Authors: Paul Fergus, Carl Chalmers, Steve Longmore, Serge Wich
Abstract: The rapid decline in global biodiversity demands innovative conservation strategies. This paper examines the use of artificial intelligence (AI) in wildlife conservation, focusing on the Conservation AI platform. Leveraging machine learning and computer vision, Conservation AI detects and classifies animals, humans, and poaching-related objects using visual spectrum and thermal infrared cameras. The platform processes this data with convolutional neural networks (CNNs) and Transformer architectures to monitor species, including those which are critically endangered. Real-time detection provides the immediate responses required for time-critical situations (e.g. poaching), while non-real-time analysis supports long-term wildlife monitoring and habitat health assessment. Case studies from Europe, North America, Africa, and Southeast Asia highlight the platform's success in species identification, biodiversity monitoring, and poaching prevention. The paper also discusses challenges related to data quality, model accuracy, and logistical constraints, while outlining future directions involving technological advancements, expansion into new geographical regions, and deeper collaboration with local communities and policymakers. Conservation AI represents a significant step forward in addressing the urgent challenges of wildlife conservation, offering a scalable and adaptable solution that can be implemented globally.
Authors: Andrew Hamara, Pablo Rivas
Abstract: This study investigates ImageBind's ability to generate meaningful fused multimodal embeddings for online auto parts listings. We propose a simplistic embedding fusion workflow that aims to capture the overlapping information of image/text pairs, ultimately combining the semantics of a post into a joint embedding. After storing such fused embeddings in a vector database, we experiment with dimensionality reduction and provide empirical evidence to convey the semantic quality of the joint embeddings by clustering and examining the posts nearest to each cluster centroid. Additionally, our initial findings with ImageBind's emergent zero-shot cross-modal retrieval suggest that pure audio embeddings can correlate with semantically similar marketplace listings, indicating potential avenues for future research.
Authors: Ghalib Ahmed Tahir
Abstract: This paper aims to shed light on the ethical problems of creating and deploying computer vision tech, particularly in using publicly available datasets. Due to the rapid growth of machine learning and artificial intelligence, computer vision has become a vital tool in many industries, including medical care, security systems, and trade. However, extensive use of visual data that is often collected without consent due to an informed discussion of its ramifications raises significant concerns about privacy and bias. The paper also examines these issues by analyzing popular datasets such as COCO, LFW, ImageNet, CelebA, PASCAL VOC, etc., that are usually used for training computer vision models. We offer a comprehensive ethical framework that addresses these challenges regarding the protection of individual rights, minimization of bias as well as openness and responsibility. We aim to encourage AI development that will take into account societal values as well as ethical standards to avoid any public harm.
Authors: Esam Ghaleb, Bulat Khaertdinov, Wim Pouw, Marlou Rasenberg, Judith Holler, Asl{\i} \"Ozy\"urek, Raquel Fern\'andez
Abstract: In face-to-face dialogues, the form-meaning relationship of co-speech gestures varies depending on contextual factors such as what the gestures refer to and the individual characteristics of speakers. These factors make co-speech gesture representation learning challenging. How can we learn meaningful gestures representations considering gestures' variability and relationship with speech? This paper tackles this challenge by employing self-supervised contrastive learning techniques to learn gesture representations from skeletal and speech information. We propose an approach that includes both unimodal and multimodal pre-training to ground gesture representations in co-occurring speech. For training, we utilize a face-to-face dialogue dataset rich with representational iconic gestures. We conduct thorough intrinsic evaluations of the learned representations through comparison with human-annotated pairwise gesture similarity. Moreover, we perform a diagnostic probing analysis to assess the possibility of recovering interpretable gesture features from the learned representations. Our results show a significant positive correlation with human-annotated gesture similarity and reveal that the similarity between the learned representations is consistent with well-motivated patterns related to the dynamics of dialogue interaction. Moreover, our findings demonstrate that several features concerning the form of gestures can be recovered from the latent representations. Overall, this study shows that multimodal contrastive learning is a promising approach for learning gesture representations, which opens the door to using such representations in larger-scale gesture analysis studies.
Authors: Kislay Raj, Teerath Kumar, Alessandra Mileo, Malika Bendechache
Abstract: Carcinoma is the prevailing type of cancer and can manifest in various body parts. It is widespread and can potentially develop in numerous locations within the body. In the medical domain, data for carcinoma cancer is often limited or unavailable due to privacy concerns. Moreover, when available, it is highly imbalanced, with a scarcity of positive class samples and an abundance of negative ones. The OXML 2023 challenge provides a small and imbalanced dataset, presenting significant challenges for carcinoma classification. To tackle these issues, participants in the challenge have employed various approaches, relying on pre-trained models, preprocessing techniques, and few-shot learning. Our work proposes a novel technique that combines padding augmentation and ensembling to address the carcinoma classification challenge. In our proposed method, we utilize ensembles of five neural networks and implement padding as a data augmentation technique, taking into account varying image sizes to enhance the classifier's performance. Using our approach, we made place into top three and declared as winner.
Authors: Arnab Kumar Roy, Hemant Kumar Kathania, Adhitiya Sharma, Abhishek Dey, Md. Sarfaraj Alam Ansari
Abstract: The human face is a silent communicator, expressing emotions and thoughts through its facial expressions. With the advancements in computer vision in recent years, facial emotion recognition technology has made significant strides, enabling machines to decode the intricacies of facial cues. In this work, we propose ResEmoteNet, a novel deep learning architecture for facial emotion recognition designed with the combination of Convolutional, Squeeze-Excitation (SE) and Residual Networks. The inclusion of SE block selectively focuses on the important features of the human face, enhances the feature representation and suppresses the less relevant ones. This helps in reducing the loss and enhancing the overall model performance. We also integrate the SE block with three residual blocks that help in learning more complex representation of the data through deeper layers. We evaluated ResEmoteNet on three open-source databases: FER2013, RAF-DB, and AffectNet, achieving accuracies of 79.79%, 94.76%, and 72.39%, respectively. The proposed network outperforms state-of-the-art models across all three databases. The source code for ResEmoteNet is available at https://github.com/ArnabKumarRoy02/ResEmoteNet.
Authors: Shawan Mohammed, Alp Argun, Nicolas Bonnotte, Gerd Ascheid
Abstract: Our research investigates the challenges Deep Reinforcement Learning (DRL) faces in complex, Partially Observable Markov Decision Processes (POMDP) such as autonomous driving (AD), and proposes a solution for vision-based navigation in these environments. Partial observability reduces RL performance significantly, and this can be mitigated by augmenting sensor information and data fusion to reflect a more Markovian environment. However, this necessitates an increasingly complex perception module, whose training via RL is complicated due to inherent limitations. As the neural network architecture becomes more complex, the reward function's effectiveness as an error signal diminishes since the only source of supervision is the reward, which is often noisy, sparse, and delayed. Task-irrelevant elements in images, such as the sky or certain objects, pose additional complexities. Our research adopts an offline-trained encoder to leverage large video datasets through self-supervised learning to learn generalizable representations. Then, we train a head network on top of these representations through DRL to learn to control an ego vehicle in the CARLA AD simulator. This study presents a broad investigation of the impact of different learning schemes for offline-training of encoders on the performance of DRL agents in challenging AD tasks. Furthermore, we show that the features learned by watching BDD100K driving videos can be directly transferred to achieve lane following and collision avoidance in CARLA simulator, in a zero-shot learning fashion. Finally, we explore the impact of various architectural decisions for the RL networks to utilize the transferred representations efficiently. Therefore, in this work, we introduce and validate an optimal way for obtaining suitable representations of the environment, and transferring them to RL networks.
Authors: Jianqiao Wangni
Abstract: Comparing to deep neural networks trained for specific tasks, those foundational deep networks trained on generic datasets such as ImageNet classification, benefits from larger-scale datasets, simpler network structure and easier training techniques. In this paper, we design a prompting module which performs few-shot adaptation of generic deep networks to new tasks. Driven by learning theory, we derive prompting modules that are as simple as possible, as they generalize better under the same training error. We use a case study on video object segmentation to experiment. We give a concrete prompting module, the Semi-parametric Deep Forest (SDForest) that combines several nonparametric methods such as correlation filter, random forest, image-guided filter, with a deep network trained for ImageNet classification task. From a learning-theoretical point of view, all these models are of significantly smaller VC dimension or complexity so tend to generalize better, as long as the empirical studies show that the training error of this simple ensemble can achieve comparable results from a end-to-end trained deep network. We also propose a novel methods of analyzing the generalization under the setting of video object segmentation to make the bound tighter. In practice, SDForest has extremely low computation cost and achieves real-time even on CPU. We test on video object segmentation tasks and achieve competitive performance at DAVIS2016 and DAVIS2017 with purely deep learning approaches, without any training or fine-tuning.
Authors: Yang Sun, Christopher M. Poskitt, Jun Sun
Abstract: The emergence of Autonomous Vehicles (AVs) has spurred research into testing the resilience of their perception systems, i.e. to ensure they are not susceptible to making critical misjudgements. It is important that they are tested not only with respect to other vehicles on the road, but also those objects placed on the roadside. Trash bins, billboards, and greenery are all examples of such objects, typically placed according to guidelines that were developed for the human visual system, and which may not align perfectly with the needs of AVs. Existing tests, however, usually focus on adversarial objects with conspicuous shapes/patches, that are ultimately unrealistic given their unnatural appearances and the need for white box knowledge. In this work, we introduce a black box attack on the perception systems of AVs, in which the objective is to create realistic adversarial scenarios (i.e. satisfying road design guidelines) by manipulating the positions of common roadside objects, and without resorting to `unnatural' adversarial patches. In particular, we propose TrashFuzz , a fuzzing algorithm to find scenarios in which the placement of these objects leads to substantial misperceptions by the AV -- such as mistaking a traffic light's colour -- with overall the goal of causing it to violate traffic laws. To ensure the realism of these scenarios, they must satisfy several rules encoding regulatory guidelines about the placement of objects on public streets. We implemented and evaluated these attacks for the Apollo, finding that TrashFuzz induced it into violating 15 out of 24 different traffic laws.
Authors: Anthony Cioppa, Silvio Giancola, Vladimir Somers, Victor Joos, Floriane Magera, Jan Held, Seyed Abolfazl Ghasemzadeh, Xin Zhou, Karolina Seweryn, Mateusz Kowalczyk, Zuzanna Mr\'oz, Szymon {\L}ukasik, Micha{\l} Ha{\l}o\'n, Hassan Mkhallati, Adrien Deli\`ege, Carlos Hinojosa, Karen Sanchez, Amir M. Mansourian, Pierre Miralles, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Adam Gorski, Albert Clap\'es, Andrei Boiarov, Anton Afanasiev, Artur Xarles, Atom Scott, ByoungKwon Lim, Calvin Yeung, Cristian Gonzalez, Dominic R\"ufenacht, Enzo Pacilio, Fabian Deuser, Faisal Sami Altawijri, Francisco Cach\'on, HanKyul Kim, Haobo Wang, Hyeonmin Choe, Hyunwoo J Kim, Il-Min Kim, Jae-Mo Kang, Jamshid Tursunboev, Jian Yang, Jihwan Hong, Jimin Lee, Jing Zhang, Junseok Lee, Kexin Zhang, Konrad Habel, Licheng Jiao, Linyi Li, Marc Guti\'errez-P\'erez, Marcelo Ortega, Menglong Li, Milosz Lopatto, Nikita Kasatkin, Nikolay Nemtsev, Norbert Oswald, Oleg Udin, Pavel Kononov, Pei Geng, Saad Ghazai Alotaibi, Sehyung Kim, Sergei Ulasen, Sergio Escalera, Shanshan Zhang, Shuyuan Yang, Sunghwan Moon, Thomas B. Moeslund, Vasyl Shandyba, Vladimir Golovkin, Wei Dai, WonTaek Chung, Xinyu Liu, Yongqiang Zhu, Youngseo Kim, Yuan Li, Yuting Yang, Yuxuan Xiao, Zehua Cheng, Zhihao Li
Abstract: The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.
URLs: https://www.soccer-net.org,, https://github.com/SoccerNet.
Authors: Federico Betti, Lorenzo Baraldi, Lorenzo Baraldi, Rita Cucchiara, Nicu Sebe
Abstract: Diffusion models have significantly advanced generative AI, but they encounter difficulties when generating complex combinations of multiple objects. As the final result heavily depends on the initial seed, accurately ensuring the desired output can require multiple iterations of the generation process. This repetition not only leads to a waste of time but also increases energy consumption, echoing the challenges of efficiency and accuracy in complex generative tasks. To tackle this issue, we introduce HEaD (Hallucination Early Detection), a new paradigm designed to swiftly detect incorrect generations at the beginning of the diffusion process. The HEaD pipeline combines cross-attention maps with a new indicator, the Predicted Final Image, to forecast the final outcome by leveraging the information available at early stages of the generation process. We demonstrate that using HEaD saves computational resources and accelerates the generation process to get a complete image, i.e. an image where all requested objects are accurately depicted. Our findings reveal that HEaD can save up to 12% of the generation time on a two objects scenario and underscore the importance of early detection mechanisms in generative models.
Authors: Alexandru Bobe, Jan C. van Gemert
Abstract: Video annotation is a critical and time-consuming task in computer vision research and applications. This paper presents a novel annotation pipeline that uses pre-extracted features and dimensionality reduction to accelerate the temporal video annotation process. Our approach uses Hierarchical Stochastic Neighbor Embedding (HSNE) to create a multi-scale representation of video features, allowing annotators to efficiently explore and label large video datasets. We demonstrate significant improvements in annotation effort compared to traditional linear methods, achieving more than a 10x reduction in clicks required for annotating over 12 hours of video. Our experiments on multiple datasets show the effectiveness and robustness of our pipeline across various scenarios. Moreover, we investigate the optimal configuration of HSNE parameters for different datasets. Our work provides a promising direction for scaling up video annotation efforts in the era of video understanding.
Authors: Bingchen Liu, Ehsan Akhgari, Alexander Visheratin, Aleks Kamko, Linmiao Xu, Shivam Shrirao, Joao Souza, Suhail Doshi, Daiqing Li
Abstract: We introduce Playground v3 (PGv3), our latest text-to-image model that achieves state-of-the-art (SoTA) performance across multiple testing benchmarks, excels in graphic design abilities and introduces new capabilities. Unlike traditional text-to-image generative models that rely on pre-trained language models like T5 or CLIP text encoders, our approach fully integrates Large Language Models (LLMs) with a novel structure that leverages text conditions exclusively from a decoder-only LLM. Additionally, to enhance image captioning quality-we developed an in-house captioner, capable of generating captions with varying levels of detail, enriching the diversity of text structures. We also introduce a new benchmark CapsBench to evaluate detailed image captioning performance. Experimental results demonstrate that PGv3 excels in text prompt adherence, complex reasoning, and accurate text rendering. User preference studies indicate the super-human graphic design ability of our model for common design applications, such as stickers, posters, and logo designs. Furthermore, PGv3 introduces new capabilities, including precise RGB color control and robust multilingual understanding.
Authors: Jinlong Li, Xinyu Liu, Baolu Li, Runsheng Xu, Jiachen Li, Hongkai Yu, Zhengzhong Tu
Abstract: Cooperative perception systems play a vital role in enhancing the safety and efficiency of vehicular autonomy. Although recent studies have highlighted the efficacy of vehicle-to-everything (V2X) communication techniques in autonomous driving, a significant challenge persists: how to efficiently integrate multiple high-bandwidth features across an expanding network of connected agents such as vehicles and infrastructure. In this paper, we introduce CoMamba, a novel cooperative 3D detection framework designed to leverage state-space models for real-time onboard vehicle perception. Compared to prior state-of-the-art transformer-based models, CoMamba enjoys being a more scalable 3D model using bidirectional state space models, bypassing the quadratic complexity pain-point of attention mechanisms. Through extensive experimentation on V2X/V2V datasets, CoMamba achieves superior performance compared to existing methods while maintaining real-time processing capabilities. The proposed framework not only enhances object detection accuracy but also significantly reduces processing time, making it a promising solution for next-generation cooperative perception systems in intelligent transportation networks.
Authors: Yanan Jian, Fuxun Yu, Qi Zhang, William Levine, Brandon Dubbs, Nikolaos Karianakis
Abstract: This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we allow the detector to look up similar object concepts from memory during test time. This is achieved through a retrieval augmented classification (RAC) module together with a memory bank that can be flexibly updated with new domain knowledge. We experimented with various off-the-shelf open-set detector and close-set detectors. With only a tiny memory bank (e.g., 10 images per category) and being training-free, our online learning method could significantly outperform baselines in adapting a detector to novel domains.
Authors: Sina Malakouti, Aysan Aghazadeh, Ashmit Khandelwal, Adriana Kovashka
Abstract: Vision language models (VLMs) have shown strong zero-shot generalization across various tasks, especially when integrated with large language models (LLMs). However, their ability to comprehend rhetorical and persuasive visual media, such as advertisements, remains understudied. Ads often employ atypical imagery, using surprising object juxtapositions to convey shared properties. For example, Fig. 1 (e) shows a beer with a feather-like texture. This requires advanced reasoning to deduce that this atypical representation signifies the beer's lightness. We introduce three novel tasks, Multi-label Atypicality Classification, Atypicality Statement Retrieval, and Aypical Object Recognition, to benchmark VLMs' understanding of atypicality in persuasive images. We evaluate how well VLMs use atypicality to infer an ad's message and test their reasoning abilities by employing semantically challenging negatives. Finally, we pioneer atypicality-aware verbalization by extracting comprehensive image descriptions sensitive to atypical elements. Our findings reveal that: (1) VLMs lack advanced reasoning capabilities compared to LLMs; (2) simple, effective strategies can extract atypicality-aware information, leading to comprehensive image verbalization; (3) atypicality aids persuasive advertisement understanding. Code and data will be made available.
Authors: Fl\'avio Coutinho, Luiz Chaimowicz
Abstract: Creating and updating pixel art character sprites with many frames spanning different animations and poses takes time and can quickly become repetitive. However, that can be partially automated to allow artists to focus on more creative tasks. In this work, we concentrate on creating pixel art character sprites in a target pose from images of them facing other three directions. We present a novel approach to character generation by framing the problem as a missing data imputation task. Our proposed generative adversarial networks model receives the images of a character in all available domains and produces the image of the missing pose. We evaluated our approach in the scenarios with one, two, and three missing images, achieving similar or better results to the state-of-the-art when more images are available. We also evaluate the impact of the proposed changes to the base architecture.
Authors: Junjie Luo, Yuxuan Liu, Emma Alexander, Qi Guo
Abstract: We propose depth from coupled optical differentiation, a low-computation passive-lighting 3D sensing mechanism. It is based on our discovery that per-pixel object distance can be rigorously determined by a coupled pair of optical derivatives of a defocused image using a simple, closed-form relationship. Unlike previous depth-from-defocus (DfD) methods that leverage spatial derivatives of the image to estimate scene depths, the proposed mechanism's use of only optical derivatives makes it significantly more robust to noise. Furthermore, unlike many previous DfD algorithms with requirements on aperture code, this relationship is proved to be universal to a broad range of aperture codes. We build the first 3D sensor based on depth from coupled optical differentiation. Its optical assembly includes a deformable lens and a motorized iris, which enables dynamic adjustments to the optical power and aperture radius. The sensor captures two pairs of images: one pair with a differential change of optical power and the other with a differential change of aperture scale. From the four images, a depth and confidence map can be generated with only 36 floating point operations per output pixel (FLOPOP), more than ten times lower than the previous lowest passive-lighting depth sensing solution to our knowledge. Additionally, the depth map generated by the proposed sensor demonstrates more than twice the working range of previous DfD methods while using significantly lower computation.
