). In addition, we have proposed a novel point prompt generator for this model to further improve segmentation results with YOLO-predicted bounding box prompts. Our approach achieved a high accuracy of 0.933 and an AUC of 0.796 in ICH detection, along with a mean Dice score of 0.629 for ICH segmentation, outperforming existing weakly supervised and popular supervised (UNet and Swin-UNETR) approaches. Overall, the proposed method provides a robust and accurate alternative to the more commonly used supervised techniques for ICH quantification without requiring refined segmentation ground truths during model training.
Authors: Hong Guan, Yancheng Wang, Lulu Xie, Soham Nag, Rajeev Goel, Niranjan Erappa Narayana Swamy, Yingzhen Yang, Chaowei Xiao, Jonathan Prisby, Ross Maciejewski, Jia Zou
Abstract: Effective fraud detection and analysis of government-issued identity documents, such as passports, driver's licenses, and identity cards, are essential in thwarting identity theft and bolstering security on online platforms. The training of accurate fraud detection and analysis tools depends on the availability of extensive identity document datasets. However, current publicly available benchmark datasets for identity document analysis, including MIDV-500, MIDV-2020, and FMIDV, fall short in several respects: they offer a limited number of samples, cover insufficient varieties of fraud patterns, and seldom include alterations in critical personal identifying fields like portrait images, limiting their utility in training models capable of detecting realistic frauds while preserving privacy. In response to these shortcomings, our research introduces a new benchmark dataset, IDNet, designed to advance privacy-preserving fraud detection efforts. The IDNet dataset comprises 837,060 images of synthetically generated identity documents, totaling approximately 490 gigabytes, categorized into 20 types from $10$ U.S. states and 10 European countries. We evaluate the utility and present use cases of the dataset, illustrating how it can aid in training privacy-preserving fraud detection methods, facilitating the generation of camera and video capturing of identity documents, and testing schema unification and other identity document management functionalities.
Authors: Xiaogen Zhou, Yiyou Sun, Min Deng, Winnie Chiu Wing Chu, Qi Dou
Abstract: Multimodal learning leverages complementary information derived from different modalities, thereby enhancing performance in medical image segmentation. However, prevailing multimodal learning methods heavily rely on extensive well-annotated data from various modalities to achieve accurate segmentation performance. This dependence often poses a challenge in clinical settings due to limited availability of such data. Moreover, the inherent anatomical misalignment between different imaging modalities further complicates the endeavor to enhance segmentation performance. To address this problem, we propose a novel semi-supervised multimodal segmentation framework that is robust to scarce labeled data and misaligned modalities. Our framework employs a novel cross modality collaboration strategy to distill modality-independent knowledge, which is inherently associated with each modality, and integrates this information into a unified fusion layer for feature amalgamation. With a channel-wise semantic consistency loss, our framework ensures alignment of modality-independent information from a feature-wise perspective across modalities, thereby fortifying it against misalignments in multimodal scenarios. Furthermore, our framework effectively integrates contrastive consistent learning to regulate anatomical structures, facilitating anatomical-wise prediction alignment on unlabeled data in semi-supervised segmentation tasks. Our method achieves competitive performance compared to other multimodal methods across three tasks: cardiac, abdominal multi-organ, and thyroid-associated orbitopathy segmentations. It also demonstrates outstanding robustness in scenarios involving scarce labeled data and misaligned modalities.
Authors: Nicholas Konz, Maciej A. Mazurowski
Abstract: In recent years, there has been interest in how geometric properties such as intrinsic dimension (ID) of a neural network's hidden representations change through its layers, and how such properties are predictive of important model behavior such as generalization ability. However, evidence has begun to emerge that such behavior can change significantly depending on the domain of the network's training data, such as natural versus medical images. Here, we further this inquiry by exploring how the ID of a network's learned representations changes through its layers, in essence, characterizing how the network successively refines the information content of input data to be used for predictions. Analyzing eleven natural and medical image datasets across six network architectures, we find that how ID changes through the network differs noticeably between natural and medical image models. Specifically, medical image models peak in representation ID earlier in the network, implying a difference in the image features and their abstractness that are typically used for downstream tasks in these domains. Additionally, we discover a strong correlation of this peak representation ID with the ID of the data in its input space, implying that the intrinsic information content of a model's learned representations is guided by that of the data it was trained on. Overall, our findings emphasize notable discrepancies in network behavior between natural and non-natural imaging domains regarding hidden representation information content, and provide further insights into how a network's learned features are shaped by its training data.
