Authors: Selvia Nafaa, Hafsa Essam, Karim Ashour, Doaa Emad, Rana Mohamed, Mohammed Elhenawy, Huthaifa I. Ashqar, Abdallah A. Hassan, Taqwa I. Alhadidi
Abstract: Roadway signs detection and recognition is an essential element in the Advanced Driving Assistant Systems (ADAS). Several artificial intelligence methods have been used widely among of them YOLOv5 and YOLOv8. In this paper, we used a modified YOLOv5 and YOLOv8 to detect and classify different roadway signs under different illumination conditions. Experimental results indicated that for the YOLOv8 model, varying the number of epochs and batch size yields consistent MAP50 scores, ranging from 94.6% to 97.1% on the testing set. The YOLOv5 model demonstrates competitive performance, with MAP50 scores ranging from 92.4% to 96.9%. These results suggest that both models perform well across different training setups, with YOLOv8 generally achieving slightly higher MAP50 scores. These findings suggest that both models can perform well under different training setups, offering valuable insights for practitioners seeking reliable and adaptable solutions in object detection applications.
Authors: Jiannan Xiang, Guangyi Liu, Yi Gu, Qiyue Gao, Yuting Ning, Yuheng Zha, Zeyu Feng, Tianhua Tao, Shibo Hao, Yemin Shi, Zhengzhong Liu, Eric P. Xing, Zhiting Hu
Abstract: World models simulate future states of the world in response to different actions. They facilitate interactive content creation and provides a foundation for grounded, long-horizon reasoning. Current foundation models do not fully meet the capabilities of general world models: large language models (LLMs) are constrained by their reliance on language modality and their limited understanding of the physical world, while video models lack interactive action control over the world simulations. This paper makes a step towards building a general world model by introducing Pandora, a hybrid autoregressive-diffusion model that simulates world states by generating videos and allows real-time control with free-text actions. Pandora achieves domain generality, video consistency, and controllability through large-scale pretraining and instruction tuning. Crucially, Pandora bypasses the cost of training-from-scratch by integrating a pretrained LLM (7B) and a pretrained video model, requiring only additional lightweight finetuning. We illustrate extensive outputs by Pandora across diverse domains (indoor/outdoor, natural/urban, human/robot, 2D/3D, etc.). The results indicate great potential of building stronger general world models with larger-scale training.
Authors: Amir Zur, Elisa Kreiss, Karel D'Oosterlinck, Christopher Potts, Atticus Geiger
Abstract: Although CLIPScore is a powerful generic metric that captures the similarity between a text and an image, it fails to distinguish between a caption that is meant to complement the information in an image and a description that is meant to replace an image entirely, e.g., for accessibility. We address this shortcoming by updating the CLIP model with the Concadia dataset to assign higher scores to descriptions than captions using parameter efficient fine-tuning and a loss objective derived from work on causal interpretability. This model correlates with the judgements of blind and low-vision people while preserving transfer capabilities and has interpretable structure that sheds light on the caption--description distinction.
Authors: Hector A. Valdez, Kyle Min, Subarna Tripathi
Abstract: Pretraining egocentric vision-language models has become essential to improving downstream egocentric video-text tasks. These egocentric foundation models commonly use the transformer architecture. The memory footprint of these models during pretraining can be substantial. Therefore, we pretrain SViTT-Ego, the first sparse egocentric video-text transformer model integrating edge and node sparsification. We pretrain on the EgoClip dataset and incorporate the egocentric-friendly objective EgoNCE, instead of the frequently used InfoNCE. Most notably, SViTT-Ego obtains a +2.8% gain on EgoMCQ (intra-video) accuracy compared to LAVILA large, with no additional data augmentation techniques other than standard image augmentations, yet pretrainable on memory-limited devices.
Authors: Yong Wu, Yang Wang, Sanqing Qu, Zhijun Li, Guang Chen
Abstract: We consider the problem of user-adaptive 3D gaze estimation. The performance of person-independent gaze estimation is limited due to interpersonal anatomical differences. Our goal is to provide a personalized gaze estimation model specifically adapted to a target user. Previous work on user-adaptive gaze estimation requires some labeled images of the target person data to fine-tune the model at test time. However, this can be unrealistic in real-world applications, since it is cumbersome for an end-user to provide labeled images. In addition, previous work requires the training data to have both gaze labels and person IDs. This data requirement makes it infeasible to use some of the available data. To tackle these challenges, this paper proposes a new problem called efficient label-free user adaptation in gaze estimation. Our model only needs a few unlabeled images of a target user for the model adaptation. During offline training, we have some labeled source data without person IDs and some unlabeled person-specific data. Our proposed method uses a meta-learning approach to learn how to adapt to a new user with only a few unlabeled images. Our key technical innovation is to use a generalization bound from domain adaptation to define the loss function in meta-learning, so that our method can effectively make use of both the labeled source data and the unlabeled person-specific data during training. Extensive experiments validate the effectiveness of our method on several challenging benchmarks.
Authors: Jiayang Meng, Tao Huang, Hong Chen, Cuiping Li
Abstract: Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients. However, existing methods are restricted to reconstructing low-resolution images where data leakage risks of image processing systems are not sufficiently explored. In this paper, by exploiting diffusion models, we propose an innovative gradient-guided fine-tuning method and introduce a new reconstruction attack that is capable of stealing private, high-resolution images from image processing systems through leaked gradients where severe data leakage encounters. Our attack method is easy to implement and requires little prior knowledge. The experimental results indicate that current reconstruction attacks can steal images only up to a resolution of $128 \times 128$ pixels, while our attack method can successfully recover and steal images with resolutions up to $512 \times 512$ pixels. Our attack method significantly outperforms the SOTA attack baselines in terms of both pixel-wise accuracy and time efficiency of image reconstruction. Furthermore, our attack can render differential privacy ineffective to some extent.
Authors: Shenghua Wan, Ziyuan Chen, Le Gan, Shuai Feng, De-Chuan Zhan
Abstract: Model-based offline reinforcement Learning (RL) is a promising approach that leverages existing data effectively in many real-world applications, especially those involving high-dimensional inputs like images and videos. To alleviate the distribution shift issue in offline RL, existing model-based methods heavily rely on the uncertainty of learned dynamics. However, the model uncertainty estimation becomes significantly biased when observations contain complex distractors with non-trivial dynamics. To address this challenge, we propose a new approach - \emph{Separated Model-based Offline Policy Optimization} (SeMOPO) - decomposing latent states into endogenous and exogenous parts via conservative sampling and estimating model uncertainty on the endogenous states only. We provide a theoretical guarantee of model uncertainty and performance bound of SeMOPO. To assess the efficacy, we construct the Low-Quality Vision Deep Data-Driven Datasets for RL (LQV-D4RL), where the data are collected by non-expert policy and the observations include moving distractors. Experimental results show that our method substantially outperforms all baseline methods, and further analytical experiments validate the critical designs in our method. The project website is \href{https://sites.google.com/view/semopo}{https://sites.google.com/view/semopo}.
URLs: https://sites.google.com/view/semopo, https://sites.google.com/view/semopo
Authors: An Dinh Vuong, Minh Nhat Vu, Baoru Huang, Nghia Nguyen, Hieu Le, Thieu Vo, Anh Nguyen
Abstract: Grasp detection is a persistent and intricate challenge with various industrial applications. Recently, many methods and datasets have been proposed to tackle the grasp detection problem. However, most of them do not consider using natural language as a condition to detect the grasp poses. In this paper, we introduce Grasp-Anything++, a new language-driven grasp detection dataset featuring 1M samples, over 3M objects, and upwards of 10M grasping instructions. We utilize foundation models to create a large-scale scene corpus with corresponding images and grasp prompts. We approach the language-driven grasp detection task as a conditional generation problem. Drawing on the success of diffusion models in generative tasks and given that language plays a vital role in this task, we propose a new language-driven grasp detection method based on diffusion models. Our key contribution is the contrastive training objective, which explicitly contributes to the denoising process to detect the grasp pose given the language instructions. We illustrate that our approach is theoretically supportive. The intensive experiments show that our method outperforms state-of-the-art approaches and allows real-world robotic grasping. Finally, we demonstrate our large-scale dataset enables zero-short grasp detection and is a challenging benchmark for future work. Project website: https://airvlab.github.io/grasp-anything/
Authors: Fengbin Guan, Xin Li, Zihao Yu, Yiting Lu, Zhibo Chen
Abstract: In this work, we take the first exploration of the recently popular foundation model, i.e., State Space Model/Mamba, in image quality assessment, aiming at observing and excavating the perception potential in vision Mamba. A series of works on Mamba has shown its significant potential in various fields, e.g., segmentation and classification. However, the perception capability of Mamba has been under-explored. Consequently, we propose Q-Mamba by revisiting and adapting the Mamba model for three crucial IQA tasks, i.e., task-specific, universal, and transferable IQA, which reveals that the Mamba model has obvious advantages compared with existing foundational models, e.g., Swin Transformer, ViT, and CNNs, in terms of perception and computational cost for IQA. To increase the transferability of Q-Mamba, we propose the StylePrompt tuning paradigm, where the basic lightweight mean and variance prompts are injected to assist the task-adaptive transfer learning of pre-trained Q-Mamba for different downstream IQA tasks. Compared with existing prompt tuning strategies, our proposed StylePrompt enables better perception transfer capability with less computational cost. Extensive experiments on multiple synthetic, authentic IQA datasets, and cross IQA datasets have demonstrated the effectiveness of our proposed Q-Mamba.
Authors: Umur Aybars Ciftci, Ali Kemal Tanriverdi, Ilke Demir
Abstract: In an era of increasing privacy concerns for our online presence, we propose that the decision to appear in a piece of content should only belong to the owner of the body. Although some automatic approaches for full-body anonymization have been proposed, human-guided anonymization can adapt to various contexts, such as cultural norms, personal relations, esthetic concerns, and security issues. ''My Body My Choice'' (MBMC) enables physical and adversarial anonymization by removal and swapping approaches aimed for four tasks, designed by single or multi, ControlNet or GAN modules, combining several diffusion models. We evaluate anonymization on seven datasets; compare with SOTA inpainting and anonymization methods; evaluate by image, adversarial, and generative metrics; and conduct reidentification experiments.
Authors: Carlos Plou, Lorenzo Mur-Labadia, Ruben Martinez-Cantin, Ana C. Murillo
Abstract: The goal of the Step Grounding task is to locate temporal boundaries of activities based on natural language descriptions. This technical report introduces a Bayesian-VSLNet to address the challenge of identifying such temporal segments in lengthy, untrimmed egocentric videos. Our model significantly improves upon traditional models by incorporating a novel Bayesian temporal-order prior during inference, enhancing the accuracy of moment predictions. This prior adjusts for cyclic and repetitive actions within videos. Our evaluations demonstrate superior performance over existing methods, achieving state-of-the-art results on the Ego4D Goal-Step dataset with a 35.18 Recall Top-1 at 0.3 IoU and 20.48 Recall Top-1 at 0.5 IoU on the test set.
Authors: Felix O'Mahony, Yulong Yang, Christine Allen-Blanchette
Abstract: Group equivariant convolutional neural networks have been designed for a variety of geometric transformations from 2D and 3D rotation groups, to semi-groups such as scale. Despite the improved interpretability, accuracy and generalizability afforded by these architectures, group equivariant networks have seen limited application in the context of perceptual quantities such as hue and saturation, even though their variation can lead to significant reductions in classification performance. In this paper, we introduce convolutional neural networks equivariant to variations in hue and saturation by design. To achieve this, we leverage the observation that hue and saturation transformations can be identified with the 2D rotation and 1D translation groups respectively. Our hue-, saturation-, and fully color-equivariant networks achieve equivariance to these perceptual transformations without an increase in network parameters. We demonstrate the utility of our networks on synthetic and real world datasets where color and lighting variations are commonplace.
Authors: Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, Shreyas Hampali, Fan Zhang, Jade Fountain, Edward Miller, Selen Basol, Richard Newcombe, Robert Wang, Jakob Julian Engel, Tomas Hodan
Abstract: We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (more than 3.7M images) of multi-view RGB/monochrome image streams showing 19 subjects interacting with 33 diverse rigid objects, multi-modal signals such as eye gaze or scene point clouds, as well as comprehensive ground truth annotations including 3D poses of objects, hands, and cameras, and 3D models of hands and objects. In addition to simple pick-up/observe/put-down actions, HOT3D contains scenarios resembling typical actions in a kitchen, office, and living room environment. The dataset is recorded by two head-mounted devices from Meta: Project Aria, a research prototype of light-weight AR/AI glasses, and Quest 3, a production VR headset sold in millions of units. Ground-truth poses were obtained by a professional motion-capture system using small optical markers attached to hands and objects. Hand annotations are provided in the UmeTrack and MANO formats and objects are represented by 3D meshes with PBR materials obtained by an in-house scanner. We aim to accelerate research on egocentric hand-object interaction by making the HOT3D dataset publicly available and by co-organizing public challenges on the dataset at ECCV 2024. The dataset can be downloaded from the project website: https://facebookresearch.github.io/hot3d/.
Authors: Qingyuan Liu, Pengyuan Shi, Yun-Yun Tsai, Chengzhi Mao, Junfeng Yang
Abstract: The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works to combat Deepfakes videos have developed detectors that are highly accurate at identifying GAN-generated samples. However, the robustness of these detectors on diffusion-generated videos generated from video creation tools (e.g., SORA by OpenAI, Runway Gen-2, and Pika, etc.) is still unexplored. In this paper, we propose a novel framework for detecting videos synthesized from multiple state-of-the-art (SOTA) generative models, such as Stable Video Diffusion. We find that the SOTA methods for detecting diffusion-generated images lack robustness in identifying diffusion-generated videos. Our analysis reveals that the effectiveness of these detectors diminishes when applied to out-of-domain videos, primarily because they struggle to track the temporal features and dynamic variations between frames. To address the above-mentioned challenge, we collect a new benchmark video dataset for diffusion-generated videos using SOTA video creation tools. We extract representation within explicit knowledge from the diffusion model for video frames and train our detector with a CNN + LSTM architecture. The evaluation shows that our framework can well capture the temporal features between frames, achieves 93.7% detection accuracy for in-domain videos, and improves the accuracy of out-domain videos by up to 16 points.
Authors: Wufei Ma, Guanning Zeng, Guofeng Zhang, Qihao Liu, Letian Zhang, Adam Kortylewski, Yaoyao Liu, Alan Yuille
Abstract: A vision model with general-purpose object-level 3D understanding should be capable of inferring both 2D (e.g., class name and bounding box) and 3D information (e.g., 3D location and 3D viewpoint) for arbitrary rigid objects in natural images. This is a challenging task, as it involves inferring 3D information from 2D signals and most importantly, generalizing to rigid objects from unseen categories. However, existing datasets with object-level 3D annotations are often limited by the number of categories or the quality of annotations. Models developed on these datasets become specialists for certain categories or domains, and fail to generalize. In this work, we present ImageNet3D, a large dataset for general-purpose object-level 3D understanding. ImageNet3D augments 200 categories from the ImageNet dataset with 2D bounding box, 3D pose, 3D location annotations, and image captions interleaved with 3D information. With the new annotations available in ImageNet3D, we could (i) analyze the object-level 3D awareness of visual foundation models, and (ii) study and develop general-purpose models that infer both 2D and 3D information for arbitrary rigid objects in natural images, and (iii) integrate unified 3D models with large language models for 3D-related reasoning.. We consider two new tasks, probing of object-level 3D awareness and open vocabulary pose estimation, besides standard classification and pose estimation. Experimental results on ImageNet3D demonstrate the potential of our dataset in building vision models with stronger general-purpose object-level 3D understanding.
Authors: Wei-Ting Chen, Gurunandan Krishnan, Qiang Gao, Sy-Yen Kuo, Sizhuo Ma, Jian Wang
Abstract: Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks. We present a novel transformer-based method for GFIQA, which is aided by two unique mechanisms. First, a Dual-Set Degradation Representation Learning (DSL) mechanism uses facial images with both synthetic and real degradations to decouple degradation from content, ensuring generalizability to real-world scenarios. This self-supervised method learns degradation features on a global scale, providing a robust alternative to conventional methods that use local patch information in degradation learning. Second, our transformer leverages facial landmarks to emphasize visually salient parts of a face image in evaluating its perceptual quality. We also introduce a balanced and diverse Comprehensive Generic Face IQA (CGFIQA-40k) dataset of 40K images carefully designed to overcome the biases, in particular the imbalances in skin tone and gender representation, in existing datasets. Extensive analysis and evaluation demonstrate the robustness of our method, marking a significant improvement over prior methods.
Authors: Wei-Ting Chen, Yu-Jiet Vong, Sy-Yen Kuo, Sizhuo Ma, Jian Wang
Abstract: Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images with degraded quality. Addressing this limitation, we propose the Robust Segment Anything Model (RobustSAM), which enhances SAM's performance on low-quality images while preserving its promptability and zero-shot generalization. Our method leverages the pre-trained SAM model with only marginal parameter increments and computational requirements. The additional parameters of RobustSAM can be optimized within 30 hours on eight GPUs, demonstrating its feasibility and practicality for typical research laboratories. We also introduce the Robust-Seg dataset, a collection of 688K image-mask pairs with different degradations designed to train and evaluate our model optimally. Extensive experiments across various segmentation tasks and datasets confirm RobustSAM's superior performance, especially under zero-shot conditions, underscoring its potential for extensive real-world application. Additionally, our method has been shown to effectively improve the performance of SAM-based downstream tasks such as single image dehazing and deblurring.
Authors: Mehreen Saeed, Adrian Chan, Anupam Mijar, Joseph Moukarzel, Georges Habchi, Carlos Younes, Amin Elias, Chau-Wai Wong, Akram Khater
Abstract: We present the Manuscripts of Handwritten Arabic~(Muharaf) dataset, which is a machine learning dataset consisting of more than 1,600 historic handwritten page images transcribed by experts in archival Arabic. Each document image is accompanied by spatial polygonal coordinates of its text lines as well as basic page elements. This dataset was compiled to advance the state of the art in handwritten text recognition (HTR), not only for Arabic manuscripts but also for cursive text in general. The Muharaf dataset includes diverse handwriting styles and a wide range of document types, including personal letters, diaries, notes, poems, church records, and legal correspondences. In this paper, we describe the data acquisition pipeline, notable dataset features, and statistics. We also provide a preliminary baseline result achieved by training convolutional neural networks using this data.
Authors: Keno Moenck, Duc Trung Thieu, Julian Koch, Thorsten Sch\"uppstuhl
Abstract: In recent years, the upstream of Large Language Models (LLM) has also encouraged the computer vision community to work on substantial multimodal datasets and train models on a scale in a self-/semi-supervised manner, resulting in Vision Foundation Models (VFM), as, e.g., Contrastive Language-Image Pre-training (CLIP). The models generalize well and perform outstandingly on everyday objects or scenes, even on downstream tasks, tasks the model has not been trained on, while the application in specialized domains, as in an industrial context, is still an open research question. Here, fine-tuning the models or transfer learning on domain-specific data is unavoidable when objecting to adequate performance. In this work, we, on the one hand, introduce a pipeline to generate the Industrial Language-Image Dataset (ILID) based on web-crawled data; on the other hand, we demonstrate effective self-supervised transfer learning and discussing downstream tasks after training on the cheaply acquired ILID, which does not necessitate human labeling or intervention. With the proposed approach, we contribute by transferring approaches from state-of-the-art research around foundation models, transfer learning strategies, and applications to the industrial domain.
Authors: Kate Sanders, Benjamin Van Durme
Abstract: While existing video benchmarks largely consider specialized downstream tasks like retrieval or question-answering (QA), contemporary multimodal AI systems must be capable of well-rounded common-sense reasoning akin to human visual understanding. A critical component of human temporal-visual perception is our ability to identify and cognitively model "things happening", or events. Historically, video benchmark tasks have implicitly tested for this ability (e.g., video captioning, in which models describe visual events with natural language), but they do not consider video event understanding as a task in itself. Recent work has begun to explore video analogues to textual event extraction but consists of competing task definitions and datasets limited to highly specific event types. Therefore, while there is a rich domain of event-centric video research spanning the past 10+ years, it is unclear how video event understanding should be framed and what resources we have to study it. In this paper, we survey 105 video datasets that require event understanding capability, consider how they contribute to the study of robust event understanding in video, and assess proposed video event extraction tasks in the context of this body of research. We propose suggestions informed by this survey for dataset curation and task framing, with an emphasis on the uniquely temporal nature of video events and ambiguity in visual content.
Authors: Risa Shinoda, Kaede Shiohara
Abstract: Animal habitat surveys play a critical role in preserving the biodiversity of the land. One of the effective ways to gain insights into animal habitats involves identifying animal footprints, which offers valuable information about species distribution, abundance, and behavior. However, due to the scarcity of animal footprint images, there are no well-maintained public datasets, preventing recent advanced techniques in computer vision from being applied to animal tracking. In this paper, we introduce OpenAnimalTracks dataset, the first publicly available labeled dataset designed to facilitate the automated classification and detection of animal footprints. It contains various footprints from 18 wild animal species. Moreover, we build benchmarks for species classification and detection and show the potential of automated footprint identification with representative classifiers and detection models. We find SwinTransformer achieves a promising classification result, reaching 69.41% in terms of the averaged accuracy. Faster-RCNN achieves mAP of 0.295. We hope our dataset paves the way for automated animal tracking techniques, enhancing our ability to protect and manage biodiversity. Our dataset and code are available at https://github.com/dahlian00/OpenAnimalTracks.
Authors: Jingcheng Li, Ye Qiao, Haocheng Xu, Sitao Huang
Abstract: Images captured under low-light scenarios often suffer from low quality. Previous CNN-based deep learning methods often involve using Retinex theory. Nevertheless, most of them cannot perform well in more complicated datasets like LOL-v2 while consuming too much computational resources. Besides, some of these methods require sophisticated training at different stages, making the procedure even more time-consuming and tedious. In this paper, we propose a more accurate, concise, and one-stage Retinex theory based framework, RSEND. RSEND first divides the low-light image into the illumination map and reflectance map, then captures the important details in the illumination map and performs light enhancement. After this step, it refines the enhanced gray-scale image and does element-wise matrix multiplication with the reflectance map. By denoising the output it has from the previous step, it obtains the final result. In all the steps, RSEND utilizes Squeeze and Excitation network to better capture the details. Comprehensive quantitative and qualitative experiments show that our Efficient Retinex model significantly outperforms other CNN-based models, achieving a PSNR improvement ranging from 0.44 dB to 4.2 dB in different datasets and even outperforms transformer-based models in the LOL-v2-real dataset.
Authors: Yuhang Zhou, Zihua Zhao, Haolin Li, Siyuan Du, Jiangchao Yao, Ya Zhang, Yanfeng Wang
Abstract: Training a unified model to take multiple targets into account is a trend towards artificial general intelligence. However, how to efficiently mitigate the training conflicts among heterogeneous data collected from different domains or tasks remains under-explored. In this study, we explore to leverage Mixture of Low-rank Adapters (MoLA) to mitigate conflicts in heterogeneous data training, which requires to jointly train the multiple low-rank adapters and their shared backbone. Specifically, we introduce two variants of MoLA, namely, MoLA-Grad and MoLA-Router, to respectively handle the target-aware and target-agnostic scenarios during inference. The former uses task identifiers to assign personalized low-rank adapters to each task, disentangling task-specific knowledge towards their adapters, thereby mitigating heterogeneity conflicts. The latter uses a novel Task-wise Decorrelation (TwD) loss to intervene the router to learn oriented weight combinations of adapters to homogeneous tasks, achieving similar effects. We conduct comprehensive experiments to verify the superiority of MoLA over previous state-of-the-art methods and present in-depth analysis on its working mechanism. Source code is available at: https://github.com/MediaBrain-SJTU/MoLA
Authors: Wei Jin, Jun Zhou
Abstract: In recent years, deep learning-based point cloud normal estimation has made great progress. However, existing methods mainly rely on the PCPNet dataset, leading to overfitting. In addition, the correlation between point clouds with different noise scales remains unexplored, resulting in poor performance in cross-domain scenarios. In this paper, we explore the consistency of intrinsic features learned from clean and noisy point clouds using an Asymmetric Siamese Network architecture. By applying reasonable constraints between features extracted from different branches, we enhance the quality of normal estimation. Moreover, we introduce a novel multi-view normal estimation dataset that includes a larger variety of shapes with different noise levels. Evaluation of existing methods on this new dataset reveals their inability to adapt to different types of shapes, indicating a degree of overfitting. Extensive experiments show that the proposed dataset poses significant challenges for point cloud normal estimation and that our feature constraint mechanism effectively improves upon existing methods and reduces overfitting in current architectures.
Authors: Qiang Zhu, Yajun Qiu, Yu Liu, Shuyuan Zhu, Bing Zeng
Abstract: In this paper, we propose a temporal group alignment and fusion network to enhance the quality of compressed videos by using the long-short term correlations between frames. The proposed model consists of the intra-group feature alignment (IntraGFA) module, the inter-group feature fusion (InterGFF) module, and the feature enhancement (FE) module. We form the group of pictures (GoP) by selecting frames from the video according to their temporal distances to the target enhanced frame. With this grouping, the composed GoP can contain either long- or short-term correlated information of neighboring frames. We design the IntraGFA module to align the features of frames of each GoP to eliminate the motion existing between frames. We construct the InterGFF module to fuse features belonging to different GoPs and finally enhance the fused features with the FE module to generate high-quality video frames. The experimental results show that our proposed method achieves up to 0.05dB gain and lower complexity compared to the state-of-the-art method.