Authors: Kaleb Kassaw, Francesco Luzi, Leslie M. Collins, Jordan M. Malof
Abstract: Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from the view of a camera. Methods to improve performance under occlusion, including data augmentation, part-based clustering, and more inherently robust architectures, including Vision Transformer (ViT) models, have, to some extent, been evaluated on their ability to classify objects under partial occlusion. However, evaluations of these methods have largely relied on images containing artificial occlusion, which are typically computer-generated and therefore inexpensive to label. Additionally, methods are rarely compared against each other, and many methods are compared against early, now outdated, deep learning models. We contribute the Image Recognition Under Occlusion (IRUO) dataset, based on the recently developed Occluded Video Instance Segmentation (OVIS) dataset (arXiv:2102.01558). IRUO utilizes real-world and artificially occluded images to test and benchmark leading methods' robustness to partial occlusion in visual recognition tasks. In addition, we contribute the design and results of a human study using images from IRUO that evaluates human classification performance at multiple levels and types of occlusion. We find that modern CNN-based models show improved recognition accuracy on occluded images compared to earlier CNN-based models, and ViT-based models are more accurate than CNN-based models on occluded images, performing only modestly worse than human accuracy. We also find that certain types of occlusion, including diffuse occlusion, where relevant objects are seen through "holes" in occluders such as fences and leaves, can greatly reduce the accuracy of deep recognition models as compared to humans, especially those with CNN backbones.
Authors: Moein Heidari, Reza Rezaeian, Reza Azad, Dorit Merhof, Hamid Soltanian-Zadeh, Ilker Hacihaliloglu
Abstract: Implicit Neural Representation (INR), leveraging a neural network to transform coordinate input into corresponding attributes, has recently driven significant advances in several vision-related domains. However, the performance of INR is heavily influenced by the choice of the nonlinear activation function used in its multilayer perceptron (MLP) architecture. Multiple nonlinearities have been investigated; yet, current INRs face limitations in capturing high-frequency components, diverse signal types, and handling inverse problems. We have identified that these problems can be greatly alleviated by introducing a paradigm shift in INRs. We find that an architecture with learnable activations in initial layers can represent fine details in the underlying signals. Specifically, we propose SL$^{2}$A-INR, a hybrid network for INR with a single-layer learnable activation function, prompting the effectiveness of traditional ReLU-based MLPs. Our method performs superior across diverse tasks, including image representation, 3D shape reconstructions, inpainting, single image super-resolution, CT reconstruction, and novel view synthesis. Through comprehensive experiments, SL$^{2}$A-INR sets new benchmarks in accuracy, quality, and convergence rates for INR.
Authors: Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita, Yuki Uranishi
Abstract: Audio-driven 3D facial animation has made immersive progress both in research and application developments. The newest approaches focus on Transformer-based methods and diffusion-based methods, however, there is still gap in the vividness and emotional expression between the generated animation and real human face. To tackle this limitation, we propose 3DFacePolicy, a diffusion policy model for 3D facial animation prediction. This method generates variable and realistic human facial movements by predicting the 3D vertex trajectory on the 3D facial template with diffusion policy instead of facial generation for every frame. It takes audio and vertex states as observations to predict the vertex trajectory and imitate real human facial expressions, which keeps the continuous and natural flow of human emotions. The experiments show that our approach is effective in variable and dynamic facial motion synthesizing.
Authors: Zhixin Xie, Jun Luo
Abstract: Real-time deepfake, a type of generative AI, is capable of "creating" non-existing contents (e.g., swapping one's face with another) in a video. It has been, very unfortunately, misused to produce deepfake videos (during web conferences, video calls, and identity authentication) for malicious purposes, including financial scams and political misinformation. Deepfake detection, as the countermeasure against deepfake, has attracted considerable attention from the academic community, yet existing works typically rely on learning passive features that may perform poorly beyond seen datasets. In this paper, we propose SFake, a new real-time deepfake detection method that innovatively exploits deepfake models' inability to adapt to physical interference. Specifically, SFake actively sends probes to trigger mechanical vibrations on the smartphone, resulting in the controllable feature on the footage. Consequently, SFake determines whether the face is swapped by deepfake based on the consistency of the facial area with the probe pattern. We implement SFake, evaluate its effectiveness on a self-built dataset, and compare it with six other detection methods. The results show that SFake outperforms other detection methods with higher detection accuracy, faster process speed, and lower memory consumption.
Authors: Philip Jacobson, Yichen Xie, Mingyu Ding, Chenfeng Xu, Masayoshi Tomizuka, Wei Zhan, Ming C. Wu
Abstract: Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework in which machine-generated pseudo-labels on a large unlabeled dataset are used in combination with a small manually-labeled dataset for training. In this work, we address the problem of improving pseudo-label quality through leveraging long-term temporal information captured in driving scenes. More specifically, we leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data to further enhance the student model training. Our approach improves pseudo-label quality in two distinct manners: first, we suppress false positive pseudo-labels through establishing consistency across multiple frames of motion forecasting outputs. Second, we compensate for false negative detections by directly inserting predicted object tracks into the pseudo-labeled scene. Experiments on the nuScenes dataset demonstrate the effectiveness of our approach, improving the performance of standard semi-supervised approaches in a variety of settings.
Authors: Gabriele Goletto, Tushar Nagarajan, Giuseppe Averta, Dima Damen
Abstract: Egocentric videos provide a unique perspective into individuals' daily experiences, yet their unstructured nature presents challenges for perception. In this paper, we introduce AMEGO, a novel approach aimed at enhancing the comprehension of very-long egocentric videos. Inspired by the human's ability to maintain information from a single watching, AMEGO focuses on constructing a self-contained representations from one egocentric video, capturing key locations and object interactions. This representation is semantic-free and facilitates multiple queries without the need to reprocess the entire visual content. Additionally, to evaluate our understanding of very-long egocentric videos, we introduce the new Active Memories Benchmark (AMB), composed of more than 20K of highly challenging visual queries from EPIC-KITCHENS. These queries cover different levels of video reasoning (sequencing, concurrency and temporal grounding) to assess detailed video understanding capabilities. We showcase improved performance of AMEGO on AMB, surpassing other video QA baselines by a substantial margin.
Authors: Yanbei Jiang, Krista A. Ehinger, Jey Han Lau
Abstract: Exploring the narratives conveyed by fine-art paintings is a challenge in image captioning, where the goal is to generate descriptions that not only precisely represent the visual content but also offer a in-depth interpretation of the artwork's meaning. The task is particularly complex for artwork images due to their diverse interpretations and varied aesthetic principles across different artistic schools and styles. In response to this, we present KALE Knowledge-Augmented vision-Language model for artwork Elaborations), a novel approach that enhances existing vision-language models by integrating artwork metadata as additional knowledge. KALE incorporates the metadata in two ways: firstly as direct textual input, and secondly through a multimodal heterogeneous knowledge graph. To optimize the learning of graph representations, we introduce a new cross-modal alignment loss that maximizes the similarity between the image and its corresponding metadata. Experimental results demonstrate that KALE achieves strong performance (when evaluated with CIDEr, in particular) over existing state-of-the-art work across several artwork datasets. Source code of the project is available at https://github.com/Yanbei-Jiang/Artwork-Interpretation.
URLs: https://github.com/Yanbei-Jiang/Artwork-Interpretation.
Authors: Zhongyan Niu, Zhen Tan
Abstract: Visual localization refers to the process of determining camera poses and orientation within a known scene representation. This task is often complicated by factors such as illumination changes and variations in viewing angles. In this paper, we propose HGSLoc, a novel lightweight, plug and-play pose optimization framework, which integrates 3D reconstruction with a heuristic refinement strategy to achieve higher pose estimation accuracy. Specifically, we introduce an explicit geometric map for 3D representation and high-fidelity rendering, allowing the generation of high-quality synthesized views to support accurate visual localization. Our method demonstrates a faster rendering speed and higher localization accuracy compared to NeRF-based neural rendering localization approaches. We introduce a heuristic refinement strategy, its efficient optimization capability can quickly locate the target node, while we set the step-level optimization step to enhance the pose accuracy in the scenarios with small errors. With carefully designed heuristic functions, it offers efficient optimization capabilities, enabling rapid error reduction in rough localization estimations. Our method mitigates the dependence on complex neural network models while demonstrating improved robustness against noise and higher localization accuracy in challenging environments, as compared to neural network joint optimization strategies. The optimization framework proposed in this paper introduces novel approaches to visual localization by integrating the advantages of 3D reconstruction and heuristic refinement strategy, which demonstrates strong performance across multiple benchmark datasets, including 7Scenes and DB dataset.
Authors: Min-Yeong Park, Jae-Ho Lee, Gyeong-Moon Park
Abstract: Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks while overcoming catastrophic forgetting. Existing IL methods typically assume that an incoming task has only increments of classes or domains, referred to as Class IL (CIL) or Domain IL (DIL), respectively. In this work, we consider a more challenging and realistic but under-explored IL scenario, named Versatile Incremental Learning (VIL), in which a model has no prior of which of the classes or domains will increase in the next task. In the proposed VIL scenario, the model faces intra-class domain confusion and inter-domain class confusion, which makes the model fail to accumulate new knowledge without interference with learned knowledge. To address these issues, we propose a simple yet effective IL framework, named Incremental Classifier with Adaptation Shift cONtrol (ICON). Based on shifts of learnable modules, we design a novel regularization method called Cluster-based Adaptation Shift conTrol (CAST) to control the model to avoid confusion with the previously learned knowledge and thereby accumulate the new knowledge more effectively. Moreover, we introduce an Incremental Classifier (IC) which expands its output nodes to address the overwriting issue from different domains corresponding to a single class while maintaining the previous knowledge. We conducted extensive experiments on three benchmarks, showcasing the effectiveness of our method across all the scenarios, particularly in cases where the next task can be randomly altered. Our implementation code is available at https://github.com/KHU-AGI/VIL.
Authors: Debin Meng, Christos Tzelepis, Ioannis Patras, Georgios Tzimiropoulos
Abstract: Generating human portraits is a hot topic in the image generation area, e.g. mask-to-face generation and text-to-face generation. However, these unimodal generation methods lack controllability in image generation. Controllability can be enhanced by exploring the advantages and complementarities of various modalities. For instance, we can utilize the advantages of text in controlling diverse attributes and masks in controlling spatial locations. Current state-of-the-art methods in multimodal generation face limitations due to their reliance on extensive hyperparameters, manual operations during the inference stage, substantial computational demands during training and inference, or inability to edit real images. In this paper, we propose a practical framework - MM2Latent - for multimodal image generation and editing. We use StyleGAN2 as our image generator, FaRL for text encoding, and train an autoencoders for spatial modalities like mask, sketch and 3DMM. We propose a strategy that involves training a mapping network to map the multimodal input into the w latent space of StyleGAN. The proposed framework 1) eliminates hyperparameters and manual operations in the inference stage, 2) ensures fast inference speeds, and 3) enables the editing of real images. Extensive experiments demonstrate that our method exhibits superior performance in multimodal image generation, surpassing recent GAN- and diffusion-based methods. Also, it proves effective in multimodal image editing and is faster than GAN- and diffusion-based methods. We make the code publicly available at: https://github.com/Open-Debin/MM2Latent
Authors: Rui Yu, Runkai Zhao, Jiagen Li, Qingsong Zhao, Songhao Zhu, HuaiCheng Yan, Meng Wang
Abstract: The LiDAR-based 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving and robotic navigation systems. To enhance the accuracy of point cloud detection, integrating global context for visual understanding improves the point clouds ability to grasp overall spatial information. However, many existing LiDAR detection models depend on intricate feature transformation and extraction processes, leading to poor real-time performance and high resource consumption, which limits their practical effectiveness. In this work, we propose a Faster LiDAR 3D object detection framework, called FASD, which implements heterogeneous model distillation by adaptively uniform cross-model voxel features. We aim to distill the transformer's capacity for high-performance sequence modeling into Mamba models with low FLOPs, achieving a significant improvement in accuracy through knowledge transfer. Specifically, Dynamic Voxel Group and Adaptive Attention strategies are integrated into the sparse backbone, creating a robust teacher model with scale-adaptive attention for effective global visual context modeling. Following feature alignment with the Adapter, we transfer knowledge from the Transformer to the Mamba through latent space feature supervision and span-head distillation, resulting in improved performance and an efficient student model. We evaluated the framework on the Waymo and nuScenes datasets, achieving a 4x reduction in resource consumption and a 1-2\% performance improvement over the current SoTA methods.
Authors: Kuinan Hou, Marco Zorzi, Alberto Testolin
Abstract: Humans share with many animal species the ability to perceive and approximately represent the number of objects in visual scenes. This ability improves throughout childhood, suggesting that learning and development play a key role in shaping our number sense. This hypothesis is further supported by computational investigations based on deep learning, which have shown that numerosity perception can spontaneously emerge in neural networks that learn the statistical structure of images with a varying number of items. However, neural network models are usually trained using synthetic datasets that might not faithfully reflect the statistical structure of natural environments. In this work, we exploit recent advances in computer vision algorithms to design and implement an original pipeline that can be used to estimate the distribution of numerosity and non-numerical magnitudes in large-scale datasets containing thousands of real images depicting objects in daily life situations. We show that in natural visual scenes the frequency of appearance of different numerosities follows a power law distribution and that numerosity is strongly correlated with many continuous magnitudes, such as cumulative areas and convex hull, which might explain why numerosity judgements are often influenced by these non-numerical cues.
Authors: Edwin Arkel Rios, Femiloye Oyerinde, Min-Chun Hu, Bo-Cheng Lai
Abstract: Ultra-fine-grained image recognition (UFGIR) categorizes objects with extremely small differences between classes, such as distinguishing between cultivars within the same species, as opposed to species-level classification in fine-grained image recognition (FGIR). The difficulty of this task is exacerbated due to the scarcity of samples per category. To tackle these challenges we introduce a novel approach employing down-sampling inter-layer adapters in a parameter-efficient setting, where the backbone parameters are frozen and we only fine-tune a small set of additional modules. By integrating dual-branch down-sampling, we significantly reduce the number of parameters and floating-point operations (FLOPs) required, making our method highly efficient. Comprehensive experiments on ten datasets demonstrate that our approach obtains outstanding accuracy-cost performance, highlighting its potential for practical applications in resource-constrained environments. In particular, our method increases the average accuracy by at least 6.8\% compared to other methods in the parameter-efficient setting while requiring at least 123x less trainable parameters compared to current state-of-the-art UFGIR methods and reducing the FLOPs by 30\% in average compared to other methods.
Authors: Bilal Faye, Hanane Azzag, Mustapha Lebbah
Abstract: Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling applications such as visual question answering and audiovisual content analysis. Current techniques rely on large modality-specific encoders, necessitating fine-tuning or training from scratch on vast aligned datasets (e.g., text-image, text-audio, image-audio). This approach has limitations: (i) it is very expensive due to the need for training large encoders on extensive datasets, (ii) acquiring aligned large paired datasets is challenging, and (iii) adding new modalities requires retraining the entire framework to incorporate these modalities. To address these issues, we propose OneEncoder, a lightweight framework that progressively represents and aligns four modalities (image, text, audio, video). Initially, we train a lightweight Universal Projection module (UP) to align image and text modalities. Then, we freeze the pretrained UP and progressively align future modalities to those already aligned. OneEncoder operates efficiently and cost-effectively, even in scenarios where vast aligned datasets are unavailable, due to its lightweight design. Trained on small paired datasets, it shows strong performance in tasks like classification, querying, and visual question answering, surpassing methods that rely on large datasets and specialized encoders.
Authors: Katharina Bendig, Ren\'e Schuster, Didier Stricker
Abstract: The novel Dynamic Vision Sensors (DVSs) gained a great amount of attention recently as they are superior compared to RGB cameras in terms of latency, dynamic range and energy consumption. This is particularly of interest for autonomous applications since event cameras are able to alleviate motion blur and allow for night vision. One challenge in real-world autonomous settings is occlusion where foreground objects hinder the view on traffic participants in the background. The ShapeAug method addresses this problem by using simulated events resulting from objects moving on linear paths for event data augmentation. However, the shapes and movements lack complexity, making the simulation fail to resemble the behavior of objects in the real world. Therefore in this paper, we propose ShapeAug++, an extended version of ShapeAug which involves randomly generated polygons as well as curved movements. We show the superiority of our method on multiple DVS classification datasets, improving the top-1 accuracy by up to 3.7% compared to ShapeAug.
Authors: Alessandro Simoni, Francesco Marchetti, Guido Borghi, Federico Becattini, Davide Davoli, Lorenzo Garattoni, Gianpiero Francesca, Lorenzo Seidenari, Roberto Vezzani
Abstract: Despite the recent advances in computer vision research, estimating the 3D human pose from single RGB images remains a challenging task, as multiple 3D poses can correspond to the same 2D projection on the image. In this context, depth data could help to disambiguate the 2D information by providing additional constraints about the distance between objects in the scene and the camera. Unfortunately, the acquisition of accurate depth data is limited to indoor spaces and usually is tied to specific depth technologies and devices, thus limiting generalization capabilities. In this paper, we propose a method able to leverage the benefits of depth information without compromising its broader applicability and adaptability in a predominantly RGB-camera-centric landscape. Our approach consists of a heatmap-based 3D pose estimator that, leveraging the paradigm of Privileged Information, is able to hallucinate depth information from the RGB frames given at inference time. More precisely, depth information is used exclusively during training by enforcing our RGB-based hallucination network to learn similar features to a backbone pre-trained only on depth data. This approach proves to be effective even when dealing with limited and small datasets. Experimental results reveal that the paradigm of Privileged Information significantly enhances the model's performance, enabling efficient extraction of depth information by using only RGB images.
Authors: Hassan Keshvarikhojasteh
Abstract: Reliable models are dependable and provide predictions acceptable given basic domain knowledge. Therefore, it is critical to develop and deploy reliable models, especially for healthcare applications. However, Multiple Instance Learning (MIL) models designed for Whole Slide Images (WSIs) classification in computational pathology are not evaluated in terms of reliability. Hence, in this paper we compare the reliability of MIL models with three suggested metrics and use three region-wise annotated datasets. We find the mean pooling instance (MEAN-POOL-INS) model more reliable than other networks despite its naive architecture design and computation efficiency. The code to reproduce the results is accessible at https://github.com/tueimage/MILs'R .
Authors: Yoichi Furukawa (Meijo University), Satoshi Kamiya (Mitsubishi Electric Advanced Technology R&D Center), Yoichi Sakurada (Yamanashi University), Kenji Kashiwagi (Yamanashi University), Kazuhiro Hotta (Meijo University)
Abstract: In recent years, there has been significant development in the analysis of medical data using machine learning. It is believed that the onset of Age-related Macular Degeneration (AMD) is associated with genetic polymorphisms. However, genetic analysis is costly, and artificial intelligence may offer assistance. This paper presents a method that predict the presence of multiple susceptibility genes for AMD using fundus and Optical Coherence Tomography (OCT) images, as well as medical records. Experimental results demonstrate that integrating information from multiple modalities can effectively predict the presence of susceptibility genes with over 80$\%$ accuracy.
