Authors: Eric Kee, Adam Pikielny, Kevin Blackburn-Matzen, Marc Levoy
Abstract: We describe a system to remove real-world reflections from images for consumer photography. Our system operates on linear (RAW) photos, with the (optional) addition of a contextual photo looking in the opposite direction, e.g., using the "selfie" camera on a mobile device, which helps disambiguate what should be considered the reflection. The system is trained using synthetic mixtures of real-world RAW images, which are combined using a reflection simulation that is photometrically and geometrically accurate. Our system consists of a base model that accepts the captured photo and optional contextual photo as input, and runs at 256p, followed by an up-sampling model that transforms output 256p images to full resolution. The system can produce images for review at 1K in 6.5 seconds on an iPhone 14 Pro. We test on RAW photos that were captured in the field and embody typical consumer photographs.
Authors: Shixuan Gu, Jason Ken Adhinarta, Mikhail Bessmeltsev, Jiancheng Yang, Jessica Zhang, Daniel Berger, Jeff W. Lichtman, Hanspeter Pfister, Donglai Wei
Abstract: Part segmentation is a crucial task for 3D curvilinear structures like neuron dendrites and blood vessels, enabling the analysis of dendritic spines and aneurysms with scientific and clinical significance. However, their diversely winded morphology poses a generalization challenge to existing deep learning methods, which leads to labor-intensive manual correction. In this work, we propose FreSeg, a framework of part segmentation tasks for 3D curvilinear structures. With Frenet-Frame-based point cloud transformation, it enables the models to learn more generalizable features and have significant performance improvements on tasks involving elongated and curvy geometries. We evaluate FreSeg on 2 datasets: 1) DenSpineEM, an in-house dataset for dendritic spine segmentation, and 2) IntrA, a public 3D dataset for intracranial aneurysm segmentation. Further, we will release the DenSpineEM dataset, which includes roughly 6,000 spines from 69 dendrites from 3 public electron microscopy (EM) datasets, to foster the development of effective dendritic spine instance extraction methods and, consequently, large-scale connectivity analysis to better understand mammalian brains.
Authors: Qunwei Lin, Qian Leng, Zhicheng Ding, Chao Yan, Xiaonan Xu
Abstract: In the pursuit of environmental sustainability, the aviation industry faces the challenge of minimizing its ecological footprint. Among the key solutions is contrail avoidance, targeting the linear ice-crystal clouds produced by aircraft exhaust. These contrails exacerbate global warming by trapping atmospheric heat, necessitating precise segmentation and comprehensive analysis of contrail images to gauge their environmental impact. However, this segmentation task is complex due to the varying appearances of contrails under different atmospheric conditions and potential misalignment issues in predictive modeling. This paper presents an innovative deep-learning approach utilizing the efficient net-b4 encoder for feature extraction, seamlessly integrating misalignment correction, soft labeling, and pseudo-labeling techniques to enhance the accuracy and efficiency of contrail detection in satellite imagery. The proposed methodology aims to redefine contrail image analysis and contribute to the objectives of sustainable aviation by providing a robust framework for precise contrail detection and analysis in satellite imagery, thus aiding in the mitigation of aviation's environmental impact.
Authors: Shiyi Zhang, Sule Bai, Guangyi Chen, Lei Chen, Jiwen Lu, Junle Wang, Yansong Tang
Abstract: In this paper, we investigate a new problem called narrative action evaluation (NAE). NAE aims to generate professional commentary that evaluates the execution of an action. Unlike traditional tasks such as score-based action quality assessment and video captioning involving superficial sentences, NAE focuses on creating detailed narratives in natural language. These narratives provide intricate descriptions of actions along with objective evaluations. NAE is a more challenging task because it requires both narrative flexibility and evaluation rigor. One existing possible solution is to use multi-task learning, where narrative language and evaluative information are predicted separately. However, this approach results in reduced performance for individual tasks because of variations between tasks and differences in modality between language information and evaluation information. To address this, we propose a prompt-guided multimodal interaction framework. This framework utilizes a pair of transformers to facilitate the interaction between different modalities of information. It also uses prompts to transform the score regression task into a video-text matching task, thus enabling task interactivity. To support further research in this field, we re-annotate the MTL-AQA and FineGym datasets with high-quality and comprehensive action narration. Additionally, we establish benchmarks for NAE. Extensive experiment results prove that our method outperforms separate learning methods and naive multi-task learning methods. Data and code are released at \href{https://github.com/shiyi-zh0408/NAE_CVPR2024 }{here}.