Authors: Shilu Yuan, Dongfeng Li, Wei Liu, Xinxin Zhang, Meng Chen, Junjie Zhang, Yongshun Gong
Abstract: Fine-grained urban flow inference (FUFI) is a crucial transportation service aimed at improving traffic efficiency and safety. FUFI can infer fine-grained urban traffic flows based solely on observed coarse-grained data. However, most of existing methods focus on the influence of single-scale static geographic information on FUFI, neglecting the interactions and dynamic information between different-scale regions within the city. Different-scale geographical features can capture redundant information from the same spatial areas. In order to effectively learn multi-scale information across time and space, we propose an effective fine-grained urban flow inference model called UrbanMSR, which uses self-supervised contrastive learning to obtain dynamic multi-scale representations of neighborhood-level and city-level geographic information, and fuses multi-scale representations to improve fine-grained accuracy. The fusion of multi-scale representations enhances fine-grained. We validate the performance through extensive experiments on three real-world datasets. The resutls compared with state-of-the-art methods demonstrate the superiority of the proposed model.
Authors: Ahmed Qazi, Taha Razzaq, Asim Iqbal
Abstract: We introduce a multimodal vision framework for precision livestock farming, harnessing the power of GroundingDINO, HQSAM, and ViTPose models. This integrated suite enables comprehensive behavioral analytics from video data without invasive animal tagging. GroundingDINO generates accurate bounding boxes around livestock, while HQSAM segments individual animals within these boxes. ViTPose estimates key body points, facilitating posture and movement analysis. Demonstrated on a sheep dataset with grazing, running, sitting, standing, and walking activities, our framework extracts invaluable insights: activity and grazing patterns, interaction dynamics, and detailed postural evaluations. Applicable across species and video resolutions, this framework revolutionizes non-invasive livestock monitoring for activity detection, counting, health assessments, and posture analyses. It empowers data-driven farm management, optimizing animal welfare and productivity through AI-powered behavioral understanding.
Authors: Abhilash Durgam, Sidike Paheding, Vikas Dhiman, Vijay Devabhaktuni
Abstract: Cross-view geo-localization has garnered notable attention in the realm of computer vision, spurred by the widespread availability of copious geotagged datasets and the advancements in machine learning techniques. This paper provides a thorough survey of cutting-edge methodologies, techniques, and associated challenges that are integral to this domain, with a focus on feature-based and deep learning strategies. Feature-based methods capitalize on unique features to establish correspondences across disparate viewpoints, whereas deep learning-based methodologies deploy convolutional neural networks to embed view-invariant attributes. This work also delineates the multifaceted challenges encountered in cross-view geo-localization, such as variations in viewpoints and illumination, the occurrence of occlusions, and it elucidates innovative solutions that have been formulated to tackle these issues. Furthermore, we delineate benchmark datasets and relevant evaluation metrics, and also perform a comparative analysis of state-of-the-art techniques. Finally, we conclude the paper with a discussion on prospective avenues for future research and the burgeoning applications of cross-view geo-localization in an intricately interconnected global landscape.
Authors: Ignacio Alzugaray, Riku Murai, Andrew Davison
Abstract: Visual sensors are not only becoming better at capturing high-quality images but also they have steadily increased their capabilities in processing data on their own on-chip. Yet the majority of VO pipelines rely on the transmission and processing of full images in a centralized unit (e.g. CPU or GPU), which often contain much redundant and low-quality information for the task. In this paper, we address the task of frame-to-frame rotational estimation but, instead of reasoning about relative motion between frames using the full images, distribute the estimation at pixel-level. In this paradigm, each pixel produces an estimate of the global motion by only relying on local information and local message-passing with neighbouring pixels. The resulting per-pixel estimates can then be communicated to downstream tasks, yielding higher-level, informative cues instead of the original raw pixel-readings. We evaluate the proposed approach on real public datasets, where we offer detailed insights about this novel technique and open-source our implementation for the future benefit of the community.
Authors: Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, Minhyuk Sung
Abstract: We propose a novel method for learning representations of poses for 3D deformable objects, which specializes in 1) disentangling pose information from the object's identity, 2) facilitating the learning of pose variations, and 3) transferring pose information to other object identities. Based on these properties, our method enables the generation of 3D deformable objects with diversity in both identities and poses, using variations of a single object. It does not require explicit shape parameterization such as skeletons or joints, point-level or shape-level correspondence supervision, or variations of the target object for pose transfer. To achieve pose disentanglement, compactness for generative models, and transferability, we first design the pose extractor to represent the pose as a keypoint-based hybrid representation and the pose applier to learn an implicit deformation field. To better distill pose information from the object's geometry, we propose the implicit pose applier to output an intrinsic mesh property, the face Jacobian. Once the extracted pose information is transferred to the target object, the pose applier is fine-tuned in a self-supervised manner to better describe the target object's shapes with pose variations. The extracted poses are also used to train a cascaded diffusion model to enable the generation of novel poses. Our experiments with the DeformThings4D and Human datasets demonstrate state-of-the-art performance in pose transfer and the ability to generate diverse deformed shapes with various objects and poses.
Authors: Richard Boadu Antwi, Samuel Takyi, Alican Karaer, Eren Erman Ozguven, Michael Kimollo, Ren Moses, Maxim A. Dulebenets, Thobias Sando
Abstract: Identification of changes in pavement markings has become crucial for infrastructure monitoring, maintenance, development, traffic management, and safety. Automated extraction of roadway geometry is critical in helping with this, given the increasing availability of high-resolution images and advancements in computer vision and object detection. Specifically, due to the substantial volume of satellite and high-resolution aerial images captured at different time instances, change detection has become a viable solution. In this study, an automated framework is developed to detect changes in crosswalks of Orange, Osceola, and Seminole counties in Florida, utilizing data extracted from high-resolution images obtained at various time intervals. Specifically, for Orange County, crosswalk changes between 2019 and 2021 were manually extracted, verified, and categorized as either new or modified crosswalks. For Seminole County, the developed model was used to automatically extract crosswalk changes between 2018 and 2021, while for Osceola County, changes between 2019 and 2020 were extracted. Findings indicate that Orange County witnessed approximately 2,094 crosswalk changes, with 312 occurring on state roads. In Seminole and Osceola counties, on the other hand, 1,040 and 1,402 crosswalk changes were observed on both local and state roads, respectively. Among these, 340 and 344 were identified on state roads in Seminole and Osceola, respectively. Spatiotemporal changes observed in crosswalks can be utilized to regularly update the existing crosswalk inventories, which is essential for agencies engaged in traffic and safety studies. Data extracted from these crosswalk changes can be combined with traffic and crash data to provide valuable insights to policymakers.
Authors: Wei Ye, Xinan He, Feng Ding
Abstract: In this paper, we propose a novel method for detecting DeepFakes, enhancing the generalization of detection through semantic decoupling. There are now multiple DeepFake forgery technologies that not only possess unique forgery semantics but may also share common forgery semantics. The unique forgery semantics and irrelevant content semantics may promote over-fitting and hamper generalization for DeepFake detectors. For our proposed method, after decoupling, the common forgery semantics could be extracted from DeepFakes, and subsequently be employed for developing the generalizability of DeepFake detectors. Also, to pursue additional generalizability, we designed an adaptive high-pass module and a two-stage training strategy to improve the independence of decoupled semantics. Evaluation on FF++, Celeb-DF, DFD, and DFDC datasets showcases our method's excellent detection and generalization performance. Code is available at: https://anonymous.4open.science/r/DFS-GDD-0F42.
Authors: Xiang Li, Kai Qiu, Hao Chen, Jason Kuen, Zhe Lin, Rita Singh, Bhiksha Raj
Abstract: Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference latency, and difficulties of integration with large language models (LLMs) have necessitated exploring alternatives to DMs. This paper introduces ControlVAR, a novel framework that explores pixel-level controls in visual autoregressive (VAR) modeling for flexible and efficient conditional generation. In contrast to traditional conditional models that learn the conditional distribution, ControlVAR jointly models the distribution of image and pixel-level conditions during training and imposes conditional controls during testing. To enhance the joint modeling, we adopt the next-scale AR prediction paradigm and unify control and image representations. A teacher-forcing guidance strategy is proposed to further facilitate controllable generation with joint modeling. Extensive experiments demonstrate the superior efficacy and flexibility of ControlVAR across various conditional generation tasks against popular conditional DMs, \eg, ControlNet and T2I-Adaptor.
Authors: Alexandros Stergiou
Abstract: This paper introduces a LArge-scale Video Interpolation Benchmark (LAVIB) for the low-level video task of video frame interpolation (VFI). LAVIB comprises a large collection of high-resolution videos sourced from the web through an automated pipeline with minimal requirements for human verification. Metrics are computed for each video's motion magnitudes, luminance conditions, frame sharpness, and contrast. The collection of videos and the creation of quantitative challenges based on these metrics are under-explored by current low-level video task datasets. In total, LAVIB includes 283K clips from 17K ultra-HD videos, covering 77.6 hours. Benchmark train, val, and test sets maintain similar video metric distributions. Further splits are also created for out-of-distribution (OOD) challenges, with train and test splits including videos of dissimilar attributes.
Authors: Vincent Leroy, Yohann Cabon, J\'er\^ome Revaud
Abstract: Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to camera pose and scene geometry, it is typically treated as a 2D problem. This makes sense as the goal of matching is to establish correspondences between 2D pixel fields, but also seems like a potentially hazardous choice. In this work, we take a different stance and propose to cast matching as a 3D task with DUSt3R, a recent and powerful 3D reconstruction framework based on Transformers. Based on pointmaps regression, this method displayed impressive robustness in matching views with extreme viewpoint changes, yet with limited accuracy. We aim here to improve the matching capabilities of such an approach while preserving its robustness. We thus propose to augment the DUSt3R network with a new head that outputs dense local features, trained with an additional matching loss. We further address the issue of quadratic complexity of dense matching, which becomes prohibitively slow for downstream applications if not carefully treated. We introduce a fast reciprocal matching scheme that not only accelerates matching by orders of magnitude, but also comes with theoretical guarantees and, lastly, yields improved results. Extensive experiments show that our approach, coined MASt3R, significantly outperforms the state of the art on multiple matching tasks. In particular, it beats the best published methods by 30% (absolute improvement) in VCRE AUC on the extremely challenging Map-free localization dataset.
Authors: Ryosuke Watanabe, Keisuke Nonaka, Eduardo Pavez, Tatsuya Kobayashi, Antonio Ortega
Abstract: Point clouds in 3D applications frequently experience quality degradation during processing, e.g., scanning and compression. Reliable point cloud quality assessment (PCQA) is important for developing compression algorithms with good bitrate-quality trade-offs and techniques for quality improvement (e.g., denoising). This paper introduces a full-reference (FR) PCQA method utilizing spectral graph wavelets (SGWs). First, we propose novel SGW-based PCQA metrics that compare SGW coefficients of coordinate and color signals between reference and distorted point clouds. Second, we achieve accurate PCQA by integrating several conventional FR metrics and our SGW-based metrics using support vector regression. To our knowledge, this is the first study to introduce SGWs for PCQA. Experimental results demonstrate the proposed PCQA metric is more accurately correlated with subjective quality scores compared to conventional PCQA metrics.
Authors: Alper G\"ung\"or, Bahri Batuhan Bilecen, Tolga \c{C}ukur
Abstract: Diffusion models have recently been shown to excel in many image reconstruction tasks that involve inverse problems based on a forward measurement operator. A common framework uses task-agnostic unconditional models that are later post-conditioned for reconstruction, an approach that typically suffers from suboptimal task performance. While task-specific conditional models have also been proposed, current methods heuristically inject measured data as a naive input channel that elicits sampling inaccuracies. Here, we address the optimal conditioning of diffusion models for solving challenging inverse problems that arise during image reconstruction. Specifically, we propose a novel Bayesian conditioning technique for diffusion models, BCDM, based on score-functions associated with the conditional distribution of desired images given measured data. We rigorously derive the theory to express and train the conditional score-function. Finally, we show state-of-the-art performance in image dealiasing, deblurring, super-resolution, and inpainting with the proposed technique.
Authors: Haowei Yang, Liyang Wang, Jingyu Zhang, Yu Cheng, Ao Xiang
Abstract: With the widespread application of Light Detection and Ranging (LiDAR) technology in fields such as autonomous driving, robot navigation, and terrain mapping, the importance of edge detection in LiDAR images has become increasingly prominent. Traditional edge detection methods often face challenges in accuracy and computational complexity when processing LiDAR images. To address these issues, this study proposes an edge detection method for LiDAR images based on artificial intelligence technology. This paper first reviews the current state of research on LiDAR technology and image edge detection, introducing common edge detection algorithms and their applications in LiDAR image processing. Subsequently, a deep learning-based edge detection model is designed and implemented, optimizing the model training process through preprocessing and enhancement of the LiDAR image dataset. Experimental results indicate that the proposed method outperforms traditional methods in terms of detection accuracy and computational efficiency, showing significant practical application value. Finally, improvement strategies are proposed for the current method's shortcomings, and the improvements are validated through experiments.
Authors: Ahsan Raza Siyal, Astrid Ellen Grams, Markus Haltmeier
Abstract: Accurate volumetric image registration is highly relevant for clinical routines and computer-aided medical diagnosis. Recently, researchers have begun to use transformers in learning-based methods for medical image registration, and have achieved remarkable success. Due to the strong global modeling capability, Transformers are considered a better option than convolutional neural networks (CNNs) for registration. However, they use bulky models with huge parameter sets, which require high computation edge devices for deployment as portable devices or in hospitals. Transformers also need a large amount of training data to produce significant results, and it is often challenging to collect suitable annotated data. Although existing CNN-based image registration can offer rich local information, their global modeling capability is poor for handling long-distance information interaction and limits registration performance. In this work, we propose a CNN-based registration method with an enhanced receptive field, a low number of parameters, and significant results on a limited training dataset. For this, we propose a residual U-Net with embedded parallel dilated-convolutional blocks to enhance the receptive field. The proposed method is evaluated on inter-patient and atlas-based datasets. We show that the performance of the proposed method is comparable and slightly better than transformer-based methods by using only $\SI{1.5}{\percent}$ of its number of parameters.
Authors: Yiqi Wu, Xiaodan Hu, Ziming Fu, Siling Zhou, Jiangong Li
Abstract: Animal ethology is an crucial aspect of animal research, and animal behavior labeling is the foundation for studying animal behavior. This process typically involves labeling video clips with behavioral semantic tags, a task that is complex, subjective, and multimodal. With the rapid development of multimodal large language models(LLMs), new application have emerged for animal behavior understanding tasks in livestock scenarios. This study evaluates the visual perception capabilities of multimodal LLMs in animal activity recognition. To achieve this, we created piglet test data comprising close-up video clips of individual piglets and annotated full-shot video clips. These data were used to assess the performance of four multimodal LLMs-Video-LLaMA, MiniGPT4-Video, Video-Chat2, and GPT-4 omni (GPT-4o)-in piglet activity understanding. Through comprehensive evaluation across five dimensions, including counting, actor referring, semantic correspondence, time perception, and robustness, we found that while current multimodal LLMs require improvement in semantic correspondence and time perception, they have initially demonstrated visual perception capabilities for animal activity recognition. Notably, GPT-4o showed outstanding performance, with Video-Chat2 and GPT-4o exhibiting significantly better semantic correspondence and time perception in close-up video clips compared to full-shot clips. The initial evaluation experiments in this study validate the potential of multimodal large language models in livestock scene video understanding and provide new directions and references for future research on animal behavior video understanding. Furthermore, by deeply exploring the influence of visual prompts on multimodal large language models, we expect to enhance the accuracy and efficiency of animal behavior recognition in livestock scenarios through human visual processing methods.
Authors: Runze Liu, Dongchen Zhu, Guanghui Zhang, Yue Xu, Wenjun Shi, Xiaolin Zhang, Lei Wang, Jiamao Li
Abstract: Unsupervised monocular depth estimation has received widespread attention because of its capability to train without ground truth. In real-world scenarios, the images may be blurry or noisy due to the influence of weather conditions and inherent limitations of the camera. Therefore, it is particularly important to develop a robust depth estimation model. Benefiting from the training strategies of generative networks, generative-based methods often exhibit enhanced robustness. In light of this, we employ a well-converging diffusion model among generative networks for unsupervised monocular depth estimation. Additionally, we propose a hierarchical feature-guided denoising module. This model significantly enriches the model's capacity for learning and interpreting depth distribution by fully leveraging image features to guide the denoising process. Furthermore, we explore the implicit depth within reprojection and design an implicit depth consistency loss. This loss function serves to enhance the performance of the model and ensure the scale consistency of depth within a video sequence. We conduct experiments on the KITTI, Make3D, and our self-collected SIMIT datasets. The results indicate that our approach stands out among generative-based models, while also showcasing remarkable robustness.
Authors: Yoni Gozlan, Antoine Falisse, Scott Uhlrich, Anthony Gatti, Michael Black, Akshay Chaudhari
Abstract: Pose estimation has promised to impact healthcare by enabling more practical methods to quantify nuances of human movement and biomechanics. However, despite the inherent connection between pose estimation and biomechanics, these disciplines have largely remained disparate. For example, most current pose estimation benchmarks use metrics such as Mean Per Joint Position Error, Percentage of Correct Keypoints, or mean Average Precision to assess performance, without quantifying kinematic and physiological correctness - key aspects for biomechanics. To alleviate this challenge, we develop OpenCapBench to offer an easy-to-use unified benchmark to assess common tasks in human pose estimation, evaluated under physiological constraints. OpenCapBench computes consistent kinematic metrics through joints angles provided by an open-source musculoskeletal modeling software (OpenSim). Through OpenCapBench, we demonstrate that current pose estimation models use keypoints that are too sparse for accurate biomechanics analysis. To mitigate this challenge, we introduce SynthPose, a new approach that enables finetuning of pre-trained 2D human pose models to predict an arbitrarily denser set of keypoints for accurate kinematic analysis through the use of synthetic data. Incorporating such finetuning on synthetic data of prior models leads to twofold reduced joint angle errors. Moreover, OpenCapBench allows users to benchmark their own developed models on our clinically relevant cohort. Overall, OpenCapBench bridges the computer vision and biomechanics communities, aiming to drive simultaneous advances in both areas.
Authors: Kailai Sun, Zhou Yang, Qianchuan Zhao
Abstract: Depth images have a wide range of applications, such as 3D reconstruction, autonomous driving, augmented reality, robot navigation, and scene understanding. Commodity-grade depth cameras are hard to sense depth for bright, glossy, transparent, and distant surfaces. Although existing depth completion methods have achieved remarkable progress, their performance is limited when applied to complex indoor scenarios. To address these problems, we propose a two-step Transformer-based network for indoor depth completion. Unlike existing depth completion approaches, we adopt a self-supervision pre-training encoder based on the masked autoencoder to learn an effective latent representation for the missing depth value; then we propose a decoder based on a token fusion mechanism to complete (i.e., reconstruct) the full depth from the jointly RGB and incomplete depth image. Compared to the existing methods, our proposed network, achieves the state-of-the-art performance on the Matterport3D dataset. In addition, to validate the importance of the depth completion task, we apply our methods to indoor 3D reconstruction. The code, dataset, and demo are available at https://github.com/kailaisun/Indoor-Depth-Completion.
Authors: Teng Hu, Ran Yi, Baihong Qian, Jiangning Zhang, Paul L. Rosin, Yu-Kun Lai
Abstract: SVG (Scalable Vector Graphics) is a widely used graphics format that possesses excellent scalability and editability. Image vectorization, which aims to convert raster images to SVGs, is an important yet challenging problem in computer vision and graphics. Existing image vectorization methods either suffer from low reconstruction accuracy for complex images or require long computation time. To address this issue, we propose SuperSVG, a superpixel-based vectorization model that achieves fast and high-precision image vectorization. Specifically, we decompose the input image into superpixels to help the model focus on areas with similar colors and textures. Then, we propose a two-stage self-training framework, where a coarse-stage model is employed to reconstruct the main structure and a refinement-stage model is used for enriching the details. Moreover, we propose a novel dynamic path warping loss to help the refinement-stage model to inherit knowledge from the coarse-stage model. Extensive qualitative and quantitative experiments demonstrate the superior performance of our method in terms of reconstruction accuracy and inference time compared to state-of-the-art approaches. The code is available in \url{https://github.com/sjtuplayer/SuperSVG}.
Authors: Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari
Abstract: Our objective is to leverage a differentiable radiance field \eg NeRF to reconstruct detailed 3D surfaces in addition to producing the standard novel view renderings. There have been related methods that perform such tasks, usually by utilizing a signed distance field (SDF). However, the state-of-the-art approaches still fail to correctly reconstruct the small-scale details, such as the leaves, ropes, and textile surfaces. Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor to prioritize the rendering and zero-crossing surface fitting on top of establishing a perfect SDF. We propose to adaptively adjust the regularization on the signed distance field so that unsatisfying rendering rays won't enforce strong Eikonal regularization which is ineffective, and allow the gradients from regions with well-learned radiance to effectively back-propagated to the SDF. Consequently, balancing the two objectives in order to generate accurate and detailed surfaces. Additionally, concerning whether there is a geometric bias between the zero-crossing surface in SDF and rendering points in the radiance field, the projection becomes adjustable as well depending on different 3D locations during optimization. Our proposed \textit{RaNeuS} are extensively evaluated on both synthetic and real datasets, achieving state-of-the-art results on both novel view synthesis and geometric reconstruction.
Authors: Xiangheng Shan, Dongyue Wu, Guilin Zhu, Yuanjie Shao, Nong Sang, Changxin Gao
Abstract: Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish this task, they are still easily overfitting to training classes due to the natural gaps in semantic information between training and new classes. To overcome this challenge, we propose a novel framework for openvocabulary semantic segmentation called EBSeg, incorporating an Adaptively Balanced Decoder (AdaB Decoder) and a Semantic Structure Consistency loss (SSC Loss). The AdaB Decoder is designed to generate different image embeddings for both training and new classes. Subsequently, these two types of embeddings are adaptively balanced to fully exploit their ability to recognize training classes and generalization ability for new classes. To learn a consistent semantic structure from CLIP, the SSC Loss aligns the inter-classes affinity in the image feature space with that in the text feature space of CLIP, thereby improving the generalization ability of our model. Furthermore, we employ a frozen SAM image encoder to complement the spatial information that CLIP features lack due to the low training image resolution and image-level supervision inherent in CLIP. Extensive experiments conducted across various benchmarks demonstrate that the proposed EBSeg outperforms the state-of-the-art methods. Our code and trained models will be here: https://github.com/slonetime/EBSeg.
Authors: Jian Chen, Peilin Zhou, Yining Hua, Dading Chong, Meng Cao, Yaowei Li, Zixuan Yuan, Bing Zhu, Junwei Liang
Abstract: Real-time detection and prediction of extreme weather protect human lives and infrastructure. Traditional methods rely on numerical threshold setting and manual interpretation of weather heatmaps with Geographic Information Systems (GIS), which can be slow and error-prone. Our research redefines Extreme Weather Events Detection (EWED) by framing it as a Visual Question Answering (VQA) problem, thereby introducing a more precise and automated solution. Leveraging Vision-Language Models (VLM) to simultaneously process visual and textual data, we offer an effective aid to enhance the analysis process of weather heatmaps. Our initial assessment of general-purpose VLMs (e.g., GPT-4-Vision) on EWED revealed poor performance, characterized by low accuracy and frequent hallucinations due to inadequate color differentiation and insufficient meteorological knowledge. To address these challenges, we introduce ClimateIQA, the first meteorological VQA dataset, which includes 8,760 wind gust heatmaps and 254,040 question-answer pairs covering four question types, both generated from the latest climate reanalysis data. We also propose Sparse Position and Outline Tracking (SPOT), an innovative technique that leverages OpenCV and K-Means clustering to capture and depict color contours in heatmaps, providing ClimateIQA with more accurate color spatial location information. Finally, we present Climate-Zoo, the first meteorological VLM collection, which adapts VLMs to meteorological applications using the ClimateIQA dataset. Experiment results demonstrate that models from Climate-Zoo substantially outperform state-of-the-art general VLMs, achieving an accuracy increase from 0% to over 90% in EWED verification. The datasets and models in this study are publicly available for future climate science research: https://github.com/AlexJJJChen/Climate-Zoo.
Authors: Trapoom Ukarapol, Kevin Pruvost
Abstract: Text-to-3D generation has shown promising results, yet common challenges such as the Multi-face Janus problem and extended generation time for high-quality assets. In this paper, we address these issues by introducing a novel three-stage training pipeline called GradeADreamer. This pipeline is capable of producing high-quality assets with a total generation time of under 30 minutes using only a single RTX 3090 GPU. Our proposed method employs a Multi-view Diffusion Model, MVDream, to generate Gaussian Splats as a prior, followed by refining geometry and texture using StableDiffusion. Experimental results demonstrate that our approach significantly mitigates the Multi-face Janus problem and achieves the highest average user preference ranking compared to previous state-of-the-art methods. The project code is available at https://github.com/trapoom555/GradeADreamer.
Authors: Fei Zhou, Zhicong Huang, Tianhao Gu, Guoping Qiu
Abstract: The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA).While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation.
Authors: Xingming Long, Jie Zhang, Shiguang Shan, Xilin Chen
Abstract: Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. However, some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sample, which makes determining the OOD sample a Sorites Paradox. In this paper, we construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue, in which we divide the test samples into subsets with different semantic and covariate shift degrees relative to the ID dataset. The data division is achieved through a shift measuring method based on our proposed Language Aligned Image feature Decomposition (LAID). Moreover, we construct a Synthetic Incremental Shift (Syn-IS) dataset that contains high-quality generated images with more diverse covariate contents to complement the IS-OOD benchmark. We evaluate current OOD detection methods on our benchmark and find several important insights: (1) The performance of most OOD detection methods significantly improves as the semantic shift increases; (2) Some methods like GradNorm may have different OOD detection mechanisms as they rely less on semantic shifts to make decisions; (3) Excessive covariate shifts in the image are also likely to be considered as OOD for some methods. Our code and data are released in https://github.com/qqwsad5/IS-OOD.