Authors: Eito Ikuta, Yohan Lee, Akihiro Iohara, Yu Saito, Toshiyuki Tanaka
Abstract: Extracting geometry features from photographic images independently of surface texture and transferring them onto different materials remains a complex challenge. In this study, we introduce Harmonizing Attention, a novel training-free approach that leverages diffusion models for texture-aware geometry transfer. Our method employs a simple yet effective modification of self-attention layers, allowing the model to query information from multiple reference images within these layers. This mechanism is seamlessly integrated into the inversion process as Texture-aligning Attention and into the generation process as Geometry-aligning Attention. This dual-attention approach ensures the effective capture and transfer of material-independent geometry features while maintaining material-specific textural continuity, all without the need for model fine-tuning.
Authors: Timo Kaiser, Vladimir Ulman, Bodo Rosenhahn
Abstract: The evaluation of cell tracking results steers the development of tracking methods, significantly impacting biomedical research. This is quantitatively achieved by means of evaluation metrics. Unfortunately, current metrics favor local correctness and weakly reward global coherence, impeding high-level biological analysis. To also foster global coherence, we propose the CHOTA metric (Cell-specific Higher Order Tracking Accuracy) which unifies the evaluation of all relevant aspects of cell tracking: cell detections and local associations, global coherence, and lineage tracking. We achieve this by introducing a new definition of the term 'trajectory' that includes the entire cell lineage and by including this into the well-established HOTA metric from general multiple object tracking. Furthermore, we provide a detailed survey of contemporary cell tracking metrics to compare our novel CHOTA metric and to show its advantages. All metrics are extensively evaluated on state-of-the-art real-data cell tracking results and synthetic results that simulate specific tracking errors. We show that CHOTA is sensitive to all tracking errors and gives a good indication of the biologically relevant capability of a method to reconstruct the full lineage of cells. It introduces a robust and comprehensive alternative to the currently used metrics in cell tracking. Python code is available at https://github.com/CellTrackingChallenge/py-ctcmetrics .
URLs: https://github.com/CellTrackingChallenge/py-ctcmetrics
Authors: Mingyu Xiao, Runze Chen, Haiyong Luo, Fang Zhao, Juan Wang, Xuepeng Ma
Abstract: Map-free relocalization technology is crucial for applications in autonomous navigation and augmented reality, but relying on pre-built maps is often impractical. It faces significant challenges due to limitations in matching methods and the inherent lack of scale in monocular images. These issues lead to substantial rotational and metric errors and even localization failures in real-world scenarios. Large matching errors significantly impact the overall relocalization process, affecting both rotational and translational accuracy. Due to the inherent limitations of the camera itself, recovering the metric scale from a single image is crucial, as this significantly impacts the translation error. To address these challenges, we propose a map-free relocalization method enhanced by instance knowledge and depth knowledge. By leveraging instance-based matching information to improve global matching results, our method significantly reduces the possibility of mismatching across different objects. The robustness of instance knowledge across the scene helps the feature point matching model focus on relevant regions and enhance matching accuracy. Additionally, we use estimated metric depth from a single image to reduce metric errors and improve scale recovery accuracy. By integrating methods dedicated to mitigating large translational and rotational errors, our approach demonstrates superior performance in map-free relocalization techniques.
Authors: Chao Chen, Yu-Shen Liu, Zhizhong Han
Abstract: It is challenging to reconstruct 3D point clouds in unseen classes from single 2D images. Instead of object-centered coordinate system, current methods generalized global priors learned in seen classes to reconstruct 3D shapes from unseen classes in viewer-centered coordinate system. However, the reconstruction accuracy and interpretability are still eager to get improved. To resolve this issue, we introduce to learn local pattern modularization for reconstructing 3D shapes in unseen classes, which achieves both good generalization ability and high reconstruction accuracy. Our insight is to learn a local prior which is class-agnostic and easy to generalize in object-centered coordinate system. Specifically, the local prior is learned via a process of learning and customizing local pattern modularization in seen classes. During this process, we first learn a set of patterns in local regions, which is the basis in the object-centered coordinate system to represent an arbitrary region on shapes across different classes. Then, we modularize each region on an initially reconstructed shape using the learned local patterns. Based on that, we customize the local pattern modularization using the input image by refining the reconstruction with more details. Our method enables to reconstruct high fidelity point clouds from unseen classes in object-centered coordinate system without requiring a large number of patterns or any additional information, such as segmentation supervision or camera poses. Our experimental results under widely used benchmarks show that our method achieves the state-of-the-art reconstruction accuracy for shapes from unseen classes. The code is available at https://github.com/chenchao15/Unseen.