Authors: Amirmojtaba Sabour, Sanja Fidler, Karsten Kreis
Abstract: Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed, relying on many sequential function evaluations through large neural networks. Sampling from DMs can be seen as solving a differential equation through a discretized set of noise levels known as the sampling schedule. While past works primarily focused on deriving efficient solvers, little attention has been given to finding optimal sampling schedules, and the entire literature relies on hand-crafted heuristics. In this work, for the first time, we propose a general and principled approach to optimizing the sampling schedules of DMs for high-quality outputs, called $\textit{Align Your Steps}$. We leverage methods from stochastic calculus and find optimal schedules specific to different solvers, trained DMs and datasets. We evaluate our novel approach on several image, video as well as 2D toy data synthesis benchmarks, using a variety of different samplers, and observe that our optimized schedules outperform previous hand-crafted schedules in almost all experiments. Our method demonstrates the untapped potential of sampling schedule optimization, especially in the few-step synthesis regime.
Authors: Yaofeng Xie, Lingwei Kong, Kai Chen, Ziqiang Zheng, Xiao Yu, Zhibin Yu, Bing Zheng
Abstract: Learning-based underwater image enhancement (UIE) methods have made great progress. However, the lack of large-scale and high-quality paired training samples has become the main bottleneck hindering the development of UIE. The inter-frame information in underwater videos can accelerate or optimize the UIE process. Thus, we constructed the first large-scale high-resolution underwater video enhancement benchmark (UVEB) to promote the development of underwater vision.It contains 1,308 pairs of video sequences and more than 453,000 high-resolution with 38\% Ultra-High-Definition (UHD) 4K frame pairs. UVEB comes from multiple countries, containing various scenes and video degradation types to adapt to diverse and complex underwater environments. We also propose the first supervised underwater video enhancement method, UVE-Net. UVE-Net converts the current frame information into convolutional kernels and passes them to adjacent frames for efficient inter-frame information exchange. By fully utilizing the redundant degraded information of underwater videos, UVE-Net completes video enhancement better. Experiments show the effective network design and good performance of UVE-Net.
Authors: Tahmim Hossain, Faisal Sayed, Solehin Islam
Abstract: The shortage of nephrologists and the growing public health concern over renal failure have spurred the demand for AI systems capable of autonomously detecting kidney abnormalities. Renal failure, marked by a gradual decline in kidney function, can result from factors like cysts, stones, and tumors. Chronic kidney disease may go unnoticed initially, leading to untreated cases until they reach an advanced stage. The dataset, comprising 12,427 images from multiple hospitals in Dhaka, was categorized into four groups: cyst, tumor, stone, and normal. Our methodology aims to enhance CT scan image quality using Cropping, Resizing, and CALHE techniques, followed by feature extraction with our proposed Adaptive Local Binary Pattern (A-LBP) feature extraction method compared with the state-of-the-art local binary pattern (LBP) method. Our proposed features fed into classifiers such as Random Forest, Decision Tree, Naive Bayes, K-Nearest Neighbor, and SVM. We explored an ensemble model with soft voting to get a more robust model for our task. We got the highest of more than 99% in accuracy using our feature descriptor and ensembling five classifiers (Random Forest, Decision Tree, Naive Bayes, K-Nearest Neighbor, Support Vector Machine) with the soft voting method.
Authors: Jiaqi Chen, Daniel Barath, Iro Armeni, Marc Pollefeys, Hermann Blum
Abstract: Natural language interfaces to embodied AI are becoming more ubiquitous in our daily lives. This opens further opportunities for language-based interaction with embodied agents, such as a user instructing an agent to execute some task in a specific location. For example, "put the bowls back in the cupboard next to the fridge" or "meet me at the intersection under the red sign." As such, we need methods that interface between natural language and map representations of the environment. To this end, we explore the question of whether we can use an open-set natural language query to identify a scene represented by a 3D scene graph. We define this task as "language-based scene-retrieval" and it is closely related to "coarse-localization," but we are instead searching for a match from a collection of disjoint scenes and not necessarily a large-scale continuous map. Therefore, we present Text2SceneGraphMatcher, a "scene-retrieval" pipeline that learns joint embeddings between text descriptions and scene graphs to determine if they are matched. The code, trained models, and datasets will be made public.