Authors: Brun\'o B. Englert, Fabrizio J. Piva, Tommie Kerssies, Daan de Geus, Gijs Dubbelman
Abstract: Achieving robust generalization across diverse data domains remains a significant challenge in computer vision. This challenge is important in safety-critical applications, where deep-neural-network-based systems must perform reliably under various environmental conditions not seen during training. Our study investigates whether the generalization capabilities of Vision Foundation Models (VFMs) and Unsupervised Domain Adaptation (UDA) methods for the semantic segmentation task are complementary. Results show that combining VFMs with UDA has two main benefits: (a) it allows for better UDA performance while maintaining the out-of-distribution performance of VFMs, and (b) it makes certain time-consuming UDA components redundant, thus enabling significant inference speedups. Specifically, with equivalent model sizes, the resulting VFM-UDA method achieves an 8.4$\times$ speed increase over the prior non-VFM state of the art, while also improving performance by +1.2 mIoU in the UDA setting and by +6.1 mIoU in terms of out-of-distribution generalization. Moreover, when we use a VFM with 3.6$\times$ more parameters, the VFM-UDA approach maintains a 3.3$\times$ speed up, while improving the UDA performance by +3.1 mIoU and the out-of-distribution performance by +10.3 mIoU. These results underscore the significant benefits of combining VFMs with UDA, setting new standards and baselines for Unsupervised Domain Adaptation in semantic segmentation.
Authors: Lingni Ma, Yuting Ye, Fangzhou Hong, Vladimir Guzov, Yifeng Jiang, Rowan Postyeni, Luis Pesqueira, Alexander Gamino, Vijay Baiyya, Hyo Jin Kim, Kevin Bailey, David Soriano Fosas, C. Karen Liu, Ziwei Liu, Jakob Engel, Renzo De Nardi, Richard Newcombe
Abstract: We introduce Nymeria - a large-scale, diverse, richly annotated human motion dataset collected in the wild with multiple multimodal egocentric devices. The dataset comes with a) full-body 3D motion ground truth; b) egocentric multimodal recordings from Project Aria devices with RGB, grayscale, eye-tracking cameras, IMUs, magnetometer, barometer, and microphones; and c) an additional "observer" device providing a third-person viewpoint. We compute world-aligned 6DoF transformations for all sensors, across devices and capture sessions. The dataset also provides 3D scene point clouds and calibrated gaze estimation. We derive a protocol to annotate hierarchical language descriptions of in-context human motion, from fine-grain pose narrations, to atomic actions and activity summarization. To the best of our knowledge, the Nymeria dataset is the world largest in-the-wild collection of human motion with natural and diverse activities; first of its kind to provide synchronized and localized multi-device multimodal egocentric data; and the world largest dataset with motion-language descriptions. It contains 1200 recordings of 300 hours of daily activities from 264 participants across 50 locations, travelling a total of 399Km. The motion-language descriptions provide 310.5K sentences in 8.64M words from a vocabulary size of 6545. To demonstrate the potential of the dataset we define key research tasks for egocentric body tracking, motion synthesis, and action recognition and evaluate several state-of-the-art baseline algorithms. Data and code will be open-sourced.
Authors: Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp, Marc Walessa, Daniel Meissner, Klaus Dietmayer
Abstract: Adverse weather conditions can severely affect the performance of LiDAR sensors by introducing unwanted noise in the measurements. Therefore, differentiating between noise and valid points is crucial for the reliable use of these sensors. Current approaches for detecting adverse weather points require large amounts of labeled data, which can be difficult and expensive to obtain. This paper proposes a label-efficient approach to segment LiDAR point clouds in adverse weather. We develop a framework that uses few-shot semantic segmentation to learn to segment adverse weather points from only a few labeled examples. Then, we use a semi-supervised learning approach to generate pseudo-labels for unlabelled point clouds, significantly increasing the amount of training data without requiring any additional labeling. We also integrate good weather data in our training pipeline, allowing for high performance in both good and adverse weather conditions. Results on real and synthetic datasets show that our method performs well in detecting snow, fog, and spray. Furthermore, we achieve competitive performance against fully supervised methods while using only a fraction of labeled data.
Authors: Zhe Yuan, Jianqi Shi
Abstract: Computer-aided design (CAD) tools are utilized in the manufacturing industry for modeling everything from cups to spacecraft. These programs are complex to use and typically require years of training and experience to master. Structured and well-constrained 2D sketches and 3D constructions are crucial components of CAD modeling. A well-executed CAD model can be seamlessly integrated into the manufacturing process, thereby enhancing production efficiency. Deep generative models of 3D shapes and 3D object reconstruction models has garnered significant research interest. However, most of these models are represented in discrete forms. Moreover, the few models based on CAD operations often have substantial input restrictions. In this work, we fine-tuned pre-trained models to create OpenECAD (0.55B, 0.89B, and 4.2B), leveraging the visual, logical, coding, and general capabilities of visual language models. OpenECAD can process images of 3D designs as input and generate highly structured 2D sketches and 3D construction commands. These outputs can be directly used with existing CAD tools' APIs to generate project files. To train our network, we created a new CAD dataset. This dataset is based on existing public CAD datasets, with adjustments and augmentations to meet the requirements of ~VLM training.
Authors: Sandeep Singh Sengar
Abstract: Developing a robust object tracker is a challenging task due to factors such as occlusion, motion blur, fast motion, illumination variations, rotation, background clutter, low resolution and deformation across the frames. In the literature, lots of good approaches based on sparse representation have already been presented to tackle the above problems. However, most of the algorithms do not focus on the learning of sparse representation. They only consider the modeling of target appearance and therefore drift away from the target with the imprecise training samples. By considering all the above factors in mind, we have proposed a visual object tracking algorithm by integrating a coarse-to-fine search strategy based on sparse representation and the weighted multiple instance learning (WMIL) algorithm. Compared with the other trackers, our approach has more information of the original signal with less complexity due to the coarse-to-fine search method, and also has weights for important samples. Thus, it can easily discriminate the background features from the foreground. Furthermore, we have also selected the samples from the un-occluded sub-regions to efficiently develop the strong classifier. As a consequence, a stable and robust object tracker is achieved to tackle all the aforementioned problems. Experimental results with quantitative as well as qualitative analysis on challenging benchmark datasets show the accuracy and efficiency of our method.
Authors: Narges Norouzi, Svetlana Orlova, Daan de Geus, Gijs Dubbelman
Abstract: This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges similar tokens within a small local window and (2) halfway through the network, it merges similar tokens across the entire image. This is motivated by an analysis in which we found that, in those situations, tokens with a high cosine similarity can likely be merged without a drop in segmentation quality. With extensive experiments across multiple datasets and network configurations, we show that ALGM not only significantly improves the throughput by up to 100%, but can also enhance the mean IoU by up to +1.1, thereby achieving a better trade-off between segmentation quality and efficiency than existing methods. Moreover, our approach is adaptive during inference, meaning that the same model can be used for optimal efficiency or accuracy, depending on the application. Code is available at https://tue-mps.github.io/ALGM.
Authors: Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp, Marc Walessa, Daniel Meissner, Klaus Dietmayer
Abstract: Autonomous vehicles rely on camera, LiDAR, and radar sensors to navigate the environment. Adverse weather conditions like snow, rain, and fog are known to be problematic for both camera and LiDAR-based perception systems. Currently, it is difficult to evaluate the performance of these methods due to the lack of publicly available datasets containing multimodal labeled data. To address this limitation, we propose the SemanticSpray++ dataset, which provides labels for camera, LiDAR, and radar data of highway-like scenarios in wet surface conditions. In particular, we provide 2D bounding boxes for the camera image, 3D bounding boxes for the LiDAR point cloud, and semantic labels for the radar targets. By labeling all three sensor modalities, the SemanticSpray++ dataset offers a comprehensive test bed for analyzing the performance of different perception methods when vehicles travel on wet surface conditions. Together with comprehensive label statistics, we also evaluate multiple baseline methods across different tasks and analyze their performances. The dataset will be available at https://semantic-spray-dataset.github.io .
Authors: Imanol Miranda, Ander Salaberria, Eneko Agirre, Gorka Azkune
Abstract: Existing Vision-Language Compositionality (VLC) benchmarks like SugarCrepe are formulated as image-to-text retrieval problems, where, given an image, the models need to select between the correct textual description and a synthetic hard negative text. In this work we present the Bidirectional Vision-Language Compositionality (BiVLC) dataset. The novelty of BiVLC is to add a synthetic hard negative image generated from the synthetic text, resulting in two image-to-text retrieval examples (one for each image) and, more importantly, two text-to-image retrieval examples (one for each text). Human annotators filter out ill-formed examples ensuring the validity of the benchmark. The experiments on BiVLC uncover a weakness of current multimodal models, as they perform poorly in the text-to-image direction. In fact, when considering both retrieval directions, the conclusions obtained in previous works change significantly. In addition to the benchmark, we show that a contrastive model trained using synthetic images and texts improves the state of the art in SugarCrepe and in BiVLC for both retrieval directions. The gap to human performance in BiVLC confirms that Vision-Language Compositionality is still a challenging problem. BiVLC and code are available at https://imirandam.github.io/BiVLC_project_page.
Authors: Tiancheng Li, Jinxiu Liu, Huajun Chen, Qi Liu
Abstract: Instruction-based image editing has made a great process in using natural human language to manipulate the visual content of images. However, existing models are limited by the quality of the dataset and cannot accurately localize editing regions in images with complex object relationships. In this paper, we propose Reinforcement Learning Guided Image Editing Method(InstructRL4Pix) to train a diffusion model to generate images that are guided by the attention maps of the target object. Our method maximizes the output of the reward model by calculating the distance between attention maps as a reward function and fine-tuning the diffusion model using proximal policy optimization (PPO). We evaluate our model in object insertion, removal, replacement, and transformation. Experimental results show that InstructRL4Pix breaks through the limitations of traditional datasets and uses unsupervised learning to optimize editing goals and achieve accurate image editing based on natural human commands.
Authors: Yuzhong Huang, Zhong Li, Zhang Chen, Zhiyuan Ren, Guosheng Lin, Fred Morstatter, Yi Xu
Abstract: In the evolving landscape of text-to-3D technology, Dreamfusion has showcased its proficiency by utilizing Score Distillation Sampling (SDS) to optimize implicit representations such as NeRF. This process is achieved through the distillation of pretrained large-scale text-to-image diffusion models. However, Dreamfusion encounters fidelity and efficiency constraints: it faces the multi-head Janus issue and exhibits a relatively slow optimization process. To circumvent these challenges, we introduce OrientDream, a camera orientation conditioned framework designed for efficient and multi-view consistent 3D generation from textual prompts. Our strategy emphasizes the implementation of an explicit camera orientation conditioned feature in the pre-training of a 2D text-to-image diffusion module. This feature effectively utilizes data from MVImgNet, an extensive external multi-view dataset, to refine and bolster its functionality. Subsequently, we utilize the pre-conditioned 2D images as a basis for optimizing a randomly initialized implicit representation (NeRF). This process is significantly expedited by a decoupled back-propagation technique, allowing for multiple updates of implicit parameters per optimization cycle. Our experiments reveal that our method not only produces high-quality NeRF models with consistent multi-view properties but also achieves an optimization speed significantly greater than existing methods, as quantified by comparative metrics.
Authors: Amedeo Ceglia, Kael Facon, Micka\"el Begon, Lama Seoud
Abstract: Biomechanical biofeedback may enhance rehabilitation and provide clinicians with more objective task evaluation. These feedbacks often rely on expensive motion capture systems, which restricts their widespread use, leading to the development of computer vision-based methods. These methods are subject to large joint angle errors, considering the upper limb, and exclude the scapula and clavicle motion in the analysis. Our open-source approach offers a user-friendly solution for high-fidelity upper-limb kinematics using a single low-cost RGBD camera and includes semi-automatic skin marker labeling. Real-time biomechanical analysis, ranging from kinematics to muscle force estimation, was conducted on eight participants performing a hand-cycling motion to demonstrate the applicability of our approach on the upper limb. Markers were recorded by the RGBD camera and an optoelectronic camera system, considered as a reference. Muscle activity and external load were recorded using eight EMG and instrumented hand pedals, respectively. Bland-Altman analysis revealed significant agreements in the 3D markers' positions between the two motion capture methods, with errors averaging 3.3$\pm$3.9 mm. For the biomechanical analysis, the level of agreement was sensitive to whether the same marker set was used. For example, joint angle differences averaging 2.3$\pm$2.8{\deg} when using the same marker set, compared to 4.5$\pm$2.9{\deg} otherwise. Biofeedback from the RGBD camera was provided at 63 Hz. Our study introduces a novel method for using an RGBD camera as a low-cost motion capture solution, emphasizing its potential for accurate kinematic reconstruction and comprehensive upper-limb biomechanical studies.
Authors: Gyusang Cho, Chan-Hyun Youn
Abstract: After the revelation that neural networks tend to produce overconfident predictions, the problem of calibration, which aims to align confidence with accuracy to enhance the reliability of predictions, has gained significant importance. Several solutions based on calibration maps have been proposed to address the problem of recalibrating a trained classifier using additional datasets. In this paper, we offer an algorithm that transforms the weights of the last layer of the classifier, distinct from the calibration-map-based approach. We concentrate on the geometry of the final linear layer, specifically its angular aspect, and adjust the weights of the corresponding layer. We name the method Tilt and Average(\textsc{Tna}), and validate the calibration effect empirically and theoretically. Through this, we demonstrate that our approach, in addition to the existing calibration-map-based techniques, can yield improved calibration performance. Code available : https://github.com/GYYYYYUUUUU/TNA_Angular_Scaling.
Authors: Hugues Turb\'e, Mina Bjelogrlic, Gianmarco Mengaldo, Christian Lovis
Abstract: Prototypical networks aim to build intrinsically explainable models based on the linear summation of concepts. However, important challenges remain in the transparency, compactness, and meaningfulness of the explanations provided by these models. This work demonstrates how frozen pre-trained ViT backbones can be effectively turned into prototypical models for both general and domain-specific tasks, in our case biomedical image classifiers. By leveraging strong spatial features combined with a novel prototypical head, ProtoS-ViT surpasses existing prototypical models showing strong performance in terms of accuracy, compactness, and explainability. Model explainability is evaluated through an extensive set of quantitative and qualitative metrics which serve as a general benchmark for the development of prototypical models. Code is available at https://github.com/hturbe/protosvit.
Authors: Chen Long-fei, Muhammad Ahmed Raza, Craig Innes, Subramanian Ramamoorthy, Robert B. Fisher
Abstract: Aging and chronic conditions affect older adults' daily lives, making early detection of developing health issues crucial. Weakness, common in many conditions, alters physical movements and daily activities subtly. However, detecting such changes can be challenging due to their subtle and gradual nature. To address this, we employ a non-intrusive camera sensor to monitor individuals' daily sitting and relaxing activities for signs of weakness. We simulate weakness in healthy subjects by having them perform physical exercise and observing the behavioral changes in their daily activities before and after workouts. The proposed system captures fine-grained features related to body motion, inactivity, and environmental context in real-time while prioritizing privacy. A Bayesian Network is used to model the relationships between features, activities, and health conditions. We aim to identify specific features and activities that indicate such changes and determine the most suitable time scale for observing the change. Results show 0.97 accuracy in distinguishing simulated weakness at the daily level. Fine-grained behavioral features, including non-dominant upper body motion speed and scale, and inactivity distribution, along with a 300-second window, are found most effective. However, individual-specific models are recommended as no universal set of optimal features and activities was identified across all participants.
Authors: Ana Davila, Jacinto Colan, Yasuhisa Hasegawa
Abstract: In the context of medical imaging and machine learning, one of the most pressing challenges is the effective adaptation of pre-trained models to specialized medical contexts. Despite the availability of advanced pre-trained models, their direct application to the highly specialized and diverse field of medical imaging often falls short due to the unique characteristics of medical data. This study provides a comprehensive analysis on the performance of various fine-tuning methods applied to pre-trained models across a spectrum of medical imaging domains, including X-ray, MRI, Histology, Dermoscopy, and Endoscopic surgery. We evaluated eight fine-tuning strategies, including standard techniques such as fine-tuning all layers or fine-tuning only the classifier layers, alongside methods such as gradually unfreezing layers, regularization based fine-tuning and adaptive learning rates. We selected three well-established CNN architectures (ResNet-50, DenseNet-121, and VGG-19) to cover a range of learning and feature extraction scenarios. Although our results indicate that the efficacy of these fine-tuning methods significantly varies depending on both the architecture and the medical imaging type, strategies such as combining Linear Probing with Full Fine-tuning resulted in notable improvements in over 50% of the evaluated cases, demonstrating general effectiveness across medical domains. Moreover, Auto-RGN, which dynamically adjusts learning rates, led to performance enhancements of up to 11% for specific modalities. Additionally, the DenseNet architecture showed more pronounced benefits from alternative fine-tuning approaches compared to traditional full fine-tuning. This work not only provides valuable insights for optimizing pre-trained models in medical image analysis but also suggests the potential for future research into more advanced architectures and fine-tuning methods.
Authors: Enming Zhang, Ruobing Yao, Huanyong Liu, Junhui Yu, Jiale Wang
Abstract: With the development of multimodal large language models (MLLMs) technology, its general capabilities are increasingly powerful. To evaluate the various abilities of MLLMs, numerous evaluation systems have emerged. But now there is still a lack of a comprehensive method to evaluate MLLMs in the tasks related to flowcharts, which are very important in daily life and work. We propose the first comprehensive method, FlowCE, to assess MLLMs across various dimensions for tasks related to flowcharts. It encompasses evaluating MLLMs' abilities in Reasoning, Localization Recognition, Information Extraction, Logical Verification, and Summarization on flowcharts. However, we find that even the GPT4o model achieves only a score of 56.63. Among open-source models, Phi-3-Vision obtained the highest score of 49.97. We hope that FlowCE can contribute to future research on multimodal large language models (MLLMs) for tasks based on flowcharts. We are open-sourcing this project: \url{https://github.com/360AILAB-NLP/FlowCE}
Authors: Li Li, Khalid N. Ismail, Hubert P. H. Shum, Toby P. Breckon
Abstract: We present DurLAR, a high-fidelity 128-channel 3D LiDAR dataset with panoramic ambient (near infrared) and reflectivity imagery, as well as a sample benchmark task using depth estimation for autonomous driving applications. Our driving platform is equipped with a high resolution 128 channel LiDAR, a 2MPix stereo camera, a lux meter and a GNSS/INS system. Ambient and reflectivity images are made available along with the LiDAR point clouds to facilitate multi-modal use of concurrent ambient and reflectivity scene information. Leveraging DurLAR, with a resolution exceeding that of prior benchmarks, we consider the task of monocular depth estimation and use this increased availability of higher resolution, yet sparse ground truth scene depth information to propose a novel joint supervised/self-supervised loss formulation. We compare performance over both our new DurLAR dataset, the established KITTI benchmark and the Cityscapes dataset. Our evaluation shows our joint use supervised and self-supervised loss terms, enabled via the superior ground truth resolution and availability within DurLAR improves the quantitative and qualitative performance of leading contemporary monocular depth estimation approaches (RMSE=3.639, Sq Rel=0.936).
Authors: Moritz Kappel, Florian Hahlbohm, Timon Scholz, Susana Castillo, Christian Theobalt, Martin Eisemann, Vladislav Golyanik, Marcus Magnor
Abstract: Dynamic reconstruction and spatiotemporal novel-view synthesis of non-rigidly deforming scenes recently gained increased attention. While existing work achieves impressive quality and performance on multi-view or teleporting camera setups, most methods fail to efficiently and faithfully recover motion and appearance from casual monocular captures. This paper contributes to the field by introducing a new method for dynamic novel view synthesis from monocular video, such as casual smartphone captures. Our approach represents the scene as a $\textit{dynamic neural point cloud}$, an implicit time-conditioned point distribution that encodes local geometry and appearance in separate hash-encoded neural feature grids for static and dynamic regions. By sampling a discrete point cloud from our model, we can efficiently render high-quality novel views using a fast differentiable rasterizer and neural rendering network. Similar to recent work, we leverage advances in neural scene analysis by incorporating data-driven priors like monocular depth estimation and object segmentation to resolve motion and depth ambiguities originating from the monocular captures. In addition to guiding the optimization process, we show that these priors can be exploited to explicitly initialize our scene representation to drastically improve optimization speed and final image quality. As evidenced by our experimental evaluation, our dynamic point cloud model not only enables fast optimization and real-time frame rates for interactive applications, but also achieves competitive image quality on monocular benchmark sequences. Our project page is available at https://moritzkappel.github.io/projects/dnpc.
Authors: Gengyuan Zhang, Mang Ling Ada Fok, Yan Xia, Yansong Tang, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu
Abstract: Video understanding is a pivotal task in the digital era, yet the dynamic and multievent nature of videos makes them labor-intensive and computationally demanding to process. Thus, localizing a specific event given a semantic query has gained importance in both user-oriented applications like video search and academic research into video foundation models. A significant limitation in current research is that semantic queries are typically in natural language that depicts the semantics of the target event. This setting overlooks the potential for multimodal semantic queries composed of images and texts. To address this gap, we introduce a new benchmark, ICQ, for localizing events in videos with multimodal queries, along with a new evaluation dataset ICQ-Highlight. Our new benchmark aims to evaluate how well models can localize an event given a multimodal semantic query that consists of a reference image, which depicts the event, and a refinement text to adjust the images' semantics. To systematically benchmark model performance, we include 4 styles of reference images and 5 types of refinement texts, allowing us to explore model performance across different domains. We propose 3 adaptation methods that tailor existing models to our new setting and evaluate 10 SOTA models, ranging from specialized to large-scale foundation models. We believe this benchmark is an initial step toward investigating multimodal queries in video event localization.
Authors: Junwei Luo, Zhen Pang, Yongjun Zhang, Tingzhu Wang, Linlin Wang, Bo Dang, Jiangwei Lao, Jian Wang, Jingdong Chen, Yihua Tan, Yansheng Li
Abstract: Remote Sensing Large Multi-Modal Models (RSLMMs) are developing rapidly and showcase significant capabilities in remote sensing imagery (RSI) comprehension. However, due to the limitations of existing datasets, RSLMMs have shortcomings in understanding the rich semantic relations among objects in complex remote sensing scenes. To unlock RSLMMs' complex comprehension ability, we propose a large-scale instruction tuning dataset FIT-RS, containing 1,800,851 instruction samples. FIT-RS covers common interpretation tasks and innovatively introduces several complex comprehension tasks of escalating difficulty, ranging from relation reasoning to image-level scene graph generation. Based on FIT-RS, we build the FIT-RSFG benchmark. Furthermore, we establish a new benchmark to evaluate the fine-grained relation comprehension capabilities of LMMs, named FIT-RSRC. Based on combined instruction data, we propose SkySenseGPT, which achieves outstanding performance on both public datasets and FIT-RSFG, surpassing existing RSLMMs. We hope the FIT-RS dataset can enhance the relation comprehension capability of RSLMMs and provide a large-scale fine-grained data source for the remote sensing community. The dataset will be available at https://github.com/Luo-Z13/SkySenseGPT
Authors: Genc Hoxha, Gencer Sumbul, Julia Henkel, Lars M\"ollenbrok, Beg\"um Demir
Abstract: Deep metric learning (DML) has shown to be very effective for content-based image retrieval (CBIR) in remote sensing (RS). Most of DML methods for CBIR rely on many annotated images to accurately learn model parameters of deep neural networks. However, gathering many image annotations is time consuming and costly. To address this, we propose an annotation cost-efficient active learning (ANNEAL) method specifically designed for DML driven CBIR in RS. ANNEAL aims to create a small but informative training set made up of similar and dissimilar image pairs to be utilized for learning a deep metric space. The informativeness of the image pairs is assessed combining uncertainty and diversity criteria. To assess the uncertainty of image pairs, we introduce two algorithms: 1) metric-guided uncertainty estimation (MGUE); and 2) binary classifier guided uncertainty estimation (BCGUE). MGUE automatically estimates a threshold value that acts as a "boundary" between similar and dissimilar image pairs based on the distances in the metric space. The closer the similarity between image pairs to the estimated threshold value the higher their uncertainty. BCGUE estimates the uncertainty of the image pairs based on the confidence of the classifier in assigning the correct similarity label. The diversity criterion is assessed through a clustering-based strategy. ANNEAL selects the most informative image pairs by combining either MGUE or BCGUE with clustering-based strategy. The selected image pairs are sent to expert annotators to be labeled as similar or dissimilar. This way of annotating images significantly reduces the annotation cost compared to the cost of annotating images with LULC labels. Experimental results carried out on two RS benchmark datasets demonstrate the effectiveness of our method. The code of the proposed method will be publicly available upon the acceptance of the paper.