Authors: Andrzej Perzanowski, Tony Lindeberg
Abstract: This paper presents an in-depth analysis of the scale generalisation properties of the scale-covariant and scale-invariant Gaussian derivative networks, complemented with both conceptual and algorithmic extensions. For this purpose, Gaussian derivative networks are evaluated on new rescaled versions of the Fashion-MNIST and the CIFAR-10 datasets, with spatial scaling variations over a factor of 4 in the testing data, that are not present in the training data. Additionally, evaluations on the previously existing STIR datasets show that the Gaussian derivative networks achieve better scale generalisation than previously reported for these datasets for other types of deep networks. We first experimentally demonstrate that the Gaussian derivative networks have quite good scale generalisation properties on the new datasets, and that average pooling of feature responses over scales may sometimes also lead to better results than the previously used approach of max pooling over scales. Then, we demonstrate that using a spatial max pooling mechanism after the final layer enables localisation of non-centred objects in image domain, with maintained scale generalisation properties. We also show that regularisation during training, by applying dropout across the scale channels, referred to as scale-channel dropout, improves both the performance and the scale generalisation. In additional ablation studies, we demonstrate that discretisations of Gaussian derivative networks, based on the discrete analogue of the Gaussian kernel in combination with central difference operators, perform best or among the best, compared to a set of other discrete approximations of the Gaussian derivative kernels. Finally, by visualising the activation maps and the learned receptive fields, we demonstrate that the Gaussian derivative networks have very good explainability properties.
Authors: Zichen Yu, Changyong Shu
Abstract: Occupancy and 3D object detection are characterized as two standard tasks in modern autonomous driving system. In order to deploy them on a series of edge chips with better precision and time-consuming trade-off, contemporary approaches either deploy standalone models for individual tasks, or design a multi-task paradigm with separate heads. However, they might suffer from deployment difficulties (i.e., 3D convolution, transformer and so on) or deficiencies in task coordination. Instead, we argue that a favorable framework should be devised in pursuit of ease deployment on diverse chips and high precision with little time-consuming. Oriented at this, we revisit the paradigm for interaction between 3D object detection and occupancy prediction, reformulate the model with 2D convolution and prioritize the tasks such that each contributes to other. Thus, we propose a method to achieve fast 3D object detection and occupancy prediction (UltimateDO), wherein the light occupancy prediction head in FlashOcc is married to 3D object detection network, with negligible additional timeconsuming of only 1.1ms while facilitating each other. We instantiate UltimateDO on the challenging nuScenes-series benchmarks.
Authors: Hochul Hwang, Krisha Adhikari, Satya Shodhaka, Donghyun Kim
Abstract: Robotic mobility aids for blind and low-vision (BLV) individuals rely heavily on deep learning-based vision models specialized for various navigational tasks. However, the performance of these models is often constrained by the availability and diversity of real-world datasets, which are challenging to collect in sufficient quantities for different tasks. In this study, we investigate the effectiveness of synthetic data, generated using Unreal Engine 4, for training robust vision models for this safety-critical application. Our findings demonstrate that synthetic data can enhance model performance across multiple tasks, showcasing both its potential and its limitations when compared to real-world data. We offer valuable insights into optimizing synthetic data generation for developing robotic mobility aids. Additionally, we publicly release our generated synthetic dataset to support ongoing research in assistive technologies for BLV individuals, available at https://hchlhwang.github.io/SToP.
Authors: Yunsheng Ma, Amr Abdelraouf, Rohit Gupta, Ziran Wang, Kyungtae Han
Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable potential for enhancing scene understanding in autonomous driving systems through powerful logical reasoning capabilities. However, the deployment of these models faces significant challenges due to their substantial parameter sizes and computational demands, which often exceed the constraints of onboard computation. One major limitation arises from the large number of visual tokens required to capture fine-grained and long-context visual information, leading to increased latency and memory consumption. To address this issue, we propose Video Token Sparsification (VTS), a novel approach that leverages the inherent redundancy in consecutive video frames to significantly reduce the total number of visual tokens while preserving the most salient information. VTS employs a lightweight CNN-based proposal model to adaptively identify key frames and prune less informative tokens, effectively mitigating hallucinations and increasing inference throughput without compromising performance. We conduct comprehensive experiments on the DRAMA and LingoQA benchmarks, demonstrating the effectiveness of VTS in achieving up to a 33\% improvement in inference throughput and a 28\% reduction in memory usage compared to the baseline without compromising performance.
Authors: Gabriele Sartor, Matteo Salis, Stefano Pinardi, Ozgur Saracik, Rosa Meo
Abstract: Deforestation is gaining an increasingly importance due to its strong influence on the sorrounding environment, especially in developing countries where population has a disadvantaged economic condition and agriculture is the main source of income. In Ivory Coast, for instance, where the cocoa production is the most remunerative activity, it is not rare to assist to the replacement of portion of ancient forests with new cocoa plantations. In order to monitor this type of deleterious activities, satellites can be employed to recognize the disappearance of the forest to prevent it from expand its area of interest. In this study, Forest-Non-Forest map (FNF) has been used as ground truth for models based on Sentinel images input. State-of-the-art models U-Net, Attention U-Net, Segnet and FCN32 are compared over different years combining Sentinel-1, Sentinel-2 and cloud probability to create forest/non-forest segmentation. Although Ivory Coast lacks of forest coverage datasets and is partially covered by Sentinel images, it is demonstrated the feasibility to create models classifying forest and non-forests pixels over the area using open datasets to predict where deforestation could have occurred. Although a significant portion of the deforestation research is carried out on visible bands, SAR acquisitions are employed to overcome the limits of RGB images over areas often covered by clouds. Finally, the most promising model is employed to estimate the hectares of forest has been cut between 2019 and 2020.
Authors: Nick Theisen, Robin Bartsch, Dietrich Paulus, Peer Neubert
Abstract: Semantic segmentation is an essential step for many vision applications in order to understand a scene and the objects within. Recent progress in hyperspectral imaging technology enables the application in driving scenarios and the hope is that the devices perceptive abilities provide an advantage over RGB-cameras. Even though some datasets exist, there is no standard benchmark available to systematically measure progress on this task and evaluate the benefit of hyperspectral data. In this paper, we work towards closing this gap by providing the HyperSpectral Semantic Segmentation benchmark (HS3-Bench). It combines annotated hyperspectral images from three driving scenario datasets and provides standardized metrics, implementations, and evaluation protocols. We use the benchmark to derive two strong baseline models that surpass the previous state-of-the-art performances with and without pre-training on the individual datasets. Further, our results indicate that the existing learning-based methods benefit more from leveraging additional RGB training data than from leveraging the additional hyperspectral channels. This poses important questions for future research on hyperspectral imaging for semantic segmentation in driving scenarios. Code to run the benchmark and the strong baseline approaches are available under https://github.com/nickstheisen/hyperseg.
Authors: Aditya Humnabadkar, Arindam Sikdar, Benjamin Cave, Huaizhong Zhang, Paul Bakaki, Ardhendu Behera
Abstract: We present an innovative framework for traffic dynamics analysis using High-Order Evolving Graphs, designed to improve spatio-temporal representations in autonomous driving contexts. Our approach constructs temporal bidirectional bipartite graphs that effectively model the complex interactions within traffic scenes in real-time. By integrating Graph Neural Networks (GNNs) with high-order multi-aggregation strategies, we significantly enhance the modeling of traffic scene dynamics, providing a more accurate and detailed analysis of these interactions. Additionally, we incorporate inductive learning techniques inspired by the GraphSAGE framework, enabling our model to adapt to new and unseen traffic scenarios without the need for retraining, thus ensuring robust generalization. Through extensive experiments on the ROAD and ROAD Waymo datasets, we establish a comprehensive baseline for further developments, demonstrating the potential of our method in accurately capturing traffic behavior. Our results emphasize the value of high-order statistical moments and feature-gated attention mechanisms in improving traffic behavior analysis, laying the groundwork for advancing autonomous driving technologies. Our source code is available at: https://github.com/Addy-1998/High\_Order\_Graphs
Authors: Marko Mihajlovic, Sergey Prokudin, Siyu Tang, Robert Maier, Federica Bogo, Tony Tung, Edmond Boyer
Abstract: Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method, gaining popularity due to its impressive reconstruction quality, real-time rendering capabilities, and compatibility with widely used visualization tools. However, the method requires a substantial number of input views to achieve high-quality scene reconstruction, introducing a significant practical bottleneck. This challenge is especially severe in capturing dynamic scenes, where deploying an extensive camera array can be prohibitively costly. In this work, we identify the lack of spatial autocorrelation of splat features as one of the factors contributing to the suboptimal performance of the 3DGS technique in sparse reconstruction settings. To address the issue, we propose an optimization strategy that effectively regularizes splat features by modeling them as the outputs of a corresponding implicit neural field. This results in a consistent enhancement of reconstruction quality across various scenarios. Our approach effectively handles static and dynamic cases, as demonstrated by extensive testing across different setups and scene complexities.
Authors: Tianqi Chen, Shujian Zhang, Mingyuan Zhou
Abstract: The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and trustworthy GenAI models. Traditional MU methods often rely on stringent assumptions and require access to real data. This paper introduces Score Forgetting Distillation (SFD), an innovative MU approach that promotes the forgetting of undesirable information in diffusion models by aligning the conditional scores of ``unsafe'' classes or concepts with those of ``safe'' ones. To eliminate the need for real data, our SFD framework incorporates a score-based MU loss into the score distillation objective of a pretrained diffusion model. This serves as a regularization term that preserves desired generation capabilities while enabling the production of synthetic data through a one-step generator. Our experiments on pretrained label-conditional and text-to-image diffusion models demonstrate that our method effectively accelerates the forgetting of target classes or concepts during generation, while preserving the quality of other classes or concepts. This unlearned and distilled diffusion not only pioneers a novel concept in MU but also accelerates the generation speed of diffusion models. Our experiments and studies on a range of diffusion models and datasets confirm that our approach is generalizable, effective, and advantageous for MU in diffusion models.
Authors: Yuta Kaneko, Abu Saleh Musa Miah, Najmul Hassan, Hyoun-Sup Lee, Si-Woong Jang, Jungpil Shin
Abstract: Weakly supervised video anomaly detection (WS-VAD) is a crucial area in computer vision for developing intelligent surveillance systems. This system uses three feature streams: RGB video, optical flow, and audio signals, where each stream extracts complementary spatial and temporal features using an enhanced attention module to improve detection accuracy and robustness. In the first stream, we employed an attention-based, multi-stage feature enhancement approach to improve spatial and temporal features from the RGB video where the first stage consists of a ViT-based CLIP module, with top-k features concatenated in parallel with I3D and Temporal Contextual Aggregation (TCA) based rich spatiotemporal features. The second stage effectively captures temporal dependencies using the Uncertainty-Regulated Dual Memory Units (UR-DMU) model, which learns representations of normal and abnormal data simultaneously, and the third stage is employed to select the most relevant spatiotemporal features. The second stream extracted enhanced attention-based spatiotemporal features from the flow data modality-based feature by taking advantage of the integration of the deep learning and attention module. The audio stream captures auditory cues using an attention module integrated with the VGGish model, aiming to detect anomalies based on sound patterns. These streams enrich the model by incorporating motion and audio signals often indicative of abnormal events undetectable through visual analysis alone. The concatenation of the multimodal fusion leverages the strengths of each modality, resulting in a comprehensive feature set that significantly improves anomaly detection accuracy and robustness across three datasets. The extensive experiment and high performance with the three benchmark datasets proved the effectiveness of the proposed system over the existing state-of-the-art system.
Authors: Tetsushi Ohki, Narishige Abe, Hidetsugu Uchida, Shigefumi Yamada
Abstract: Biometric recognition systems, known for their convenience, are widely adopted across various fields. However, their security faces risks depending on the authentication algorithm and deployment environment. Current risk assessment methods faces significant challenges in incorporating the crucial factor of attacker's motivation, leading to incomplete evaluations. This paper presents a novel human-centered risk evaluation framework using conjoint analysis to quantify the impact of risk factors, such as surveillance cameras, on attacker's motivation. Our framework calculates risk values incorporating the False Acceptance Rate (FAR) and attack probability, allowing comprehensive comparisons across use cases. A survey of 600 Japanese participants demonstrates our method's effectiveness, showing how security measures influence attacker's motivation. This approach helps decision-makers customize biometric systems to enhance security while maintaining usability.
Authors: Clifford Broni-Bediako, Junshi Xia, Jian Song, Hongruixuan Chen, Mennatullah Siam, Naoto Yokoya
Abstract: Learning with limited labelled data is a challenging problem in various applications, including remote sensing. Few-shot semantic segmentation is one approach that can encourage deep learning models to learn from few labelled examples for novel classes not seen during the training. The generalized few-shot segmentation setting has an additional challenge which encourages models not only to adapt to the novel classes but also to maintain strong performance on the training base classes. While previous datasets and benchmarks discussed the few-shot segmentation setting in remote sensing, we are the first to propose a generalized few-shot segmentation benchmark for remote sensing. The generalized setting is more realistic and challenging, which necessitates exploring it within the remote sensing context. We release the dataset augmenting OpenEarthMap with additional classes labelled for the generalized few-shot evaluation setting. The dataset is released during the OpenEarthMap land cover mapping generalized few-shot challenge in the L3D-IVU workshop in conjunction with CVPR 2024. In this work, we summarize the dataset and challenge details in addition to providing the benchmark results on the two phases of the challenge for the validation and test sets.
Authors: Jianbo Ma, Chuanming Tang, Fei Wu, Can Zhao, Jianlin Zhang, Zhiyong Xu
Abstract: Multiple object tracking (MOT) in Unmanned Aerial Vehicle (UAV) videos is important for diverse applications in computer vision. Current MOT trackers rely on accurate object detection results and precise matching of target reidentification (ReID). These methods focus on optimizing target spatial attributes while overlooking temporal cues in modelling object relationships, especially for challenging tracking conditions such as object deformation and blurring, etc. To address the above-mentioned issues, we propose a novel Spatio-Temporal Cohesion Multiple Object Tracking framework (STCMOT), which utilizes historical embedding features to model the representation of ReID and detection features in a sequential order. Concretely, a temporal embedding boosting module is introduced to enhance the discriminability of individual embedding based on adjacent frame cooperation. While the trajectory embedding is then propagated by a temporal detection refinement module to mine salient target locations in the temporal field. Extensive experiments on the VisDrone2019 and UAVDT datasets demonstrate our STCMOT sets a new state-of-the-art performance in MOTA and IDF1 metrics. The source codes are released at https://github.com/ydhcg-BoBo/STCMOT.
Authors: Siyuan Li, Lei Ke, Yung-Hsu Yang, Luigi Piccinelli, Mattia Seg\`u, Martin Danelljan, Luc Van Gool
Abstract: Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the complexity of motion patterns in the large-vocabulary scenarios and unstable classification of the novel objects, the motion and semantics cues are either ignored or applied based on heuristics in the final matching steps by existing methods. In this paper, we present a unified framework SLAck that jointly considers semantics, location, and appearance priors in the early steps of association and learns how to integrate all valuable information through a lightweight spatial and temporal object graph. Our method eliminates complex post-processing heuristics for fusing different cues and boosts the association performance significantly for large-scale open-vocabulary tracking. Without bells and whistles, we outperform previous state-of-the-art methods for novel classes tracking on the open-vocabulary MOT and TAO TETA benchmarks. Our code is available at \href{https://github.com/siyuanliii/SLAck}{github.com/siyuanliii/SLAck}.
Authors: Zixuan Fu, Lanqing Guo, Chong Wang, Yufei Wang, Zhihao Li, Bihan Wen
Abstract: Recent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision. However, the challenge of acquiring paired videos for dynamic scenes hampers the practical deployment of deep video denoising techniques. In contrast, this obstacle is less pronounced in image denoising, where paired data is more readily available. Thus, a well-trained image denoiser could serve as a reliable spatial prior for video denoising. In this paper, we propose a novel unsupervised video denoising framework, named ``Temporal As a Plugin'' (TAP), which integrates tunable temporal modules into a pre-trained image denoiser. By incorporating temporal modules, our method can harness temporal information across noisy frames, complementing its power of spatial denoising. Furthermore, we introduce a progressive fine-tuning strategy that refines each temporal module using the generated pseudo clean video frames, progressively enhancing the network's denoising performance. Compared to other unsupervised video denoising methods, our framework demonstrates superior performance on both sRGB and raw video denoising datasets.
Authors: Yichen Zhang, Zihan Wang, Jiali Han, Peilin Li, Jiaxun Zhang, Jianqiang Wang, Lei He, Keqiang Li
Abstract: 3D Gaussian Splatting (3DGS) integrates the strengths of primitive-based representations and volumetric rendering techniques, enabling real-time, high-quality rendering. However, 3DGS models typically overfit to single-scene training and are highly sensitive to the initialization of Gaussian ellipsoids, heuristically derived from Structure from Motion (SfM) point clouds, which limits both generalization and practicality. To address these limitations, we propose GS-Net, a generalizable, plug-and-play 3DGS module that densifies Gaussian ellipsoids from sparse SfM point clouds, enhancing geometric structure representation. To the best of our knowledge, GS-Net is the first plug-and-play 3DGS module with cross-scene generalization capabilities. Additionally, we introduce the CARLA-NVS dataset, which incorporates additional camera viewpoints to thoroughly evaluate reconstruction and rendering quality. Extensive experiments demonstrate that applying GS-Net to 3DGS yields a PSNR improvement of 2.08 dB for conventional viewpoints and 1.86 dB for novel viewpoints, confirming the method's effectiveness and robustness.
Authors: Jianxiong Gao, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng, Yanwei Fu
Abstract: Reconstructing 3D visuals from functional Magnetic Resonance Imaging (fMRI) data, introduced as Recon3DMind in our conference work, is of significant interest to both cognitive neuroscience and computer vision. To advance this task, we present the fMRI-3D dataset, which includes data from 15 participants and showcases a total of 4768 3D objects. The dataset comprises two components: fMRI-Shape, previously introduced and accessible at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Shape, and fMRI-Objaverse, proposed in this paper and available at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Objaverse. fMRI-Objaverse includes data from 5 subjects, 4 of whom are also part of the Core set in fMRI-Shape, with each subject viewing 3142 3D objects across 117 categories, all accompanied by text captions. This significantly enhances the diversity and potential applications of the dataset. Additionally, we propose MinD-3D, a novel framework designed to decode 3D visual information from fMRI signals. The framework first extracts and aggregates features from fMRI data using a neuro-fusion encoder, then employs a feature-bridge diffusion model to generate visual features, and finally reconstructs the 3D object using a generative transformer decoder. We establish new benchmarks by designing metrics at both semantic and structural levels to evaluate model performance. Furthermore, we assess our model's effectiveness in an Out-of-Distribution setting and analyze the attribution of the extracted features and the visual ROIs in fMRI signals. Our experiments demonstrate that MinD-3D not only reconstructs 3D objects with high semantic and spatial accuracy but also deepens our understanding of how human brain processes 3D visual information. Project page at: https://jianxgao.github.io/MinD-3D.
URLs: https://huggingface.co/datasets/Fudan-fMRI/fMRI-Shape,, https://huggingface.co/datasets/Fudan-fMRI/fMRI-Objaverse., https://jianxgao.github.io/MinD-3D.