Authors: Weijie Wang, Jichao Zhang, Chang Liu, Xia Li, Xingqian Xu, Humphrey Shi, Nicu Sebe, Bruno Lepri
Abstract: Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D text-to-image diffusion models into the 3D domain for generating human textures (UV Maps). However, some important problems about UV Map Generative models are still not solved, i.e., how to generate personalized texture maps for any given face image, and how to define and evaluate the quality of these generated texture maps. To solve the above problems, we introduce a novel method, UVMap-ID, which is a controllable and personalized UV Map generative model. Unlike traditional large-scale training methods in 2D, we propose to fine-tune a pre-trained text-to-image diffusion model which is integrated with a face fusion module for achieving ID-driven customized generation. To support the finetuning strategy, we introduce a small-scale attribute-balanced training dataset, including high-quality textures with labeled text and Face ID. Additionally, we introduce some metrics to evaluate the multiple aspects of the textures. Finally, both quantitative and qualitative analyses demonstrate the effectiveness of our method in controllable and personalized UV Map generation. Code is publicly available via https://github.com/twowwj/UVMap-ID.
Authors: Yuying Li, Zeyan Liu, Junyi Zhao, Liangqin Ren, Fengjun Li, Jiebo Luo, Bo Luo
Abstract: Generative AI models can produce high-quality images based on text prompts. The generated images often appear indistinguishable from images generated by conventional optical photography devices or created by human artists (i.e., real images). While the outstanding performance of such generative models is generally well received, security concerns arise. For instance, such image generators could be used to facilitate fraud or scam schemes, generate and spread misinformation, or produce fabricated artworks. In this paper, we present a systematic attempt at understanding and detecting AI-generated images (AI-art) in adversarial scenarios. First, we collect and share a dataset of real images and their corresponding artificial counterparts generated by four popular AI image generators. The dataset, named ARIA, contains over 140K images in five categories: artworks (painting), social media images, news photos, disaster scenes, and anime pictures. This dataset can be used as a foundation to support future research on adversarial AI-art. Next, we present a user study that employs the ARIA dataset to evaluate if real-world users can distinguish with or without reference images. In a benchmarking study, we further evaluate if state-of-the-art open-source and commercial AI image detectors can effectively identify the images in the ARIA dataset. Finally, we present a ResNet-50 classifier and evaluate its accuracy and transferability on the ARIA dataset.
Authors: Armando Zhu, Keqin Li, Tong Wu, Peng Zhao, Wenjing Zhou, Bo Hong
Abstract: With wearing masks becoming a new cultural norm, facial expression recognition (FER) while taking masks into account has become a significant challenge. In this paper, we propose a unified multi-branch vision transformer for facial expression recognition and mask wearing classification tasks. Our approach extracts shared features for both tasks using a dual-branch architecture that obtains multi-scale feature representations. Furthermore, we propose a cross-task fusion phase that processes tokens for each task with separate branches, while exchanging information using a cross attention module. Our proposed framework reduces the overall complexity compared with using separate networks for both tasks by the simple yet effective cross-task fusion phase. Extensive experiments demonstrate that our proposed model performs better than or on par with different state-of-the-art methods on both facial expression recognition and facial mask wearing classification task.
Authors: Vandad Davoodnia, Saeed Ghorbani, Marc-Andr\'e Carbonneau, Alexandre Messier, Ali Etemad
Abstract: We introduce UPose3D, a novel approach for multi-view 3D human pose estimation, addressing challenges in accuracy and scalability. Our method advances existing pose estimation frameworks by improving robustness and flexibility without requiring direct 3D annotations. At the core of our method, a pose compiler module refines predictions from a 2D keypoints estimator that operates on a single image by leveraging temporal and cross-view information. Our novel cross-view fusion strategy is scalable to any number of cameras, while our synthetic data generation strategy ensures generalization across diverse actors, scenes, and viewpoints. Finally, UPose3D leverages the prediction uncertainty of both the 2D keypoint estimator and the pose compiler module. This provides robustness to outliers and noisy data, resulting in state-of-the-art performance in out-of-distribution settings. In addition, for in-distribution settings, UPose3D yields a performance rivaling methods that rely on 3D annotated data, while being the state-of-the-art among methods relying only on 2D supervision.