Authors: Xiqian Yu, Hanxin Zhu, Tianyu He, Zhibo Chen
Abstract: Achieving high-resolution novel view synthesis (HRNVS) from low-resolution input views is a challenging task due to the lack of high-resolution data. Previous methods optimize high-resolution Neural Radiance Field (NeRF) from low-resolution input views but suffer from slow rendering speed. In this work, we base our method on 3D Gaussian Splatting (3DGS) due to its capability of producing high-quality images at a faster rendering speed. To alleviate the shortage of data for higher-resolution synthesis, we propose to leverage off-the-shelf 2D diffusion priors by distilling the 2D knowledge into 3D with Score Distillation Sampling (SDS). Nevertheless, applying SDS directly to Gaussian-based 3D super-resolution leads to undesirable and redundant 3D Gaussian primitives, due to the randomness brought by generative priors. To mitigate this issue, we introduce two simple yet effective techniques to reduce stochastic disturbances introduced by SDS. Specifically, we 1) shrink the range of diffusion timestep in SDS with an annealing strategy; 2) randomly discard redundant Gaussian primitives during densification. Extensive experiments have demonstrated that our proposed GaussainSR can attain high-quality results for HRNVS with only low-resolution inputs on both synthetic and real-world datasets. Project page: https://chchnii.github.io/GaussianSR/
Authors: Daan de Geus, Gijs Dubbelman
Abstract: Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their parent object. Existing methods approach PPS by separately conducting object-level and part-level segmentation. However, their part-level predictions are not linked to individual parent objects. Therefore, their learning objective is not aligned with the PPS task objective, which harms the PPS performance. To solve this, and make more accurate PPS predictions, we propose Task-Aligned Part-aware Panoptic Segmentation (TAPPS). This method uses a set of shared queries to jointly predict (a) object-level segments, and (b) the part-level segments within those same objects. As a result, TAPPS learns to predict part-level segments that are linked to individual parent objects, aligning the learning objective with the task objective, and allowing TAPPS to leverage joint object-part representations. With experiments, we show that TAPPS considerably outperforms methods that predict objects and parts separately, and achieves new state-of-the-art PPS results.
Authors: Mehar Khurana, Neehar Peri, Deva Ramanan, James Hays
Abstract: State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. Contemporary methods adapt best-practices for self-supervised learning from the image domain to point clouds (such as contrastive learning). However, publicly available 3D datasets are considerably smaller and less diverse than those used for image-based self-supervised learning, limiting their effectiveness. We do note, however, that such data is naturally collected in a multimodal fashion, often paired with images. Rather than pre-training with only self-supervised objectives, we argue that it is better to bootstrap point cloud representations using image-based foundation models trained on internet-scale image data. Specifically, we propose a shelf-supervised approach (e.g. supervised with off-the-shelf image foundation models) for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. Pre-training 3D detectors with such pseudo-labels yields significantly better semi-supervised detection accuracy than prior self-supervised pretext tasks. Importantly, we show that image-based shelf-supervision is helpful for training LiDAR-only and multi-modal (RGB + LiDAR) detectors. We demonstrate the effectiveness of our approach on nuScenes and WOD, significantly improving over prior work in limited data settings.
Authors: Zhongyu Yang, Mai Liu, Jinluo Xie, Yueming Zhang, Chen Shen, Wei Shao, Jichao Jiao, Tengfei Xing, Runbo Hu, Pengfei Xu
Abstract: Autonomous driving without high-definition (HD) maps demands a higher level of active scene understanding. In this competition, the organizers provided the multi-perspective camera images and standard-definition (SD) maps to explore the boundaries of scene reasoning capabilities. We found that most existing algorithms construct Bird's Eye View (BEV) features from these multi-perspective images and use multi-task heads to delineate road centerlines, boundary lines, pedestrian crossings, and other areas. However, these algorithms perform poorly at the far end of roads and struggle when the primary subject in the image is occluded. Therefore, in this competition, we not only used multi-perspective images as input but also incorporated SD maps to address this issue. We employed map encoder pre-training to enhance the network's geometric encoding capabilities and utilized YOLOX to improve traffic element detection precision. Additionally, for area detection, we innovatively introduced LDTR and auxiliary tasks to achieve higher precision. As a result, our final OLUS score is 0.58.
Authors: Chen Hou, Guoqiang Wei, Yan Zeng, Zhibo Chen
Abstract: We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Unlike previous work, our method does not require any supervised finetuning on camera-annotated datasets or self-supervised training via data augmentation. Instead, it can be plugged and played with most pretrained video diffusion models and generate camera controllable videos with a single image or text prompt as input. The inspiration of our work comes from the layout prior that intermediate latents hold towards generated results, thus rearranging noisy pixels in them will make output content reallocated as well. As camera move could also be seen as a kind of pixel rearrangement caused by perspective change, videos could be reorganized following specific camera motion if their noisy latents change accordingly. Established on this, we propose our method CamTrol, which enables robust camera control for video diffusion models. It is achieved by a two-stage process. First, we model image layout rearrangement through explicit camera movement in 3D point cloud space. Second, we generate videos with camera motion using layout prior of noisy latents formed by a series of rearranged images. Extensive experiments have demonstrated the robustness our method holds in controlling camera motion of generated videos. Furthermore, we show that our method can produce impressive results in generating 3D rotation videos with dynamic content. Project page at https://lifedecoder.github.io/CamTrol/.
Authors: Adnan Md Tayeb, Mst Ayesha Khatun, Mohtasin Golam, Md Facklasur Rahaman, Ali Aouto, Oroceo Paul Angelo, Minseon Lee, Dong-Seong Kim, Jae-Min Lee, Jung-Hyeon Kim
Abstract: Precise and prompt identification of road surface conditions enables vehicles to adjust their actions, like changing speed or using specific traction control techniques, to lower the chance of accidents and potential danger to drivers and pedestrians. However, most of the existing methods for detecting road surfaces solely rely on visual data, which may be insufficient in certain situations, such as when the roads are covered by debris, in low light conditions, or in the presence of fog. Therefore, we introduce a multimodal approach for the automated detection of road surface conditions by integrating audio and images. The robustness of the proposed method is tested on a diverse dataset collected under various environmental conditions and road surface types. Through extensive evaluation, we demonstrate the effectiveness and reliability of our multimodal approach in accurately identifying road surface conditions in real-time scenarios. Our findings highlight the potential of integrating auditory and visual cues for enhancing road safety and minimizing accident risks
Authors: Mujadded Al Rabbani Alif, Muhammad Hussain
Abstract: This survey investigates the transformative potential of various YOLO variants, from YOLOv1 to the state-of-the-art YOLOv10, in the context of agricultural advancements. The primary objective is to elucidate how these cutting-edge object detection models can re-energise and optimize diverse aspects of agriculture, ranging from crop monitoring to livestock management. It aims to achieve key objectives, including the identification of contemporary challenges in agriculture, a detailed assessment of YOLO's incremental advancements, and an exploration of its specific applications in agriculture. This is one of the first surveys to include the latest YOLOv10, offering a fresh perspective on its implications for precision farming and sustainable agricultural practices in the era of Artificial Intelligence and automation. Further, the survey undertakes a critical analysis of YOLO's performance, synthesizes existing research, and projects future trends. By scrutinizing the unique capabilities packed in YOLO variants and their real-world applications, this survey provides valuable insights into the evolving relationship between YOLO variants and agriculture. The findings contribute towards a nuanced understanding of the potential for precision farming and sustainable agricultural practices, marking a significant step forward in the integration of advanced object detection technologies within the agricultural sector.
Authors: Yiwen Chen, Tong He, Di Huang, Weicai Ye, Sijin Chen, Jiaxiang Tang, Xin Chen, Zhongang Cai, Lei Yang, Gang Yu, Guosheng Lin, Chi Zhang
Abstract: Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because these assets always need to be converted to meshes for 3D industry applications, and the meshes produced by current mesh extraction methods are significantly inferior to Artist-Created Meshes (AMs), i.e., meshes created by human artists. Specifically, current mesh extraction methods rely on dense faces and ignore geometric features, leading to inefficiencies, complicated post-processing, and lower representation quality. To address these issues, we introduce MeshAnything, a model that treats mesh extraction as a generation problem, producing AMs aligned with specified shapes. By converting 3D assets in any 3D representation into AMs, MeshAnything can be integrated with various 3D asset production methods, thereby enhancing their application across the 3D industry. The architecture of MeshAnything comprises a VQ-VAE and a shape-conditioned decoder-only transformer. We first learn a mesh vocabulary using the VQ-VAE, then train the shape-conditioned decoder-only transformer on this vocabulary for shape-conditioned autoregressive mesh generation. Our extensive experiments show that our method generates AMs with hundreds of times fewer faces, significantly improving storage, rendering, and simulation efficiencies, while achieving precision comparable to previous methods.
Authors: Katrin Renz, Long Chen, Ana-Maria Marcu, Jan H\"unermann, Benoit Hanotte, Alice Karnsund, Jamie Shotton, Elahe Arani, Oleg Sinavski
Abstract: In this technical report, we present CarLLaVA, a Vision Language Model (VLM) for autonomous driving, developed for the CARLA Autonomous Driving Challenge 2.0. CarLLaVA uses the vision encoder of the LLaVA VLM and the LLaMA architecture as backbone, achieving state-of-the-art closed-loop driving performance with only camera input and without the need for complex or expensive labels. Additionally, we show preliminary results on predicting language commentary alongside the driving output. CarLLaVA uses a semi-disentangled output representation of both path predictions and waypoints, getting the advantages of the path for better lateral control and the waypoints for better longitudinal control. We propose an efficient training recipe to train on large driving datasets without wasting compute on easy, trivial data. CarLLaVA ranks 1st place in the sensor track of the CARLA Autonomous Driving Challenge 2.0 outperforming the previous state of the art by 458% and the best concurrent submission by 32.6%.
Authors: Xiaoyan Cong, Haitao Yang, Liyan Chen, Kaifeng Zhang, Li Yi, Chandrajit Bajaj, Qixing Huang
Abstract: This paper presents a novel approach 4DRecons that takes a single camera RGB-D sequence of a dynamic subject as input and outputs a complete textured deforming 3D model over time. 4DRecons encodes the output as a 4D neural implicit surface and presents an optimization procedure that combines a data term and two regularization terms. The data term fits the 4D implicit surface to the input partial observations. We address fundamental challenges in fitting a complete implicit surface to partial observations. The first regularization term enforces that the deformation among adjacent frames is as rigid as possible (ARAP). To this end, we introduce a novel approach to compute correspondences between adjacent textured implicit surfaces, which are used to define the ARAP regularization term. The second regularization term enforces that the topology of the underlying object remains fixed over time. This regularization is critical for avoiding self-intersections that are typical in implicit-based reconstructions. We have evaluated the performance of 4DRecons on a variety of datasets. Experimental results show that 4DRecons can handle large deformations and complex inter-part interactions and outperform state-of-the-art approaches considerably.
Authors: Weide Liu, Jingwen Hou, Xiaoyang Zhong, Huijing Zhan, Jun Cheng, Yuming Fang, Guanghui Yue
Abstract: Deep learning-based brain tumor segmentation (BTS) models for multi-modal MRI images have seen significant advancements in recent years. However, a common problem in practice is the unavailability of some modalities due to varying scanning protocols and patient conditions, making segmentation from incomplete MRI modalities a challenging issue. Previous methods have attempted to address this by fusing accessible multi-modal features, leveraging attention mechanisms, and synthesizing missing modalities using generative models. However, these methods ignore the intrinsic problems of medical image segmentation, such as the limited availability of training samples, particularly for cases with tumors. Furthermore, these methods require training and deploying a specific model for each subset of missing modalities. To address these issues, we propose a novel approach that enhances the BTS model from two perspectives. Firstly, we introduce a pre-training stage that generates a diverse pre-training dataset covering a wide range of different combinations of tumor shapes and brain anatomy. Secondly, we propose a post-training stage that enables the model to reconstruct missing modalities in the prediction results when only partial modalities are available. To achieve the pre-training stage, we conceptually decouple the MRI image into two parts: `anatomy' and `tumor'. We pre-train the BTS model using synthesized data generated from the anatomy and tumor parts across different training samples. ... Extensive experiments demonstrate that our proposed method significantly improves the performance over the baseline and achieves new state-of-the-art results on three brain tumor segmentation datasets: BRATS2020, BRATS2018, and BRATS2015.
Authors: Eric-Tuan L\^e, Antonis Kakolyris, Petros Koutras, Himmy Tam, Efstratios Skordos, George Papandreou, R{\i}za Alp G\"uler, Iasonas Kokkinos
Abstract: DensePose provides a pixel-accurate association of images with 3D mesh coordinates, but does not provide a 3D mesh, while Human Mesh Reconstruction (HMR) systems have high 2D reprojection error, as measured by DensePose localization metrics. In this work we introduce MeshPose to jointly tackle DensePose and HMR. For this we first introduce new losses that allow us to use weak DensePose supervision to accurately localize in 2D a subset of the mesh vertices ('VertexPose'). We then lift these vertices to 3D, yielding a low-poly body mesh ('MeshPose'). Our system is trained in an end-to-end manner and is the first HMR method to attain competitive DensePose accuracy, while also being lightweight and amenable to efficient inference, making it suitable for real-time AR applications.
Authors: Jiawei Chen, Dingkang Yang, Tong Wu, Yue Jiang, Xiaolu Hou, Mingcheng Li, Shunli Wang, Dongling Xiao, Ke Li, Lihua Zhang
Abstract: Large Vision Language Models (LVLMs) are increasingly integral to healthcare applications, including medical visual question answering and imaging report generation. While these models inherit the robust capabilities of foundational Large Language Models (LLMs), they also inherit susceptibility to hallucinations-a significant concern in high-stakes medical contexts where the margin for error is minimal. However, currently, there are no dedicated methods or benchmarks for hallucination detection and evaluation in the medical field. To bridge this gap, we introduce Med-HallMark, the first benchmark specifically designed for hallucination detection and evaluation within the medical multimodal domain. This benchmark provides multi-tasking hallucination support, multifaceted hallucination data, and hierarchical hallucination categorization. Furthermore, we propose the MediHall Score, a new medical evaluative metric designed to assess LVLMs' hallucinations through a hierarchical scoring system that considers the severity and type of hallucination, thereby enabling a granular assessment of potential clinical impacts. We also present MediHallDetector, a novel Medical LVLM engineered for precise hallucination detection, which employs multitask training for hallucination detection. Through extensive experimental evaluations, we establish baselines for popular LVLMs using our benchmark. The findings indicate that MediHall Score provides a more nuanced understanding of hallucination impacts compared to traditional metrics and demonstrate the enhanced performance of MediHallDetector. We hope this work can significantly improve the reliability of LVLMs in medical applications. All resources of this work will be released soon.
Authors: Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni, R. Venkatesh Babu, Srikrishna Karanam
Abstract: Text-to-image generation from large generative models like Stable Diffusion, DALLE-2, etc., have become a common base for various tasks due to their superior quality and extensive knowledge bases. As image composition and generation are creative processes the artists need control over various parts of the images being generated. We find that just adding details about parts in the base text prompt either leads to an entirely different image (e.g., missing/incorrect identity) or the extra part details simply being ignored. To mitigate these issues, we introduce PartCraft, which enables image generation based on fine-grained part-level details specified for objects in the base text prompt. This allows more control for artists and enables novel object compositions by combining distinctive object parts. PartCraft first localizes object parts by denoising the object region from a specific diffusion process. This enables each part token to be localized to the right object region. After obtaining part masks, we run a localized diffusion process in each of the part regions based on fine-grained part descriptions and combine them to produce the final image. All the stages of PartCraft are based on repurposing a pre-trained diffusion model, which enables it to generalize across various domains without training. We demonstrate the effectiveness of part-level control provided by PartCraft qualitatively through visual examples and quantitatively in comparison to the contemporary baselines.
Authors: Ziang Xu, Jens Rittscher, Sharib Ali
Abstract: Polyps are early cancer indicators, so assessing occurrences of polyps and their removal is critical. They are observed through a colonoscopy screening procedure that generates a stream of video frames. Segmenting polyps in their natural video screening procedure has several challenges, such as the co-existence of imaging artefacts, motion blur, and floating debris. Most existing polyp segmentation algorithms are developed on curated still image datasets that do not represent real-world colonoscopy. Their performance often degrades on video data. We propose a video polyp segmentation method that performs self-supervised learning as an auxiliary task and a spatial-temporal self-attention mechanism for improved representation learning. Our end-to-end configuration and joint optimisation of losses enable the network to learn more discriminative contextual features in videos. Our experimental results demonstrate an improvement with respect to several state-of-the-art (SOTA) methods. Our ablation study also confirms that the choice of the proposed joint end-to-end training improves network accuracy by over 3% and nearly 10% on both the Dice similarity coefficient and intersection-over-union compared to the recently proposed method PNS+ and Polyp-PVT, respectively. Results on previously unseen video data indicate that the proposed method generalises.
Authors: Zeyu Liu, Weicong Liang, Yiming Zhao, Bohan Chen, Ji Li, Yuhui Yuan
Abstract: Recently, Glyph-ByT5 has achieved highly accurate visual text rendering performance in graphic design images. However, it still focuses solely on English and performs relatively poorly in terms of visual appeal. In this work, we address these two fundamental limitations by presenting Glyph-ByT5-v2 and Glyph-SDXL-v2, which not only support accurate visual text rendering for 10 different languages but also achieve much better aesthetic quality. To achieve this, we make the following contributions: (i) creating a high-quality multilingual glyph-text and graphic design dataset consisting of more than 1 million glyph-text pairs and 10 million graphic design image-text pairs covering nine other languages, (ii) building a multilingual visual paragraph benchmark consisting of 1,000 prompts, with 100 for each language, to assess multilingual visual spelling accuracy, and (iii) leveraging the latest step-aware preference learning approach to enhance the visual aesthetic quality. With the combination of these techniques, we deliver a powerful customized multilingual text encoder, Glyph-ByT5-v2, and a strong aesthetic graphic generation model, Glyph-SDXL-v2, that can support accurate spelling in 10 different languages. We perceive our work as a significant advancement, considering that the latest DALL-E3 and Ideogram 1.0 still struggle with the multilingual visual text rendering task.
Authors: Lital Binyamin, Yoad Tewel, Hilit Segev, Eran Hirsch, Royi Rassin, Gal Chechik
Abstract: Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various applications from technical documents, to children's books to illustrating cooking recipes. Generating object-correct counts is fundamentally challenging because the generative model needs to keep a sense of separate identity for every instance of the object, even if several objects look identical or overlap, and then carry out a global computation implicitly during generation. It is still unknown if such representations exist. To address count-correct generation, we first identify features within the diffusion model that can carry the object identity information. We then use them to separate and count instances of objects during the denoising process and detect over-generation and under-generation. We fix the latter by training a model that predicts both the shape and location of a missing object, based on the layout of existing ones, and show how it can be used to guide denoising with correct object count. Our approach, CountGen, does not depend on external source to determine object layout, but rather uses the prior from the diffusion model itself, creating prompt-dependent and seed-dependent layouts. Evaluated on two benchmark datasets, we find that CountGen strongly outperforms the count-accuracy of existing baselines.
Authors: Bowen Song, Jason Hu, Zhaoxu Luo, Jeffrey A. Fessler, Liyue Shen
Abstract: Diffusion models face significant challenges when employed for large-scale medical image reconstruction in real practice such as 3D Computed Tomography (CT). Due to the demanding memory, time, and data requirements, it is difficult to train a diffusion model directly on the entire volume of high-dimensional data to obtain an efficient 3D diffusion prior. Existing works utilizing diffusion priors on single 2D image slice with hand-crafted cross-slice regularization would sacrifice the z-axis consistency, which results in severe artifacts along the z-axis. In this work, we propose a novel framework that enables learning the 3D image prior through position-aware 3D-patch diffusion score blending for reconstructing large-scale 3D medical images. To the best of our knowledge, we are the first to utilize a 3D-patch diffusion prior for 3D medical image reconstruction. Extensive experiments on sparse view and limited angle CT reconstruction show that our DiffusionBlend method significantly outperforms previous methods and achieves state-of-the-art performance on real-world CT reconstruction problems with high-dimensional 3D image (i.e., $256 \times 256 \times 500$). Our algorithm also comes with better or comparable computational efficiency than previous state-of-the-art methods.
Authors: Akshat Dave, Tianyi Zhang, Aaron Young, Ramesh Raskar, Wolfgang Heidrich, Ashok Veeraraghavan
Abstract: Photoelasticity enables full-field stress analysis in transparent objects through stress-induced birefringence. Existing techniques are limited to 2D slices and require destructively slicing the object. Recovering the internal 3D stress distribution of the entire object is challenging as it involves solving a tensor tomography problem and handling phase wrapping ambiguities. We introduce NeST, an analysis-by-synthesis approach for reconstructing 3D stress tensor fields as neural implicit representations from polarization measurements. Our key insight is to jointly handle phase unwrapping and tensor tomography using a differentiable forward model based on Jones calculus. Our non-linear model faithfully matches real captures, unlike prior linear approximations. We develop an experimental multi-axis polariscope setup to capture 3D photoelasticity and experimentally demonstrate that NeST reconstructs the internal stress distribution for objects with varying shape and force conditions. Additionally, we showcase novel applications in stress analysis, such as visualizing photoelastic fringes by virtually slicing the object and viewing photoelastic fringes from unseen viewpoints. NeST paves the way for scalable non-destructive 3D photoelastic analysis.
Authors: Alex Hanson, Allen Tu, Vasu Singla, Mayuka Jayawardhana, Matthias Zwicker, Tom Goldstein
Abstract: Recent advancements in novel view synthesis have enabled real-time rendering speeds and high reconstruction accuracy. 3D Gaussian Splatting (3D-GS), a foundational point-based parametric 3D scene representation, models scenes as large sets of 3D Gaussians. Complex scenes can comprise of millions of Gaussians, amounting to large storage and memory requirements that limit the viability of 3D-GS on devices with limited resources. Current techniques for compressing these pretrained models by pruning Gaussians rely on combining heuristics to determine which ones to remove. In this paper, we propose a principled spatial sensitivity pruning score that outperforms these approaches. It is computed as a second-order approximation of the reconstruction error on the training views with respect to the spatial parameters of each Gaussian. Additionally, we propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing the training pipeline. After pruning 88.44% of the Gaussians, we observe that our PUP 3D-GS pipeline increases the average rendering speed of 3D-GS by 2.65$\times$ while retaining more salient foreground information and achieving higher image quality metrics than previous pruning techniques on scenes from the Mip-NeRF 360, Tanks & Temples, and Deep Blending datasets.
Authors: Ridouane Ghermi, Xi Wang, Vicky Kalogeiton, Ivan Laptev
Abstract: Recent advances in vision-language models have significantly propelled video understanding. Existing datasets and tasks, however, have notable limitations. Most datasets are confined to short videos with limited events and narrow narratives. For example, datasets with instructional and egocentric videos often document the activities of one person in a single scene. Although some movie datasets offer richer content, they are often limited to short-term tasks, lack publicly available videos and frequently encounter data leakage given the use of movie forums and other resources in LLM training. To address the above limitations, we propose the Short Film Dataset (SFD) with 1,078 publicly available amateur movies, a wide variety of genres and minimal data leakage issues. SFD offers long-term story-oriented video tasks in the form of multiple-choice and open-ended question answering. Our extensive experiments emphasize the need for long-term reasoning to solve SFD tasks. Notably, we find strong signals in movie transcripts leading to the on-par performance of people and LLMs. We also show significantly lower performance of current models compared to people when using vision data alone.
Authors: Julian Straub, Daniel DeTone, Tianwei Shen, Nan Yang, Chris Sweeney, Richard Newcombe
Abstract: The advent of wearable computers enables a new source of context for AI that is embedded in egocentric sensor data. This new egocentric data comes equipped with fine-grained 3D location information and thus presents the opportunity for a novel class of spatial foundation models that are rooted in 3D space. To measure progress on what we term Egocentric Foundation Models (EFMs) we establish EFM3D, a benchmark with two core 3D egocentric perception tasks. EFM3D is the first benchmark for 3D object detection and surface regression on high quality annotated egocentric data of Project Aria. We propose Egocentric Voxel Lifting (EVL), a baseline for 3D EFMs. EVL leverages all available egocentric modalities and inherits foundational capabilities from 2D foundation models. This model, trained on a large simulated dataset, outperforms existing methods on the EFM3D benchmark.
Authors: Zhaoxu Luo, Bowen Song, Liyue Shen
Abstract: During the acquisition of satellite images, there is generally a trade-off between spatial resolution and temporal resolution (acquisition frequency) due to the onboard sensors of satellite imaging systems. High-resolution satellite images are very important for land crop monitoring, urban planning, wildfire management and a variety of applications. It is a significant yet challenging task to achieve high spatial-temporal resolution in satellite imaging. With the advent of diffusion models, we can now learn strong generative priors to generate realistic satellite images with high resolution, which can be utilized to promote the super-resolution task as well. In this work, we propose a novel diffusion-based fusion algorithm called \textbf{SatDiffMoE} that can take an arbitrary number of sequential low-resolution satellite images at the same location as inputs, and fuse them into one high-resolution reconstructed image with more fine details, by leveraging and fusing the complementary information from different time points. Our algorithm is highly flexible and allows training and inference on arbitrary number of low-resolution images. Experimental results show that our proposed SatDiffMoE method not only achieves superior performance for the satellite image super-resolution tasks on a variety of datasets, but also gets an improved computational efficiency with reduced model parameters, compared with previous methods.