Authors: Amirreza Fateh, Mohammad Reza Mohammadi, Mohammad Reza Jahed Motlagh
Abstract: Few-shot Semantic Segmentation addresses the challenge of segmenting objects in query images with only a handful of annotated examples. However, many previous state-of-the-art methods either have to discard intricate local semantic features or suffer from high computational complexity. To address these challenges, we propose a new Few-shot Semantic Segmentation framework based on the transformer architecture. Our approach introduces the spatial transformer decoder and the contextual mask generation module to improve the relational understanding between support and query images. Moreover, we introduce a multi-scale decoder to refine the segmentation mask by incorporating features from different resolutions in a hierarchical manner. Additionally, our approach integrates global features from intermediate encoder stages to improve contextual understanding, while maintaining a lightweight structure to reduce complexity. This balance between performance and efficiency enables our method to achieve state-of-the-art results on benchmark datasets such as $PASCAL-5^i$ and $COCO-20^i$ in both 1-shot and 5-shot settings. Notably, our model with only 1.5 million parameters demonstrates competitive performance while overcoming limitations of existing methodologies. https://github.com/amirrezafateh/MSDNet
Authors: Bowen Dong, Pan Zhou, Wangmeng Zuo
Abstract: We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of three core components. The first is a universal long-tailed adaptation module, which aggregates long-tailed prompts and visual adapters to adapt the pretrained model to the target domain, meanwhile improving its discriminative ability. The second is the mixture of long-tailed experts framework with a mixture-of-experts (MoE) scorer, which adaptively calculates reweighting coefficients for confidence scores from both visual-only and visual-language (VL) model experts to generate more accurate predictions. Finally, LPT++ employs a three-phase training framework, wherein each critical module is learned separately, resulting in a stable and effective long-tailed classification training paradigm. Besides, we also propose the simple version of LPT++ namely LPT, which only integrates visual-only pretrained ViT and long-tailed prompts to formulate a single model method. LPT can clearly illustrate how long-tailed prompts works meanwhile achieving comparable performance without VL pretrained models. Experiments show that, with only ~1% extra trainable parameters, LPT++ achieves comparable accuracy against all the counterparts.
Authors: M. Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc, Alptekin Temizel
Abstract: Recently, the centerline has become a popular representation of lanes due to its advantages in solving the road topology problem. To enhance centerline prediction, we have developed a new approach called TopoMask. Unlike previous methods that rely on keypoints or parametric methods, TopoMask utilizes an instance-mask-based formulation coupled with a masked-attention-based transformer architecture. We introduce a quad-direction label representation to enrich the mask instances with flow information and design a corresponding post-processing technique for mask-to-centerline conversion. Additionally, we demonstrate that the instance-mask formulation provides complementary information to parametric Bezier regressions, and fusing both outputs leads to improved detection and topology performance. Moreover, we analyze the shortcomings of the pillar assumption in the Lift Splat technique and adapt a multi-height bin configuration. Experimental results show that TopoMask achieves state-of-the-art performance in the OpenLane-V2 dataset, increasing from 44.1 to 49.4 for Subset-A and 44.7 to 51.8 for Subset-B in the V1.1 OLS baseline.
Authors: Kotaro Nagata, Hiromu Ono, Kazuhiro Hotta
Abstract: In continual learning, there is a serious problem of catastrophic forgetting, in which previous knowledge is forgotten when a model learns new tasks. Various methods have been proposed to solve this problem. Replay methods which replay data from previous tasks in later training, have shown good accuracy. However, replay methods have a generalizability problem from a limited memory buffer. In this paper, we tried to solve this problem by acquiring transferable knowledge through self-distillation using highly generalizable output in shallow layer as a teacher. Furthermore, when we deal with a large number of classes or challenging data, there is a risk of learning not converging and not experiencing overfitting. Therefore, we attempted to achieve more efficient and thorough learning by prioritizing the storage of easily misclassified samples through a new method of memory update. We confirmed that our proposed method outperformed conventional methods by experiments on CIFAR10, CIFAR100, and MiniimageNet datasets.
Authors: Alexey Kravets, Vinay Namboodiri
Abstract: Numerous methods have been proposed to adapt a pre-trained foundational CLIP model for few-shot classification. As CLIP is trained on a large corpus, it generalises well through adaptation to few-shot classification. In this work, we analyse the intra-modal overlap in image space in terms of embedding representation. Our analysis shows that, due to contrastive learning, embeddings from CLIP model exhibit high cosine similarity distribution overlap in the image space between paired and unpaired examples affecting the performance of few-shot training-free classification methods which rely on similarity in the image space for their predictions. To tackle intra-modal overlap we propose to train a lightweight adapter on a generic set of samples from the Google Open Images dataset demonstrating that this improves accuracy for few-shot training-free classification. We validate our contribution through extensive empirical analysis and demonstrate that reducing the intra-modal overlap leads to a) improved performance on a number of standard datasets, b) increased robustness to distribution shift and c) higher feature variance rendering the features more discriminative for downstream tasks.
Authors: Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xingrun Xing, Ruiran Yan, Shuting Wang, Tiejun Huang, Zheng Liu
Abstract: In this work, we introduce OmniGen, a new diffusion model for unified image generation. Unlike popular diffusion models (e.g., Stable Diffusion), OmniGen no longer requires additional modules such as ControlNet or IP-Adapter to process diverse control conditions. OmniGenis characterized by the following features: 1) Unification: OmniGen not only demonstrates text-to-image generation capabilities but also inherently supports other downstream tasks, such as image editing, subject-driven generation, and visual-conditional generation. Additionally, OmniGen can handle classical computer vision tasks by transforming them into image generation tasks, such as edge detection and human pose recognition. 2) Simplicity: The architecture of OmniGen is highly simplified, eliminating the need for additional text encoders. Moreover, it is more user-friendly compared to existing diffusion models, enabling complex tasks to be accomplished through instructions without the need for extra preprocessing steps (e.g., human pose estimation), thereby significantly simplifying the workflow of image generation. 3) Knowledge Transfer: Through learning in a unified format, OmniGen effectively transfers knowledge across different tasks, manages unseen tasks and domains, and exhibits novel capabilities. We also explore the model's reasoning capabilities and potential applications of chain-of-thought mechanism. This work represents the first attempt at a general-purpose image generation model, and there remain several unresolved issues. We will open-source the related resources at https://github.com/VectorSpaceLab/OmniGen to foster advancements in this field.
Authors: Gonzalo Martin Garcia, Karim Abou Zeid, Christian Schmidt, Daan de Geus, Alexander Hermans, Bastian Leibe
Abstract: Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results, high computational demands due to multi-step inference limited its use in many scenarios. In this paper, we show that the perceived inefficiency was caused by a flaw in the inference pipeline that has so far gone unnoticed. The fixed model performs comparably to the best previously reported configuration while being more than 200$\times$ faster. To optimize for downstream task performance, we perform end-to-end fine-tuning on top of the single-step model with task-specific losses and get a deterministic model that outperforms all other diffusion-based depth and normal estimation models on common zero-shot benchmarks. We surprisingly find that this fine-tuning protocol also works directly on Stable Diffusion and achieves comparable performance to current state-of-the-art diffusion-based depth and normal estimation models, calling into question some of the conclusions drawn from prior works.
Authors: Ziyang Yan, Wenzhen Dong, Yihua Shao, Yuhang Lu, Liu Haiyang, Jingwen Liu, Haozhe Wang, Zhe Wang, Yan Wang, Fabio Remondino, Yuexin Ma
Abstract: End-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we propose RenderWorld, a vision-only end-to-end autonomous driving framework, which generates 3D occupancy labels using a self-supervised gaussian-based Img2Occ Module, then encodes the labels by AM-VAE, and uses world model for forecasting and planning. RenderWorld employs Gaussian Splatting to represent 3D scenes and render 2D images greatly improves segmentation accuracy and reduces GPU memory consumption compared with NeRF-based methods. By applying AM-VAE to encode air and non-air separately, RenderWorld achieves more fine-grained scene element representation, leading to state-of-the-art performance in both 4D occupancy forecasting and motion planning from autoregressive world model.
Authors: Xiaofeng Mao, Zhengkai Jiang, Fu-Yun Wang, Wenbing Zhu, Jiangning Zhang, Hao Chen, Mingmin Chi, Yabiao Wang
Abstract: Video diffusion models have shown great potential in generating high-quality videos, making them an increasingly popular focus. However, their inherent iterative nature leads to substantial computational and time costs. While efforts have been made to accelerate video diffusion by reducing inference steps (through techniques like consistency distillation) and GAN training (these approaches often fall short in either performance or training stability). In this work, we introduce a two-stage training framework that effectively combines consistency distillation with GAN training to address these challenges. Additionally, we propose a novel video discriminator design, which eliminates the need for decoding the video latents and improves the final performance. Our model is capable of producing high-quality videos in merely one-step, with the flexibility to perform multi-step refinement for further performance enhancement. Our quantitative evaluation on the OpenWebVid-1M benchmark shows that our model significantly outperforms existing methods. Notably, our 1-step performance(FVD 171.15) exceeds the 8-step performance of the consistency distillation based method, AnimateLCM (FVD 184.79), and approaches the 25-step performance of advanced Stable Video Diffusion (FVD 156.94).
Authors: Edgar Heinert, Stephan Tilgner, Timo Palm, Matthias Rottmann
Abstract: When employing deep neural networks (DNNs) for semantic segmentation in safety-critical applications like automotive perception or medical imaging, it is important to estimate their performance at runtime, e.g. via uncertainty estimates or prediction quality estimates. Previous works mostly performed uncertainty estimation on pixel-level. In a line of research, a connected-component-wise (segment-wise) perspective was taken, approaching uncertainty estimation on an object-level by performing so-called meta classification and regression to estimate uncertainty and prediction quality, respectively. In those works, each predicted segment is considered individually to estimate its uncertainty or prediction quality. However, the neighboring segments may provide additional hints on whether a given predicted segment is of high quality, which we study in the present work. On the basis of uncertainty indicating metrics on segment-level, we use graph neural networks (GNNs) to model the relationship of a given segment's quality as a function of the given segment's metrics as well as those of its neighboring segments. We compare different GNN architectures and achieve a notable performance improvement.
Authors: Fatema-E- Jannat, Sina Gholami, Jennifer I. Lim, Theodore Leng, Minhaj Nur Alam, Hamed Tabkhi
Abstract: In the medical domain, acquiring large datasets poses significant challenges due to privacy concerns. Nonetheless, the development of a robust deep-learning model for retinal disease diagnosis necessitates a substantial dataset for training. The capacity to generalize effectively on smaller datasets remains a persistent challenge. The scarcity of data presents a significant barrier to the practical implementation of scalable medical AI solutions. To address this issue, we've combined a wide range of data sources to improve performance and generalization to new data by giving it a deeper understanding of the data representation from multi-modal datasets and developed a self-supervised framework based on large language models (LLMs), SwinV2 to gain a deeper understanding of multi-modal dataset representations, enhancing the model's ability to extrapolate to new data for the detection of eye diseases using optical coherence tomography (OCT) images. We adopt a two-phase training methodology, self-supervised pre-training, and fine-tuning on a downstream supervised classifier. An ablation study conducted across three datasets employing various encoder backbones, without data fusion, with low data availability setting, and without self-supervised pre-training scenarios, highlights the robustness of our method. Our findings demonstrate consistent performance across these diverse conditions, showcasing superior generalization capabilities compared to the baseline model, ResNet-50.
Authors: Yuxin Zhang, Cl\'ement Huneau, J\'er\^ome Idier, Diana Mateus
Abstract: Ultrasound imaging, despite its widespread use in medicine, often suffers from various sources of noise and artifacts that impact the signal-to-noise ratio and overall image quality. Enhancing ultrasound images requires a delicate balance between contrast, resolution, and speckle preservation. This paper introduces a novel approach that integrates adaptive beamforming with denoising diffusion-based variance imaging to address this challenge. By applying Eigenspace-Based Minimum Variance (EBMV) beamforming and employing a denoising diffusion model fine-tuned on ultrasound data, our method computes the variance across multiple diffusion-denoised samples to produce high-quality despeckled images. This approach leverages both the inherent multiplicative noise of ultrasound and the stochastic nature of diffusion models. Experimental results on a publicly available dataset demonstrate the effectiveness of our method in achieving superior image reconstructions from single plane-wave acquisitions. The code is available at: https://github.com/Yuxin-Zhang-Jasmine/IUS2024_Diffusion.
URLs: https://github.com/Yuxin-Zhang-Jasmine/IUS2024_Diffusion.
Authors: J\'er\'emy Lebreton, Ingo Ahrns, Roland Brochard, Christoph Haskamp, Matthieu Le Goff, Nicolas Menga, Nicolas Ollagnier, Ralf Regele, Francesco Capolupo, Massimo Casasco
Abstract: Vision Based Navigation consists in utilizing cameras as precision sensors for GNC after extracting information from images. To enable the adoption of machine learning for space applications, one of obstacles is the demonstration that available training datasets are adequate to validate the algorithms. The objective of the study is to generate datasets of images and metadata suitable for training machine learning algorithms. Two use cases were selected and a robust methodology was developed to validate the datasets including the ground truth. The first use case is in-orbit rendezvous with a man-made object: a mockup of satellite ENVISAT. The second use case is a Lunar landing scenario. Datasets were produced from archival datasets (Chang'e 3), from the laboratory at DLR TRON facility and at Airbus Robotic laboratory, from SurRender software high fidelity image simulator using Model Capture and from Generative Adversarial Networks. The use case definition included the selection of algorithms as benchmark: an AI-based pose estimation algorithm and a dense optical flow algorithm were selected. Eventually it is demonstrated that datasets produced with SurRender and selected laboratory facilities are adequate to train machine learning algorithms.
Authors: Zhenwei Wang, Tengfei Wang, Zexin He, Gerhard Hancke, Ziwei Liu, Rynson W. H. Lau
Abstract: In 3D modeling, designers often use an existing 3D model as a reference to create new ones. This practice has inspired the development of Phidias, a novel generative model that uses diffusion for reference-augmented 3D generation. Given an image, our method leverages a retrieved or user-provided 3D reference model to guide the generation process, thereby enhancing the generation quality, generalization ability, and controllability. Our model integrates three key components: 1) meta-ControlNet that dynamically modulates the conditioning strength, 2) dynamic reference routing that mitigates misalignment between the input image and 3D reference, and 3) self-reference augmentations that enable self-supervised training with a progressive curriculum. Collectively, these designs result in a clear improvement over existing methods. Phidias establishes a unified framework for 3D generation using text, image, and 3D conditions with versatile applications.
Authors: Yi-Chia Chen, Wei-Hua Li, Cheng Sun, Yu-Chiang Frank Wang, Chu-Song Chen
Abstract: We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based manner without additional computational overhead in learning. Experimental results on pubic benchmarks demonstrate the effectiveness of our approach.
Authors: Vidhisha Balachandran, Jingya Chen, Neel Joshi, Besmira Nushi, Hamid Palangi, Eduardo Salinas, Vibhav Vineet, James Woffinden-Luey, Safoora Yousefi
Abstract: Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in practice due to several reasons, including benchmark saturation, lack of transparency in methods used for measurement, development challenges in extracting measurements for generative tasks, and, more generally, the extensive number of capabilities required for a well-rounded comparison across models. We make three contributions to alleviate the above challenges. First, we present Eureka, an open-source framework for standardizing evaluations of large foundation models beyond single-score reporting and rankings. Second, we introduce Eureka-Bench as an extensible collection of benchmarks testing capabilities that (i) are still challenging for state-of-the-art models and (ii) represent fundamental but overlooked language and multimodal capabilities. The inherent space for improvement in non-saturated benchmarks enables us to discover meaningful differences between models at a capability level. Third, using Eureka, we conduct an analysis of 12 state-of-the-art models, providing in-depth insights into failure understanding and model comparison, which can be leveraged to plan targeted improvements. In contrast to recent trends in reports and leaderboards showing absolute rankings and claims for one model or another to be the best, our analysis shows that there is no such best model. Different models have different strengths, but there are models that appear more often than others as best performers for some capabilities. Despite the recent improvements, current models still struggle with several fundamental capabilities including detailed image understanding, benefiting from multimodal input when available rather than fully relying on language, factuality and grounding for information retrieval, and over refusals.
Authors: Justin Lyu Kim, Kyoungwan Woo
Abstract: In the age of powerful diffusion models such as DALL-E and Stable Diffusion, many in the digital art community have suffered style mimicry attacks due to fine-tuning these models on their works. The ability to mimic an artist's style via text-to-image diffusion models raises serious ethical issues, especially without explicit consent. Glaze, a tool that applies various ranges of perturbations to digital art, has shown significant success in preventing style mimicry attacks, at the cost of artifacts ranging from imperceptible noise to severe quality degradation. The release of Glaze has sparked further discussions regarding the effectiveness of similar protection methods. In this paper, we propose GLEAN- applying I2I generative networks to strip perturbations from Glazed images, evaluating the performance of style mimicry attacks before and after GLEAN on the results of Glaze. GLEAN aims to support and enhance Glaze by highlighting its limitations and encouraging further development.
Authors: Pranav Jeevan, Neeraj Nixon, Amit Sethi
Abstract: Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks ($4\times$). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR.
Authors: Xingyi Yang, Xinchao Wang
Abstract: Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model. Integrating KANs into transformers, however, is no easy feat, especially when scaled up. Specifically, we identify three key challenges: (C1) Base function. The standard B-spline function used in KANs is not optimized for parallel computing on modern hardware, resulting in slower inference speeds. (C2) Parameter and Computation Inefficiency. KAN requires a unique function for each input-output pair, making the computation extremely large. (C3) Weight initialization. The initialization of weights in KANs is particularly challenging due to their learnable activation functions, which are critical for achieving convergence in deep neural networks. To overcome the aforementioned challenges, we propose three key solutions: (S1) Rational basis. We replace B-spline functions with rational functions to improve compatibility with modern GPUs. By implementing this in CUDA, we achieve faster computations. (S2) Group KAN. We share the activation weights through a group of neurons, to reduce the computational load without sacrificing performance. (S3) Variance-preserving initialization. We carefully initialize the activation weights to make sure that the activation variance is maintained across layers. With these designs, KAT scales effectively and readily outperforms traditional MLP-based transformers.