Authors: Achyut Paudel, Jostan Brown, Priyanka Upadhyaya, Atif Bilal Asad, Safal Kshetri, Manoj Karkee, Joseph R. Davidson, Cindy Grimm, Ashley Thompson
Abstract: Apple trees being deciduous trees, shed leaves each year which is preceded by the change in color of leaves from green to yellow (also known as senescence) during the fall season. The rate and timing of color change are affected by the number of factors including nitrogen (N) deficiencies. The green color of leaves is highly dependent on the chlorophyll content, which in turn depends on the nitrogen concentration in the leaves. The assessment of the leaf color can give vital information on the nutrient status of the tree. The use of a machine vision based system to capture and quantify these timings and changes in leaf color can be a great tool for that purpose. \par This study is based on data collected during the fall of 2021 and 2023 at a commercial orchard using a ground-based stereo-vision sensor for five weeks. The point cloud obtained from the sensor was segmented to get just the tree in the foreground. The study involved the segmentation of the trees in a natural background using point cloud data and quantification of the color using a custom-defined metric, \textit{yellowness index}, varying from $-1$ to $+1$ ($-1$ being completely green and $+1$ being completely yellow), which gives the proportion of yellow leaves on a tree. The performance of K-means based algorithm and gradient boosting algorithm were compared for \textit{yellowness index} calculation. The segmentation method proposed in the study was able to estimate the \textit{yellowness index} on the trees with $R^2 = 0.72$. The results showed that the metric was able to capture the gradual color transition from green to yellow over the study duration. It was also observed that the trees with lower nitrogen showed the color transition to yellow earlier than the trees with higher nitrogen. The onset of color transition during both years aligned with the $29^{th}$ week post-full bloom.
Authors: Abhishek Aich, Yumin Suh, Samuel Schulter, Manmohan Chandraker
Abstract: A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses ~50% of its compute only on the transformer encoder. This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer. With this observation, we propose a strategy termed PROgressive Token Length SCALing for Efficient transformer encoders (PRO-SCALE) that can be plugged-in to the Mask2Former-style segmentation architectures to significantly reduce the computational cost. The underlying principle of PRO-SCALE is: progressively scale the length of the tokens with the layers of the encoder. This allows PRO-SCALE to reduce computations by a large margin with minimal sacrifice in performance (~52% GFLOPs reduction with no drop in performance on COCO dataset). We validate our framework on multiple public benchmarks.
Authors: Guangpeng Fan, Fei Yan, Xiangquan Zeng, Qingtao Xu, Ruoyoulan Wang, Binghong Zhang, Jialing Zhou, Liangliang Nan, Jinhu Wang, Zhiwei Zhang, Jia Wang
Abstract: We have developed the world's first canopy height map of the distribution area of world-level giant trees. This mapping is crucial for discovering more individual and community world-level giant trees, and for analyzing and quantifying the effectiveness of biodiversity conservation measures in the Yarlung Tsangpo Grand Canyon (YTGC) National Nature Reserve. We proposed a method to map the canopy height of the primeval forest within the world-level giant tree distribution area by using a spaceborne LiDAR fusion satellite imagery (Global Ecosystem Dynamics Investigation (GEDI), ICESat-2, and Sentinel-2) driven deep learning modeling. And we customized a pyramid receptive fields depth separable CNN (PRFXception). PRFXception, a CNN architecture specifically customized for mapping primeval forest canopy height to infer the canopy height at the footprint level of GEDI and ICESat-2 from Sentinel-2 optical imagery with a 10-meter spatial resolution. We conducted a field survey of 227 permanent plots using a stratified sampling method and measured several giant trees using UAV-LS. The predicted canopy height was compared with ICESat-2 and GEDI validation data (RMSE =7.56 m, MAE=6.07 m, ME=-0.98 m, R^2=0.58 m), UAV-LS point clouds (RMSE =5.75 m, MAE =3.72 m, ME = 0.82 m, R^2= 0.65 m), and ground survey data (RMSE = 6.75 m, MAE = 5.56 m, ME= 2.14 m, R^2=0.60 m). We mapped the potential distribution map of world-level giant trees and discovered two previously undetected giant tree communities with an 89% probability of having trees 80-100 m tall, potentially taller than Asia's tallest tree. This paper provides scientific evidence confirming southeastern Tibet--northwestern Yunnan as the fourth global distribution center of world-level giant trees initiatives and promoting the inclusion of the YTGC giant tree distribution area within the scope of China's national park conservation.