Authors: Haozhuo Zhang, Bin Zhu, Yu Cao, Yanbin Hao
Abstract: Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model's understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing, and colors.
Authors: Peng Xing, Haofan Wang, Yanpeng Sun, Qixun Wang, Xu Bai, Hao Ai, Renyuan Huang, Zechao Li
Abstract: The diffusion model has shown exceptional capabilities in controlled image generation, which has further fueled interest in image style transfer. Existing works mainly focus on training free-based methods (e.g., image inversion) due to the scarcity of specific data. In this study, we present a data construction pipeline for content-style-stylized image triplets that generates and automatically cleanses stylized data triplets. Based on this pipeline, we construct a dataset IMAGStyle, the first large-scale style transfer dataset containing 210k image triplets, available for the community to explore and research. Equipped with IMAGStyle, we propose CSGO, a style transfer model based on end-to-end training, which explicitly decouples content and style features employing independent feature injection. The unified CSGO implements image-driven style transfer, text-driven stylized synthesis, and text editing-driven stylized synthesis. Extensive experiments demonstrate the effectiveness of our approach in enhancing style control capabilities in image generation. Additional visualization and access to the source code can be located on the project page: \url{https://csgo-gen.github.io/}.
Authors: Yuxi Zhang, Xiang Chen, Jiazheng Wang, Min Liu, Yaonan Wang, Dongdong Liu, Renjiu Hu, Hang Zhang
Abstract: In this paper, we summarize the methods and experimental results we proposed for Task 2 in the learn2reg 2024 Challenge. This task focuses on unsupervised registration of anatomical structures in brain MRI images between different patients. The difficulty lies in: (1) without segmentation labels, and (2) a large amount of data. To address these challenges, we built an efficient backbone network and explored several schemes to further enhance registration accuracy. Under the guidance of the NCC loss function and smoothness regularization loss function, we obtained a smooth and reasonable deformation field. According to the leaderboard, our method achieved a Dice coefficient of 77.34%, which is 1.4% higher than the TransMorph. Overall, we won second place on the leaderboard for Task 2.
Authors: Long Li, Nian Liu, Dingwen Zhang, Zhongyu Li, Salman Khan, Rao Anwer, Hisham Cholakkal, Junwei Han, Fahad Shahbaz Khan
Abstract: Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.
Authors: Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Tsung-Yi Ho
Abstract: Adapting pre-trained models to new tasks can exhibit varying effectiveness across datasets. Visual prompting, a state-of-the-art parameter-efficient transfer learning method, can significantly improve the performance of out-of-distribution tasks. On the other hand, linear probing, a standard transfer learning method, can sometimes become the best approach. We propose a log-likelihood ratio (LLR) approach to analyze the comparative benefits of visual prompting and linear probing. By employing the LLR score alongside resource-efficient visual prompts approximations, our cost-effective measure attains up to a 100-fold reduction in run time compared to full training, while achieving prediction accuracies up to 91%. The source code is available at https://github.com/IBM/VP-LLR.
Authors: Kanchan Poudel, Lisasha Poudel, Prabin Raj Shakya, Atit Poudel, Archana Shrestha, Bishesh Khanal
Abstract: Visual Inspection with Acetic Acid (VIA) remains the most feasible cervical cancer screening test in resource-constrained settings of low- and middle-income countries (LMICs), which are often performed screening camps or primary/community health centers by nurses instead of the preferred but unavailable expert Gynecologist. To address the highly subjective nature of the test, various handheld devices integrating cameras or smartphones have been recently explored to capture cervical images during VIA and aid decision-making via telemedicine or AI models. Most studies proposing AI models retrospectively use a relatively small number of already collected images from specific devices, digital cameras, or smartphones; the challenges and protocol for quality image acquisition during VIA in resource-constrained camp settings, challenges in getting gold standard, data imbalance, etc. are often overlooked. We present a novel approach and describe the end-to-end design process to build a robust smartphone-based AI-assisted system that does not require buying a separate integrated device: the proposed protocol for quality image acquisition in resource-constrained settings, dataset collected from 1,430 women during VIA performed by nurses in screening camps, preprocessing pipeline, and training and evaluation of a deep-learning-based classification model aimed to identify (pre)cancerous lesions. Our work shows that the readily available smartphones and a suitable protocol can capture the cervix images with the required details for the VIA test well; the deep-learning-based classification model provides promising results to assist nurses in VIA screening; and provides a direction for large-scale data collection and validation in resource-constrained settings.