Authors: Kevin Qinghong Lin, Linjie Li, Difei Gao, Qinchen WU, Mingyi Yan, Zhengyuan Yang, Lijuan Wang, Mike Zheng Shou
Abstract: Graphical User Interface (GUI) automation holds significant promise for enhancing human productivity by assisting with computer tasks. Existing task formulations primarily focus on simple tasks that can be specified by a single, language-only instruction, such as "Insert a new slide." In this work, we introduce VideoGUI, a novel multi-modal benchmark designed to evaluate GUI assistants on visual-centric GUI tasks. Sourced from high-quality web instructional videos, our benchmark focuses on tasks involving professional and novel software (e.g., Adobe Photoshop or Stable Diffusion WebUI) and complex activities (e.g., video editing). VideoGUI evaluates GUI assistants through a hierarchical process, allowing for identification of the specific levels at which they may fail: (i) high-level planning: reconstruct procedural subtasks from visual conditions without language descriptions; (ii) middle-level planning: generate sequences of precise action narrations based on visual state (i.e., screenshot) and goals; (iii) atomic action execution: perform specific actions such as accurately clicking designated elements. For each level, we design evaluation metrics across individual dimensions to provide clear signals, such as individual performance in clicking, dragging, typing, and scrolling for atomic action execution. Our evaluation on VideoGUI reveals that even the SoTA large multimodal model GPT4o performs poorly on visual-centric GUI tasks, especially for high-level planning.
Authors: Chenyu Zhou, Mengdan Zhang, Peixian Chen, Chaoyou Fu, Yunhang Shen, Xiawu Zheng, Xing Sun, Rongrong Ji
Abstract: The swift progress of Multi-modal Large Models (MLLMs) has showcased their impressive ability to tackle tasks blending vision and language. Yet, most current models and benchmarks cater to scenarios with a narrow scope of visual and textual contexts. These models often fall short when faced with complex comprehension tasks, which involve navigating through a plethora of irrelevant and potentially misleading information in both text and image forms. To bridge this gap, we introduce a new, more demanding task known as Interleaved Image-Text Comprehension (IITC). This task challenges models to discern and disregard superfluous elements in both images and text to accurately answer questions and to follow intricate instructions to pinpoint the relevant image. In support of this task, we further craft a new VEGA dataset, tailored for the IITC task on scientific content, and devised a subtask, Image-Text Association (ITA), to refine image-text correlation skills. Our evaluation of four leading closed-source models, as well as various open-source models using VEGA, underscores the rigorous nature of IITC. Even the most advanced models, such as Gemini-1.5-pro and GPT4V, only achieved modest success. By employing a multi-task, multi-scale post-training strategy, we have set a robust baseline for MLLMs on the IITC task, attaining an $85.8\%$ accuracy rate in image association and a $0.508$ Rouge score. These results validate the effectiveness of our dataset in improving MLLMs capabilities for nuanced image-text comprehension.
Authors: Zekai Chen, Arda Pekis, Kevin Brown
Abstract: Multi-modal learning has significantly advanced generative AI, especially in vision-language modeling. Innovations like GPT-4V and open-source projects such as LLaVA have enabled robust conversational agents capable of zero-shot task completions. However, applying these technologies in the biomedical field presents unique challenges. Recent initiatives like LLaVA-Med have started to adapt instruction-tuning for biomedical contexts using large datasets such as PMC-15M. Our research offers three key contributions: (i) we present a new instruct dataset enriched with medical image-text pairs from Claude3-Opus and LLaMA3 70B, (ii) we propose a novel image encoding strategy using hierarchical representations to improve fine-grained biomedical visual comprehension, and (iii) we develop the Llama3-Med model, which achieves state-of-the-art zero-shot performance on biomedical visual question answering benchmarks, with an average performance improvement of over 10% compared to previous methods. These advancements provide more accurate and reliable tools for medical professionals, bridging gaps in current multi-modal conversational assistants and promoting further innovations in medical AI.
Authors: Ziyan Wang, Hao Wang
Abstract: Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from mice (as a source domain) and humans (as a target domain). Unfortunately, adapting a contextual bandit algorithm from a source domain to a target domain with distribution shift still remains a major challenge and largely unexplored. In this paper, we introduce the first general domain adaptation method for contextual bandits. Our approach learns a bandit model for the target domain by collecting feedback from the source domain. Our theoretical analysis shows that our algorithm maintains a sub-linear regret bound even adapting across domains. Empirical results show that our approach outperforms the state-of-the-art contextual bandit algorithms on real-world datasets.
Authors: Thibaut Issenhuth, Ludovic Dos Santos, Jean-Yves Franceschi, Alain Rakotomamonjy
Abstract: Consistency models are promising generative models as they distill the multi-step sampling of score-based diffusion in a single forward pass of a neural network. Without access to sampling trajectories of a pre-trained diffusion model, consistency training relies on proxy trajectories built on an independent coupling between the noise and data distributions. Refining this coupling is a key area of improvement to make it more adapted to the task and reduce the resulting randomness in the training process. In this work, we introduce a novel coupling associating the input noisy data with their generated output from the consistency model itself, as a proxy to the inaccessible diffusion flow output. Our affordable approach exploits the inherent capacity of consistency models to compute the transport map in a single step. We provide intuition and empirical evidence of the relevance of our generator-induced coupling (GC), which brings consistency training closer to score distillation. Consequently, our method not only accelerates consistency training convergence by significant amounts but also enhances the resulting performance. The code is available at: https://github.com/thibautissenhuth/consistency_GC.
Authors: Alexander Gao, Maurice Chu, Mubbasir Kapadia, Ming C. Lin, Hsueh-Ti Derek Liu
Abstract: Vector fields are widely used to represent and model flows for many science and engineering applications. This paper introduces a novel neural network architecture for learning tangent vector fields that are intrinsically defined on manifold surfaces embedded in 3D. Previous approaches to learning vector fields on surfaces treat vectors as multi-dimensional scalar fields, using traditional scalar-valued architectures to process channels individually, thus fail to preserve fundamental intrinsic properties of the vector field. The core idea of this work is to introduce a trainable vector heat diffusion module to spatially propagate vector-valued feature data across the surface, which we incorporate into our proposed architecture that consists of vector-valued neurons. Our architecture is invariant to rigid motion of the input, isometric deformation, and choice of local tangent bases, and is robust to discretizations of the surface. We evaluate our Vector Heat Network on triangle meshes, and empirically validate its invariant properties. We also demonstrate the effectiveness of our method on the useful industrial application of quadrilateral mesh generation.
Authors: Freda Shi
Abstract: Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers of the same language. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and generalize to sentences that contain unseen words. Motivated by human language learning, in this dissertation, we consider a family of machine learning tasks that aim to learn language structures through grounding. We seek distant supervision from other data sources (i.e., grounds), including but not limited to other modalities (e.g., vision), execution results of programs, and other languages. We demonstrate the potential of this task formulation and advocate for its adoption through three schemes. In Part I, we consider learning syntactic parses through visual grounding. We propose the task of visually grounded grammar induction, present the first models to induce syntactic structures from visually grounded text and speech, and find that the visual grounding signals can help improve the parsing quality over language-only models. As a side contribution, we propose a novel evaluation metric that enables the evaluation of speech parsing without text or automatic speech recognition systems involved. In Part II, we propose two execution-aware methods to map sentences into corresponding semantic structures (i.e., programs), significantly improving compositional generalization and few-shot program synthesis. In Part III, we propose methods that learn language structures from annotations in other languages. Specifically, we propose a method that sets a new state of the art on cross-lingual word alignment. We then leverage the learned word alignments to improve the performance of zero-shot cross-lingual dependency parsing, by proposing a novel substructure-based projection method that preserves structural knowledge learned from the source language.
Authors: Conghao Xiong, Hao Chen, Hao Zheng, Dong Wei, Yefeng Zheng, Joseph J. Y. Sung, Irwin King
Abstract: Survival analysis, as a challenging task, requires integrating Whole Slide Images (WSIs) and genomic data for comprehensive decision-making. There are two main challenges in this task: significant heterogeneity and complex inter- and intra-modal interactions between the two modalities. Previous approaches utilize co-attention methods, which fuse features from both modalities only once after separate encoding. However, these approaches are insufficient for modeling the complex task due to the heterogeneous nature between the modalities. To address these issues, we propose a Biased Progressive Encoding (BPE) paradigm, performing encoding and fusion simultaneously. This paradigm uses one modality as a reference when encoding the other. It enables deep fusion of the modalities through multiple alternating iterations, progressively reducing the cross-modal disparities and facilitating complementary interactions. Besides modality heterogeneity, survival analysis involves various biomarkers from WSIs, genomics, and their combinations. The critical biomarkers may exist in different modalities under individual variations, necessitating flexible adaptation of the models to specific scenarios. Therefore, we further propose a Mixture of Multimodal Experts (MoME) layer to dynamically selects tailored experts in each stage of the BPE paradigm. Experts incorporate reference information from another modality to varying degrees, enabling a balanced or biased focus on different modalities during the encoding process. Extensive experimental results demonstrate the superior performance of our method on various datasets, including TCGA-BLCA, TCGA-UCEC and TCGA-LUAD. Codes are available at https://github.com/BearCleverProud/MoME.
Authors: Teli Ma, Jiaming Zhou, Zifan Wang, Ronghe Qiu, Junwei Liang
Abstract: Developing robots capable of executing various manipulation tasks, guided by natural language instructions and visual observations of intricate real-world environments, remains a significant challenge in robotics. Such robot agents need to understand linguistic commands and distinguish between the requirements of different tasks. In this work, we present Sigma-Agent, an end-to-end imitation learning agent for multi-task robotic manipulation. Sigma-Agent incorporates contrastive Imitation Learning (contrastive IL) modules to strengthen vision-language and current-future representations. An effective and efficient multi-view querying Transformer (MVQ-Former) for aggregating representative semantic information is introduced. Sigma-Agent shows substantial improvement over state-of-the-art methods under diverse settings in 18 RLBench tasks, surpassing RVT by an average of 5.2% and 5.9% in 10 and 100 demonstration training, respectively. Sigma-Agent also achieves 62% success rate with a single policy in 5 real-world manipulation tasks. The code will be released upon acceptance.
Authors: Esmaeil S. Nadimi, Jan-Matthias Braun, Benedicte Schelde-Olesen, Emile Prudhomme, Victoria Blanes-Vidal, Gunnar Baatrup
Abstract: Despite recent surge of interest in deploying colon capsule endoscopy (CCE) for early diagnosis of colorectal diseases, there remains a large gap between the current state of CCE in clinical practice, and the state of its counterpart optical colonoscopy (OC). Our study is aimed at closing this gap, by focusing on the full integration of AI in CCE's pathway, where image processing steps linked to the detection, localization and characterisation of important findings are carried out autonomously using various AI algorithms. We developed a recognition network, that with an impressive sensitivity of 99.9%, a specificity of 99.4%, and a negative predictive value (NPV) of 99.8%, detected colorectal polyps. After recognising a polyp within a sequence of images, only those images containing polyps were fed into two parallel independent networks for characterisation, and estimation of the size of those important findings. The characterisation network reached a sensitivity of 82% and a specificity of 80% in classifying polyps to two groups, namely neoplastic vs. non-neoplastic. The size estimation network reached an accuracy of 88% in correctly segmenting the polyps. By automatically incorporating this crucial information into CCE's pathway, we moved a step closer towards the full integration of AI in CCE's routine clinical practice.
Authors: Jingtao Cao, Zheng Zhang, Hongru Wang, Bin Liang, Hao Wang, Kam-Fai Wong
Abstract: Memes, which rapidly disseminate personal opinions and positions across the internet, also pose significant challenges in propagating social bias and prejudice. This study presents a novel approach to detecting harmful memes, particularly within the multicultural and multilingual context of Singapore. Our methodology integrates image captioning, Optical Character Recognition (OCR), and Large Language Model (LLM) analysis to comprehensively understand and classify harmful memes. Utilizing the BLIP model for image captioning, PP-OCR and TrOCR for text recognition across multiple languages, and the Qwen LLM for nuanced language understanding, our system is capable of identifying harmful content in memes created in English, Chinese, Malay, and Tamil. To enhance the system's performance, we fine-tuned our approach by leveraging additional data labeled using GPT-4V, aiming to distill the understanding capability of GPT-4V for harmful memes to our system. Our framework achieves top-1 at the public leaderboard of the Online Safety Prize Challenge hosted by AI Singapore, with the AUROC as 0.7749 and accuracy as 0.7087, significantly ahead of the other teams. Notably, our approach outperforms previous benchmarks, with FLAVA achieving an AUROC of 0.5695 and VisualBERT an AUROC of 0.5561.
Authors: Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi, Shuqiang Jiang
Abstract: Vision-and-language navigation (VLN) enables the agent to navigate to a remote location in 3D environments following the natural language instruction. In this field, the agent is usually trained and evaluated in the navigation simulators, lacking effective approaches for sim-to-real transfer. The VLN agents with only a monocular camera exhibit extremely limited performance, while the mainstream VLN models trained with panoramic observation, perform better but are difficult to deploy on most monocular robots. For this case, we propose a sim-to-real transfer approach to endow the monocular robots with panoramic traversability perception and panoramic semantic understanding, thus smoothly transferring the high-performance panoramic VLN models to the common monocular robots. In this work, the semantic traversable map is proposed to predict agent-centric navigable waypoints, and the novel view representations of these navigable waypoints are predicted through the 3D feature fields. These methods broaden the limited field of view of the monocular robots and significantly improve navigation performance in the real world. Our VLN system outperforms previous SOTA monocular VLN methods in R2R-CE and RxR-CE benchmarks within the simulation environments and is also validated in real-world environments, providing a practical and high-performance solution for real-world VLN.
Authors: Zhenzhou Jin, Li You, Jue Wang, Xiang-Gen Xia, Xiqi Gao
Abstract: Channel knowledge map (CKM) has received widespread attention as an emerging enabling technology for environment-aware wireless communications. It involves the construction of databases containing location-specific channel knowledge, which are then leveraged to facilitate channel state information (CSI) acquisition and transceiver design. In this context, a fundamental challenge lies in efficiently constructing the CKM based on a given wireless propagation environment. Most existing methods are based on stochastic modeling and sequence prediction, which do not fully exploit the inherent physical characteristics of the propagation environment, resulting in low accuracy and high computational complexity. To address these limitations, we propose a Laplacian pyramid (LP)-based CKM construction scheme to predict the channel knowledge at arbitrary locations in a targeted area. Specifically, we first view the channel knowledge as a 2-D image and transform the CKM construction problem into an image-to-image (I2I) inpainting task, which predicts the channel knowledge at a specific location by recovering the corresponding pixel value in the image matrix. Then, inspired by the reversible and closed-form structure of the LP, we show its natural suitability for our task in designing a fast I2I mapping network. For different frequency components of LP decomposition, we design tailored networks accordingly. Besides, to encode the global structural information of the propagation environment, we introduce self-attention and cross-covariance attention mechanisms in different layers, respectively. Finally, experimental results show that the proposed scheme outperforms the benchmark, achieving higher reconstruction accuracy while with lower computational complexity. Moreover, the proposed approach has a strong generalization ability and can be implemented in different wireless communication scenarios.
Authors: Heejun Lee, Geon Park, Youngwan Lee, Jina Kim, Wonyoung Jeong, Myeongjae Jeon, Sung Ju Hwang
Abstract: In modern large language models (LLMs), increasing sequence lengths is a crucial challenge for enhancing their comprehension and coherence in handling complex tasks such as multi-modal question answering. However, handling long context sequences with LLMs is prohibitively costly due to the conventional attention mechanism's quadratic time and space complexity, and the context window size is limited by the GPU memory. Although recent works have proposed linear and sparse attention mechanisms to address this issue, their real-world applicability is often limited by the need to re-train pre-trained models. In response, we propose a novel approach, Hierarchically Pruned Attention (HiP), which simultaneously reduces the training and inference time complexity from $O(T^2)$ to $O(T \log T)$ and the space complexity from $O(T^2)$ to $O(T)$. To this end, we devise a dynamic sparse attention mechanism that generates an attention mask through a novel tree-search-like algorithm for a given query on the fly. HiP is training-free as it only utilizes the pre-trained attention scores to spot the positions of the top-$k$ most significant elements for each query. Moreover, it ensures that no token is overlooked, unlike the sliding window-based sub-quadratic attention methods, such as StreamingLLM. Extensive experiments on diverse real-world benchmarks demonstrate that HiP significantly reduces prompt (i.e., prefill) and decoding latency and memory usage while maintaining high generation performance with little or no degradation. As HiP allows pretrained LLMs to scale to millions of tokens on commodity GPUs with no additional engineering due to its easy plug-and-play deployment, we believe that our work will have a large practical impact, opening up the possibility to many long-context LLM applications previously infeasible.
Authors: Wei Wei, Tom De Schepper, Kevin Mets
Abstract: Dataset condensation (DC) methods aim to learn a smaller synthesized dataset with informative data records to accelerate the training of machine learning models. Current distribution matching (DM) based DC methods learn a synthesized dataset by matching the mean of the latent embeddings between the synthetic and the real dataset. However two distributions with the same mean can still be vastly different. In this work we demonstrate the shortcomings of using Maximum Mean Discrepancy to match latent distributions i.e. the weak matching power and lack of outlier regularization. To alleviate these shortcomings we propose our new method: Latent Quantile Matching (LQM) which matches the quantiles of the latent embeddings to minimize the goodness of fit test statistic between two distributions. Empirical experiments on both image and graph-structured datasets show that LQM matches or outperforms previous state of the art in distribution matching based DC. Moreover we show that LQM improves the performance in continual graph learning (CGL) setting where memory efficiency and privacy can be important. Our work sheds light on the application of DM based DC for CGL.
Authors: Grigor Bezirganyan, Sana Sellami, Laure Berti-\'Equille, S\'ebastien Fournier
Abstract: Multimodal Deep Learning enhances decision-making by integrating diverse information sources, such as texts, images, audio, and videos. To develop trustworthy multimodal approaches, it is essential to understand how uncertainty impacts these models. We introduce LUMA, a unique benchmark dataset, featuring audio, image, and textual data from 50 classes, for learning from uncertain and multimodal data. It extends the well-known CIFAR 10/100 dataset with audio samples extracted from three audio corpora, and text data generated using the Gemma-7B Large Language Model (LLM). The LUMA dataset enables the controlled injection of varying types and degrees of uncertainty to achieve and tailor specific experiments and benchmarking initiatives. LUMA is also available as a Python package including the functions for generating multiple variants of the dataset with controlling the diversity of the data, the amount of noise for each modality, and adding out-of-distribution samples. A baseline pre-trained model is also provided alongside three uncertainty quantification methods: Monte-Carlo Dropout, Deep Ensemble, and Reliable Conflictive Multi-View Learning. This comprehensive dataset and its tools are intended to promote and support the development and benchmarking of trustworthy and robust multimodal deep learning approaches.
Authors: Weijie Tu, Weijian Deng, Liang Zheng, Tom Gedeon
Abstract: This work aims to develop a measure that can accurately rank the performance of various classifiers when they are tested on unlabeled data from out-of-distribution (OOD) distributions. We commence by demonstrating that conventional uncertainty metrics, notably the maximum Softmax prediction probability, possess inherent utility in forecasting model generalization across certain OOD contexts. Building on this insight, we introduce a new measure called Softmax Correlation (SoftmaxCorr). It calculates the cosine similarity between a class-class correlation matrix, constructed from Softmax output vectors across an unlabeled test dataset, and a predefined reference matrix that embodies ideal class correlations. A high resemblance of predictions to the reference matrix signals that the model delivers confident and uniform predictions across all categories, reflecting minimal uncertainty and confusion. Through rigorous evaluation across a suite of datasets, including ImageNet, CIFAR-10, and WILDS, we affirm the predictive validity of SoftmaxCorr in accurately forecasting model performance within both in-distribution (ID) and OOD settings. Furthermore, we discuss the limitations of our proposed measure and suggest avenues for future research.
Authors: Yifei Chen, Zhu Zhu, Shenghao Zhu, Linwei Qiu, Binfeng Zou, Fan Jia, Yunpeng Zhu, Chenyan Zhang, Zhaojie Fang, Feiwei Qin, Jin Fan, Changmiao Wang, Yu Gao, Gang Yu
Abstract: The incidence and mortality rates of malignant tumors, such as acute leukemia, have risen significantly. Clinically, hospitals rely on cytological examination of peripheral blood and bone marrow smears to diagnose malignant tumors, with accurate blood cell counting being crucial. Existing automated methods face challenges such as low feature expression capability, poor interpretability, and redundant feature extraction when processing high-dimensional microimage data. We propose a novel fine-grained classification model, SCKansformer, for bone marrow blood cells, which addresses these challenges and enhances classification accuracy and efficiency. The model integrates the Kansformer Encoder, SCConv Encoder, and Global-Local Attention Encoder. The Kansformer Encoder replaces the traditional MLP layer with the KAN, improving nonlinear feature representation and interpretability. The SCConv Encoder, with its Spatial and Channel Reconstruction Units, enhances feature representation and reduces redundancy. The Global-Local Attention Encoder combines Multi-head Self-Attention with a Local Part module to capture both global and local features. We validated our model using the Bone Marrow Blood Cell Fine-Grained Classification Dataset (BMCD-FGCD), comprising over 10,000 samples and nearly 40 classifications, developed with a partner hospital. Comparative experiments on our private dataset, as well as the publicly available PBC and ALL-IDB datasets, demonstrate that SCKansformer outperforms both typical and advanced microcell classification methods across all datasets. Our source code and private BMCD-FGCD dataset are available at https://github.com/JustlfC03/SCKansformer.
Authors: Chufan Shi, Cheng Yang, Yaxin Liu, Bo Shui, Junjie Wang, Mohan Jing, Linran Xu, Xinyu Zhu, Siheng Li, Yuxiang Zhang, Gongye Liu, Xiaomei Nie, Deng Cai, Yujiu Yang
Abstract: We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 1,000 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains(e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 191 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of 3 proprietary models and 11 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4V, Claude-3-opus only achieve an average score of 73.2 and 53.7, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence.
Authors: Zhiyan Bo, Laura C. Coates, Bartlomiej W. Papiez
Abstract: The van der Heijde modification of the Sharp (SvdH) score is a widely used radiographic scoring method to quantify damage in Rheumatoid Arthritis (RA) in clinical trials. However, its complexity with a necessity to score each individual joint, and the expertise required limit its application in clinical practice, especially in disease progression measurement. In this work, we addressed this limitation by developing a bespoke, automated pipeline that is capable of predicting the SvdH score and RA severity from hand radiographs without the need to localise the joints first. Using hand radiographs from RA and suspected RA patients, we first investigated the performance of the state-of-the-art architectures in predicting the total SvdH score for hands and wrists and its corresponding severity class. Secondly, we leveraged publicly available data sets to perform transfer learning with different finetuning schemes and ensemble learning, which resulted in substantial improvement in model performance being on par with an experienced human reader. The best model for RA scoring achieved a Pearson's correlation coefficient (PCC) of 0.925 and root mean squared error (RMSE) of 18.02, while the best model for RA severity classification achieved an accuracy of 0.358 and PCC of 0.859. Our score prediction model attained almost comparable accuracy with experienced radiologists (PCC = 0.97, RMSE = 18.75). Finally, using Grad-CAM, we showed that our models could focus on the anatomical structures in hands and wrists which clinicians deemed as relevant to RA progression in the majority of cases.
Authors: Lenka T\v{e}tkov\'a, Erik Schou Dreier, Robin Malm, Lars Kai Hansen
Abstract: Much machine learning research progress is based on developing models and evaluating them on a benchmark dataset (e.g., ImageNet for images). However, applying such benchmark-successful methods to real-world data often does not work as expected. This is particularly the case for biological data where we expect variability at multiple time and spatial scales. In this work, we are using grain data and the goal is to detect diseases and damages. Pink fusarium, skinned grains, and other diseases and damages are key factors in setting the price of grains or excluding dangerous grains from food production. Apart from challenges stemming from differences of the data from the standard toy datasets, we also present challenges that need to be overcome when explaining deep learning models. For example, explainability methods have many hyperparameters that can give different results, and the ones published in the papers do not work on dissimilar images. Other challenges are more general: problems with visualization of the explanations and their comparison since the magnitudes of their values differ from method to method. An open fundamental question also is: How to evaluate explanations? It is a non-trivial task because the "ground truth" is usually missing or ill-defined. Also, human annotators may create what they think is an explanation of the task at hand, yet the machine learning model might solve it in a different and perhaps counter-intuitive way. We discuss several of these challenges and evaluate various post-hoc explainability methods on grain data. We focus on robustness, quality of explanations, and similarity to particular "ground truth" annotations made by experts. The goal is to find the methods that overall perform well and could be used in this challenging task. We hope the proposed pipeline will be used as a framework for evaluating explainability methods in specific use cases.
Authors: Mikhail Gorbunov, Nikolay Yudin, Vera Soboleva, Aibek Alanov, Alexey Naumov, Maxim Rakhuba
Abstract: The increasing size of neural networks has led to a growing demand for methods of efficient fine-tuning. Recently, an orthogonal fine-tuning paradigm was introduced that uses orthogonal matrices for adapting the weights of a pretrained model. In this paper, we introduce a new class of structured matrices, which unifies and generalizes structured classes from previous works. We examine properties of this class and build a structured orthogonal parametrization upon it. We then use this parametrization to modify the orthogonal fine-tuning framework, improving parameter and computational efficiency. We empirically validate our method on different domains, including adapting of text-to-image diffusion models and downstream task fine-tuning in language modeling. Additionally, we adapt our construction for orthogonal convolutions and conduct experiments with 1-Lipschitz neural networks.
Authors: Andrew Rouditchenko, Yuan Gong, Samuel Thomas, Leonid Karlinsky, Hilde Kuehne, Rogerio Feris, James Glass
Abstract: Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast, speech models such as Whisper are trained with hundreds of thousands of hours of data, and thus learn a better speech-to-text decoder. The huge training data difference motivates us to adapt Whisper to handle video inputs. Inspired by Flamingo which injects visual features into language models, we propose Whisper-Flamingo which integrates visual features into the Whisper speech recognition and translation model with gated cross attention. Our audio-visual Whisper-Flamingo outperforms audio-only Whisper on English speech recognition and En-X translation for 6 languages in noisy conditions. Moreover, Whisper-Flamingo is a versatile model and conducts all of these tasks using one set of parameters, while prior methods are trained separately on each language.