Authors: Siddharth Nijhawan, Takuya Yashima, Tamaki Kojima
Abstract: Performing facial expression transfer under one-shot setting has been increasing in popularity among research community with a focus on precise control of expressions. Existing techniques showcase compelling results in perceiving expressions, but they lack robustness with extreme head poses. They also struggle to accurately reconstruct background details, thus hindering the realism. In this paper, we propose a novel warping technology which integrates the advantages of both 2D and 3D methods to achieve robust face re-enactment. We generate dense 3D facial flow fields in feature space to warp an input image based on target expressions without depth information. This enables explicit 3D geometric control for re-enacting misaligned source and target faces. We regularize the motion estimation capability of the 3D flow prediction network through proposed "Cyclic warp loss" by converting warped 3D features back into 2D RGB space. To ensure the generation of finer facial region with natural-background, our framework only renders the facial foreground region first and learns to inpaint the blank area which needs to be filled due to source face translation, thus reconstructing the detailed background without any unwanted pixel motion. Extensive evaluation reveals that our method outperforms state-of-the-art techniques in rendering artifact-free facial images.
Authors: Ming Nie, Xinyue Cai, Hang Xu, Li Zhang
Abstract: Lane detection has evolved highly functional autonomous driving system to understand driving scenes even under complex environments. In this paper, we work towards developing a generalized computer vision system able to detect lanes without using any annotation. We make the following contributions: (i) We illustrate how to perform unsupervised 3D lane segmentation by leveraging the distinctive intensity of lanes on the LiDAR point cloud frames, and then obtain the noisy lane labels in the 2D plane by projecting the 3D points; (ii) We propose a novel self-supervised training scheme, dubbed LaneCorrect, that automatically corrects the lane label by learning geometric consistency and instance awareness from the adversarial augmentations; (iii) With the self-supervised pre-trained model, we distill to train a student network for arbitrary target lane (e.g., TuSimple) detection without any human labels; (iv) We thoroughly evaluate our self-supervised method on four major lane detection benchmarks (including TuSimple, CULane, CurveLanes and LLAMAS) and demonstrate excellent performance compared with existing supervised counterpart, whilst showing more effective results on alleviating the domain gap, i.e., training on CULane and test on TuSimple.
Authors: Linxuan Xin, Zheng Zhang, Jinfu Wei, Ge Li, Duan Gao
Abstract: Prior material creation methods had limitations in producing diverse results mainly because reconstruction-based methods relied on real-world measurements and generation-based methods were trained on relatively small material datasets. To address these challenges, we propose DreamPBR, a novel diffusion-based generative framework designed to create spatially-varying appearance properties guided by text and multi-modal controls, providing high controllability and diversity in material generation. Key to achieving diverse and high-quality PBR material generation lies in integrating the capabilities of recent large-scale vision-language models trained on billions of text-image pairs, along with material priors derived from hundreds of PBR material samples. We utilize a novel material Latent Diffusion Model (LDM) to establish the mapping between albedo maps and the corresponding latent space. The latent representation is then decoded into full SVBRDF parameter maps using a rendering-aware PBR decoder. Our method supports tileable generation through convolution with circular padding. Furthermore, we introduce a multi-modal guidance module, which includes pixel-aligned guidance, style image guidance, and 3D shape guidance, to enhance the control capabilities of the material LDM. We demonstrate the effectiveness of DreamPBR in material creation, showcasing its versatility and user-friendliness on a wide range of controllable generation and editing applications.