Authors: Aneesh Rangnekar, Nishant Nadkarni, Jue Jiang, Harini Veeraraghavan
Abstract: Medical image foundation models have shown the ability to segment organs and tumors with minimal fine-tuning. These models are typically evaluated on task-specific in-distribution (ID) datasets. However, reliable performance on ID dataset does not guarantee robust generalization on out-of-distribution (OOD) datasets. Importantly, once deployed for clinical use, it is impractical to have `ground truth' delineations to assess ongoing performance drifts, especially when images fall into OOD category due to different imaging protocols. Hence, we introduced a comprehensive set of computationally fast metrics to evaluate the performance of multiple foundation models (Swin UNETR, SimMIM, iBOT, SMIT) trained with self-supervised learning (SSL). SSL pretraining was selected as this approach is applicable for large, diverse, and unlabeled image sets. All models were fine-tuned on identical datasets for lung tumor segmentation from computed tomography (CT) scans. SimMIM, iBOT, and SMIT used identical architecture, pretraining, and fine-tuning datasets to assess performance variations with the choice of pretext tasks used in SSL. Evaluation was performed on two public lung cancer datasets (LRAD: n = 140, 5Rater: n = 21) with different image acquisitions and tumor stage compared to training data (n = 317 public resource with stage III-IV lung cancers) and a public non-cancer dataset containing volumetric CT scans of patients with pulmonary embolism (n = 120). All models produced similarly accurate tumor segmentation on the lung cancer testing datasets. SMIT produced a highest F1-score (LRAD: 0.60, 5Rater: 0.64) and lowest entropy (LRAD: 0.06, 5Rater: 0.12), indicating higher tumor detection rate and confident segmentations. In the OOD dataset, SMIT misdetected least number of tumors, indicated by median volume occupancy of 5.67 cc compared to second best method SimMIM of 9.97 cc.
Authors: Francisco Mena, Diego Arenas, Andreas Dengel
Abstract: Studying and analyzing cropland is a difficult task due to its dynamic and heterogeneous growth behavior. Usually, diverse data sources can be collected for its estimation. Although deep learning models have proven to excel in the crop classification task, they face substantial challenges when dealing with multiple inputs, named Multi-View Learning (MVL). The methods used in the MVL scenario can be structured based on the encoder architecture, the fusion strategy, and the optimization technique. The literature has primarily focused on using specific encoder architectures for local regions, lacking a deeper exploration of other components in the MVL methodology. In contrast, we investigate the simultaneous selection of the fusion strategy and encoder architecture, assessing global-scale cropland and crop-type classifications. We use a range of five fusion strategies (Input, Feature, Decision, Ensemble, Hybrid) and five temporal encoders (LSTM, GRU, TempCNN, TAE, L-TAE) as possible configurations in the MVL method. We use the CropHarvest dataset for validation, which provides optical, radar, weather time series, and topographic information as input data. We found that in scenarios with a limited number of labeled samples, a unique configuration is insufficient for all the cases. Instead, a specialized combination should be meticulously sought, including an encoder and fusion strategy. To streamline this search process, we suggest identifying the optimal encoder architecture tailored for a particular fusion strategy, and then determining the most suitable fusion strategy for the classification task. We provide a methodological framework for researchers exploring crop classification through an MVL methodology.
Authors: Zhiyuan Li, Yanhui Zhou, Hao Wei, Chenyang Ge, Jingwen Jiang
Abstract: Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the powerful generative capability of pre-trained diffusion models to achieve realistic image reconstruction at extremely low bitrates. In the first stage, we treat the latent representation of images in the diffusion space as guidance, employing a VAE-based compression approach to compress images and initially decode the compressed information into content variables. The second stage leverages pre-trained stable diffusion to reconstruct images under the guidance of content variables. Specifically, we introduce a small control module to inject content information while keeping the stable diffusion model fixed to maintain its generative capability. Furthermore, we design a space alignment loss to force the content variables to align with the diffusion space and provide the necessary constraints for optimization. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in terms of visual performance at extremely low bitrates. The source code and trained models are available at https://github.com/huai-chang/DiffEIC.