Authors: Haresh Rengaraj Rajamohan, Richard Kijowski, Kyunghyun Cho, Cem M. Deniz
Abstract: Current methods for predicting osteoarthritis (OA) outcomes do not incorporate disease specific prior knowledge to improve the outcome prediction models. We developed a novel approach that effectively uses consecutive imaging studies to improve OA outcome predictions by incorporating an OA severity constraint. This constraint ensures that the risk of OA for a knee should either increase or remain the same over time. DL models were trained to predict TKR within multiple time periods (1 year, 2 years, and 4 years) using knee radiographs and MRI scans. Models with and without the risk constraint were evaluated using the area under the receiver operator curve (AUROC) and the area under the precision recall curve (AUPRC) analysis. The novel RiskFORM2 method, leveraging a dual model risk constraint architecture, demonstrated superior performance, yielding an AUROC of 0.87 and AUPRC of 0.47 for 1 year TKR prediction on the OAI radiograph test set, a marked improvement over the 0.79 AUROC and 0.34 AUPRC of the baseline approach. The performance advantage extended to longer followup periods, with RiskFORM2 maintaining a high AUROC of 0.86 and AUPRC of 0.75 in predicting TKR within 4 years. Additionally, when generalizing to the external MOST radiograph test set, RiskFORM2 generalized better with an AUROC of 0.77 and AUPRC of 0.25 for 1 year predictions, which was higher than the 0.71 AUROC and 0.19 AUPRC of the baseline approach. In the MRI test sets, similar patterns emerged, with RiskFORM2 outperforming the baseline approach consistently. However, RiskFORM1 exhibited the highest AUROC of 0.86 and AUPRC of 0.72 for 4 year predictions on the OAI set.
Authors: Stanislav Dereka, Ivan Karpukhin, Maksim Zhdanov, Sergey Kolesnikov
Abstract: Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection. However, their effectiveness is limited due to the homogeneity of learned patterns within ensembles. To overcome this issue, our study introduces Saliency Diversified Deep Ensemble (SDDE), a novel approach that promotes diversity among ensemble members by leveraging saliency maps. Through incorporating saliency map diversification, our method outperforms conventional ensemble techniques and improves calibration in multiple classification and OOD detection tasks. In particular, the proposed method achieves state-of-the-art OOD detection quality, calibration, and accuracy on multiple benchmarks, including CIFAR10/100 and large-scale ImageNet datasets.
Authors: Dachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang
Abstract: Recent vision-language models have achieved tremendous advances. However, their computational costs are also escalating dramatically, making model acceleration exceedingly critical. To pursue more efficient vision-language Transformers, this paper introduces Cross-Guided Ensemble of Tokens (CrossGET), a general acceleration framework for vision-language Transformers. This framework adaptively combines tokens in real-time during inference, significantly reducing computational costs while maintaining high performance. CrossGET features two primary innovations: 1) Cross-Guided Matching and Ensemble. CrossGET leverages cross-modal guided token matching and ensemble to effectively utilize cross-modal information, achieving wider applicability across both modality-independent models, e.g., CLIP, and modality-dependent ones, e.g., BLIP2. 2) Complete-Graph Soft Matching. CrossGET introduces an algorithm for the token-matching mechanism, ensuring reliable matching results while facilitating parallelizability and high efficiency. Extensive experiments have been conducted on various vision-language tasks, such as image-text retrieval, visual reasoning, image captioning, and visual question answering. The performance on both classic multimodal architectures and emerging multimodal LLMs demonstrates the framework's effectiveness and versatility. The code is available at https://github.com/sdc17/CrossGET.
Authors: Guilherme Schardong, Tiago Novello, Hallison Paz, Iurii Medvedev, Vin\'icius da Silva, Luiz Velho, Nuno Gon\c{c}alves
Abstract: Face morphing is a problem in computer graphics with numerous artistic and forensic applications. It is challenging due to variations in pose, lighting, gender, and ethnicity. This task consists of a warping for feature alignment and a blending for a seamless transition between the warped images. We propose to leverage coord-based neural networks to represent such warpings and blendings of face images. During training, we exploit the smoothness and flexibility of such networks by combining energy functionals employed in classical approaches without discretizations. Additionally, our method is time-dependent, allowing a continuous warping/blending of the images. During morphing inference, we need both direct and inverse transformations of the time-dependent warping. The first (second) is responsible for warping the target (source) image into the source (target) image. Our neural warping stores those maps in a single network dismissing the need for inverting them. The results of our experiments indicate that our method is competitive with both classical and generative models under the lens of image quality and face-morphing detectors. Aesthetically, the resulting images present a seamless blending of diverse faces not yet usual in the literature.
Authors: Yake Wei, Ruoxuan Feng, Zihe Wang, Di Hu
Abstract: One primary topic of multimodal learning is to jointly incorporate heterogeneous information from different modalities. However most models often suffer from unsatisfactory multimodal cooperation which cannot jointly utilize all modalities well. Some methods are proposed to identify and enhance the worse learnt modality but they are often hard to provide the fine-grained observation of multimodal cooperation at sample-level with theoretical support. Hence it is essential to reasonably observe and improve the fine-grained cooperation between modalities especially when facing realistic scenarios where the modality discrepancy could vary across different samples. To this end we introduce a sample-level modality valuation metric to evaluate the contribution of each modality for each sample. Via modality valuation we observe that modality discrepancy indeed could be different at sample-level beyond the global contribution discrepancy at dataset-level. We further analyze this issue and improve cooperation between modalities at sample-level by enhancing the discriminative ability of low-contributing modalities in a targeted manner. Overall our methods reasonably observe the fine-grained uni-modal contribution and achieve considerable improvement. The source code and dataset are available at https://github.com/GeWu-Lab/Valuate-and-Enhance-Multimodal-Cooperation.
URLs: https://github.com/GeWu-Lab/Valuate-and-Enhance-Multimodal-Cooperation.
Authors: Rebecca S. Stone, Pedro E. Chavarrias-Solano, Andrew J. Bulpitt, David C. Hogg, Sharib Ali
Abstract: While several previous studies have devised methods for segmentation of polyps, most of these methods are not rigorously assessed on multi-center datasets. Variability due to appearance of polyps from one center to another, difference in endoscopic instrument grades, and acquisition quality result in methods with good performance on in-distribution test data, and poor performance on out-of-distribution or underrepresented samples. Unfair models have serious implications and pose a critical challenge to clinical applications. We adapt an implicit bias mitigation method which leverages Bayesian predictive uncertainties during training to encourage the model to focus on underrepresented sample regions. We demonstrate the potential of this approach to improve generalisability without sacrificing state-of-the-art performance on a challenging multi-center polyp segmentation dataset (PolypGen) with different centers and image modalities.
Authors: Muhammad Hamza Asad, Saeed Anwar, Abdul Bais
Abstract: Modern agriculture heavily relies on Site-Specific Farm Management practices, necessitating accurate detection, localization, and quantification of crops and weeds in the field, which can be achieved using deep learning techniques. In this regard, crop and weed-specific binary segmentation models have shown promise. However, uncontrolled field conditions limit their performance from one field to the other. To improve semantic model generalization, existing methods augment and synthesize agricultural data to account for uncontrolled field conditions. However, given highly varied field conditions, these methods have limitations. To overcome the challenges of model deterioration in such conditions, we propose utilizing data specific to other crops and weeds for our specific target problem. To achieve this, we propose a novel ensemble framework. Our approach involves utilizing different crop and weed models trained on diverse datasets and employing a teacher-student configuration. By using homogeneous stacking of base models and a trainable meta-architecture to combine their outputs, we achieve significant improvements for Canola crops and Kochia weeds on unseen test data, surpassing the performance of single semantic segmentation models. We identify the UNET meta-architecture as the most effective in this context. Finally, through ablation studies, we demonstrate and validate the effectiveness of our proposed model. We observe that including base models trained on other target crops and weeds can help generalize the model to capture varied field conditions. Lastly, we propose two novel datasets with varied conditions for comparisons.
Authors: Zhiwei Wang, Qiang Hu, Hongkuan Shi, Li He, Man He, Wenxuan Dai, Ting Li, Yitong Zhang, Dun Li, Mei Liu, Qiang Li
Abstract: Box-supervised polyp segmentation attracts increasing attention for its cost-effective potential. Existing solutions often rely on learning-free methods or pretrained models to laboriously generate pseudo masks, triggering Dice constraint subsequently. In this paper, we found that a model guided by the simplest box-filled masks can accurately predict polyp locations/sizes, but suffers from shape collapsing. In response, we propose two innovative learning fashions, Improved Box-dice (IBox) and Contrastive Latent-Anchors (CLA), and combine them to train a robust box-supervised model IBoxCLA. The core idea behind IBoxCLA is to decouple the learning of location/size and shape, allowing for focused constraints on each of them. Specifically, IBox transforms the segmentation map into a proxy map using shape decoupling and confusion-region swapping sequentially. Within the proxy map, shapes are disentangled, while locations/sizes are encoded as box-like responses. By constraining the proxy map instead of the raw prediction, the box-filled mask can well supervise IBoxCLA without misleading its shape learning. Furthermore, CLA contributes to shape learning by generating two types of latent anchors, which are learned and updated using momentum and segmented polyps to steadily represent polyp and background features. The latent anchors facilitate IBoxCLA to capture discriminative features within and outside boxes in a contrastive manner, yielding clearer boundaries. We benchmark IBoxCLA on five public polyp datasets. The experimental results demonstrate the competitive performance of IBoxCLA compared to recent fully-supervised polyp segmentation methods, and its superiority over other box-supervised state-of-the-arts with a relative increase of overall mDice and mIoU by at least 6.5% and 7.5%, respectively.
Authors: Bissmella Bahaduri, Zuheng Ming, Fangchen Feng, Anissa Mokraou
Abstract: Object detection in Remote Sensing Images (RSI) is a critical task for numerous applications in Earth Observation (EO). Differing from object detection in natural images, object detection in remote sensing images faces challenges of scarcity of annotated data and the presence of small objects represented by only a few pixels. Multi-modal fusion has been determined to enhance the accuracy by fusing data from multiple modalities such as RGB, infrared (IR), lidar, and synthetic aperture radar (SAR). To this end, the fusion of representations at the mid or late stage, produced by parallel subnetworks, is dominant, with the disadvantages of increasing computational complexity in the order of the number of modalities and the creation of additional engineering obstacles. Using the cross-attention mechanism, we propose a novel multi-modal fusion strategy for mapping relationships between different channels at the early stage, enabling the construction of a coherent input by aligning the different modalities. By addressing fusion in the early stage, as opposed to mid or late-stage methods, our method achieves competitive and even superior performance compared to existing techniques. Additionally, we enhance the SWIN transformer by integrating convolution layers into the feed-forward of non-shifting blocks. This augmentation strengthens the model's capacity to merge separated windows through local attention, thereby improving small object detection. Extensive experiments prove the effectiveness of the proposed multimodal fusion module and the architecture, demonstrating their applicability to object detection in multimodal aerial imagery.
Authors: Dipanjyoti Paul, Arpita Chowdhury, Xinqi Xiong, Feng-Ju Chang, David Carlyn, Samuel Stevens, Kaiya L. Provost, Anuj Karpatne, Bryan Carstens, Daniel Rubenstein, Charles Stewart, Tanya Berger-Wolf, Yu Su, Wei-Lun Chao
Abstract: We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image. We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR). We learn "class-specific" queries (one for each class) as input to the decoder, enabling each class to localize its patterns in an image via cross-attention. We name our approach INterpretable TRansformer (INTR), which is fairly easy to implement and exhibits several compelling properties. We show that INTR intrinsically encourages each class to attend distinctively; the cross-attention weights thus provide a faithful interpretation of the prediction. Interestingly, via "multi-head" cross-attention, INTR could identify different "attributes" of a class, making it particularly suitable for fine-grained classification and analysis, which we demonstrate on eight datasets. Our code and pre-trained models are publicly accessible at the Imageomics Institute GitHub site: https://github.com/Imageomics/INTR.
Authors: Bar{\i}\c{s} B\"uy\"ukta\c{s}, Gencer Sumbul, Beg\"um Demir
Abstract: Federated learning (FL) enables the collaboration of multiple deep learning models to learn from decentralized data archives (i.e., clients) without accessing data on clients. Although FL offers ample opportunities in knowledge discovery from distributed image archives, it is seldom considered in remote sensing (RS). In this paper, as a first time in RS, we present a comparative study of state-of-the-art FL algorithms for RS image classification problems. To this end, we initially provide a systematic review of the FL algorithms presented in the computer vision and machine learning communities. Then, we select several state-of-the-art FL algorithms based on their effectiveness with respect to training data heterogeneity across clients (known as non-IID data). After presenting an extensive overview of the selected algorithms, a theoretical comparison of the algorithms is conducted based on their: 1) local training complexity; 2) aggregation complexity; 3) learning efficiency; 4) communication cost; and 5) scalability in terms of number of clients. After the theoretical comparison, experimental analyses are presented to compare them under different decentralization scenarios. For the experimental analyses, we focus our attention on multi-label image classification problems in RS. Based on our comprehensive analyses, we finally derive a guideline for selecting suitable FL algorithms in RS. The code of this work is publicly available at https://git.tu-berlin.de/rsim/FL-RS.
Authors: Shivam Aggarwal, Hans Jakob Damsgaard, Alessandro Pappalardo, Giuseppe Franco, Thomas B. Preu{\ss}er, Michaela Blott, Tulika Mitra
Abstract: Post-training quantization (PTQ) is a powerful technique for model compression, reducing the numerical precision in neural networks without additional training overhead. Recent works have investigated adopting 8-bit floating-point formats(FP8) in the context of PTQ for model inference. However, floating-point formats smaller than 8 bits and their relative comparison in terms of accuracy-hardware cost with integers remains unexplored on FPGAs. In this work, we present minifloats, which are reduced-precision floating-point formats capable of further reducing the memory footprint, latency, and energy cost of a model while approaching full-precision model accuracy. We implement a custom FPGA-based multiply-accumulate operator library and explore the vast design space, comparing minifloat and integer representations across 3 to 8 bits for both weights and activations. We also examine the applicability of various integerbased quantization techniques to minifloats. Our experiments show that minifloats offer a promising alternative for emerging workloads such as vision transformers.
Authors: Zhiyu Qu, Lan Yang, Honggang Zhang, Tao Xiang, Kaiyue Pang, Yi-Zhe Song
Abstract: Creating multi-view wire art (MVWA), a static 3D sculpture with diverse interpretations from different viewpoints, is a complex task even for skilled artists. In response, we present DreamWire, an AI system enabling everyone to craft MVWA easily. Users express their vision through text prompts or scribbles, freeing them from intricate 3D wire organisation. Our approach synergises 3D B\'ezier curves, Prim's algorithm, and knowledge distillation from diffusion models or their variants (e.g., ControlNet). This blend enables the system to represent 3D wire art, ensuring spatial continuity and overcoming data scarcity. Extensive evaluation and analysis are conducted to shed insight on the inner workings of the proposed system, including the trade-off between connectivity and visual aesthetics.
Authors: Jinsong Zhang, Minjie Zhu, Yuxiang Zhang, Yebin Liu, Kun Li
Abstract: This paper addresses the problem of generating whole-body motion from speech. Despite great successes, prior methods still struggle to produce reasonable and diverse whole-body motions from speech. This is due to their reliance on suboptimal representations and a lack of strategies for generating diverse results. To address these challenges, we present a novel hybrid point representation to achieve accurate and continuous motion generation, e.g., avoiding foot skating, and this representation can be transformed into an easy-to-use representation, i.e., SMPL-X body mesh, for many applications. To generate whole-body motion from speech, for facial motion, closely tied to the audio signal, we introduce an encoder-decoder architecture to achieve deterministic outcomes. However, for the body and hands, which have weaker connections to the audio signal, we aim to generate diverse yet reasonable motions. To boost diversity in motion generation, we propose a contrastive motion learning method to encourage the model to produce more distinctive representations. Specifically, we design a robust VQ-VAE to learn a quantized motion codebook using our hybrid representation. Then, we regress the motion representation from the audio signal by a translation model employing our contrastive motion learning method. Experimental results validate the superior performance and the correctness of our model. The project page is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/SpeechAct.
URLs: http://cic.tju.edu.cn/faculty/likun/projects/SpeechAct.
Authors: Yuanwang Yang, Qiao Feng, Yu-Kun Lai, Kun Li
Abstract: Rendering 3D human appearance in different views is crucial for achieving holographic communication and immersive VR/AR. Existing methods either rely on multi-camera setups or have low-quality rendered images from a single image. In this paper, we propose R2Human, the first approach for real-time inference and rendering of photorealistic 3D human appearance from a single image. The core of our approach is to combine the strengths of implicit texture fields and explicit neural rendering with our novel representation, namely Z-map. Based on this, we present an end-to-end network that performs high-fidelity color reconstruction of visible areas and provides reliable color inference for occluded regions. To further enhance the 3D perception ability of our network, we leverage the Fourier occupancy field as a prior for generating the texture field and providing a sampling surface in the rendering stage. We also propose a consistency loss and a spatio-temporal fusion strategy to ensure the multi-view coherence. Experimental results show that our method outperforms the state-of-the-art methods on both synthetic data and challenging real-world images, in real time.
Authors: Yechi Ma, Neehar Peri, Shuoquan Wei, Wei Hua, Deva Ramanan, Yanan Li, Shu Kong
Abstract: Long-Tailed 3D Object Detection (LT3D) addresses the problem of accurately detecting objects from both common and rare classes. Contemporary multi-modal detectors achieve low AP on rare-classes (e.g., CMT only achieves 9.4 AP on stroller), presumably because training detectors end-to-end with significant class imbalance is challenging. To address this limitation, we delve into a simple late-fusion framework that ensembles independently trained uni-modal LiDAR and RGB detectors. Importantly, such a late-fusion framework allows us to leverage large-scale uni-modal datasets (with more examples for rare classes) to train better uni-modal RGB detectors, unlike prevailing multimodal detectors that require paired multi-modal training data. Notably, our approach significantly improves rare-class detection by 7.2% over prior work. Further, we examine three critical components of our simple late-fusion approach from first principles and investigate whether to train 2D or 3D RGB detectors, whether to match RGB and LiDAR detections in 3D or the projected 2D image plane for fusion, and how to fuse matched detections. Extensive experiments reveal that 2D RGB detectors achieve better recognition accuracy for rare classes than 3D RGB detectors and matching on the 2D image plane mitigates depth estimation errors. Our late-fusion approach achieves 51.4 mAP on the established nuScenes LT3D benchmark, improving over prior work by 5.9 mAP!
Authors: Anish Madan, Neehar Peri, Shu Kong, Deva Ramanan
Abstract: The era of vision-language models (VLMs) trained on large web-scale datasets challenges conventional formulations of "open-world" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent foundational VLMs. First, we point out that zero-shot VLMs such as GroundingDINO significantly outperform state-of-the-art few-shot detectors (48 vs. 33 AP) on COCO. Despite their strong zero-shot performance, such foundational models may still be sub-optimal. For example, trucks on the web may be defined differently from trucks for a target application such as autonomous vehicle perception. We argue that the task of few-shot recognition can be reformulated as aligning foundation models to target concepts using a few examples. Interestingly, such examples can be multi-modal, using both text and visual cues, mimicking instructions that are often given to human annotators when defining a target concept of interest. Concretely, we propose Foundational FSOD, a new benchmark protocol that evaluates detectors pre-trained on any external datasets and fine-tuned on multi-modal (text and visual) K-shot examples per target class. We repurpose nuImages for Foundational FSOD, benchmark several popular open-source VLMs, and provide an empirical analysis of state-of-the-art methods. Lastly, we discuss our recent CVPR 2024 Foundational FSOD competition and share insights from the community. Notably, the winning team significantly outperforms our baseline by 23.9 mAP!
Authors: Chen Tang, Yuan Meng, Jiacheng Jiang, Shuzhao Xie, Rongwei Lu, Xinzhu Ma, Zhi Wang, Wenwu Zhu
Abstract: Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation ability. Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression. Specifically, in the first stage, all potential bit-width configurations are coupled and thus optimized simultaneously within a set of shared weights. However, our observations reveal a previously unseen and severe bit-width interference phenomenon among highly coupled weights during optimization, leading to considerable performance degradation under a high compression ratio. To tackle this problem, we first design a bit-width scheduler to dynamically freeze the most turbulent bit-width of layers during training, to ensure the rest bit-widths converged properly. Then, taking inspiration from information theory, we present an information distortion mitigation technique to align the behavior of the bad-performing bit-widths to the well-performing ones. In the second stage, an inference-only greedy search scheme is devised to evaluate the goodness of configurations without introducing any additional training costs. Extensive experiments on three representative models and three datasets demonstrate the effectiveness of the proposed method. Code can be available on \href{https://www.github.com/1hunters/retraining-free-quantization}{https://github.com/1hunters/retraining-free-quantization}.
URLs: https://www.github.com/1hunters/retraining-free-quantization, https://github.com/1hunters/retraining-free-quantization
Authors: Weijie Tu, Weijian Deng, Dylan Campbell, Stephen Gould, Tom Gedeon
Abstract: Vision-Language Models (VLMs) have emerged as the dominant approach for zero-shot recognition, adept at handling diverse scenarios and significant distribution changes. However, their deployment in risk-sensitive areas requires a deeper understanding of their uncertainty estimation capabilities, a relatively uncharted area. In this study, we explore the calibration properties of VLMs across different architectures, datasets, and training strategies. In particular, we analyze the uncertainty estimation performance of VLMs when calibrated in one domain, label set or hierarchy level, and tested in a different one. Our findings reveal that while VLMs are not inherently calibrated for uncertainty, temperature scaling significantly and consistently improves calibration, even across shifts in distribution and changes in label set. Moreover, VLMs can be calibrated with a very small set of examples. Through detailed experimentation, we highlight the potential applications and importance of our insights, aiming for more reliable and effective use of VLMs in critical, real-world scenarios.
Authors: Jiwon Yoo, Jangwon Lee, Gyeonghwan Kim
Abstract: Multi-scale architecture, including hierarchical vision transformer, has been commonly applied to high-resolution semantic segmentation to deal with computational complexity with minimum performance loss. In this paper, we propose a novel decoding scheme for semantic segmentation in this regard, which takes multi-level features from the encoder with multi-scale architecture. The decoding scheme based on a multi-level vision transformer aims to achieve not only reduced computational expense but also higher segmentation accuracy, by introducing successive cross-attention in aggregation of the multi-level features. Furthermore, a way to enhance the multi-level features by the aggregated semantics is proposed. The effort is focused on maintaining the contextual consistency from the perspective of attention allocation and brings improved performance with significantly lower computational cost. Set of experiments on popular datasets demonstrates superiority of the proposed scheme to the state-of-the-art semantic segmentation models in terms of computational cost without loss of accuracy, and extensive ablation studies prove the effectiveness of ideas proposed.
Authors: Yihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Rao Kompella, Xiaoming Liu, Sijia Liu
Abstract: The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. However, they have also raised significant societal concerns, such as the generation of harmful content and copyright disputes. Machine unlearning (MU) has emerged as a promising solution, capable of removing undesired generative capabilities from DMs. However, existing MU evaluation systems present several key challenges that can result in incomplete and inaccurate assessments. To address these issues, we propose UnlearnCanvas, a comprehensive high-resolution stylized image dataset that facilitates the evaluation of the unlearning of artistic styles and associated objects. This dataset enables the establishment of a standardized, automated evaluation framework with 7 quantitative metrics assessing various aspects of the unlearning performance for DMs. Through extensive experiments, we benchmark 9 state-of-the-art MU methods for DMs, revealing novel insights into their strengths, weaknesses, and underlying mechanisms. Additionally, we explore challenging unlearning scenarios for DMs to evaluate worst-case performance against adversarial prompts, the unlearning of finer-scale concepts, and sequential unlearning. We hope that this study can pave the way for developing more effective, accurate, and robust DM unlearning methods, ensuring safer and more ethical applications of DMs in the future. The dataset, benchmark, and codes are publicly available at https://unlearn-canvas.netlify.app/.
Authors: Abdullah Nazhat Abdullah, Tarkan Aydin
Abstract: The attention mechanism is the main component of the transformer architecture, and since its introduction, it has led to significant advancements in deep learning that span many domains and multiple tasks. The attention mechanism was utilized in computer vision as the Vision Transformer ViT, and its usage has expanded into many tasks in the vision domain, such as classification, segmentation, object detection, and image generation. While this mechanism is very expressive and capable, it comes with the drawback of being computationally expensive and requiring datasets of considerable size for effective optimization. To address these shortcomings, many designs have been proposed in the literature to reduce the computational burden and alleviate the data size requirements. Examples of such attempts in the vision domain are the MLP-Mixer, the Conv-Mixer, the Perciver-IO, and many more. This paper introduces a new computational block as an alternative to the standard ViT block that reduces the compute burdens by replacing the normal attention layers with a Network in Network structure that enhances the static approach of the MLP-Mixer with a dynamic system of learning an element-wise gating function by a token mixing process. Extensive experimentation shows that the proposed design provides better performance than the baseline architectures on multiple datasets applied in the image classification task of the vision domain.