Authors: Junjie Zhang, Tianci Hu, Xiaoshui Huang, Yongshun Gong, Dan Zeng
Abstract: Evaluating the performance of Multi-modal Large Language Models (MLLMs), integrating both point cloud and language, presents significant challenges. The lack of a comprehensive assessment hampers determining whether these models truly represent advancements, thereby impeding further progress in the field. Current evaluations heavily rely on classification and caption tasks, falling short in providing a thorough assessment of MLLMs. A pressing need exists for a more sophisticated evaluation method capable of thoroughly analyzing the spatial understanding and expressive capabilities of these models. To address these issues, we introduce a scalable 3D benchmark, accompanied by a large-scale instruction-tuning dataset known as 3DBench, providing an extensible platform for a comprehensive evaluation of MLLMs. Specifically, we establish the benchmark that spans a wide range of spatial and semantic scales, from object-level to scene-level, addressing both perception and planning tasks. Furthermore, we present a rigorous pipeline for automatically constructing scalable 3D instruction-tuning datasets, covering 10 diverse multi-modal tasks with more than 0.23 million QA pairs generated in total. Thorough experiments evaluating trending MLLMs, comparisons against existing datasets, and variations of training protocols demonstrate the superiority of 3DBench, offering valuable insights into current limitations and potential research directions.
Authors: Yuxiang Yang, Lu Wen, Yuanyuan Xu, Jiliu Zhou, Yan Wang
Abstract: Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple labeled source domains to an unlabeled target domain under domain shifts (different data distribution) and class shifts (unknown target classes). Existing solutions focus on excavating image features to detect unknown samples, ignoring abundant information contained in textual semantics. In this paper, we propose an Adaptive Prompt learning with Negative textual semantics and uncErtainty modeling method based on Contrastive Language-Image Pre-training (APNE-CLIP) for UniMDA classification tasks. Concretely, we utilize the CLIP with adaptive prompts to leverage textual information of class semantics and domain representations, helping the model identify unknown samples and address domain shifts. Additionally, we design a novel global instance-level alignment objective by utilizing negative textual semantics to achieve more precise image-text pair alignment. Furthermore, we propose an energy-based uncertainty modeling strategy to enlarge the margin distance between known and unknown samples. Extensive experiments demonstrate the superiority of our proposed method.
Authors: Clifford Broni-Bediako, Junshi Xia, Naoto Yokoya
Abstract: Unsupervised domain adaptation (UDA) is a challenging open problem in land cover mapping. Previous studies show encouraging progress in addressing cross-domain distribution shifts on remote sensing benchmarks for land cover mapping. The existing works are mainly built on large neural network architectures, which makes them resource-hungry systems, limiting their practical impact for many real-world applications in resource-constrained environments. Thus, we proposed a simple yet effective framework to search for lightweight neural networks automatically for land cover mapping tasks under domain shifts. This is achieved by integrating Markov random field neural architecture search (MRF-NAS) into a self-training UDA framework to search for efficient and effective networks under a limited computation budget. This is the first attempt to combine NAS with self-training UDA as a single framework for land cover mapping. We also investigate two different pseudo-labelling approaches (confidence-based and energy-based) in self-training scheme. Experimental results on two recent datasets (OpenEarthMap & FLAIR #1) for remote sensing UDA demonstrate a satisfactory performance. With only less than 2M parameters and 30.16 GFLOPs, the best-discovered lightweight network reaches state-of-the-art performance on the regional target domain of OpenEarthMap (59.38% mIoU) and the considered target domain of FLAIR #1 (51.19% mIoU). The code is at https://github.com/cliffbb/UDA-NAS}{https://github.com/cliffbb/UDA-NAS.
URLs: https://github.com/cliffbb/UDA-NAS, https://github.com/cliffbb/UDA-NAS.