Authors: Minyoung Hwang, Joey Hejna, Dorsa Sadigh, Yonatan Bisk
Abstract: While success in many robotics tasks can be determined by only observing the final state and how it differs from the initial state - e.g., if an apple is picked up - many tasks require observing the full motion of the robot to correctly determine success. For example, brushing hair requires repeated strokes that correspond to the contours and type of hair. Prior works often use off-the-shelf vision-language models (VLMs) as success detectors; however, when success depends on the full trajectory, VLMs struggle to make correct judgments for two reasons. First, modern VLMs are trained only on single frames, and cannot capture changes over a full trajectory. Second, even if we provide state-of-the-art VLMs with an aggregate input of multiple frames, they still fail to detect success due to a lack of robot data. Our key idea is to fine-tune VLMs using abstract representations that are able to capture trajectory-level information such as the path the robot takes by overlaying keypoint trajectories on the final image. We propose motion instruction fine-tuning (MotIF), a method that fine-tunes VLMs using the aforementioned abstract representations to semantically ground the robot's behavior in the environment. To benchmark and fine-tune VLMs for robotic motion understanding, we introduce the MotIF-1K dataset containing 653 human and 369 robot demonstrations across 13 task categories. MotIF assesses the success of robot motion given the image observation of the trajectory, task instruction, and motion description. Our model significantly outperforms state-of-the-art VLMs by at least twice in precision and 56.1% in recall, generalizing across unseen motions, tasks, and environments. Finally, we demonstrate practical applications of MotIF in refining and terminating robot planning, and ranking trajectories on how they align with task and motion descriptions. Project page: https://motif-1k.github.io
Authors: Hao Fang, Zhe Liu, Yi Feng, Zhen Qiu, Pierre Bagnaninchi, Yunjie Yang
Abstract: Multi-frequency Electrical Impedance Tomography (mfEIT) is a promising biomedical imaging technique that estimates tissue conductivities across different frequencies. Current state-of-the-art (SOTA) algorithms, which rely on supervised learning and Multiple Measurement Vectors (MMV), require extensive training data, making them time-consuming, costly, and less practical for widespread applications. Moreover, the dependency on training data in supervised MMV methods can introduce erroneous conductivity contrasts across frequencies, posing significant concerns in biomedical applications. To address these challenges, we propose a novel unsupervised learning approach based on Multi-Branch Attention Image Prior (MAIP) for mfEIT reconstruction. Our method employs a carefully designed Multi-Branch Attention Network (MBA-Net) to represent multiple frequency-dependent conductivity images and simultaneously reconstructs mfEIT images by iteratively updating its parameters. By leveraging the implicit regularization capability of the MBA-Net, our algorithm can capture significant inter- and intra-frequency correlations, enabling robust mfEIT reconstruction without the need for training data. Through simulation and real-world experiments, our approach demonstrates performance comparable to, or better than, SOTA algorithms while exhibiting superior generalization capability. These results suggest that the MAIP-based method can be used to improve the reliability and applicability of mfEIT in various settings.
Authors: S. Rohollah Hosseyni, Ali Ahmad Rahmani, S. Jamal Seyedmohammadi, Sanaz Seyedin, Arash Mohammadi
Abstract: Autoregressive models excel in modeling sequential dependencies by enforcing causal constraints, yet they struggle to capture complex bidirectional patterns due to their unidirectional nature. In contrast, mask-based models leverage bidirectional context, enabling richer dependency modeling. However, they often assume token independence during prediction, which undermines the modeling of sequential dependencies. Additionally, the corruption of sequences through masking or absorption can introduce unnatural distortions, complicating the learning process. To address these issues, we propose Bidirectional Autoregressive Diffusion (BAD), a novel approach that unifies the strengths of autoregressive and mask-based generative models. BAD utilizes a permutation-based corruption technique that preserves the natural sequence structure while enforcing causal dependencies through randomized ordering, enabling the effective capture of both sequential and bidirectional relationships. Comprehensive experiments show that BAD outperforms autoregressive and mask-based models in text-to-motion generation, suggesting a novel pre-training strategy for sequence modeling. The codebase for BAD is available on https://github.com/RohollahHS/BAD.
Authors: Tianao Li, Manxiu Cui, Cheng Ma, Emma Alexander
Abstract: Photoacoustic computed tomography (PACT) is a non-invasive imaging modality with wide medical applications. Conventional PACT image reconstruction algorithms suffer from wavefront distortion caused by the heterogeneous speed of sound (SOS) in tissue, which leads to image degradation. Accounting for these effects improves image quality, but measuring the SOS distribution is experimentally expensive. An alternative approach is to perform joint reconstruction of the initial pressure image and SOS using only the PA signals. Existing joint reconstruction methods come with limitations: high computational cost, inability to directly recover SOS, and reliance on inaccurate simplifying assumptions. Implicit neural representation, or neural fields, is an emerging technique in computer vision to learn an efficient and continuous representation of physical fields with a coordinate-based neural network. In this work, we introduce NF-APACT, an efficient self-supervised framework utilizing neural fields to estimate the SOS in service of an accurate and robust multi-channel deconvolution. Our method removes SOS aberrations an order of magnitude faster and more accurately than existing methods. We demonstrate the success of our method on a novel numerical phantom as well as an experimentally collected phantom and in vivo data. Our code and numerical phantom are available at https://github.com/Lukeli0425/NF-APACT.
Authors: Shun Zou, Mingya Zhang, Bingjian Fan, Zhengyi Zhou, Xiuguo Zou
Abstract: Skin lesion segmentation is a crucial method for identifying early skin cancer. In recent years, both convolutional neural network (CNN) and Transformer-based methods have been widely applied. Moreover, combining CNN and Transformer effectively integrates global and local relationships, but remains limited by the quadratic complexity of Transformer. To address this, we propose a hybrid architecture based on Mamba and CNN, called SkinMamba. It maintains linear complexity while offering powerful long-range dependency modeling and local feature extraction capabilities. Specifically, we introduce the Scale Residual State Space Block (SRSSB), which captures global contextual relationships and cross-scale information exchange at a macro level, enabling expert communication in a global state. This effectively addresses challenges in skin lesion segmentation related to varying lesion sizes and inconspicuous target areas. Additionally, to mitigate boundary blurring and information loss during model downsampling, we introduce the Frequency Boundary Guided Module (FBGM), providing sufficient boundary priors to guide precise boundary segmentation, while also using the retained information to assist the decoder in the decoding process. Finally, we conducted comparative and ablation experiments on two public lesion segmentation datasets (ISIC2017 and ISIC2018), and the results demonstrate the strong competitiveness of SkinMamba in skin lesion segmentation tasks. The code is available at https://github.com/zs1314/SkinMamba.
Authors: Denglin Kang, Youqian Zhang, Wai Cheong Tam, Eugene Y. Fu
Abstract: Cameras are integral components of many critical intelligent systems. However, a growing threat, known as Electromagnetic Signal Injection Attacks (ESIA), poses a significant risk to these systems, where ESIA enables attackers to remotely manipulate images captured by cameras, potentially leading to malicious actions and catastrophic consequences. Despite the severity of this threat, the underlying reasons for ESIA's effectiveness remain poorly understood, and effective countermeasures are lacking. This paper aims to address these gaps by investigating ESIA from two distinct aspects: pixel loss and color strips. By analyzing these aspects separately on image classification tasks, we gain a deeper understanding of how ESIA can compromise intelligent systems. Additionally, we explore a lightweight solution to mitigate the effects of ESIA while acknowledging its limitations. Our findings provide valuable insights for future research and development in the field of camera security and intelligent systems.
Authors: Manthan Patel, Jonas Frey, Deegan Atha, Patrick Spieler, Marco Hutter, Shehryar Khattak
Abstract: Autonomous robot navigation in off-road environments requires a comprehensive understanding of the terrain geometry and traversability. The degraded perceptual conditions and sparse geometric information at longer ranges make the problem challenging especially when driving at high speeds. Furthermore, the sensing-to-mapping latency and the look-ahead map range can limit the maximum speed of the vehicle. Building on top of the recent work RoadRunner, in this work, we address the challenge of long-range (100 m) traversability estimation. Our RoadRunner (M&M) is an end-to-end learning-based framework that directly predicts the traversability and elevation maps at multiple ranges (50 m, 100 m) and resolutions (0.2 m, 0.8 m) taking as input multiple images and a LiDAR voxel map. Our method is trained in a self-supervised manner by leveraging the dense supervision signal generated by fusing predictions from an existing traversability estimation stack (X-Racer) in hindsight and satellite Digital Elevation Maps. RoadRunner M&M achieves a significant improvement of up to 50% for elevation mapping and 30% for traversability estimation over RoadRunner, and is able to predict in 30% more regions compared to X-Racer while achieving real-time performance. Experiments on various out-of-distribution datasets also demonstrate that our data-driven approach starts to generalize to novel unstructured environments. We integrate our proposed framework in closed-loop with the path planner to demonstrate autonomous high-speed off-road robotic navigation in challenging real-world environments. Project Page: https://leggedrobotics.github.io/roadrunner_mm/
Authors: Dewinda Julianensi Rumala, Reza Fuad Rachmadi, Anggraini Dwi Sensusiati, I Ketut Eddy Purnama
Abstract: Achieving high accuracy with computational efficiency in brain disease classification from Magnetic Resonance Imaging (MRI) scans is challenging, particularly when both coarse and fine-grained distinctions are crucial. Current deep learning methods often struggle to balance accuracy with computational demands. We propose Lite-FBCN, a novel Lightweight Fast Bilinear Convolutional Network designed to address this issue. Unlike traditional dual-network bilinear models, Lite-FBCN utilizes a single-network architecture, significantly reducing computational load. Lite-FBCN leverages lightweight, pre-trained CNNs fine-tuned to extract relevant features and incorporates a channel reducer layer before bilinear pooling, minimizing feature map dimensionality and resulting in a compact bilinear vector. Extensive evaluations on cross-validation and hold-out data demonstrate that Lite-FBCN not only surpasses baseline CNNs but also outperforms existing bilinear models. Lite-FBCN with MobileNetV1 attains 98.10% accuracy in cross-validation and 69.37% on hold-out data (a 3% improvement over the baseline). UMAP visualizations further confirm its effectiveness in distinguishing closely related brain disease classes. Moreover, its optimal trade-off between performance and computational efficiency positions Lite-FBCN as a promising solution for enhancing diagnostic capabilities in resource-constrained and or real-time clinical environments.
Authors: Yongyang Pan, Xiaohong Liu, Siqi Luo, Yi Xin, Xiao Guo, Xiaoming Liu, Xiongkuo Min, Guangtao Zhai
Abstract: Rapid advancements in multimodal large language models have enabled the creation of hyper-realistic images from textual descriptions. However, these advancements also raise significant concerns about unauthorized use, which hinders their broader distribution. Traditional watermarking methods often require complex integration or degrade image quality. To address these challenges, we introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB). TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models. This approach ensures that each user can directly apply a pre-configured set of parameters to the model without altering the original model parameters or compromising image quality. Additionally, noise and augmentation operations are embedded at the pixel level to further secure and stabilize watermarked images. Extensive experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.
Authors: Xuanzhao Dong, Vamsi Krishna Vasa, Wenhui Zhu, Peijie Qiu, Xiwen Chen, Yi Su, Yujian Xiong, Zhangsihao Yang, Yanxi Chen, Yalin Wang
Abstract: Retinal fundus photography is significant in diagnosing and monitoring retinal diseases. However, systemic imperfections and operator/patient-related factors can hinder the acquisition of high-quality retinal images. Previous efforts in retinal image enhancement primarily relied on GANs, which are limited by the trade-off between training stability and output diversity. In contrast, the Schr\"{o}dinger Bridge (SB), offers a more stable solution by utilizing Optimal Transport (OT) theory to model a stochastic differential equation (SDE) between two arbitrary distributions. This allows SB to effectively transform low-quality retinal images into their high-quality counterparts. In this work, we leverage the SB framework to propose an image-to-image translation pipeline for retinal image enhancement. Additionally, previous methods often fail to capture fine structural details, such as blood vessels. To address this, we enhance our pipeline by introducing Dynamic Snake Convolution, whose tortuous receptive field can better preserve tubular structures. We name the resulting retinal fundus image enhancement framework the Context-aware Unpaired Neural Schr\"{o}dinger Bridge (CUNSB-RFIE). To the best of our knowledge, this is the first endeavor to use the SB approach for retinal image enhancement. Experimental results on a large-scale dataset demonstrate the advantage of the proposed method compared to several state-of-the-art supervised and unsupervised methods in terms of image quality and performance on downstream tasks.The code is available at \url{https://github.com/Retinal-Research/CUNSB-RFIE}.
Authors: Ryugo Morita, Hitoshi Nishimura, Ko Watanabe, Andreas Dengel, Jinjia Zhou
Abstract: In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in reconstructed images, learning inefficiencies due to mode collapse, and data loss during transmission persist. To address these issues, we propose a novel compression model that incorporates a denoising step with diffusion models, significantly enhancing image reconstruction fidelity by sub-information(e.g., edge and depth) from leveraging latent space. Empirical experiments demonstrate that our model achieves superior or comparable results in terms of image quality and compression efficiency when measured against the existing models. Notably, our model excels in scenarios of partial image loss or excessive noise by introducing an edge estimation network to preserve the integrity of reconstructed images, offering a robust solution to the current limitations of image compression.
Authors: Jieyun Bai, Zihao Zhou, Zhanhong Ou, Gregor Koehler, Raphael Stock, Klaus Maier-Hein, Marawan Elbatel, Robert Mart\'i, Xiaomeng Li, Yaoyang Qiu, Panjie Gou, Gongping Chen, Lei Zhao, Jianxun Zhang, Yu Dai, Fangyijie Wang, Gu\'enol\'e Silvestre, Kathleen Curran, Hongkun Sun, Jing Xu, Pengzhou Cai, Lu Jiang, Libin Lan, Dong Ni, Mei Zhong, Gaowen Chen, V\'ictor M. Campello, Yaosheng Lu, Karim Lekadir
Abstract: Segmentation of the fetal and maternal structures, particularly intrapartum ultrasound imaging as advocated by the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) for monitoring labor progression, is a crucial first step for quantitative diagnosis and clinical decision-making. This requires specialized analysis by obstetrics professionals, in a task that i) is highly time- and cost-consuming and ii) often yields inconsistent results. The utility of automatic segmentation algorithms for biometry has been proven, though existing results remain suboptimal. To push forward advancements in this area, the Grand Challenge on Pubic Symphysis-Fetal Head Segmentation (PSFHS) was held alongside the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023). This challenge aimed to enhance the development of automatic segmentation algorithms at an international scale, providing the largest dataset to date with 5,101 intrapartum ultrasound images collected from two ultrasound machines across three hospitals from two institutions. The scientific community's enthusiastic participation led to the selection of the top 8 out of 179 entries from 193 registrants in the initial phase to proceed to the competition's second stage. These algorithms have elevated the state-of-the-art in automatic PSFHS from intrapartum ultrasound images. A thorough analysis of the results pinpointed ongoing challenges in the field and outlined recommendations for future work. The top solutions and the complete dataset remain publicly available, fostering further advancements in automatic segmentation and biometry for intrapartum ultrasound imaging.
Authors: Gautier Dagan, Olga Loginova, Anil Batra
Abstract: Vision Language Models (VLMs) are typically evaluated with Visual Question Answering (VQA) tasks which assess a model's understanding of scenes. Good VQA performance is taken as evidence that the model will perform well on a broader range of tasks that require both visual and language inputs. However, scene-aware VQA does not fully capture input biases or assess hallucinations caused by a misalignment between modalities. To address this, we propose a Cross-modal Alignment Similarity Test (CAST) to probe VLMs for self-consistency across modalities. This test involves asking the models to identify similarities between two scenes through text-only, image-only, or both and then assess the truthfulness of the similarities they generate. Since there is no ground-truth to compare against, this evaluation does not focus on objective accuracy but rather on whether VLMs are internally consistent in their outputs. We argue that while not all self-consistent models are capable or accurate, all capable VLMs must be self-consistent.
Authors: Emile Saillard, Aur\'elie Levillain, David Mitton, Jean-Baptiste Pialat, Cyrille Confavreux, H\'el\`ene Follet, Thomas Grenier
Abstract: Purpose: Bone metastasis have a major impact on the quality of life of patients and they are diverse in terms of size and location, making their segmentation complex. Manual segmentation is time-consuming, and expert segmentations are subject to operator variability, which makes obtaining accurate and reproducible segmentations of bone metastasis on CT-scans a challenging yet important task to achieve. Materials and Methods: Deep learning methods tackle segmentation tasks efficiently but require large datasets along with expert manual segmentations to generalize on new images. We propose an automated data synthesis pipeline using 3D Denoising Diffusion Probabilistic Models (DDPM) to enchance the segmentation of femoral metastasis from CT-scan volumes of patients. We used 29 existing lesions along with 26 healthy femurs to create new realistic synthetic metastatic images, and trained a DDPM to improve the diversity and realism of the simulated volumes. We also investigated the operator variability on manual segmentation. Results: We created 5675 new volumes, then trained 3D U-Net segmentation models on real and synthetic data to compare segmentation performance, and we evaluated the performance of the models depending on the amount of synthetic data used in training. Conclusion: Our results showed that segmentation models trained with synthetic data outperformed those trained on real volumes only, and that those models perform especially well when considering operator variability.
Authors: Tianyu Zhang, Haotian Zhang, Yuqi Li, Li Li, Dong Liu
Abstract: Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC and observe that out-of-training-domain images disrupt pre-trained channel-wise decomposition. Consequently, we introduce a method for channel-wise re-allocation using convolution-based adapters and low-rank adapters, which are lightweight and compatible to mainstream LIC schemes. Extensive experiments across multiple domains and multiple representative LIC schemes demonstrate that our method significantly enhances pre-trained models, achieving comparable performance to H.266/VVC intra coding with merely 25 target-domain samples. Additionally, our method matches the performance of full-model finetune while transmitting fewer than $2\%$ of the parameters.
Authors: Sharon Peled, Yosef E. Maruvka, Moti Freiman
Abstract: Whole Slide Images (WSIs) are critical for various clinical applications, including histopathological analysis. However, current deep learning approaches in this field predominantly focus on individual tumor types, limiting model generalization and scalability. This relatively narrow focus ultimately stems from the inherent heterogeneity in histopathology and the diverse morphological and molecular characteristics of different tumors. To this end, we propose a novel approach for multi-cohort WSI analysis, designed to leverage the diversity of different tumor types. We introduce a Cohort-Aware Attention module, enabling the capture of both shared and tumor-specific pathological patterns, enhancing cross-tumor generalization. Furthermore, we construct an adversarial cohort regularization mechanism to minimize cohort-specific biases through mutual information minimization. Additionally, we develop a hierarchical sample balancing strategy to mitigate cohort imbalances and promote unbiased learning. Together, these form a cohesive framework for unbiased multi-cohort WSI analysis. Extensive experiments on a uniquely constructed multi-cancer dataset demonstrate significant improvements in generalization, providing a scalable solution for WSI classification across diverse cancer types. Our code for the experiments is publicly available at .
Authors: Debarpan Bhattacharya, Amir H. Poorjam, Deepak Mittal, Sriram Ganapathy
Abstract: The recent advancements in artificial intelligence (AI), with the release of several large models having only query access, make a strong case for explainability of deep models in a post-hoc gradient free manner. In this paper, we propose a framework, named distillation aided explainability (DAX), that attempts to generate a saliency-based explanation in a model agnostic gradient free application. The DAX approach poses the problem of explanation in a learnable setting with a mask generation network and a distillation network. The mask generation network learns to generate the multiplier mask that finds the salient regions of the input, while the student distillation network aims to approximate the local behavior of the black-box model. We propose a joint optimization of the two networks in the DAX framework using the locally perturbed input samples, with the targets derived from input-output access to the black-box model. We extensively evaluate DAX across different modalities (image and audio), in a classification setting, using a diverse set of evaluations (intersection over union with ground truth, deletion based and subjective human evaluation based measures) and benchmark it with respect to $9$ different methods. In these evaluations, the DAX significantly outperforms the existing approaches on all modalities and evaluation metrics.