Authors: Ozge Mercanoglu Sincan, Necati Cihan Camgoz, Richard Bowden
Abstract: Sign Language Translation (SLT) is a challenging task that aims to generate spoken language sentences from sign language videos. In this paper, we introduce a hybrid SLT approach, Spotter+GPT, that utilizes a sign spotter and a powerful Large Language Model (LLM) to improve SLT performance. Spotter+GPT breaks down the SLT task into two stages. The videos are first processed by the Spotter, which is trained on a linguistic sign language dataset, to identify individual signs. These spotted signs are then passed to an LLM, which transforms them into coherent and contextually appropriate spoken language sentences. The source code of the Spotter is available at https://gitlab.surrey.ac.uk/cogvispublic/sign-spotter.
URLs: https://gitlab.surrey.ac.uk/cogvispublic/sign-spotter.
Authors: Chong Ma, Hanqi Jiang, Wenting Chen, Yiwei Li, Zihao Wu, Xiaowei Yu, Zhengliang Liu, Lei Guo, Dajiang Zhu, Tuo Zhang, Dinggang Shen, Tianming Liu, Xiang Li
Abstract: In the medical multi-modal frameworks, the alignment of cross-modality features presents a significant challenge. However, existing works have learned features that are implicitly aligned from the data, without considering the explicit relationships in the medical context. This data-reliance may lead to low generalization of the learned alignment relationships. In this work, we propose the Eye-gaze Guided Multi-modal Alignment (EGMA) framework to harness eye-gaze data for better alignment of medical visual and textual features. We explore the natural auxiliary role of radiologists' eye-gaze data in aligning medical images and text, and introduce a novel approach by using eye-gaze data, collected synchronously by radiologists during diagnostic evaluations. We conduct downstream tasks of image classification and image-text retrieval on four medical datasets, where EGMA achieved state-of-the-art performance and stronger generalization across different datasets. Additionally, we explore the impact of varying amounts of eye-gaze data on model performance, highlighting the feasibility and utility of integrating this auxiliary data into multi-modal alignment framework.
Authors: Mengyu Yang, Ye Tian, Lanshan Zhang, Xiao Liang, Xuming Ran, Wendong Wang
Abstract: Recently, prompt-based methods have emerged as a new alternative `parameter-efficient fine-tuning' paradigm, which only fine-tunes a small number of additional parameters while keeping the original model frozen. However, despite achieving notable results, existing prompt methods mainly focus on `what to add', while overlooking the equally important aspect of `where to add', typically relying on the manually crafted placement. To this end, we propose a region-based Adaptive Visual Prompt, named AdaViPro, which integrates the `where to add' optimization of the prompt into the learning process. Specifically, we reconceptualize the `where to add' optimization as a problem of regional decision-making. During inference, AdaViPro generates a regionalized mask map for the whole image, which is composed of 0 and 1, to designate whether to apply or discard the prompt in each specific area. Therefore, we employ Gumbel-Softmax sampling to enable AdaViPro's end-to-end learning through standard back-propagation. Extensive experiments demonstrate that our AdaViPro yields new efficiency and accuracy trade-offs for adapting pre-trained models.
Authors: Paritosh Parmar, Eric Peh, Ruirui Chen, Ting En Lam, Yuhan Chen, Elston Tan, Basura Fernando
Abstract: Causal video question answering (QA) has garnered increasing interest, yet existing datasets often lack depth in causal reasoning. To address this gap, we capitalize on the unique properties of cartoons and construct CausalChaos!, a novel, challenging causal Why-QA dataset built upon the iconic "Tom and Jerry" cartoon series. Cartoons use the principles of animation that allow animators to create expressive, unambiguous causal relationships between events to form a coherent storyline. Utilizing these properties, along with thought-provoking questions and multi-level answers (answer and detailed causal explanation), our questions involve causal chains that interconnect multiple dynamic interactions between characters and visual scenes. These factors demand models to solve more challenging, yet well-defined causal relationships. We also introduce hard incorrect answer mining, including a causally confusing version that is even more challenging. While models perform well, there is much room for improvement, especially, on open-ended answers. We identify more advanced/explicit causal relationship modeling & joint modeling of vision and language as the immediate areas for future efforts to focus upon. Along with the other complementary datasets, our new challenging dataset will pave the way for these developments in the field.
Authors: Ehsan Pajouheshgar, Yitao Xu, Sabine S\"usstrunk
Abstract: Neural Cellular Automata (NCA) is a class of Cellular Automata where the update rule is parameterized by a neural network that can be trained using gradient descent. In this paper, we focus on NCA models used for texture synthesis, where the update rule is inspired by partial differential equations (PDEs) describing reaction-diffusion systems. To train the NCA model, the spatio-temporal domain is discretized, and Euler integration is used to numerically simulate the PDE. However, whether a trained NCA truly learns the continuous dynamic described by the corresponding PDE or merely overfits the discretization used in training remains an open question. We study NCA models at the limit where space-time discretization approaches continuity. We find that existing NCA models tend to overfit the training discretization, especially in the proximity of the initial condition, also called "seed". To address this, we propose a solution that utilizes uniform noise as the initial condition. We demonstrate the effectiveness of our approach in preserving the consistency of NCA dynamics across a wide range of spatio-temporal granularities. Our improved NCA model enables two new test-time interactions by allowing continuous control over the speed of pattern formation and the scale of the synthesized patterns. We demonstrate this new NCA feature in our interactive online demo. Our work reveals that NCA models can learn continuous dynamics and opens new venues for NCA research from a dynamical system's perspective.
Authors: Yitao Xu, Ehsan Pajouheshgar, Sabine S\"usstrunk
Abstract: Neural Cellular Automata (NCA) models are trainable variations of traditional Cellular Automata (CA). Emergent motion in the patterns created by NCA has been successfully applied to synthesize dynamic textures. However, the conditions required for an NCA to display dynamic patterns remain unexplored. Here, we investigate the relationship between the NCA architecture and the emergent dynamics of the trained models. Specifically, we vary the number of channels in the cell state and the number of hidden neurons in the MultiLayer Perceptron (MLP), and draw a relationship between the combination of these two variables and the motion strength between successive frames. Our analysis reveals that the disparity and proportionality between these two variables have a strong correlation with the emergent dynamics in the NCA output. We thus propose a design principle for creating dynamic NCA.
Authors: Jingyao Xu, Yuetong Lu, Yandong Li, Siyang Lu, Dongdong Wang, Xiang Wei
Abstract: Diffusion models (DMs) embark a new era of generative modeling and offer more opportunities for efficient generating high-quality and realistic data samples. However, their widespread use has also brought forth new challenges in model security, which motivates the creation of more effective adversarial attackers on DMs to understand its vulnerability. We propose CAAT, a simple but generic and efficient approach that does not require costly training to effectively fool latent diffusion models (LDMs). The approach is based on the observation that cross-attention layers exhibits higher sensitivity to gradient change, allowing for leveraging subtle perturbations on published images to significantly corrupt the generated images. We show that a subtle perturbation on an image can significantly impact the cross-attention layers, thus changing the mapping between text and image during the fine-tuning of customized diffusion models. Extensive experiments demonstrate that CAAT is compatible with diverse diffusion models and outperforms baseline attack methods in a more effective (more noise) and efficient (twice as fast as Anti-DreamBooth and Mist) manner.
Authors: Minguk Kang, Richard Zhang, Connelly Barnes, Sylvain Paris, Suha Kwak, Jaesik Park, Eli Shechtman, Jun-Yan Zhu, Taesung Park
Abstract: We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a paired image-to-image translation task, using noise-to-image pairs of the diffusion model's ODE trajectory. For efficient regression loss computation, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space, utilizing an ensemble of augmentations. Furthermore, we adapt a diffusion model to construct a multi-scale discriminator with a text alignment loss to build an effective conditional GAN-based formulation. E-LatentLPIPS converges more efficiently than many existing distillation methods, even accounting for dataset construction costs. We demonstrate that our one-step generator outperforms cutting-edge one-step diffusion distillation models -- DMD, SDXL-Turbo, and SDXL-Lightning -- on the zero-shot COCO benchmark.
Authors: Ruchit Rawal, Khalid Saifullah, Ronen Basri, David Jacobs, Gowthami Somepalli, Tom Goldstein
Abstract: Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames from a video. To address this issue, we present a novel dataset and benchmark, CinePile, specifically designed for authentic long-form video understanding. This paper details our innovative approach for creating a question-answer dataset, utilizing advanced LLMs with human-in-the-loop and building upon human-generated raw data. Our comprehensive dataset comprises 305,000 multiple-choice questions (MCQs), covering various visual and multimodal aspects, including temporal comprehension, understanding human-object interactions, and reasoning about events or actions within a scene. Additionally, we evaluate recent video-centric LLMs, both open-source and proprietary, on the test split of our dataset. The findings reveal that even state-of-the-art video-centric LLMs significantly lag behind human performance in these tasks, highlighting the complexity and challenge inherent in video understanding. The dataset is available at https://hf.co/datasets/tomg-group-umd/cinepile
Authors: Malika Nisal Ratnayake, Lex Gallon, Adel N. Toosi, Alan Dorin
Abstract: Field-captured video allows for detailed studies of spatiotemporal aspects of animal locomotion, decision-making, and environmental interactions. However, despite the affordability of data capture with mass-produced hardware, storage, processing, and transmission overheads pose a significant hurdle to acquiring high-resolution video from field-deployed camera traps. Therefore, efficient compression algorithms are crucial for monitoring with camera traps that have limited access to power, storage, and bandwidth. In this article, we introduce a new motion analysis-based video compression algorithm designed to run on camera trap devices. We implemented and tested this algorithm using a case study of insect-pollinator motion tracking. The algorithm identifies and stores only image regions depicting motion relevant to pollination monitoring, reducing the overall data size by an average of 84% across a diverse set of test datasets while retaining the information necessary for relevant behavioural analysis. The methods outlined in this paper facilitate the broader application of computer vision-enabled, low-powered camera trap devices for remote, in-situ video-based animal motion monitoring.
Authors: Neehar Kondapaneni, Markus Marks, Oisin MacAodha, Pietro Perona
Abstract: We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual explanations that are critical for discriminating between classes. This is achieved by simultaneously optimizing three criteria: the explanations should be few, diverse, and human-interpretable. Our approach builds on the recently introduced Concept Relevance Propagation (CRP) explainability method. While CRP is effective at describing individual neuronal activations, it generates too many concepts, which impacts human comprehension. Instead, DCNE selects the few most important explanations. We introduce a new evaluation dataset centered on the challenging task of classifying birds, enabling us to compare the alignment of DCNE's explanations to those of human expert-defined ones. Compared to existing eXplainable Artificial Intelligence (XAI) methods, DCNE has a desirable trade-off between conciseness and completeness when summarizing network explanations. It produces 1/30 of CRP's explanations while only resulting in a slight reduction in explanation quality. DCNE represents a step forward in making neural network decisions accessible and interpretable to humans, providing a valuable tool for both researchers and practitioners in XAI and model alignment.
Authors: Jihao Liu, Jinliang Zheng, Boxiao Liu, Yu Liu, Hongsheng Li
Abstract: Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on noisy web-scale datasets is computationally demanding. On the other hand, mask-then-predict pre-training approaches, like Masked Image Modeling (MIM), offer efficient self-supervised learning for single-modal representations. This paper introduces Unmasked Token Alignment (UTA), a method that leverages existing CLIP models to further enhance its vision-language representations. UTA trains a Vision Transformer (ViT) by aligning unmasked visual tokens to the corresponding image tokens from a frozen CLIP vision encoder, which automatically aligns the ViT model with the CLIP text encoder. The pre-trained ViT can be directly applied for zero-shot evaluation even without training on image-text pairs. Compared to MIM approaches, UTA does not suffer from training-finetuning inconsistency and is much more training-efficient by avoiding using the extra [MASK] tokens. Extensive experimental results demonstrate that UTA can enhance CLIP models and outperform existing MIM methods on various uni- and multi-modal benchmarks. Code and models are available at https://github.com/jihaonew/UTA.
Authors: Haitao Cao, Baoping Cheng, Qiran Pu, Haocheng Zhang, Bin Luo, Yixiang Zhuang, Juncong Lin, Liyan Chen, Xuan Cheng
Abstract: Parametric 3D models have enabled a wide variety of computer vision and graphics tasks, such as modeling human faces, bodies and hands. In 3D face modeling, 3DMM is the most widely used parametric model, but can't generate fine geometric details solely from identity and expression inputs. To tackle this limitation, we propose a neural parametric model named DNPM for the facial geometric details, which utilizes deep neural network to extract latent codes from facial displacement maps encoding details and wrinkles. Built upon DNPM, a novel 3DMM named Detailed3DMM is proposed, which augments traditional 3DMMs by including the synthesis of facial details only from the identity and expression inputs. Moreover, we show that DNPM and Detailed3DMM can facilitate two downstream applications: speech-driven detailed 3D facial animation and 3D face reconstruction from a degraded image. Extensive experiments have shown the usefulness of DNPM and Detailed3DMM, and the progressiveness of two proposed applications.
Authors: Xin Wen, Bingchen Zhao, Yilun Chen, Jiangmiao Pang, Xiaojuan Qi
Abstract: Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates significant effectiveness in learning generalizable representations. With an aim to investigate the reasons behind this finding, we conduct controlled experiments to study various underlying factors, and reveal that CLIP's pretext task forms a dynamic classification problem wherein only a subset of classes is present in training. This isolates the bias from dominant classes and implicitly balances the learning signal. Furthermore, the robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts, which are inaccessible to supervised learning. Our study not only uncovers the mechanisms behind CLIP's generalizability beyond data imbalance but also provides transferable insights for the research community. The findings are validated in both supervised and self-supervised learning, enabling models trained on imbalanced data to achieve CLIP-level performance on diverse recognition tasks. Code and data are available at: https://github.com/CVMI-Lab/clip-beyond-tail.
Authors: Yi-Ting Hsiao, Siavash Khodadadeh, Kevin Duarte, Wei-An Lin, Hui Qu, Mingi Kwon, Ratheesh Kalarot
Abstract: Diffusion models have shown tremendous results in image generation. However, due to the iterative nature of the diffusion process and its reliance on classifier-free guidance, inference times are slow. In this paper, we propose a new distillation approach for guided diffusion models in which an external lightweight guide model is trained while the original text-to-image model remains frozen. We show that our method reduces the inference computation of classifier-free guided latent-space diffusion models by almost half, and only requires 1\% trainable parameters of the base model. Furthermore, once trained, our guide model can be applied to various fine-tuned, domain-specific versions of the base diffusion model without the need for additional training: this "plug-and-play" functionality drastically improves inference computation while maintaining the visual fidelity of generated images. Empirically, we show that our approach is able to produce visually appealing results and achieve a comparable FID score to the teacher with as few as 8 to 16 steps.
Authors: Haolin Li, Jinyang Liu, Mario Sznaier, Octavia Camps
Abstract: Photo-realistic 3D Reconstruction is a fundamental problem in 3D computer vision. This domain has seen considerable advancements owing to the advent of recent neural rendering techniques. These techniques predominantly aim to focus on learning volumetric representations of 3D scenes and refining these representations via loss functions derived from rendering. Among these, 3D Gaussian Splatting (3D-GS) has emerged as a significant method, surpassing Neural Radiance Fields (NeRFs). 3D-GS uses parameterized 3D Gaussians for modeling both spatial locations and color information, combined with a tile-based fast rendering technique. Despite its superior rendering performance and speed, the use of 3D Gaussian kernels has inherent limitations in accurately representing discontinuous functions, notably at edges and corners for shape discontinuities, and across varying textures for color discontinuities. To address this problem, we propose to employ 3D Half-Gaussian (3D-HGS) kernels, which can be used as a plug-and-play kernel. Our experiments demonstrate their capability to improve the performance of current 3D-GS related methods and achieve state-of-the-art rendering performance on various datasets without compromising rendering speed.
Authors: Jun Liu, Jiantao Zhou, Jiandian Zeng, Jinyu Tian
Abstract: This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a \textit{Hierarchical} \textbf{Di}sentangled \textbf{F}eature space and \textit{cross domain}, called \textbf{DifAttack++}, which differs significantly from the existing ones operating over the entire feature space. Specifically, DifAttack++ firstly disentangles an image's latent feature into an \textit{adversarial feature} (AF) and a \textit{visual feature} (VF) via an autoencoder equipped with our specially designed \textbf{H}ierarchical \textbf{D}ecouple-\textbf{F}usion (HDF) module, where the AF dominates the adversarial capability of an image, while the VF largely determines its visual appearance. We train such autoencoders for the clean and adversarial image domains respectively, meanwhile realizing feature disentanglement, by using pairs of clean images and their Adversarial Examples (AEs) generated from available surrogate models via white-box attack methods. Eventually, in the black-box attack stage, DifAttack++ iteratively optimizes the AF according to the query feedback from the victim model until a successful AE is generated, while keeping the VF unaltered. Extensive experimental results demonstrate that our method achieves superior ASR and query efficiency than SOTA methods, meanwhile exhibiting much better visual quality of AEs. The code is available at https://github.com/csjunjun/DifAttack.git.
Authors: Salvatore Esposito, Qingshan Xu, Kacper Kania, Charlie Hewitt, Octave Mariotti, Lohit Petikam, Julien Valentin, Arno Onken, Oisin Mac Aodha
Abstract: We introduce a new generative approach for synthesizing 3D geometry and images from single-view collections. Most existing approaches predict volumetric density to render multi-view consistent images. By employing volumetric rendering using neural radiance fields, they inherit a key limitation: the generated geometry is noisy and unconstrained, limiting the quality and utility of the output meshes. To address this issue, we propose GeoGen, a new SDF-based 3D generative model trained in an end-to-end manner. Initially, we reinterpret the volumetric density as a Signed Distance Function (SDF). This allows us to introduce useful priors to generate valid meshes. However, those priors prevent the generative model from learning details, limiting the applicability of the method to real-world scenarios. To alleviate that problem, we make the transformation learnable and constrain the rendered depth map to be consistent with the zero-level set of the SDF. Through the lens of adversarial training, we encourage the network to produce higher fidelity details on the output meshes. For evaluation, we introduce a synthetic dataset of human avatars captured from 360-degree camera angles, to overcome the challenges presented by real-world datasets, which often lack 3D consistency and do not cover all camera angles. Our experiments on multiple datasets show that GeoGen produces visually and quantitatively better geometry than the previous generative models based on neural radiance fields.
Authors: Peiye Zhuang, Songfang Han, Chaoyang Wang, Aliaksandr Siarohin, Jiaxu Zou, Michael Vasilkovsky, Vladislav Shakhrai, Sergey Korolev, Sergey Tulyakov, Hsin-Ying Lee
Abstract: We propose a novel approach for 3D mesh reconstruction from multi-view images. Our method takes inspiration from large reconstruction models like LRM that use a transformer-based triplane generator and a Neural Radiance Field (NeRF) model trained on multi-view images. However, in our method, we introduce several important modifications that allow us to significantly enhance 3D reconstruction quality. First of all, we examine the original LRM architecture and find several shortcomings. Subsequently, we introduce respective modifications to the LRM architecture, which lead to improved multi-view image representation and more computationally efficient training. Second, in order to improve geometry reconstruction and enable supervision at full image resolution, we extract meshes from the NeRF field in a differentiable manner and fine-tune the NeRF model through mesh rendering. These modifications allow us to achieve state-of-the-art performance on both 2D and 3D evaluation metrics, such as a PSNR of 28.67 on Google Scanned Objects (GSO) dataset. Despite these superior results, our feed-forward model still struggles to reconstruct complex textures, such as text and portraits on assets. To address this, we introduce a lightweight per-instance texture refinement procedure. This procedure fine-tunes the triplane representation and the NeRF color estimation model on the mesh surface using the input multi-view images in just 4 seconds. This refinement improves the PSNR to 29.79 and achieves faithful reconstruction of complex textures, such as text. Additionally, our approach enables various downstream applications, including text- or image-to-3D generation.
Authors: Hao Sun, Yu Song
Abstract: Large models have demonstrated exceptional generalization capabilities in computer vision and natural language processing. Recent efforts have focused on enhancing these models with multimodal processing abilities. However, addressing the challenges posed by scenarios where one modality is absent remains a significant hurdle. In response to this issue, we propose a robust latent representation tuning method for large models. Specifically, our approach introduces a modality latent translation module to maximize the correlation between modalities, resulting in a robust representation. Following this, a newly designed fusion module is employed to facilitate information interaction between the modalities. Within this framework, common semantics are refined during training, and robust performance is achieved even in the absence of one modality. Importantly, our method maintains the frozen state of the image and text foundation models to preserve their capabilities acquired through large-scale pretraining. We conduct experiments on several public datasets, and the results underscore the effectiveness of our proposed method.
Authors: Anna Wirth-Singh, Jinlin Xiang, Minho Choi, Johannes E. Fr\"och, Luocheng Huang, Shane Colburn, Eli Shlizerman, Arka Majumdar
Abstract: Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification and computer vision tasks. However, implementing optical nonlinearity is challenging, and omitting the nonlinear layers in a standard CNN comes at a significant reduction in accuracy. In this work, we use knowledge distillation to compress modified AlexNet to a single linear convolutional layer and an electronic backend (two fully connected layers). We obtain comparable performance to a purely electronic CNN with five convolutional layers and three fully connected layers. We implement the convolution optically via engineering the point spread function of an inverse-designed meta-optic. Using this hybrid approach, we estimate a reduction in multiply-accumulate operations from 17M in a conventional electronic modified AlexNet to only 86K in the hybrid compressed network enabled by the optical frontend. This constitutes over two orders of magnitude reduction in latency and power consumption. Furthermore, we experimentally demonstrate that the classification accuracy of the system exceeds 93% on the MNIST dataset.
Authors: Jiannan Wu, Muyan Zhong, Sen Xing, Zeqiang Lai, Zhaoyang Liu, Wenhai Wang, Zhe Chen, Xizhou Zhu, Lewei Lu, Tong Lu, Ping Luo, Yu Qiao, Jifeng Dai
Abstract: We present VisionLLM v2, an end-to-end generalist multimodal large model (MLLM) that unifies visual perception, understanding, and generation within a single framework. Unlike traditional MLLMs limited to text output, VisionLLM v2 significantly broadens its application scope. It excels not only in conventional visual question answering (VQA) but also in open-ended, cross-domain vision tasks such as object localization, pose estimation, and image generation and editing. To this end, we propose a new information transmission mechanism termed "super link", as a medium to connect MLLM with task-specific decoders. It not only allows flexible transmission of task information and gradient feedback between the MLLM and multiple downstream decoders but also effectively resolves training conflicts in multi-tasking scenarios. In addition, to support the diverse range of tasks, we carefully collected and combed training data from hundreds of public vision and vision-language tasks. In this way, our model can be joint-trained end-to-end on hundreds of vision language tasks and generalize to these tasks using a set of shared parameters through different user prompts, achieving performance comparable to task-specific models. We believe VisionLLM v2 will offer a new perspective on the generalization of MLLMs.
Authors: Qingyun Li, Zhe Chen, Weiyun Wang, Wenhai Wang, Shenglong Ye, Zhenjiang Jin, Guanzhou Chen, Yinan He, Zhangwei Gao, Erfei Cui, Jiashuo Yu, Hao Tian, Jiasheng Zhou, Chao Xu, Bin Wang, Xingjian Wei, Wei Li, Wenjian Zhang, Bo Zhang, Pinlong Cai, Licheng Wen, Xiangchao Yan, Zhenxiang Li, Pei Chu, Yi Wang, Min Dou, Changyao Tian, Xizhou Zhu, Lewei Lu, Yushi Chen, Junjun He, Zhongying Tu, Tong Lu, Yali Wang, Limin Wang, Dahua Lin, Yu Qiao, Botian Shi, Conghui He, Jifeng Dai
Abstract: Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. However, the limited scale and diversity of current image-text interleaved data restrict the development of multimodal large language models. In this paper, we introduce OmniCorpus, a 10 billion-scale image-text interleaved dataset. Using an efficient data engine, we filter and extract large-scale high-quality documents, which contain 8.6 billion images and 1,696 billion text tokens. Compared to counterparts (e.g., MMC4, OBELICS), our dataset 1) has 15 times larger scales while maintaining good data quality; 2) features more diverse sources, including both English and non-English websites as well as video-centric websites; 3) is more flexible, easily degradable from an image-text interleaved format to pure text corpus and image-text pairs. Through comprehensive analysis and experiments, we validate the quality, usability, and effectiveness of the proposed dataset. We hope this could provide a solid data foundation for future multimodal model research. Code and data are released at https://github.com/OpenGVLab/OmniCorpus.
Authors: Yi-Fan Zhang, Qingsong Wen, Chaoyou Fu, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin
Abstract: Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image consists of global and local branches, with the latter being the sliced image patches but resized to the same resolution as the former. This means that higher resolution requires more local patches, resulting in exorbitant computational expenses, and meanwhile, the dominance of local image tokens may diminish the global context. In this paper, we dive into the problems and propose a new framework as well as an elaborate optimization strategy. Specifically, we extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. With regard to local patches, learnable query embeddings are introduced to reduce image tokens, the most important tokens accounting for the user question will be further selected by a similarity-based selector. Our empirical results demonstrate a `less is more' pattern, where \textit{utilizing fewer but more informative local image tokens leads to improved performance}. Besides, a significant challenge lies in the training strategy, as simultaneous end-to-end training of the global mining block and local compression block does not yield optimal results. We thus advocate for an alternating training way, ensuring balanced learning between global and local aspects. Finally, we also introduce a challenging dataset with high requirements for image detail, enhancing the training of the local compression layer. The proposed method, termed LMM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME), achieves leading performance across various benchmarks with only 2 million training data.