Authors: Qingrong He, Kejun Lin, Shizhe Chen, Anwen Hu, Qin Jin
Abstract: This work addresses the 3D situated reasoning task which aims to answer questions given egocentric observations in a 3D environment. The task remains challenging as it requires comprehensive 3D perception and complex reasoning skills. End-to-end models trained on supervised data for 3D situated reasoning suffer from data scarcity and generalization ability. Inspired by the recent success of leveraging large language models (LLMs) for visual reasoning, we propose LLM-TPC, a novel framework that leverages the planning, tool usage, and reflection capabilities of LLMs through a ThinkProgram-reCtify loop. The Think phase first decomposes the compositional question into a sequence of steps, and then the Program phase grounds each step to a piece of code and calls carefully designed 3D visual perception modules. Finally, the Rectify phase adjusts the plan and code if the program fails to execute. Experiments and analysis on the SQA3D benchmark demonstrate the effectiveness, interpretability and robustness of our method. Our code is publicly available at https://qingrongh.github.io/LLM-TPC/.
Authors: Tong Zhang, Wenxue Cui, Shaohui Liu, Feng Jiang
Abstract: Convolutional Neural Network (CNN) and Transformer have attracted much attention recently for video post-processing (VPP). However, the interaction between CNN and Transformer in existing VPP methods is not fully explored, leading to inefficient communication between the local and global extracted features. In this paper, we explore the interaction between CNN and Transformer in the task of VPP, and propose a novel Spatial and Channel Hybrid-Attention Video Post-Processing Network (SC-HVPPNet), which can cooperatively exploit the image priors in both spatial and channel domains. Specifically, in the spatial domain, a novel spatial attention fusion module is designed, in which two attention weights are generated to fuse the local and global representations collaboratively. In the channel domain, a novel channel attention fusion module is developed, which can blend the deep representations at the channel dimension dynamically. Extensive experiments show that SC-HVPPNet notably boosts video restoration quality, with average bitrate savings of 5.29%, 12.42%, and 13.09% for Y, U, and V components in the VTM-11.0-NNVC RA configuration.
Authors: Hang Hua, Jing Shi, Kushal Kafle, Simon Jenni, Daoan Zhang, John Collomosse, Scott Cohen, Jiebo Luo
Abstract: Recent progress in large-scale pre-training has led to the development of advanced vision-language models (VLMs) with remarkable proficiency in comprehending and generating multimodal content. Despite the impressive ability to perform complex reasoning for VLMs, current models often struggle to effectively and precisely capture the compositional information on both the image and text sides. To address this, we propose FineMatch, a new aspect-based fine-grained text and image matching benchmark, focusing on text and image mismatch detection and correction. This benchmark introduces a novel task for boosting and evaluating the VLMs' compositionality for aspect-based fine-grained text and image matching. In this task, models are required to identify mismatched aspect phrases within a caption, determine the aspect's class, and propose corrections for an image-text pair that may contain between 0 and 3 mismatches. To evaluate the models' performance on this new task, we propose a new evaluation metric named ITM-IoU for which our experiments show a high correlation to human evaluation. In addition, we also provide a comprehensive experimental analysis of existing mainstream VLMs, including fully supervised learning and in-context learning settings. We have found that models trained on FineMatch demonstrate enhanced proficiency in detecting fine-grained text and image mismatches. Moreover, models (e.g., GPT-4V, Gemini Pro Vision) with strong abilities to perform multimodal in-context learning are not as skilled at fine-grained compositional image and text matching analysis. With FineMatch, we are able to build a system for text-to-image generation hallucination detection and correction.
Authors: Utkarsh Gupta, Emmanouil Nikolakakis, Moritz Zaiss, Razvan Marinescu
Abstract: Reconstructing digital brain phantoms in the form of multi-channeled brain tissue probability maps for individual subjects is essential for capturing brain anatomical variability, understanding neurological diseases, as well as for testing image processing methods. We demonstrate the first framework that optimizes brain tissue probability maps (Gray Matter - GM, White Matter - WM, and Cerebrospinal fluid - CSF) with the help of a Physics-based differentiable MRI simulator that models the magnetization signal at each voxel in the image. Given an observed $T_1$/$T_2$-weighted MRI scan, the corresponding clinical MRI sequence, and the MRI differentiable simulator, we optimize the simulator's input probability maps by back-propagating the L2 loss between the simulator's output and the $T_1$/$T_2$-weighted scan. This approach has the significant advantage of not relying on any training data, and instead uses the strong inductive bias of the MRI simulator. We tested the model on 20 scans from the BrainWeb database and demonstrate a highly accurate reconstruction of GM, WM, and CSF.