Authors: Zhenghao Chen, Luping Zhou, Zhihao Hu, Dong Xu
Abstract: Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Although these methods have been very practical in neural image compression (NIC), their application in neural video compression (NVC) is still limited due to two main aspects: 1), video compression relies heavily on temporal redundancy, therefore updating just one or a few frames can lead to significant errors accumulating over time; 2), NVC frameworks are generally more complex, with many large components that are not easy to update quickly during encoding. To address the previously mentioned challenges, we have developed a content-adaptive NVC technique called Group-aware Parameter-Efficient Updating (GPU). Initially, to minimize error accumulation, we adopt a group-aware approach for updating encoder parameters. This involves adopting a patch-based Group of Pictures (GoP) training strategy to segment a video into patch-based GoPs, which will be updated to facilitate a globally optimized domain-transferable solution. Subsequently, we introduce a parameter-efficient delta-tuning strategy, which is achieved by integrating several light-weight adapters into each coding component of the encoding process by both serial and parallel configuration. Such architecture-agnostic modules stimulate the components with large parameters, thereby reducing both the update cost and the encoding time. We incorporate our GPU into the latest NVC framework and conduct comprehensive experiments, whose results showcase outstanding video compression efficiency across four video benchmarks and adaptability of one medical image benchmark.
Authors: Ivan Bili\'c, Filip Mari\'c, Fabio Bonsignorio, Ivan Petrovi\'c
Abstract: In autonomous robotics, measurement of the robot's internal state and perception of its environment, including interaction with other agents such as collaborative robots, are essential. Estimating the pose of the robot arm from a single view has the potential to replace classical eye-to-hand calibration approaches and is particularly attractive for online estimation and dynamic environments. In addition to its pose, recovering the robot configuration provides a complete spatial understanding of the observed robot that can be used to anticipate the actions of other agents in advanced robotics use cases. Furthermore, this additional redundancy enables the planning and execution of recovery protocols in case of sensor failures or external disturbances. We introduce GISR - a deep configuration and robot-to-camera pose estimation method that prioritizes execution in real-time. GISR consists of two modules: (i) a geometric initialization module that efficiently computes an approximate robot pose and configuration, and (ii) a deep iterative silhouette-based refinement module that arrives at a final solution in just a few iterations. We evaluate GISR on publicly available data and show that it outperforms existing methods of the same class in terms of both speed and accuracy, and can compete with approaches that rely on ground-truth proprioception and recover only the pose.
Authors: Tianhao Peng, Chen Feng, Duolikun Danier, Fan Zhang, Benoit Vallade, Alex Mackin, David Bull
Abstract: With recent advances in deep learning, numerous algorithms have been developed to enhance video quality, reduce visual artifacts, and improve perceptual quality. However, little research has been reported on the quality assessment of enhanced content - the evaluation of enhancement methods is often based on quality metrics that were designed for compression applications. In this paper, we propose a novel blind deep video quality assessment (VQA) method specifically for enhanced video content. It employs a new Recurrent Memory Transformer (RMT) based network architecture to obtain video quality representations, which is optimized through a novel content-quality-aware contrastive learning strategy based on a new database containing 13K training patches with enhanced content. The extracted quality representations are then combined through linear regression to generate video-level quality indices. The proposed method, RMT-BVQA, has been evaluated on the VDPVE (VQA Dataset for Perceptual Video Enhancement) database through a five-fold cross validation. The results show its superior correlation performance when compared to ten existing no-reference quality metrics.
Authors: Xuehan Liu, Md Rakibul Hasan, Tom Gedeon, Md Zakir Hossain
Abstract: In response to the global need for efficient early diagnosis of Autism Spectrum Disorder (ASD), this paper bridges the gap between traditional, time-consuming diagnostic methods and potential automated solutions. We propose a multi-atlas deep ensemble network, MADE-for-ASD, that integrates multiple atlases of the brain's functional magnetic resonance imaging (fMRI) data through a weighted deep ensemble network. Our approach integrates demographic information into the prediction workflow, which enhances ASD diagnosis performance and offers a more holistic perspective on patient profiling. We experiment with the well-known publicly available ABIDE (Autism Brain Imaging Data Exchange) I dataset, consisting of resting state fMRI data from 17 different laboratories around the globe. Our proposed system achieves 75.20% accuracy on the entire dataset and 96.40% on a specific subset $-$ both surpassing reported ASD diagnosis accuracy in ABIDE I fMRI studies. Specifically, our model improves by 4.4 percentage points over prior works on the same amount of data. The model exhibits a sensitivity of 82.90% and a specificity of 69.70% on the entire dataset, and 91.00% and 99.50%, respectively, on the specific subset. We leverage the F-score to pinpoint the top 10 ROI in ASD diagnosis, such as precuneus and anterior cingulate/ventromedial. The proposed system can potentially pave the way for more cost-effective, efficient and scalable strategies in ASD diagnosis. Codes and evaluations are publicly available at https://github.com/hasan-rakibul/MADE-for-ASD.