Authors: Pengfei Guo, Can Zhao, Dong Yang, Ziyue Xu, Vishwesh Nath, Yucheng Tang, Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, Daguang Xu
Abstract: Medical imaging analysis faces challenges such as data scarcity, high annotation costs, and privacy concerns. This paper introduces the Medical AI for Synthetic Imaging (MAISI), an innovative approach using the diffusion model to generate synthetic 3D computed tomography (CT) images to address those challenges. MAISI leverages the foundation volume compression network and the latent diffusion model to produce high-resolution CT images (up to a landmark volume dimension of 512 x 512 x 768 ) with flexible volume dimensions and voxel spacing. By incorporating ControlNet, MAISI can process organ segmentation, including 127 anatomical structures, as additional conditions and enables the generation of accurately annotated synthetic images that can be used for various downstream tasks. Our experiment results show that MAISI's capabilities in generating realistic, anatomically accurate images for diverse regions and conditions reveal its promising potential to mitigate challenges using synthetic data.
Authors: Yihong Xu, Victor Letzelter, Micka\"el Chen, \'Eloi Zablocki, Matthieu Cord
Abstract: In autonomous driving, motion prediction aims at forecasting the future trajectories of nearby agents, helping the ego vehicle to anticipate behaviors and drive safely. A key challenge is generating a diverse set of future predictions, commonly addressed using data-driven models with Multiple Choice Learning (MCL) architectures and Winner-Takes-All (WTA) training objectives. However, these methods face initialization sensitivity and training instabilities. Additionally, to compensate for limited performance, some approaches rely on training with a large set of hypotheses, requiring a post-selection step during inference to significantly reduce the number of predictions. To tackle these issues, we take inspiration from annealed MCL, a recently introduced technique that improves the convergence properties of MCL methods through an annealed Winner-Takes-All loss (aWTA). In this paper, we demonstrate how the aWTA loss can be integrated with state-of-the-art motion forecasting models to enhance their performance using only a minimal set of hypotheses, eliminating the need for the cumbersome post-selection step. Our approach can be easily incorporated into any trajectory prediction model normally trained using WTA and yields significant improvements. To facilitate the application of our approach to future motion forecasting models, the code will be made publicly available upon acceptance: https://github.com/valeoai/MF_aWTA.
Authors: Xin Li, Anand Sarwate
Abstract: Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs, VQ-GANs, etc.), which has demonstrated state-of-the-art performance in many modern generative modeling applications. Quantizing the latent space has been justified by the assumption that the data themselves are inherently discrete in the latent space (like pixel values). In this paper, we propose an alternative representation of the latent space by relaxing the structural assumption than the VQ formulation. Specifically, we assume that the latent space can be approximated by a union of subspaces model corresponding to a dictionary-based representation under a sparsity constraint. The dictionary is learned/updated during the training process. We apply this approach to look at two models: Dictionary Learning Variational Autoencoders (DL-VAEs) and DL-VAEs with Generative Adversarial Networks (DL-GANs). We show empirically that our more latent space is more expressive and has leads to better representations than the VQ approach in terms of reconstruction quality at the expense of a small computational overhead for the latent space computation. Our results thus suggest that the true benefit of the VQ approach might not be from discretization of the latent space, but rather the lossy compression of the latent space. We confirm this hypothesis by showing that our sparse representations also address the codebook collapse issue as found common in VQ-family models.
Authors: Rong Zhou, Zhengqing Yuan, Zhiling Yan, Weixiang Sun, Kai Zhang, Yiwei Li, Yanfang Ye, Xiang Li, Lifang He, Lichao Sun
Abstract: Biomedical image segmentation is crucial for accurately diagnosing and analyzing various diseases. However, Convolutional Neural Networks (CNNs) and Transformers, the most commonly used architectures for this task, struggle to effectively capture long-range dependencies due to the inherent locality of CNNs and the computational complexity of Transformers. To address this limitation, we introduce TTT-Unet, a novel framework that integrates Test-Time Training (TTT) layers into the traditional U-Net architecture for biomedical image segmentation. TTT-Unet dynamically adjusts model parameters during the testing time, enhancing the model's ability to capture both local and long-range features. We evaluate TTT-Unet on multiple medical imaging datasets, including 3D abdominal organ segmentation in CT and MR images, instrument segmentation in endoscopy images, and cell segmentation in microscopy images. The results demonstrate that TTT-Unet consistently outperforms state-of-the-art CNN-based and Transformer-based segmentation models across all tasks. The code is available at https://github.com/rongzhou7/TTT-Unet.
Authors: Mathilde Monvoisin, Yuxin Zhang, Diana Mateus
Abstract: Ultrafast Plane-Wave (PW) imaging often produces artifacts and shadows that vary with insonification angles. We propose a novel approach using Implicit Neural Representations (INRs) to compactly encode multi-planar sequences while preserving crucial orientation-dependent information. To our knowledge, this is the first application of INRs for PW angular interpolation. Our method employs a Multi-Layer Perceptron (MLP)-based model with a concise physics-enhanced rendering technique. Quantitative evaluations using SSIM, PSNR, and standard ultrasound metrics, along with qualitative visual assessments, confirm the effectiveness of our approach. Additionally, our method demonstrates significant storage efficiency, with model weights requiring 530 KB compared to 8 MB for directly storing the 75 PW images, achieving a notable compression ratio of approximately 15:1.
Authors: Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuoling Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
Abstract: We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training. In terms of model design, we perform a comprehensive comparison between decoder-only multimodal LLMs (e.g., LLaVA) and cross-attention-based models (e.g., Flamingo). Based on the strengths and weaknesses of both approaches, we propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. Furthermore, we introduce a 1-D tile-tagging design for tile-based dynamic high-resolution images, which significantly boosts performance on multimodal reasoning and OCR-related tasks. Regarding training data, we meticulously curate and provide detailed information on our multimodal pretraining and supervised fine-tuning datasets. Our findings indicate that dataset quality and task diversity are more important than scale, even during the pretraining phase, across all architectures. Notably, we develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks while maintaining and even improving text-only performance compared to their LLM backbones. To achieve this, we craft and integrate a high-quality text-only dataset into multimodal training, alongside a substantial amount of multimodal math and reasoning data, leading to enhanced math and coding capabilities across modalities. To advance research in the field, we are releasing the model weights and will open-source the code for the community: https://nvlm-project.github.io/.
Authors: Pk Douglas, Farzad Vasheghani Farahani
Abstract: The increasing use of deep neural networks (DNNs) has motivated a parallel endeavor: the design of adversaries that profit from successful misclassifications. However, not all adversarial examples are crafted for malicious purposes. For example, real world systems often contain physical, temporal, and sampling variability across instrumentation. Adversarial examples in the wild may inadvertently prove deleterious for accurate predictive modeling. Conversely, naturally occurring covariance of image features may serve didactic purposes. Here, we studied the stability of deep learning representations for neuroimaging classification across didactic and adversarial conditions characteristic of MRI acquisition variability. We show that representational similarity and performance vary according to the frequency of adversarial examples in the input space.
Authors: Yong He, Hongshan Yu, Xiaoyan Liu, Zhengeng Yang, Wei Sun, Saeed Anwar, Ajmal Mian
Abstract: 3D segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving and robotics. It has received significant attention from the computer vision, graphics and machine learning communities. Conventional methods for 3D segmentation, based on hand-crafted features and machine learning classifiers, lack generalization ability. Driven by their success in 2D computer vision, deep learning techniques have recently become the tool of choice for 3D segmentation tasks. This has led to an influx of many methods in the literature that have been evaluated on different benchmark datasets. Whereas survey papers on RGB-D and point cloud segmentation exist, there is a lack of a recent in-depth survey that covers all 3D data modalities and application domains. This paper fills the gap and comprehensively surveys the recent progress in deep learning-based 3D segmentation techniques. We cover over 220 works from the last six years, analyze their strengths and limitations, and discuss their competitive results on benchmark datasets. The survey provides a summary of the most commonly used pipelines and finally highlights promising research directions for the future.
Authors: Rezaul Karim, He Zhao, Richard P. Wildes, Mennatullah Siam
Abstract: In this paper, we present an end-to-end trainable unified multiscale encoder-decoder transformer that is focused on dense prediction tasks in video. The presented Multiscale Encoder-Decoder Video Transformer (MED-VT) uses multiscale representation throughout and employs an optional input beyond video (e.g., audio), when available, for multimodal processing (MED-VT++). Multiscale representation at both encoder and decoder yields three key benefits: (i) implicit extraction of spatiotemporal features at different levels of abstraction for capturing dynamics without reliance on input optical flow, (ii) temporal consistency at encoding and (iii) coarse-to-fine detection for high-level (e.g., object) semantics to guide precise localization at decoding. Moreover, we present a transductive learning scheme through many-to-many label propagation to provide temporally consistent video predictions. We showcase MED-VT/MED-VT++ on three unimodal video segmentation tasks (Automatic Video Object Segmentation (AVOS), actor-action segmentation and Video Semantic Segmentation (VSS)) as well as a multimodal segmentation task (Audio-Visual Segmentation (AVS)). Results show that the proposed architecture outperforms alternative state-of-the-art approaches on multiple benchmarks using only video (and optional audio) as input, without reliance on optical flow. Finally, to document details of the model's internal learned representations, we present a detailed interpretability study, encompassing both quantitative and qualitative analyses.
Authors: Devis Tuia, Konrad Schindler, Beg\"um Demir, Xiao Xiang Zhu, Mrinalini Kochupillai, Sa\v{s}o D\v{z}eroski, Jan N. van Rijn, Holger H. Hoos, Fabio Del Frate, Mihai Datcu, Volker Markl, Bertrand Le Saux, Rochelle Schneider, Gustau Camps-Valls
Abstract: Earth observation (EO) is a prime instrument for monitoring land and ocean processes, studying the dynamics at work, and taking the pulse of our planet. This article gives a bird's eye view of the essential scientific tools and approaches informing and supporting the transition from raw EO data to usable EO-based information. The promises, as well as the current challenges of these developments, are highlighted under dedicated sections. Specifically, we cover the impact of (i) Computer vision; (ii) Machine learning; (iii) Advanced processing and computing; (iv) Knowledge-based AI; (v) Explainable AI and causal inference; (vi) Physics-aware models; (vii) User-centric approaches; and (viii) the much-needed discussion of ethical and societal issues related to the massive use of ML technologies in EO.
Authors: Md Yousuf Harun, Christopher Kanan
Abstract: Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the DNN's predictions become more erroneous over time, resulting in revenue loss or unhappy users. To mitigate model decay, DNNs are retrained from scratch using old and new data. This is computationally expensive, so retraining happens only once performance significantly decreases. Here, we study how continual learning (CL) could potentially overcome model decay in large pre-trained DNNs and greatly reduce computational costs for keeping DNNs up-to-date. We identify the "stability gap" as a major obstacle in our setting. The stability gap refers to a phenomenon where learning new data causes large drops in performance for past tasks before CL mitigation methods eventually compensate for this drop. We test two hypotheses to investigate the factors influencing the stability gap and identify a method that vastly reduces this gap. In large-scale experiments for both easy and hard CL distributions (e.g., class incremental learning), we demonstrate that our method reduces the stability gap and greatly increases computational efficiency. Our work aligns CL with the goals of the production setting, where CL is needed for many applications.
Authors: Yupan Huang, Zaiqiao Meng, Fangyu Liu, Yixuan Su, Nigel Collier, Yutong Lu
Abstract: Large language models exhibit enhanced zero-shot performance on various tasks when fine-tuned with instruction-following data. Multimodal instruction-following models extend these capabilities by integrating both text and images. However, existing models such as MiniGPT-4 and LLaVA face challenges in maintaining dialogue coherence in scenarios involving multiple images. A primary reason is the lack of a specialized dataset for this critical application. To bridge these gaps, we introduce SparklesDialogue, the first machine-generated dialogue dataset tailored for word-level interleaved multi-image and text interactions. Furthermore, we construct SparklesEval, a GPT-assisted benchmark for quantitatively assessing a model's conversational competence across multiple images and dialogue turns. We then present SparklesChat, a multimodal instruction-following model for open-ended dialogues across multiple images. Our experiments validate the effectiveness of training SparklesChat with SparklesDialogue based on MiniGPT-4 and LLaVA-v1.5, which enhances comprehension across multiple images and dialogue turns, and does not compromise single-image understanding capabilities. Qualitative evaluations further demonstrate SparklesChat's generality in handling real-world applications. All resources related to this study are publicly available at https://github.com/HYPJUDY/Sparkles.
Authors: Nazmus Sakib Ahmed, Saad Sakib Noor, Ashraful Islam Shanto Sikder, Abhijit Paul
Abstract: This paper focuses on enhancing Bengali Document Layout Analysis (DLA) using the YOLOv8 model and innovative post-processing techniques. We tackle challenges unique to the complex Bengali script by employing data augmentation for model robustness. After meticulous validation set evaluation, we fine-tune our approach on the complete dataset, leading to a two-stage prediction strategy for accurate element segmentation. Our ensemble model, combined with post-processing, outperforms individual base architectures, addressing issues identified in the BaDLAD dataset. By leveraging this approach, we aim to advance Bengali document analysis, contributing to improved OCR and document comprehension and BaDLAD serves as a foundational resource for this endeavor, aiding future research in the field. Furthermore, our experiments provided key insights to incorporate new strategies into the established solution.
Authors: Md Kaykobad Reza, Ashley Prater-Bennette, M. Salman Asif
Abstract: Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in some correlated modalities. However, we observe that the performance of several existing multimodal networks significantly deteriorates if one or multiple modalities are absent at test time. To enable robustness to missing modalities, we propose a simple and parameter-efficient adaptation procedure for pretrained multimodal networks. In particular, we exploit modulation of intermediate features to compensate for the missing modalities. We demonstrate that such adaptation can partially bridge performance drop due to missing modalities and outperform independent, dedicated networks trained for the available modality combinations in some cases. The proposed adaptation requires extremely small number of parameters (e.g., fewer than 1% of the total parameters) and applicable to a wide range of modality combinations and tasks. We conduct a series of experiments to highlight the missing modality robustness of our proposed method on five different multimodal tasks across seven datasets. Our proposed method demonstrates versatility across various tasks and datasets, and outperforms existing methods for robust multimodal learning with missing modalities.
Authors: Zhixuan Liang, Xingyu Zeng, Rui Zhao, Ping Luo
Abstract: Active learning strategies aim to train high-performance models with minimal labeled data by selecting the most informative instances for labeling. However, existing methods for assessing data informativeness often fail to align directly with task model performance metrics, such as mean average precision (mAP) in object detection. This paper introduces Mean-AP Guided Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model output changes as informativeness for deep detection networks, directly optimizing the sampling strategy using mAP. MGRAL employs a reinforcement learning agent based on LSTM architecture to efficiently navigate the combinatorial challenge of batch sample selection and the non-differentiable nature between performance and selected batches. The agent optimizes selection using policy gradient with mAP improvement as the reward signal. To address the computational intensity of mAP estimation with unlabeled samples, we implement fast look-up tables, ensuring real-world feasibility. We evaluate MGRAL on PASCAL VOC and MS COCO benchmarks across various backbone architectures. Our approach demonstrates strong performance, establishing a new paradigm in reinforcement learning-based active learning for object detection.
Authors: Yuhang Li, Youngeun Kim, Donghyun Lee, Souvik Kundu, Priyadarshini Panda
Abstract: In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availability of training data to mitigate quantization errors, a significant challenge when data availability is scarce or restricted due to privacy or copyright concerns. Addressing this, we introduce GenQ, a novel approach employing an advanced Generative AI model to generate photorealistic, high-resolution synthetic data, overcoming the limitations of traditional methods that struggle to accurately mimic complex objects in extensive datasets like ImageNet. Our methodology is underscored by two robust filtering mechanisms designed to ensure the synthetic data closely aligns with the intrinsic characteristics of the actual training data. In case of limited data availability, the actual data is used to guide the synthetic data generation process, enhancing fidelity through the inversion of learnable token embeddings. Through rigorous experimentation, GenQ establishes new benchmarks in data-free and data-scarce quantization, significantly outperforming existing methods in accuracy and efficiency, thereby setting a new standard for quantization in low data regimes. Code is released at \url{https://github.com/Intelligent-Computing-Lab-Yale/GenQ}.
URLs: https://github.com/Intelligent-Computing-Lab-Yale/GenQ
Authors: Yonghao Yu, Shunan Zhu, Huai Qin, Haorui Li
Abstract: Witnessing the evolution of text-to-image diffusion models, significant strides have been made in text-to-3D generation. Currently, two primary paradigms dominate the field of text-to-3D: the feed-forward generation solutions, capable of swiftly producing 3D assets but often yielding coarse results, and the Score Distillation Sampling (SDS) based solutions, known for generating high-fidelity 3D assets albeit at a slower pace. The synergistic integration of these methods holds substantial promise for advancing 3D generation techniques. In this paper, we present BoostDream, a highly efficient plug-and-play 3D refining method designed to transform coarse 3D assets into high-quality. The BoostDream framework comprises three distinct processes: (1) We introduce 3D model distillation that fits differentiable representations from the 3D assets obtained through feed-forward generation. (2) A novel multi-view SDS loss is designed, which utilizes a multi-view aware 2D diffusion model to refine the 3D assets. (3) We propose to use prompt and multi-view consistent normal maps as guidance in refinement.Our extensive experiment is conducted on different differentiable 3D representations, revealing that BoostDream excels in generating high-quality 3D assets rapidly, overcoming the Janus problem compared to conventional SDS-based methods. This breakthrough signifies a substantial advancement in both the efficiency and quality of 3D generation processes.
Authors: Zhuoling Li, Xiaogang Xu, SerNam Lim, Hengshuang Zhao
Abstract: Realizing unified monocular 3D object detection, including both indoor and outdoor scenes, holds great importance in applications like robot navigation. However, involving various scenarios of data to train models poses challenges due to their significantly different characteristics, e.g., diverse geometry properties and heterogeneous domain distributions. To address these challenges, we build a detector based on the bird's-eye-view (BEV) detection paradigm, where the explicit feature projection is beneficial to addressing the geometry learning ambiguity when employing multiple scenarios of data to train detectors. Then, we split the classical BEV detection architecture into two stages and propose an uneven BEV grid design to handle the convergence instability caused by the aforementioned challenges. Moreover, we develop a sparse BEV feature projection strategy to reduce computational cost and a unified domain alignment method to handle heterogeneous domains. Combining these techniques, a unified detector UniMODE is derived, which surpasses the previous state-of-the-art on the challenging Omni3D dataset (a large-scale dataset including both indoor and outdoor scenes) by 4.9% AP_3D, revealing the first successful generalization of a BEV detector to unified 3D object detection.
Authors: Yuelin Zhang, Kim Yan, Chun Ping Lam, Chengyu Fang, Wenxuan Xie, Yufu Qiu, Raymond Shing-Yan Tang, Shing Shin Cheng
Abstract: Flexible endoscope motion tracking and analysis in mechanical simulators have proven useful for endoscopy training. Common motion tracking methods based on electromagnetic tracker are however limited by their high cost and material susceptibility. In this work, the motion-guided dual-camera vision tracker is proposed to provide robust and accurate tracking of the endoscope tip's 3D position. The tracker addresses several unique challenges of tracking flexible endoscope tip inside a dynamic, life-sized mechanical simulator. To address the appearance variation and keep dual-camera tracking consistency, the cross-camera mutual template strategy (CMT) is proposed by introducing dynamic transient mutual templates. To alleviate large occlusion and light-induced distortion, the Mamba-based motion-guided prediction head (MMH) is presented to aggregate historical motion with visual tracking. The proposed tracker achieves superior performance against state-of-the-art vision trackers, achieving 42% and 72% improvements against the second-best method in average error and maximum error. Further motion analysis involving novice and expert endoscopists also shows that the tip 3D motion provided by the proposed tracker enables more reliable motion analysis and more substantial differentiation between different expertise levels, compared with other trackers.