Authors: Jaeyeon Jang, Young-Ik Kim, Jisu Lim, Hyeonseong Lee
Abstract: Knowledge distillation (KD) is a technique used to transfer knowledge from an overparameterized teacher network to a less-parameterized student network, thereby minimizing the incurred performance loss. KD methods can be categorized into offline and online approaches. Offline KD leverages a powerful pretrained teacher network, while online KD allows the teacher network to be adjusted dynamically to enhance the learning effectiveness of the student network. Recently, it has been discovered that sharing the classifier of the teacher network can significantly boost the performance of the student network with only a minimal increase in the number of network parameters. Building on these insights, we propose adaptive teaching with a shared classifier (ATSC). In ATSC, the pretrained teacher network self-adjusts to better align with the learning needs of the student network based on its capabilities, and the student network benefits from the shared classifier, enhancing its performance. Additionally, we extend ATSC to environments with multiple teachers. We conduct extensive experiments, demonstrating the effectiveness of the proposed KD method. Our approach achieves state-of-the-art results on the CIFAR-100 and ImageNet datasets in both single-teacher and multiteacher scenarios, with only a modest increase in the number of required model parameters. The source code is publicly available at https://github.com/random2314235/ATSC.
Authors: Yijun Bei, Hengrui Lou, Jinsong Geng, Erteng Liu, Lechao Cheng, Jie Song, Mingli Song, Zunlei Feng
Abstract: With the rapid development of AI-generated content (AIGC) technology, the production of realistic fake facial images and videos that deceive human visual perception has become possible. Consequently, various face forgery detection techniques have been proposed to identify such fake facial content. However, evaluating the effectiveness and generalizability of these detection techniques remains a significant challenge. To address this, we have constructed a large-scale evaluation benchmark called DeepFaceGen, aimed at quantitatively assessing the effectiveness of face forgery detection and facilitating the iterative development of forgery detection technology. DeepFaceGen consists of 776,990 real face image/video samples and 773,812 face forgery image/video samples, generated using 34 mainstream face generation techniques. During the construction process, we carefully consider important factors such as content diversity, fairness across ethnicities, and availability of comprehensive labels, in order to ensure the versatility and convenience of DeepFaceGen. Subsequently, DeepFaceGen is employed in this study to evaluate and analyze the performance of 13 mainstream face forgery detection techniques from various perspectives. Through extensive experimental analysis, we derive significant findings and propose potential directions for future research. The code and dataset for DeepFaceGen are available at https://github.com/HengruiLou/DeepFaceGen.
Authors: Athmanarayanan Lakshmi Narayanan, Ranganath Krishnan, Amrutha Machireddy, Mahesh Subedar
Abstract: Foundational vision transformer models have shown impressive few shot performance on many vision tasks. This research presents a novel investigation into the application of parameter efficient fine-tuning methods within an active learning (AL) framework, to advance the sampling selection process in extremely budget constrained classification tasks. The focus on image datasets, known for their out-of-distribution characteristics, adds a layer of complexity and relevance to our study. Through a detailed evaluation, we illustrate the improved AL performance on these challenging datasets, highlighting the strategic advantage of merging parameter efficient fine tuning methods with foundation models. This contributes to the broader discourse on optimizing AL strategies, presenting a promising avenue for future exploration in leveraging foundation models for efficient and effective data annotation in specialized domains.
Authors: Hong-Xing Yu, Haoyi Duan, Charles Herrmann, William T. Freeman, Jiajun Wu
Abstract: We present WonderWorld, a novel framework for interactive 3D scene extrapolation that enables users to explore and shape virtual environments based on a single input image and user-specified text. While significant improvements have been made to the visual quality of scene generation, existing methods are run offline, taking tens of minutes to hours to generate a scene. By leveraging Fast Gaussian Surfels and a guided diffusion-based depth estimation method, WonderWorld generates geometrically consistent extrapolation while significantly reducing computational time. Our framework generates connected and diverse 3D scenes in less than 10 seconds on a single A6000 GPU, enabling real-time user interaction and exploration. We demonstrate the potential of WonderWorld for applications in virtual reality, gaming, and creative design, where users can quickly generate and navigate immersive, potentially infinite virtual worlds from a single image. Our approach represents a significant advancement in interactive 3D scene generation, opening up new possibilities for user-driven content creation and exploration in virtual environments. We will release full code and software for reproducibility. Project website: https://WonderWorld-2024.github.io/
Authors: Roman Bachmann, O\u{g}uzhan Fatih Kar, David Mizrahi, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir
Abstract: Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small) number of modalities and tasks they are trained on. In this paper, we expand upon the capabilities of them by training a single model on tens of highly diverse modalities and by performing co-training on large-scale multimodal datasets and text corpora. This includes training on several semantic and geometric modalities, feature maps from recent state of the art models like DINOv2 and ImageBind, pseudo labels of specialist models like SAM and 4DHumans, and a range of new modalities that allow for novel ways to interact with the model and steer the generation, for example image metadata or color palettes. A crucial step in this process is performing discrete tokenization on various modalities, whether they are image-like, neural network feature maps, vectors, structured data like instance segmentation or human poses, or data that can be represented as text. Through this, we expand on the out-of-the-box capabilities of multimodal models and specifically show the possibility of training one model to solve at least 3x more tasks/modalities than existing ones and doing so without a loss in performance. This enables more fine-grained and controllable multimodal generation capabilities and allows us to study the distillation of models trained on diverse data and objectives into a unified model. We successfully scale the training to a three billion parameter model using tens of modalities and different datasets. The resulting models and training code are open sourced at 4m.epfl.ch.
Authors: Milton L. Montero, Jeffrey S. Bowers, Rui Ponte Costa, Casimir J. H. Ludwig, Gaurav Malhotra
Abstract: Recent research has shown that generative models with highly disentangled representations fail to generalise to unseen combination of generative factor values. These findings contradict earlier research which showed improved performance in out-of-training distribution settings when compared to entangled representations. Additionally, it is not clear if the reported failures are due to (a) encoders failing to map novel combinations to the proper regions of the latent space or (b) novel combinations being mapped correctly but the decoder/downstream process is unable to render the correct output for the unseen combinations. We investigate these alternatives by testing several models on a range of datasets and training settings. We find that (i) when models fail, their encoders also fail to map unseen combinations to correct regions of the latent space and (ii) when models succeed, it is either because the test conditions do not exclude enough examples, or because excluded generative factors determine independent parts of the output image. Based on these results, we argue that to generalise properly, models not only need to capture factors of variation, but also understand how to invert the generative process that was used to generate the data.
Authors: Raffaella Fiamma Cabini, Anna Pichiecchio, Alessandro Lascialfari, Silvia Figini, Mattia Zanella
Abstract: In this work, we apply a kinetic version of a bounded confidence consensus model to biomedical segmentation problems. In the presented approach, time-dependent information on the microscopic state of each particle/pixel includes its space position and a feature representing a static characteristic of the system, i.e. the gray level of each pixel. From the introduced microscopic model we derive a kinetic formulation of the model. The large time behavior of the system is then computed with the aid of a surrogate Fokker-Planck approach that can be obtained in the quasi-invariant scaling. We exploit the computational efficiency of direct simulation Monte Carlo methods for the obtained Boltzmann-type description of the problem for parameter identification tasks. Based on a suitable loss function measuring the distance between the ground truth segmentation mask and the evaluated mask, we minimize the introduced segmentation metric for a relevant set of 2D gray-scale images. Applications to biomedical segmentation concentrate on different imaging research contexts.
Authors: Malte Hoffmann, Andrew Hoopes, Douglas N. Greve, Bruce Fischl, Adrian V. Dalca
Abstract: Affine image registration is a cornerstone of medical image analysis. While classical algorithms can achieve excellent accuracy, they solve a time-consuming optimization for every image pair. Deep-learning (DL) methods learn a function that maps an image pair to an output transform. Evaluating the function is fast, but capturing large transforms can be challenging, and networks tend to struggle if a test-image characteristic shifts from the training domain, such as resolution. Most affine methods are agnostic to the anatomy the user wishes to align, meaning the registration will be inaccurate if algorithms consider all structures in the image. We address these shortcomings with SynthMorph, a fast, symmetric, diffeomorphic, and easy-to-use DL tool for joint affine-deformable registration of any brain image without preprocessing. First, we leverage a strategy that trains networks with widely varying images synthesized from label maps, yielding robust performance for image types unseen at training. Second, we optimize the spatial overlap of select anatomical labels. This enables networks to distinguish anatomy of interest from irrelevant structures, removing the need for preprocessing that excludes content that may impinge on anatomy-specific registration. Third, we combine the affine model with a deformable hypernetwork that lets users choose the optimal deformation-field regularity for their specific data, at registration time, in a fraction of the time required by classical methods. We analyze how competing architectures learn affine transforms and compare state-of-the-art registration tools across an extremely diverse set of neuroimaging data, aiming to truly capture the behavior of methods in the real world. SynthMorph demonstrates high accuracy and is available at https://w3id.org/synthmorph, as a single complete end-to-end solution for registration of brain MRI.
Authors: Yaoxian Song, Penglei Sun, Piaopiao Jin, Yi Ren, Yu Zheng, Zhixu Li, Xiaowen Chu, Yue Zhang, Tiefeng Li, Jason Gu
Abstract: Robotic grasping is a fundamental ability for a robot to interact with the environment. Current methods focus on how to obtain a stable and reliable grasping pose in object level, while little work has been studied on part (shape)-wise grasping which is related to fine-grained grasping and robotic affordance. Parts can be seen as atomic elements to compose an object, which contains rich semantic knowledge and a strong correlation with affordance. However, lacking a large part-wise 3D robotic dataset limits the development of part representation learning and downstream applications. In this paper, we propose a new large Language-guided SHape grAsPing datasEt (named LangSHAPE) to promote 3D part-level affordance and grasping ability learning. From the perspective of robotic cognition, we design a two-stage fine-grained robotic grasping framework (named LangPartGPD), including a novel 3D part language grounding model and a part-aware grasp pose detection model, in which explicit language input from human or large language models (LLMs) could guide a robot to generate part-level 6-DoF grasping pose with textual explanation. Our method combines the advantages of human-robot collaboration and LLMs' planning ability using explicit language as a symbolic intermediate. To evaluate the effectiveness of our proposed method, we perform 3D part grounding and fine-grained grasp detection experiments on both simulation and physical robot settings, following language instructions across different degrees of textual complexity. Results show our method achieves competitive performance in 3D geometry fine-grained grounding, object affordance inference, and 3D part-aware grasping tasks. Our dataset and code are available on our project website https://sites.google.com/view/lang-shape
Authors: Bahjat Kawar, Noam Elata, Tomer Michaeli, Michael Elad
Abstract: Diffusion models have demonstrated impressive results in both data generation and downstream tasks such as inverse problems, text-based editing, classification, and more. However, training such models usually requires large amounts of clean signals which are often difficult or impossible to obtain. In this work, we propose a novel training technique for generative diffusion models based only on corrupted data. We introduce a loss function based on the Generalized Stein's Unbiased Risk Estimator (GSURE), and prove that under some conditions, it is equivalent to the training objective used in fully supervised diffusion models. We demonstrate our technique on face images as well as Magnetic Resonance Imaging (MRI), where the use of undersampled data significantly alleviates data collection costs. Our approach achieves generative performance comparable to its fully supervised counterpart without training on any clean signals. In addition, we deploy the resulting diffusion model in various downstream tasks beyond the degradation present in the training set, showcasing promising results.
Authors: Muyang He, Shuo Yang, Tiejun Huang, Bo Zhao
Abstract: The state of the art of many learning tasks, e.g., image classification, is advanced by collecting larger datasets and then training larger models on them. As the outcome, the increasing computational cost is becoming unaffordable. In this paper, we investigate how to prune the large-scale datasets, and thus produce an informative subset for training sophisticated deep models with negligible performance drop. We propose a simple yet effective dataset pruning method by exploring both the prediction uncertainty and training dynamics. We study dataset pruning by measuring the variation of predictions during the whole training process on large-scale datasets, i.e., ImageNet-1K and ImageNet-21K, and advanced models, i.e., Swin Transformer and ConvNeXt. Extensive experimental results indicate that our method outperforms the state of the art and achieves 25% lossless pruning ratio on both ImageNet-1K and ImageNet-21K. The code and pruned datasets are available at https://github.com/BAAI-DCAI/Dataset-Pruning.
Authors: Maren H{\o}ib{\o}, Andr\'e Pedersen, Vibeke Grotnes Dale, Sissel Marie Berget, Borgny Ytterhus, Cecilia Lindskog, Elisabeth Wik, Lars A. Akslen, Ingerid Reinertsen, Erik Smistad, Marit Valla
Abstract: Digital pathology enables automatic analysis of histopathological sections using artificial intelligence (AI). Automatic evaluation could improve diagnostic efficiency and help find associations between morphological features and clinical outcome. For development of such prediction models, identifying invasive epithelial cells, and separating these from benign epithelial cells and in situ lesions would be the first step. In this study, we aimed to develop an AI model for segmentation of epithelial cells in sections from breast cancer. We generated epithelial ground truth masks by restaining hematoxylin and eosin (HE) sections with cytokeratin (CK) AE1/AE3, and by pathologists' annotations. HE/CK image pairs were used to train a convolutional neural network, and data augmentation was used to make the model more robust. Tissue microarrays (TMAs) from 839 patients, and whole slide images from two patients were used for training and evaluation of the models. The sections were derived from four cohorts of breast cancer patients. TMAs from 21 patients from a fifth cohort was used as a second test set. In quantitative evaluation, a mean Dice score of 0.70, 0.79, and 0.75 for invasive epithelial cells, benign epithelial cells, and in situ lesions, respectively, were achieved. In qualitative scoring (0-5) by pathologists, results were best for all epithelium and invasive epithelium, with scores of 4.7 and 4.4. Scores for benign epithelium and in situ lesions were 3.7 and 2.0. The proposed model segmented epithelial cells in HE stained breast cancer slides well, but further work is needed for accurate division between the classes. Immunohistochemistry, together with pathologists' annotations, enabled the creation of accurate ground truths. The model is made freely available in FastPathology and the code is available at https://github.com/AICAN-Research/breast-epithelium-segmentation
URLs: https://github.com/AICAN-Research/breast-epithelium-segmentation
Authors: Zifan Wang, Junyu Chen, Ziqing Chen, Pengwei Xie, Rui Chen, Li Yi
Abstract: This paper presents GenH2R, a framework for learning generalizable vision-based human-to-robot (H2R) handover skills. The goal is to equip robots with the ability to reliably receive objects with unseen geometry handed over by humans in various complex trajectories. We acquire such generalizability by learning H2R handover at scale with a comprehensive solution including procedural simulation assets creation, automated demonstration generation, and effective imitation learning. We leverage large-scale 3D model repositories, dexterous grasp generation methods, and curve-based 3D animation to create an H2R handover simulation environment named \simabbns, surpassing the number of scenes in existing simulators by three orders of magnitude. We further introduce a distillation-friendly demonstration generation method that automatically generates a million high-quality demonstrations suitable for learning. Finally, we present a 4D imitation learning method augmented by a future forecasting objective to distill demonstrations into a visuo-motor handover policy. Experimental evaluations in both simulators and the real world demonstrate significant improvements (at least +10\% success rate) over baselines in all cases. The project page is https://GenH2R.github.io/.
Authors: Ho Hin Lee, Adam M. Saunders, Michael E. Kim, Samuel W. Remedios, Lucas W. Remedios, Yucheng Tang, Qi Yang, Xin Yu, Shunxing Bao, Chloe Cho, Louise A. Mawn, Tonia S. Rex, Kevin L. Schey, Blake E. Dewey, Jeffrey M. Spraggins, Jerry L. Prince, Yuankai Huo, Bennett A. Landman
Abstract: Purpose: Eye morphology varies significantly across the population, especially for the orbit and optic nerve. These variations limit the feasibility and robustness of generalizing population-wise features of eye organs to an unbiased spatial reference. Approach: To tackle these limitations, we propose a process for creating high-resolution unbiased eye atlases. First, to restore spatial details from scans with a low through-plane resolution compared to a high in-plane resolution, we apply a deep learning-based super-resolution algorithm. Then, we generate an initial unbiased reference with an iterative metric-based registration using a small portion of subject scans. We register the remaining scans to this template and refine the template using an unsupervised deep probabilistic approach that generates a more expansive deformation field to enhance the organ boundary alignment. We demonstrate this framework using magnetic resonance images across four different tissue contrasts, generating four atlases in separate spatial alignments. Results: For each tissue contrast, we find a significant improvement using the Wilcoxon signed-rank test in the average Dice score across four labeled regions compared to a standard registration framework consisting of rigid, affine, and deformable transformations. These results highlight the effective alignment of eye organs and boundaries using our proposed process. Conclusions: By combining super-resolution preprocessing and deep probabilistic models, we address the challenge of generating an eye atlas to serve as a standardized reference across a largely variable population.
Authors: Jingwei Zhang, Cheuk Ting Li, Farzan Farnia
Abstract: The massive developments of generative model frameworks require principled methods for the evaluation of a model's novelty compared to a reference dataset. While the literature has extensively studied the evaluation of the quality, diversity, and generalizability of generative models, the assessment of a model's novelty compared to a reference model has not been adequately explored in the machine learning community. In this work, we focus on the novelty assessment for multi-modal distributions and attempt to address the following differential clustering task: Given samples of a generative model $P_\mathcal{G}$ and a reference model $P_\mathrm{ref}$, how can we discover the sample types expressed by $P_\mathcal{G}$ more frequently than in $P_\mathrm{ref}$? We introduce a spectral approach to the differential clustering task and propose the Kernel-based Entropic Novelty (KEN) score to quantify the mode-based novelty of $P_\mathcal{G}$ with respect to $P_\mathrm{ref}$. We analyze the KEN score for mixture distributions with well-separable components and develop a kernel-based method to compute the KEN score from empirical data. We support the KEN framework by presenting numerical results on synthetic and real image datasets, indicating the framework's effectiveness in detecting novel modes and comparing generative models. The paper's code is available at: www.github.com/buyeah1109/KEN
Authors: Xiujie Song, Mengyue Wu, Kenny Q. Zhu, Chunhao Zhang, Yanyi Chen
Abstract: Large Vision-Language Models (LVLMs), despite their recent success, are hardly comprehensively tested for their cognitive abilities. Inspired by the prevalent use of the "Cookie Theft" task in human cognition test, we propose a novel evaluation benchmark to evaluate high-level cognitive ability of LVLMs using images with rich semantics. It defines eight reasoning capabilities and consists of an image description task and a visual question answering task. Our evaluation on well-known LVLMs shows that there is still a large gap in cognitive ability between LVLMs and humans.
Authors: Chongyu Fan, Jiancheng Liu, Alfred Hero, Sijia Liu
Abstract: The trustworthy machine learning (ML) community is increasingly recognizing the crucial need for models capable of selectively 'unlearning' data points after training. This leads to the problem of machine unlearning (MU), aiming to eliminate the influence of chosen data points on model performance, while still maintaining the model's utility post-unlearning. Despite various MU methods for data influence erasure, evaluations have largely focused on random data forgetting, ignoring the vital inquiry into which subset should be chosen to truly gauge the authenticity of unlearning performance. To tackle this issue, we introduce a new evaluative angle for MU from an adversarial viewpoint. We propose identifying the data subset that presents the most significant challenge for influence erasure, i.e., pinpointing the worst-case forget set. Utilizing a bi-level optimization principle, we amplify unlearning challenges at the upper optimization level to emulate worst-case scenarios, while simultaneously engaging in standard training and unlearning at the lower level, achieving a balance between data influence erasure and model utility. Our proposal offers a worst-case evaluation of MU's resilience and effectiveness. Through extensive experiments across different datasets (including CIFAR-10, 100, CelebA, Tiny ImageNet, and ImageNet) and models (including both image classifiers and generative models), we expose critical pros and cons in existing (approximate) unlearning strategies. Our results illuminate the complex challenges of MU in practice, guiding the future development of more accurate and robust unlearning algorithms. The code is available at https://github.com/OPTML-Group/Unlearn-WorstCase.
Authors: Qingze Bai, Tiange Liu, Zhi Liu, Yubing Tong, Drew Torigian, Jayaram Udupa
Abstract: In this paper, we present XctDiff, an algorithm framework for reconstructing CT from a single radiograph, which decomposes the reconstruction process into two easily controllable tasks: feature extraction and CT reconstruction. Specifically, we first design a progressive feature extraction strategy that is able to extract robust 3D priors from radiographs. Then, we use the extracted prior information to guide the CT reconstruction in the latent space. Moreover, we design a homogeneous spatial codebook to improve the reconstruction quality further. The experimental results show that our proposed method achieves state-of-the-art reconstruction performance and overcomes the blurring issue. We also apply XctDiff on self-supervised pre-training task. The effectiveness indicates that it has promising additional applications in medical image analysis. The code is available at:https://github.com/qingze-bai/XctDiff
Authors: Sojung An, Tae-Jin Oh, Eunha Sohn, Donghyun Kim
Abstract: Deep learning-based time series forecasting has dominated the short-term precipitation forecasting field with the help of its ability to estimate motion flow in high-resolution datasets. The growing interest in precipitation nowcasting offers substantial opportunities for the advancement of current forecasting technologies. Nevertheless, there has been a scarcity of in-depth surveys of time series precipitation forecasting using deep learning. Thus, this paper systemically reviews recent progress in time series precipitation forecasting models. Specifically, we investigate the following key points within background components, covering: i) preprocessing, ii) objective functions, and iii) evaluation metrics. We then categorize forecasting models into \textit{recursive} and \textit{multiple} strategies based on their approaches to predict future frames, investigate the impacts of models using the strategies, and performance assessments. Finally, we evaluate current deep learning-based models for precipitation forecasting on a public benchmark, discuss their limitations and challenges, and present some promising research directions. Our contribution lies in providing insights for a better understanding of time series precipitation forecasting and in aiding the development of robust AI solutions for the future.
Authors: Rongyuan Wu, Lingchen Sun, Zhiyuan Ma, Lei Zhang
Abstract: The pre-trained text-to-image diffusion models have been increasingly employed to tackle the real-world image super-resolution (Real-ISR) problem due to their powerful generative image priors. Most of the existing methods start from random noise to reconstruct the high-quality (HQ) image under the guidance of the given low-quality (LQ) image. While promising results have been achieved, such Real- ISR methods require multiple diffusion steps to reproduce the HQ image, increasing the computational cost. Meanwhile, the random noise introduces uncertainty in the output, which is unfriendly to image restoration tasks. To address these issues, we propose a one-step effective diffusion network, namely OSEDiff, for the Real- ISR problem. We argue that the LQ image contains rich information to restore its HQ counterpart, and hence the given LQ image can be directly taken as the starting point for diffusion, eliminating the uncertainty introduced by random noise sampling. We finetune the pre-trained diffusion network with trainable layers to adapt it to complex image degradations. To ensure that the one-step diffusion model could yield HQ Real-ISR output, we apply variational score distillation in the latent space to conduct KL-divergence regularization. As a result, our OSEDiff model can efficiently and effectively generate HQ images in just one diffusion step. Our experiments demonstrate that OSEDiff achieves comparable or even better Real-ISR results, in terms of both objective metrics and subjective evaluations, than previous diffusion model based Real-ISR methods that require dozens or hundreds of steps. The source codes will be released at https://github.com/cswry/OSEDiff.
Authors: Melvin Wong, Thiago Rios, Stefan Menzel, Yew Soon Ong
Abstract: Engineering design optimization requires an efficient combination of a 3D shape representation, an optimization algorithm, and a design performance evaluation method, which is often computationally expensive. We present a prompt evolution design optimization (PEDO) framework contextualized in a vehicle design scenario that leverages a vision-language model for penalizing impractical car designs synthesized by a generative model. The backbone of our framework is an evolutionary strategy coupled with an optimization objective function that comprises a physics-based solver and a vision-language model for practical or functional guidance in the generated car designs. In the prompt evolutionary search, the optimizer iteratively generates a population of text prompts, which embed user specifications on the aerodynamic performance and visual preferences of the 3D car designs. Then, in addition to the computational fluid dynamics simulations, the pre-trained vision-language model is used to penalize impractical designs and, thus, foster the evolutionary algorithm to seek more viable designs. Our investigations on a car design optimization problem show a wide spread of potential car designs generated at the early phase of the search, which indicates a good diversity of designs in the initial populations, and an increase of over 20\% in the probability of generating practical designs compared to a baseline framework without using a vision-language model. Visual inspection of the designs against the performance results demonstrates prompt evolution as a very promising paradigm for finding novel designs with good optimization performance while providing ease of use in specifying design specifications and preferences via a natural language interface.
Authors: Yuhang Wu, Wenmeng Yu, Yean Cheng, Yan Wang, Xiaohan Zhang, Jiazheng Xu, Ming Ding, Yuxiao Dong
Abstract: Evaluating the alignment capabilities of large Vision-Language Models (VLMs) is essential for determining their effectiveness as helpful assistants. However, existing benchmarks primarily focus on basic abilities using nonverbal methods, such as yes-no and multiple-choice questions. In this paper, we address this gap by introducing AlignMMBench, a comprehensive alignment benchmark specifically designed for emerging Chinese VLMs. This benchmark is meticulously curated from real-world scenarios and Chinese Internet sources, encompassing thirteen specific tasks across three categories, and includes both single-turn and multi-turn dialogue scenarios. Incorporating a prompt rewrite strategy, AlignMMBench encompasses 1,054 images and 4,978 question-answer pairs. To facilitate the evaluation pipeline, we propose CritiqueVLM, a rule-calibrated evaluator that exceeds GPT-4's evaluation ability. Finally, we report the performance of representative VLMs on AlignMMBench, offering insights into the capabilities and limitations of different VLM architectures. All evaluation codes and data are available on https://alignmmbench.github.io.