Authors: Francisco Mena, Diego Arenas, Andreas Dengel
Abstract: Multi-sensor ML models for EO aim to enhance prediction accuracy by integrating data from various sources. However, the presence of missing data poses a significant challenge, particularly in non-persistent sensors that can be affected by external factors. Existing literature has explored strategies like temporal dropout and sensor-invariant models to address the generalization to missing data issues. Inspired by these works, we study two novel methods tailored for multi-sensor scenarios, namely Input Sensor Dropout (ISensD) and Ensemble Sensor Invariant (ESensI). Through experimentation on three multi-sensor temporal EO datasets, we demonstrate that these methods effectively increase the robustness of model predictions to missing sensors. Particularly, we focus on how the predictive performance of models drops when sensors are missing at different levels. We observe that ensemble multi-sensor models are the most robust to the lack of sensors. In addition, the sensor dropout component in ISensD shows promising robustness results.
Authors: Mingya Zhang, Liang Wang, Zhihao Chen, Yiyuan Ge, Xianping Tao
Abstract: The semantic segmentation task in pathology plays an indispensable role in assisting physicians in determining the condition of tissue lesions. With the proposal of Segment Anything Model (SAM), more and more foundation models have seen rapid development in the field of image segmentation. Recently, SAM2 has garnered widespread attention in both natural image and medical image segmentation. Compared to SAM, it has significantly improved in terms of segmentation accuracy and generalization performance. We compared the foundational models based on SAM and found that their performance in semantic segmentation of pathological images was hardly satisfactory. In this paper, we propose Path-SAM2, which for the first time adapts the SAM2 model to cater to the task of pathological semantic segmentation. We integrate the largest pretrained vision encoder for histopathology (UNI) with the original SAM2 encoder, adding more pathology-based prior knowledge. Additionally, we introduce a learnable Kolmogorov-Arnold Networks (KAN) classification module to replace the manual prompt process. In three adenoma pathological datasets, Path-SAM2 has achieved state-of-the-art performance.This study demonstrates the great potential of adapting SAM2 to pathology image segmentation tasks. We plan to release the code and model weights for this paper at: https://github.com/simzhangbest/SAM2PATH
Authors: Yosuke Yamagishi, Shouhei Hanaoka, Tomohiro Kikuchi, Takahiro Nakao, Yuta Nakamura, Yukihiro Nomura, Soichiro Miki, Takeharu Yoshikawa, Osamu Abe
Abstract: Purpose: To evaluate the zero-shot performance of Segment Anything Model 2 (SAM 2) in 3D segmentation of abdominal organs in CT scans, and to investigate the effects of prompt settings on segmentation results. Materials and Methods: Using a subset of the TotalSegmentator CT dataset (n = 123) from eight institutions, we assessed SAM 2's ability to segment eight abdominal organs. Segmentation was initiated from three different z-coordinate levels (caudal, mid, and cranial levels) of each organ. Performance was measured using the Dice similarity coefficient (DSC). We also analyzed the impact of "negative prompts," which explicitly exclude certain regions from the segmentation process, on accuracy. Additionally, we analyzed organ volumes to contextualize the segmentation performance. Results: As a zero-shot approach, larger organs with clear boundaries demonstrated high segmentation performance, with mean(median) DSCs as follows: liver 0.821(0.898), left kidney 0.870(0.921), right kidney 0.862(0.935), and spleen 0.891(0.932). Smaller organs showed lower performance: gallbladder 0.531(0.590), pancreas 0.361(0.359), and adrenal glands, right 0.203(0.109), left 0.308(0.231). The initial slice for segmentation and the use of negative prompts significantly influenced the results. By removing negative prompts from the input, the DSCs significantly decreased for six organs. Moderate positive correlations were observed between volume sizes and DSCs. Conclusion: SAM 2 demonstrated promising zero-shot performance in segmenting certain abdominal organs in CT scans, particularly larger organs with clear boundaries. Performance was significantly influenced by input negative prompts and initial slice selection, highlighting the importance of optimizing these factors for effective segmentation.