Authors: Melanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia, Galvin Khara, Ben Glocker
Abstract: Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice of augmentation pipeline. Positive pairs should preserve semantic information while destroying domain-specific information. Standard augmentation pipelines emulate domain-specific changes with pre-defined photometric transformations, but what if we could simulate realistic domain changes instead? In this work, we show how to utilise recent progress in counterfactual image generation to this effect. We propose CF-SimCLR, a counterfactual contrastive learning approach which leverages approximate counterfactual inference for positive pair creation. Comprehensive evaluation across five datasets, on chest radiography and mammography, demonstrates that CF-SimCLR substantially improves robustness to acquisition shift with higher downstream performance on both in- and out-of-distribution data, particularly for domains which are under-represented during training.
Authors: Miao Zhang, Rumi Chunara
Abstract: Performance disparities of image recognition across different demographic populations are known to exist in deep learning-based models, but previous work has largely addressed such fairness problems assuming knowledge of sensitive attribute labels. To overcome this reliance, previous strategies have involved separate learning structures to expose and adjust for disparities. In this work, we explore a new paradigm that does not require sensitive attribute labels, and evades the need for extra training by leveraging general-purpose vision-language model (VLM), as a rich knowledge source for common sensitive attributes. We analyze the correspondence between VLM predicted and human defined sensitive attribute distribution. We find that VLMs can recognize samples with clear attribute information encoded in image representations, thus capture under-performed samples conflicting with attribute-related bias. We train downstream target classifiers by re-sampling and augmenting under-performed attribute groups. Extensive experiments on multiple benchmark facial attribute classification datasets show fairness gains of the model over existing unsupervised baselines that tackle with arbitrary bias. The work indicates that vision-language models can extract discriminative sensitive information prompted by language, and be used to promote model fairness.
Authors: Giulia Rizzoli, Matteo Caligiuri, Donald Shenaj, Francesco Barbato, Pietro Zanuttigh
Abstract: In Federated Learning (FL), multiple clients collaboratively train a global model without sharing private data. In semantic segmentation, the Federated source Free Domain Adaptation (FFreeDA) setting is of particular interest, where clients undergo unsupervised training after supervised pretraining at the server side. While few recent works address FL for autonomous vehicles, intrinsic real-world challenges such as the presence of adverse weather conditions and the existence of different autonomous agents are still unexplored. To bridge this gap, we address both problems and introduce a new federated semantic segmentation setting where both car and drone clients co-exist and collaborate. Specifically, we propose a novel approach for this setting which exploits a batch-norm weather-aware strategy to dynamically adapt the model to the different weather conditions, while hyperbolic space prototypes are used to align the heterogeneous client representations. Finally, we introduce FLYAWARE, the first semantic segmentation dataset with adverse weather data for aerial vehicles.
Authors: Changkun Liu, Jianhao Jiao, Huajian Huang, Zhengyang Ma, Dimitrios Kanoulas, Tristan Braud
Abstract: State-of-the-art hierarchical localisation pipelines (HLoc) employ image retrieval (IR) to establish 2D-3D correspondences by selecting the top-$k$ most similar images from a reference database. While increasing $k$ improves localisation robustness, it also linearly increases computational cost and runtime, creating a significant bottleneck. This paper investigates the relationship between global and local descriptors, showing that greater similarity between the global descriptors of query and database images increases the proportion of feature matches. Low similarity queries significantly benefit from increasing $k$, while high similarity queries rapidly experience diminishing returns. Building on these observations, we propose an adaptive strategy that adjusts $k$ based on the similarity between the query's global descriptor and those in the database, effectively mitigating the feature-matching bottleneck. Our approach optimizes processing time without sacrificing accuracy. Experiments on three indoor and outdoor datasets show that AIR-HLoc reduces feature matching time by up to 30\%, while preserving state-of-the-art accuracy. The results demonstrate that AIR-HLoc facilitates a latency-sensitive localisation system.
Authors: Peijie Qiu, Jin Yang, Sayantan Kumar, Soumyendu Sekhar Ghosh, Aristeidis Sotiras
Abstract: In the past decades, deep neural networks, particularly convolutional neural networks, have achieved state-of-the-art performance in a variety of medical image segmentation tasks. Recently, the introduction of the vision transformer (ViT) has significantly altered the landscape of deep segmentation models. There has been a growing focus on ViTs, driven by their excellent performance and scalability. However, we argue that the current design of the vision transformer-based UNet (ViT-UNet) segmentation models may not effectively handle the heterogeneous appearance (e.g., varying shapes and sizes) of objects of interest in medical image segmentation tasks. To tackle this challenge, we present a structured approach to introduce spatially dynamic components to the ViT-UNet. This adaptation enables the model to effectively capture features of target objects with diverse appearances. This is achieved by three main components: \textbf{(i)} deformable patch embedding; \textbf{(ii)} spatially dynamic multi-head attention; \textbf{(iii)} deformable positional encoding. These components were integrated into a novel architecture, termed AgileFormer. AgileFormer is a spatially agile ViT-UNet designed for medical image segmentation. Experiments in three segmentation tasks using publicly available datasets demonstrated the effectiveness of the proposed method. The code is available at \href{https://github.com/sotiraslab/AgileFormer}{https://github.com/sotiraslab/AgileFormer}.
URLs: https://github.com/sotiraslab/AgileFormer, https://github.com/sotiraslab/AgileFormer
Authors: Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Abstract: Text-to-image (T2I) generative models have gained increased popularity in the public domain. While boasting impressive user-guided generative abilities, their black-box nature exposes users to intentionally- and intrinsically-biased outputs. Bias manipulation (and mitigation) techniques typically rely on careful tuning of learning parameters and training data to adjust decision boundaries to influence model bias characteristics, which is often computationally demanding. We propose a dynamic and computationally efficient manipulation of T2I model biases by exploiting their rich language embedding spaces without model retraining. We show that leveraging foundational vector algebra allows for a convenient control over language model embeddings to shift T2I model outputs and control the distribution of generated classes. As a by-product, this control serves as a form of precise prompt engineering to generate images which are generally implausible using regular text prompts. We demonstrate a constructive application of our technique by balancing the frequency of social classes in generated images, effectively balancing class distributions across three social bias dimensions. We also highlight a negative implication of bias manipulation by framing our method as a backdoor attack with severity control using semantically-null input triggers, reporting up to 100% attack success rate. Key-words: Text-to-Image Models, Generative Models, Bias, Prompt Engineering, Backdoor Attacks
Authors: Jingxuan Xu, Wuyang Chen, Yao Zhao, Yunchao Wei
Abstract: Recent success of pre-trained foundation vision-language models makes Open-Vocabulary Segmentation (OVS) possible. Despite the promising performance, this approach introduces heavy computational overheads for two challenges: 1) large model sizes of the backbone; 2) expensive costs during the fine-tuning. These challenges hinder this OVS strategy from being widely applicable and affordable in real-world scenarios. Although traditional methods such as model compression and efficient fine-tuning can address these challenges, they often rely on heuristics. This means that their solutions cannot be easily transferred and necessitate re-training on different models, which comes at a cost. In the context of efficient OVS, we target achieving performance that is comparable to or even better than prior OVS works based on large vision-language foundation models, by utilizing smaller models that incur lower training costs. The core strategy is to make our efficiency principled and thus seamlessly transferable from one OVS framework to others without further customization. Comprehensive experiments on diverse OVS benchmarks demonstrate our superior trade-off between segmentation accuracy and computation costs over previous works. Our code is available on https://github.com/Xujxyang/OpenTrans
Authors: Sina Hajimiri, Ismail Ben Ayed, Jose Dolz
Abstract: Despite the significant progress in deep learning for dense visual recognition problems, such as semantic segmentation, traditional methods are constrained by fixed class sets. Meanwhile, vision-language foundation models, such as CLIP, have showcased remarkable effectiveness in numerous zero-shot image-level tasks, owing to their robust generalizability. Recently, a body of work has investigated utilizing these models in open-vocabulary semantic segmentation (OVSS). However, existing approaches often rely on impractical supervised pre-training or access to additional pre-trained networks. In this work, we propose a strong baseline for training-free OVSS, termed Neighbour-Aware CLIP (NACLIP), representing a straightforward adaptation of CLIP tailored for this scenario. Our method enforces localization of patches in the self-attention of CLIP's vision transformer which, despite being crucial for dense prediction tasks, has been overlooked in the OVSS literature. By incorporating design choices favouring segmentation, our approach significantly improves performance without requiring additional data, auxiliary pre-trained networks, or extensive hyperparameter tuning, making it highly practical for real-world applications. Experiments are performed on 8 popular semantic segmentation benchmarks, yielding state-of-the-art performance on most scenarios. Our code is publicly available at https://github.com/sinahmr/NACLIP.
Authors: Seungwook Kim, Kejie Li, Xueqing Deng, Yichun Shi, Minsu Cho, Peng Wang
Abstract: Leveraging multi-view diffusion models as priors for 3D optimization have alleviated the problem of 3D consistency, e.g., the Janus face problem or the content drift problem, in zero-shot text-to-3D models. However, the 3D geometric fidelity of the output remains an unresolved issue; albeit the rendered 2D views are realistic, the underlying geometry may contain errors such as unreasonable concavities. In this work, we propose CorrespondentDream, an effective method to leverage annotation-free, cross-view correspondences yielded from the diffusion U-Net to provide additional 3D prior to the NeRF optimization process. We find that these correspondences are strongly consistent with human perception, and by adopting it in our loss design, we are able to produce NeRF models with geometries that are more coherent with common sense, e.g., more smoothed object surface, yielding higher 3D fidelity. We demonstrate the efficacy of our approach through various comparative qualitative results and a solid user study.
Authors: Akshay Chandrasekhar
Abstract: This paper presents a new algorithm to estimate absolute camera pose given an axis of the camera's rotation matrix. Current algorithms solve the problem via algebraic solutions on limited input domains. This paper shows that the problem can be solved efficiently by finding the intersection points of a hyperbola and the unit circle. The solution can flexibly accommodate combinations of point and line features in minimal and overconstrained configurations. In addition, the two special cases of planar and minimal configurations are identified to yield simpler closed-form solutions. Extensive experiments validate the approach.
Authors: Zakaria Patel, Kirill Serkh
Abstract: Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images (e.g., bounding boxes) require fine-tuning, a smaller and more recent subset of these methods take advantage of the models' attention mechanism, and are training-free. These methods generally fall into one of two categories. The first entails modifying the cross-attention maps of specific tokens directly to enhance the signal in certain regions of the image. The second works by defining a loss function over the cross-attention maps, and using the gradient of this loss to guide the latent. While previous work explores these as alternative strategies, we provide an interpretation for these methods which highlights their complimentary features, and demonstrate that it is possible to obtain superior performance when both methods are used in concert.
Authors: Andr\'e Sacilotti, Samuel Felipe dos Santos, Nicu Sebe, Jurandy Almeida
Abstract: Unsupervised domain adaptation (UDA) in videos is a challenging task that remains not well explored compared to image-based UDA techniques. Although vision transformers (ViT) achieve state-of-the-art performance in many computer vision tasks, their use in video UDA has been little explored. Our key idea is to use transformer layers as a feature encoder and incorporate spatial and temporal transferability relationships into the attention mechanism. A Transferable-guided Attention (TransferAttn) framework is then developed to exploit the capacity of the transformer to adapt cross-domain knowledge across different backbones. To improve the transferability of ViT, we introduce a novel and effective module, named Domain Transferable-guided Attention Block (DTAB). DTAB compels ViT to focus on the spatio-temporal transferability relationship among video frames by changing the self-attention mechanism to a transferability attention mechanism. Extensive experiments were conducted on UCF-HMDB, Kinetics-Gameplay, and Kinetics-NEC Drone datasets, with different backbones, like ResNet101, I3D, and STAM, to verify the effectiveness of TransferAttn compared with state-of-the-art approaches. Also, we demonstrate that DTAB yields performance gains when applied to other state-of-the-art transformer-based UDA methods from both video and image domains. Our code is available at https://github.com/Andre-Sacilotti/transferattn-project-code.
URLs: https://github.com/Andre-Sacilotti/transferattn-project-code.
Authors: Qingwen Zhang, Yi Yang, Peizheng Li, Olov Andersson, Patric Jensfelt
Abstract: Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current state-of-the-art methods require annotated data to train scene flow networks and the expense of labeling inherently limits their scalability. Self-supervised approaches can overcome the above limitations, yet face two principal challenges that hinder optimal performance: point distribution imbalance and disregard for object-level motion constraints. In this paper, we propose SeFlow, a self-supervised method that integrates efficient dynamic classification into a learning-based scene flow pipeline. We demonstrate that classifying static and dynamic points helps design targeted objective functions for different motion patterns. We also emphasize the importance of internal cluster consistency and correct object point association to refine the scene flow estimation, in particular on object details. Our real-time capable method achieves state-of-the-art performance on the self-supervised scene flow task on Argoverse 2 and Waymo datasets. The code is open-sourced at https://github.com/KTH-RPL/SeFlow along with trained model weights.
Authors: Anay Majee, Ryan Sharp, Rishabh Iyer
Abstract: Confusion and forgetting of object classes have been challenges of prime interest in Few-Shot Object Detection (FSOD). To overcome these pitfalls in metric learning based FSOD techniques, we introduce a novel Submodular Mutual Information Learning (SMILe) framework which adopts combinatorial mutual information functions to enforce the creation of tighter and discriminative feature clusters in FSOD. Our proposed approach generalizes to several existing approaches in FSOD, agnostic of the backbone architecture demonstrating elevated performance gains. A paradigm shift from instance based objective functions to combinatorial objectives in SMILe naturally preserves the diversity within an object class resulting in reduced forgetting when subjected to few training examples. Furthermore, the application of mutual information between the already learnt (base) and newly added (novel) objects ensures sufficient separation between base and novel classes, minimizing the effect of class confusion. Experiments on popular FSOD benchmarks, PASCAL-VOC and MS-COCO show that our approach generalizes to State-of-the-Art (SoTA) approaches improving their novel class performance by up to 5.7% (3.3 mAP points) and 5.4% (2.6 mAP points) on the 10-shot setting of VOC (split 3) and 30-shot setting of COCO datasets respectively. Our experiments also demonstrate better retention of base class performance and up to 2x faster convergence over existing approaches agnostic of the underlying architecture.
Authors: Ali Nasiri-Sarvi, Mahdi S. Hosseini, Hassan Rivaz
Abstract: Mamba-based models, VMamba and Vim, are a recent family of vision encoders that offer promising performance improvements in many computer vision tasks. This paper compares Mamba-based models with traditional Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) using the breast ultrasound BUSI dataset and Breast Ultrasound B dataset. Our evaluation, which includes multiple runs of experiments and statistical significance analysis, demonstrates that some of the Mamba-based architectures often outperform CNN and ViT models with statistically significant results. For example, in the B dataset, the best Mamba-based models have a 1.98\% average AUC and a 5.0\% average Accuracy improvement compared to the best non-Mamba-based model in this study. These Mamba-based models effectively capture long-range dependencies while maintaining some inductive biases, making them suitable for applications with limited data. The code is available at \url{https://github.com/anasiri/BU-Mamba}
Authors: Federico Magistri, Thomas L\"abe, Elias Marks, Sumanth Nagulavancha, Yue Pan, Claus Smitt, Lasse Klingbeil, Michael Halstead, Heiner Kuhlmann, Chris McCool, Jens Behley, Cyrill Stachniss
Abstract: As the world population is expected to reach 10 billion by 2050, our agricultural production system needs to double its productivity despite a decline of human workforce in the agricultural sector. Autonomous robotic systems are one promising pathway to increase productivity by taking over labor-intensive manual tasks like fruit picking. To be effective, such systems need to monitor and interact with plants and fruits precisely, which is challenging due to the cluttered nature of agricultural environments causing, for example, strong occlusions. Thus, being able to estimate the complete 3D shapes of objects in presence of occlusions is crucial for automating operations such as fruit harvesting. In this paper, we propose the first publicly available 3D shape completion dataset for agricultural vision systems. We provide an RGB-D dataset for estimating the 3D shape of fruits. Specifically, our dataset contains RGB-D frames of single sweet peppers in lab conditions but also in a commercial greenhouse. For each fruit, we additionally collected high-precision point clouds that we use as ground truth. For acquiring the ground truth shape, we developed a measuring process that allows us to record data of real sweet pepper plants, both in the lab and in the greenhouse with high precision, and determine the shape of the sensed fruits. We release our dataset, consisting of almost 7,000 RGB-D frames belonging to more than 100 different fruits. We provide segmented RGB-D frames, with camera intrinsics to easily obtain colored point clouds, together with the corresponding high-precision, occlusion-free point clouds obtained with a high-precision laser scanner. We additionally enable evaluation of shape completion approaches on a hidden test set through a public challenge on a benchmark server.
Authors: Seok Hwan Lee, Taein Son, Soo Won Seo, Jisong Kim, Jun Won Choi
Abstract: Video action detection (VAD) is a formidable vision task that involves the localization and classification of actions within the spatial and temporal dimensions of a video clip. Among the myriad VAD architectures, two-stage VAD methods utilize a pre-trained person detector to extract the region of interest features, subsequently employing these features for action detection. However, the performance of two-stage VAD methods has been limited as they depend solely on localized actor features to infer action semantics. In this study, we propose a new two-stage VAD framework called Joint Actor-scene context Relation modeling based on Visual Semantics (JARViS), which effectively consolidates cross-modal action semantics distributed globally across spatial and temporal dimensions using Transformer attention. JARViS employs a person detector to produce densely sampled actor features from a keyframe. Concurrently, it uses a video backbone to create spatio-temporal scene features from a video clip. Finally, the fine-grained interactions between actors and scenes are modeled through a Unified Action-Scene Context Transformer to directly output the final set of actions in parallel. Our experimental results demonstrate that JARViS outperforms existing methods by significant margins and achieves state-of-the-art performance on three popular VAD datasets, including AVA, UCF101-24, and JHMDB51-21.
Authors: Robert Geirhos, Priyank Jaini, Austin Stone, Sourabh Medapati, Xi Yi, George Toderici, Abhijit Ogale, Jonathon Shlens
Abstract: Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is nearly impossible, since all information is distributed across the network's weights. We here explore a simple, compelling alternative by marrying the representational power of deep neural networks with the flexibility of a database. Decomposing the task of image classification into image similarity (from a pre-trained embedding) and search (via fast nearest neighbor retrieval from a knowledge database), we build a simple and flexible visual memory that has the following key capabilities: (1.) The ability to flexibly add data across scales: from individual samples all the way to entire classes and billion-scale data; (2.) The ability to remove data through unlearning and memory pruning; (3.) An interpretable decision-mechanism on which we can intervene to control its behavior. Taken together, these capabilities comprehensively demonstrate the benefits of an explicit visual memory. We hope that it might contribute to a conversation on how knowledge should be represented in deep vision models -- beyond carving it in "stone" weights.
Authors: Sha Lu, Xuecheng Xu, Yuxuan Wu, Haojian Lu, Xieyuanli Chen, Rong Xiong, Yue Wang
Abstract: Global localization using onboard perception sensors, such as cameras and LiDARs, is crucial in autonomous driving and robotics applications when GPS signals are unreliable. Most approaches achieve global localization by sequential place recognition (PR) and pose estimation (PE). Some methods train separate models for each task, while others employ a single model with dual heads, trained jointly with separate task-specific losses. However, the accuracy of localization heavily depends on the success of place recognition, which often fails in scenarios with significant changes in viewpoint or environmental appearance. Consequently, this renders the final pose estimation of localization ineffective. To address this, we introduce a new paradigm, PR-by-PE localization, which bypasses the need for separate place recognition by directly deriving it from pose estimation. We propose RING#, an end-to-end PR-by-PE localization network that operates in the bird's-eye-view (BEV) space, compatible with both vision and LiDAR sensors. RING# incorporates a novel design that learns two equivariant representations from BEV features, enabling globally convergent and computationally efficient pose estimation. Comprehensive experiments on the NCLT and Oxford datasets show that RING# outperforms state-of-the-art methods in both vision and LiDAR modalities, validating the effectiveness of the proposed approach. The code will be publicly released.
Authors: Houwang Jiang, Zhuxian Liu, Guodong Liu, Xiaolong Liu, Shihua Zhan
Abstract: Recent advances in unsupervised representation learning frequently leverage class information to improve the extraction and clustering of features. However, this dependence on class priors limits the applicability of such methods in real-world scenarios where class information is unavailable or ambiguous. In this paper, we propose \textit{Contrastive Disentangling (CD)}, a simple yet effective framework that learns representations without any relying on class priors. CD employs a multi-level contrastive learning strategy, integrating instance-level and feature-level losses with a normalized entropy loss to learn semantically rich and fine-grained representations. Specifically, (1) the instance-level contrastive loss encourages the separation of feature representations between different samples; (2) the feature-level contrastive loss promotes independence among feature prediction heads; and (3) the normalized entropy loss ensures that the feature heads capture meaningful and prevalent attributes from the data. These components together enable CD to outperform existing methods in scenarios lacking class priors, as demonstrated by extensive experiments on benchmark datasets including CIFAR-10, CIFAR-100, STL-10, and ImageNet-10. The code is available at https://github.com/Hoper-J/Contrastive-Disentangling.
Authors: Yohan Poirier-Ginter, Alban Gauthier, Julien Philip, Jean-Francois Lalonde, George Drettakis
Abstract: Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We introduce a method to create relightable radiance fields using such single-illumination data by exploiting priors extracted from 2D image diffusion models. We first fine-tune a 2D diffusion model on a multi-illumination dataset conditioned by light direction, allowing us to augment a single-illumination capture into a realistic -- but possibly inconsistent -- multi-illumination dataset from directly defined light directions. We use this augmented data to create a relightable radiance field represented by 3D Gaussian splats. To allow direct control of light direction for low-frequency lighting, we represent appearance with a multi-layer perceptron parameterized on light direction. To enforce multi-view consistency and overcome inaccuracies we optimize a per-image auxiliary feature vector. We show results on synthetic and real multi-view data under single illumination, demonstrating that our method successfully exploits 2D diffusion model priors to allow realistic 3D relighting for complete scenes. Project site https://repo-sam.inria.fr/fungraph/generative-radiance-field-relighting/
URLs: https://repo-sam.inria.fr/fungraph/generative-radiance-field-relighting/
Authors: Haoyu Wu, Ziqiao Peng, Xukun Zhou, Yunfei Cheng, Jun He, Hongyan Liu, Zhaoxin Fan
Abstract: 3D face reconstruction from monocular images has promoted the development of various applications such as augmented reality. Though existing methods have made remarkable progress, most of them emphasize geometric reconstruction, while overlooking the importance of texture prediction. To address this issue, we propose VGG-Tex, a novel Vivid Geometry-Guided Facial Texture Estimation model designed for High Fidelity Monocular 3D Face Reconstruction. The core of this approach is leveraging 3D parametric priors to enhance the outcomes of 2D UV texture estimation. Specifically, VGG-Tex includes a Facial Attributes Encoding Module, a Geometry-Guided Texture Generator, and a Visibility-Enhanced Texture Completion Module. These components are responsible for extracting parametric priors, generating initial textures, and refining texture details, respectively. Based on the geometry-texture complementarity principle, VGG-Tex also introduces a Texture-guided Geometry Refinement Module to further balance the overall fidelity of the reconstructed 3D faces, along with corresponding losses. Comprehensive experiments demonstrate that our method significantly improves texture reconstruction performance compared to existing state-of-the-art methods.
Authors: Teerapong Panboonyuen
Abstract: This paper introduces a novel framework for detecting and segmenting critical road assets on Thai highways using an advanced Refined Generalized Focal Loss (REG) formulation. Integrated into state-of-the-art vision-based detection and segmentation models, the proposed method effectively addresses class imbalance and the challenges of localizing small, underrepresented road elements, including pavilions, pedestrian bridges, information signs, single-arm poles, bus stops, warning signs, and concrete guardrails. To improve both detection and segmentation accuracy, a multi-task learning strategy is adopted, optimizing REG across multiple tasks. REG is further enhanced by incorporating a spatial-contextual adjustment term, which accounts for the spatial distribution of road assets, and a probabilistic refinement that captures prediction uncertainty in complex environments, such as varying lighting conditions and cluttered backgrounds. Our rigorous mathematical formulation demonstrates that REG minimizes localization and classification errors by applying adaptive weighting to hard-to-detect instances while down-weighting easier examples. Experimental results show a substantial performance improvement, achieving a mAP50 of 80.34 and an F1-score of 77.87, significantly outperforming conventional methods. This research underscores the capability of advanced loss function refinements to enhance the robustness and accuracy of road asset detection and segmentation, thereby contributing to improved road safety and infrastructure management. For an in-depth discussion of the mathematical background and related methods, please refer to previous work available at \url{https://github.com/kaopanboonyuen/REG}.
Authors: Anqi Shi, Yuze Cai, Xiangyu Chen, Jian Pu, Zeyu Fu, Hong Lu
Abstract: High-definition (HD) maps are essential for autonomous driving systems. Traditionally, an expensive and labor-intensive pipeline is implemented to construct HD maps, which is limited in scalability. In recent years, crowdsourcing and online mapping have emerged as two alternative methods, but they have limitations respectively. In this paper, we provide a novel methodology, namely global map construction, to perform direct generation of vectorized global maps, combining the benefits of crowdsourcing and online mapping. We introduce GlobalMapNet, the first online framework for vectorized global HD map construction, which updates and utilizes a global map on the ego vehicle. To generate the global map from scratch, we propose GlobalMapBuilder to match and merge local maps continuously. We design a new algorithm, Map NMS, to remove duplicate map elements and produce a clean map. We also propose GlobalMapFusion to aggregate historical map information, improving consistency of prediction. We examine GlobalMapNet on two widely recognized datasets, Argoverse2 and nuScenes, showing that our framework is capable of generating globally consistent results.
Authors: Yuchen Guo, Weifeng Su
Abstract: Although multi-modality medical image segmentation holds significant potential for enhancing the diagnosis and understanding of complex diseases by integrating diverse imaging modalities, existing methods predominantly rely on feature-level fusion strategies. We argue the current feature-level fusion strategy is prone to semantic inconsistencies and misalignments across various imaging modalities because it merges features at intermediate layers in a neural network without evaluative control. To mitigate this, we introduce a novel image-level fusion based multi-modality medical image segmentation method, Fuse4Seg, which is a bi-level learning framework designed to model the intertwined dependencies between medical image segmentation and medical image fusion. The image-level fusion process is seamlessly employed to guide and enhance the segmentation results through a layered optimization approach. Besides, the knowledge gained from the segmentation module can effectively enhance the fusion module. This ensures that the resultant fused image is a coherent representation that accurately amalgamates information from all modalities. Moreover, we construct a BraTS-Fuse benchmark based on BraTS dataset, which includes 2040 paired original images, multi-modal fusion images, and ground truth. This benchmark not only serves image-level medical segmentation but is also the largest dataset for medical image fusion to date. Extensive experiments on several public datasets and our benchmark demonstrate the superiority of our approach over prior state-of-the-art (SOTA) methodologies.
Authors: Aryaman Gupta, Kaustav Chakraborty, Somil Bansal
Abstract: Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these vision-based controllers can make erroneous predictions when faced with novel or out-of-distribution inputs. Such errors can cascade to catastrophic system failures and compromise system safety. In this work, we introduce a run-time anomaly monitor to detect and mitigate such closed-loop, system-level failures. Specifically, we leverage a reachability-based framework to stress-test the vision-based controller offline and mine its system-level failures. This data is then used to train a classifier that is leveraged online to flag inputs that might cause system breakdowns. The anomaly detector highlights issues that transcend individual modules and pertain to the safety of the overall system. We also design a fallback controller that robustly handles these detected anomalies to preserve system safety. We validate the proposed approach on an autonomous aircraft taxiing system that uses a vision-based controller for taxiing. Our results show the efficacy of the proposed approach in identifying and handling system-level anomalies, outperforming methods such as prediction error-based detection, and ensembling, thereby enhancing the overall safety and robustness of autonomous systems.
Authors: Shreyank N Gowda, Xinyue Hao, Gen Li, Shashank Narayana Gowda, Xiaobo Jin, Laura Sevilla-Lara
Abstract: Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy. However, their increasing energy consumption has raised concerns about their environmental impact, disadvantaging smaller entities in research and exacerbating global energy consumption. In this paper, we explore the trade-off between model accuracy and electricity consumption, proposing a metric that penalizes large consumption of electricity. We conduct a comprehensive study on the electricity consumption of various deep learning models across different GPUs, presenting a detailed analysis of their accuracy-efficiency trade-offs. By evaluating accuracy per unit of electricity consumed, we demonstrate how smaller, more energy-efficient models can significantly expedite research while mitigating environmental concerns. Our results highlight the potential for a more sustainable approach to deep learning, emphasizing the importance of optimizing models for efficiency. This research also contributes to a more equitable research landscape, where smaller entities can compete effectively with larger counterparts. This advocates for the adoption of efficient deep learning practices to reduce electricity consumption, safeguarding the environment for future generations whilst also helping ensure a fairer competitive landscape.
Authors: Krishna Mullia, Fujun Luan, Xin Sun, Milo\v{s} Ha\v{s}an
Abstract: High-fidelity 3D assets with materials composed of fibers (including hair), complex layered material shaders, or fine scattering geometry are ubiquitous in high-end realistic rendering applications. Rendering such models is computationally expensive due to heavy shaders and long scattering paths. Moreover, implementing the shading and scattering models is non-trivial and has to be done not only in the 3D content authoring software (which is necessarily complex), but also in all downstream rendering solutions. For example, web and mobile viewers for complex 3D assets are desirable, but frequently cannot support the full shading complexity allowed by the authoring application. Our goal is to design a neural representation for 3D assets with complex shading that supports full relightability and full integration into existing renderers. We provide an end-to-end shading solution at the first intersection of a ray with the underlying geometry. All shading and scattering is precomputed and included in the neural asset; no multiple scattering paths need to be traced, and no complex shading models need to be implemented to render our assets, beyond a single neural architecture. We combine an MLP decoder with a feature grid. Shading consists of querying a feature vector, followed by an MLP evaluation producing the final reflectance value. Our method provides high-fidelity shading, close to the ground-truth Monte Carlo estimate even at close-up views. We believe our neural assets could be used in practical renderers, providing significant speed-ups and simplifying renderer implementations.
Authors: Chollette C. Olisah, Sofie V. Cauter
Abstract: Despite the advancement in computational modeling towards brain tumor segmentation, of which several models have been developed, it is evident from the computational complexity of existing models that performance and efficiency under clinical application scenarios are still limited. Therefore, this paper proposes a tumor segmentation framework. It includes a novel shallow encoder and decoder network named SEDNet for brain tumor segmentation. The highlights of SEDNet include sufficiency in hierarchical convolutional downsampling and selective skip mechanism for cost-efficient and effective brain tumor semantic segmentation, among other features. The preprocessor and optimization function approaches are devised to minimize the uncertainty in feature learning impacted by nontumor slices or empty masks with corresponding brain slices and address class imbalances as well as boundary irregularities of tumors, respectively. Through experiments, SEDNet achieved impressive dice and Hausdorff scores of 0.9308 %, 0.9451 %, and 0.9026 %, and 0.7040 mm, 1.2866 mm, and 0.7762 mm for the non-enhancing tumor core (NTC), peritumoral edema (ED), and enhancing tumor (ET), respectively. This is one of the few works to report segmentation performance on NTC. Furthermore, through transfer learning with initialized SEDNet pre-trained weights, termed SEDNetX, a performance increase is observed. The dice and Hausdorff scores recorded are 0.9336%, 0.9478%, 0.9061%, 0.6983 mm, 1.2691 mm, and 0.7711 mm for NTC, ED, and ET, respectively. With about 1.3 million parameters and impressive performance in comparison to the state-of-the-art, SEDNet(X) is shown to be computationally efficient for real-time clinical diagnosis. The code is available on Github .
Authors: Andreas Ziegler, Karl Vetter, Thomas Gossard, Jonas Tebbe, Sebastian Otte, Andreas Zell
Abstract: Neuromorphic Computing (NC) and Spiking Neural Networks (SNNs) in particular are often viewed as the next generation of Neural Networks (NNs). NC is a novel bio-inspired paradigm for energy efficient neural computation, often relying on SNNs in which neurons communicate via spikes in a sparse, event-based manner. This communication via spikes can be exploited by neuromorphic hardware implementations very effectively and results in a drastic reductions of power consumption and latency in contrast to regular GPU-based NNs. In recent years, neuromorphic hardware has become more accessible, and the support of learning frameworks has improved. However, available hardware is partially still experimental, and it is not transparent what these solutions are effectively capable of, how they integrate into real-world robotics applications, and how they realistically benefit energy efficiency and latency. In this work, we provide the robotics research community with an overview of what is possible with SNNs on neuromorphic hardware focusing on real-time processing. We introduce a benchmark of three popular neuromorphic hardware devices for the task of event-based object detection. Moreover, we show that an SNN on a neuromorphic hardware is able to run in a challenging table tennis robot setup in real-time.
Authors: Sarah Matta, Mathieu Lamard, Philippe Zhang, Alexandre Le Guilcher, Laurent Borderie, B\'eatrice Cochener, Gwenol\'e Quellec
Abstract: Numerous Deep Learning (DL) classification models have been developed for a large spectrum of medical image analysis applications, which promises to reshape various facets of medical practice. Despite early advances in DL model validation and implementation, which encourage healthcare institutions to adopt them, a fundamental questions remain: how can these models effectively handle domain shift? This question is crucial to limit DL models performance degradation. Medical data are dynamic and prone to domain shift, due to multiple factors. Two main shift types can occur over time: 1) covariate shift mainly arising due to updates to medical equipment and 2) concept shift caused by inter-grader variability. To mitigate the problem of domain shift, existing surveys mainly focus on domain adaptation techniques, with an emphasis on covariate shift. More generally, no work has reviewed the state-of-the-art solutions while focusing on the shift types. This paper aims to explore existing domain generalization methods for DL-based classification models through a systematic review of literature. It proposes a taxonomy based on the shift type they aim to solve. Papers were searched and gathered on Scopus till 10 April 2023, and after the eligibility screening and quality evaluation, 77 articles were identified. Exclusion criteria included: lack of methodological novelty (e.g., reviews, benchmarks), experiments conducted on a single mono-center dataset, or articles not written in English. The results of this paper show that learning based methods are emerging, for both shift types. Finally, we discuss future challenges, including the need for improved evaluation protocols and benchmarks, and envisioned future developments to achieve robust, generalized models for medical image classification.
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: Guanxiong Luo, Shoujin Huang, Martin Uecker
Abstract: Magnetic resonance imaging (MRI) is a widely used non-invasive imaging modality. However, a persistent challenge lies in balancing image quality with imaging speed. This trade-off is primarily constrained by k-space measurements, which traverse specific trajectories in the spatial Fourier domain (k-space). These measurements are often undersampled to shorten acquisition times, resulting in image artifacts and compromised quality. Generative models learn image distributions and can be used to reconstruct high-quality images from undersampled k-space data. In this work, we present the autoregressive image diffusion (AID) model for image sequences and use it to sample the posterior for accelerated MRI reconstruction. The algorithm incorporates both undersampled k-space and pre-existing information. Models trained with fastMRI dataset are evaluated comprehensively. The results show that the AID model can robustly generate sequentially coherent image sequences. In 3D and dynamic MRI, the AID can outperform the standard diffusion model and reduce hallucinations, due to the learned inter-image dependencies.
Authors: Chen Liu, Ke Xu, Liangbo L. Shen, Guillaume Huguet, Zilong Wang, Alexander Tong, Danilo Bzdok, Jay Stewart, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy
Abstract: Advances in medical imaging technologies have enabled the collection of longitudinal images, which involve repeated scanning of the same patients over time, to monitor disease progression. However, predictive modeling of such data remains challenging due to high dimensionality, irregular sampling, and data sparsity. To address these issues, we propose ImageFlowNet, a novel model designed to forecast disease trajectories from initial images while preserving spatial details. ImageFlowNet first learns multiscale joint representation spaces across patients and time points, then optimizes deterministic or stochastic flow fields within these spaces using a position-parameterized neural ODE/SDE framework. The model leverages a UNet architecture to create robust multiscale representations and mitigates data scarcity by combining knowledge from all patients. We provide theoretical insights that support our formulation of ODEs, and motivate our regularizations involving high-level visual features, latent space organization, and trajectory smoothness. We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods. Our contributions include the development of ImageFlowNet, its theoretical underpinnings, and empirical validation on real-world datasets. The official implementation is available at https://github.com/KrishnaswamyLab/ImageFlowNet.
Authors: Melissa Dell
Abstract: Deep learning provides powerful methods to impute structured information from large-scale, unstructured text and image datasets. For example, economists might wish to detect the presence of economic activity in satellite images, or to measure the topics or entities mentioned in social media, the congressional record, or firm filings. This review introduces deep neural networks, covering methods such as classifiers, regression models, generative AI, and embedding models. Applications include classification, document digitization, record linkage, and methods for data exploration in massive scale text and image corpora. When suitable methods are used, deep learning models can be cheap to tune and can scale affordably to problems involving millions or billions of data points.. The review is accompanied by a companion website, EconDL, with user-friendly demo notebooks, software resources, and a knowledge base that provides technical details and additional applications.
Authors: Xue Wang, Tian Zhou, Jianqing Zhu, Jialin Liu, Kun Yuan, Tao Yao, Wotao Yin, Rong Jin, HanQin Cai
Abstract: Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved Attention structures are proposed to reduce the computation cost by inducing low rankness and approximating the whole sequence by sub-sequences. The most challenging part of those approaches is maintaining the proper balance between information preservation and computation reduction: the longer sub-sequences used, the better information is preserved, but at the price of introducing more noise and computational costs. In this paper, we propose a smoothed skeleton sketching based Attention structure, coined S$^3$Attention, which significantly improves upon the previous attempts to negotiate this trade-off. S$^3$Attention has two mechanisms to effectively minimize the impact of noise while keeping the linear complexity to the sequence length: a smoothing block to mix information over long sequences and a matrix sketching method that simultaneously selects columns and rows from the input matrix. We verify the effectiveness of S$^3$Attention both theoretically and empirically. Extensive studies over Long Range Arena (LRA) datasets and six time-series forecasting show that S$^3$Attention significantly outperforms both vanilla Attention and other state-of-the-art variants of Attention structures.