Authors: Shantanu Ghosh, Rayan Syed, Chenyu Wang, Clare B. Poynton, Kayhan Batmanghelich
Abstract: Error slice discovery associates structured patterns with model errors. Existing methods discover error slices by clustering the error-prone samples with similar patterns or assigning discrete attributes to each sample for post-hoc analysis. While these methods aim for interpretability and easier mitigation through reweighting or rebalancing, they may not capture the full complexity of error patterns due to incomplete or missing attributes. Contrary to the existing approach, this paper utilizes the reasoning capabilities of the Large Language Model (LLM) to analyze complex error patterns and generate testable hypotheses. This paper proposes LADDER: Language Driven slice Discovery and Error Rectification. It first projects the model's representation into a language-aligned feature space (eg CLIP) to preserve semantics in the original model feature space. This ensures the accurate retrieval of sentences that highlight the model's errors. Next, the LLM utilizes the sentences and generates hypotheses to discover error slices. Finally, we mitigate the error by fine-tuning the classification head by creating a group-balanced dataset using the hypotheses. Our entire method does not require any attribute annotation, either explicitly or through external tagging models. We validate our method with \textbf{five} image classification datasets. The code is available (https://github.com/batmanlab/Ladder).
Authors: Miriam Cobo, Amaia P\'erez del Barrio, Pablo Men\'endez Fern\'andez-Miranda, Pablo Sanz Bell\'on, Lara Lloret Iglesias, Wilson Silva
Abstract: Prognosis after intracranial hemorrhage (ICH) is influenced by a complex interplay between imaging and tabular data. Rapid and reliable prognosis are crucial for effective patient stratification and informed treatment decision-making. In this study, we aim to enhance image-based prognosis by learning a robust feature representation shared between prognosis and the clinical and demographic variables most highly correlated with it. Our approach mimics clinical decision-making by reinforcing the model to learn valuable prognostic data embedded in the image. We propose a 3D multi-task image model to predict prognosis, Glasgow Coma Scale and age, improving accuracy and interpretability. Our method outperforms current state-of-the-art baseline image models, and demonstrates superior performance in ICH prognosis compared to four board-certified neuroradiologists using only CT scans as input. We further validate our model with interpretability saliency maps. Code is available at https://github.com/MiriamCobo/MultitaskLearning_ICH_Prognosis.git.
URLs: https://github.com/MiriamCobo/MultitaskLearning_ICH_Prognosis.git.
Authors: An Vuong, Thinh Nguyen
Abstract: Multiplicative noise, also known as speckle or pepper noise, commonly affects images produced by synthetic aperture radar (SAR), lasers, or optical lenses. Unlike additive noise, which typically arises from thermal processes or external factors, multiplicative noise is inherent to the system, originating from the fluctuation in diffuse reflections. These fluctuations result in multiple copies of the same signal with varying magnitudes being combined. Consequently, despeckling, or removing multiplicative noise, necessitates different techniques compared to those used for additive noise removal. In this paper, we propose a novel approach using Stochastic Differential Equations based diffusion models to address multiplicative noise. We demonstrate that multiplicative noise can be effectively modeled as a Geometric Brownian Motion process in the logarithmic domain. Utilizing the Fokker-Planck equation, we derive the corresponding reverse process for image denoising. To validate our method, we conduct extensive experiments on two different datasets, comparing our approach to both classical signal processing techniques and contemporary CNN-based noise removal models. Our results indicate that the proposed method significantly outperforms existing methods on perception-based metrics such as FID and LPIPS, while maintaining competitive performance on traditional metrics like PSNR and SSIM.
Authors: Yuan Zhao, Zhenqi Jia, Rui Liu, De Hu, Feilong Bao, Guanglai Gao
Abstract: Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized speech. However, it is crucial to consider whether the prosody of the generated dubbing aligns with the multimodal context, as the dubbing will be combined with the original context in the final video. This aspect has been overlooked in previous studies. To address this issue, we propose a Multimodal Context-aware video Dubbing model, termed \textbf{MCDubber}, to convert the modeling object from a single sentence to a longer sequence with context information to ensure the consistency of the global context prosody. MCDubber comprises three main components: (1) A context duration aligner aims to learn the context-aware alignment between the text and lip frames; (2) A context prosody predictor seeks to read the global context visual sequence and predict the context-aware global energy and pitch; (3) A context acoustic decoder ultimately predicts the global context mel-spectrogram with the assistance of adjacent ground-truth mel-spectrograms of the target sentence. Through this process, MCDubber fully considers the influence of multimodal context on the prosody expressiveness of the current sentence when dubbing. The extracted mel-spectrogram belonging to the target sentence from the output context mel-spectrograms is the final required dubbing audio. Extensive experiments on the Chem benchmark dataset demonstrate that our MCDubber significantly improves dubbing expressiveness compared to all advanced baselines. The code and demos are available at https://github.com/XiaoYuanJun-zy/MCDubber.
Authors: Theo Di Piazza
Abstract: The rapid increase of computed tomography (CT) scans and their time-consuming manual analysis have created an urgent need for robust automated analysis techniques in clinical settings. These aim to assist radiologists and help them managing their growing workload. Existing methods typically generate entire reports directly from 3D CT images, without explicitly focusing on observed abnormalities. This unguided approach often results in repetitive content or incomplete reports, failing to prioritize anomaly-specific descriptions. We propose a new anomaly-guided report generation model, which first predicts abnormalities and then generates targeted descriptions for each. Evaluation on a public dataset demonstrates significant improvements in report quality and clinical relevance. We extend our work by conducting an ablation study to demonstrate its effectiveness.
Authors: Guangyi Zhang, Hanlei Li, Yunlong Cai, Qiyu Hu, Guanding Yu, Runmin Zhang
Abstract: In this paper, we introduce an innovative hierarchical joint source-channel coding (HJSCC) framework for image transmission, utilizing a hierarchical variational autoencoder (VAE). Our approach leverages a combination of bottom-up and top-down paths at the transmitter to autoregressively generate multiple hierarchical representations of the original image. These representations are then directly mapped to channel symbols for transmission by the JSCC encoder. We extend this framework to scenarios with a feedback link, modeling transmission over a noisy channel as a probabilistic sampling process and deriving a novel generative formulation for JSCC with feedback. Compared with existing approaches, our proposed HJSCC provides enhanced adaptability by dynamically adjusting transmission bandwidth, encoding these representations into varying amounts of channel symbols. Additionally, we introduce a rate attention module to guide the JSCC encoder in optimizing its encoding strategy based on prior information. Extensive experiments on images of varying resolutions demonstrate that our proposed model outperforms existing baselines in rate-distortion performance and maintains robustness against channel noise.
Authors: Ahmad Mohammad Saber, Alaa Selim, Mohamed M. Hammad, Amr Youssef, Deepa Kundur, Ehab El-Saadany
Abstract: With the rapid integration of electronically interfaced renewable energy resources and loads into smart grids, there is increasing interest in power quality disturbances (PQD) classification to enhance the security and efficiency of these grids. This paper introduces a new approach to PQD classification based on the Vision Transformer (ViT) model. When a PQD occurs, the proposed approach first converts the power quality signal into an image and then utilizes a pre-trained ViT to accurately determine the class of the PQD. Unlike most previous works, which were limited to a few disturbance classes or small datasets, the proposed method is trained and tested on a large dataset with 17 disturbance classes. Our experimental results show that the proposed ViT-based approach achieves PQD classification precision and recall of 98.28% and 97.98%, respectively, outperforming recently proposed techniques applied to the same dataset.
Authors: Jinglin Liang, Jin Zhong, Hanlin Gu, Zhongqi Lu, Xingxing Tang, Gang Dai, Shuangping Huang, Lixin Fan, Qiang Yang
Abstract: Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue that has been explored to some extent in Continual Learning (CL). However, due to privacy preservation requirements, some conventional methods, such as experience replay, are not directly applicable to FCCL. Existing FCCL methods mitigate forgetting by generating historical data through federated training of GANs or data-free knowledge distillation. However, these approaches often suffer from unstable training of generators or low-quality generated data, limiting their guidance for the model. To address this challenge, we propose a novel method of data replay based on diffusion models. Instead of training a diffusion model, we employ a pre-trained conditional diffusion model to reverse-engineer each class, searching the corresponding input conditions for each class within the model's input space, significantly reducing computational resources and time consumption while ensuring effective generation. Furthermore, we enhance the classifier's domain generalization ability on generated and real data through contrastive learning, indirectly improving the representational capability of generated data for real data. Comprehensive experiments demonstrate that our method significantly outperforms existing baselines. Code is available at https://github.com/jinglin-liang/DDDR.