Authors: Runqi Wang, Caoyuan Ma, GuoPeng Li, Zheng Wang
Abstract: Text2Motion aims to generate human motions from texts. Existing datasets rely on the assumption that texts include action labels (such as "walk, bend, and pick up"), which is not flexible for practical scenarios. This paper redefines this problem with a more realistic assumption that the texts are arbitrary. Specifically, arbitrary texts include existing action texts composed of action labels (e.g., A person walks and bends to pick up something), and introduce scene texts without explicit action labels (e.g., A person notices his wallet on the ground ahead). To bridge the gaps between this realistic setting and existing datasets, we expand the action texts on the HumanML3D dataset to more scene texts, thereby creating a new HumanML3D++ dataset including arbitrary texts. In this challenging dataset, we benchmark existing state-of-the-art methods and propose a novel two-stage framework to extract action labels from arbitrary texts by the Large Language Model (LLM) and then generate motions from action labels. Extensive experiments are conducted under different application scenarios to validate the effectiveness of the proposed framework on existing and proposed datasets. The results indicate that Text2Motion in this realistic setting is very challenging, fostering new research in this practical direction. Our dataset and code will be released.
Authors: Mareike Thies, Noah Maul, Siyuan Mei, Laura Pfaff, Nastassia Vysotskaya, Mingxuan Gu, Jonas Utz, Dennis Possart, Lukas Folle, Fabian Wagner, Andreas Maier
Abstract: Motion artifacts can compromise the diagnostic value of computed tomography (CT) images. Motion correction approaches require a per-scan estimation of patient-specific motion patterns. In this work, we train a score-based model to act as a probability density estimator for clean head CT images. Given the trained model, we quantify the deviation of a given motion-affected CT image from the ideal distribution through likelihood computation. We demonstrate that the likelihood can be utilized as a surrogate metric for motion artifact severity in the CT image facilitating the application of an iterative, gradient-based motion compensation algorithm. By optimizing the underlying motion parameters to maximize likelihood, our method effectively reduces motion artifacts, bringing the image closer to the distribution of motion-free scans. Our approach achieves comparable performance to state-of-the-art methods while eliminating the need for a representative data set of motion-affected samples. This is particularly advantageous in real-world applications, where patient motion patterns may exhibit unforeseen variability, ensuring robustness without implicit assumptions about recoverable motion types.
Authors: Qiao Deng, Zhongzhen Huang, Yunqi Wang, Zhichuan Wang, Zhao Wang, Xiaofan Zhang, Qi Dou, Yeung Yu Hui, Edward S. Hui
Abstract: Medical vision-language pre-training has emerged as a promising approach for learning domain-general representations of medical image and text. Current algorithms that exploit the global and local alignment between medical image and text could however be marred by the redundant information in medical data. To address this issue, we propose a grounded knowledge-enhanced medical vision-language pre-training (GK-MVLP) framework for chest X-ray. In this framework, medical knowledge is grounded to the appropriate anatomical regions by using a transformer-based grounded knowledge-enhanced module for fine-grained alignment between anatomical region-level visual features and the textural features of medical knowledge. The performance of GK-MVLP is competitive with or exceeds the state of the art on downstream chest X-ray disease classification, disease localization, report generation, and medical visual question-answering tasks. Our results show the advantage of incorporating grounding mechanism to remove biases and improve the alignment between chest X-ray image and radiology report.
Authors: Yao Yuan, Wutao Liu, Pan Gao, Qun Dai, Jie Qin
Abstract: Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks such as RGB and RGB-D, neglecting the potential for task migration. In this paper, we propose a unified USOD framework for generic USOD tasks. Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network. This mechanism starts with easy samples and progressively moves towards harder ones, to avoid initial interference caused by hard samples. Afterwards, the obtained saliency cues are utilized to train a saliency detector, and we employ a Self-rectify Pseudo-label Refinement (SPR) mechanism to improve the quality of pseudo-labels. Finally, an adapter-tuning method is devised to transfer the acquired saliency knowledge, leveraging shared knowledge to attain superior transferring performance on the target tasks. Extensive experiments on five representative SOD tasks confirm the effectiveness and feasibility of our proposed method. Code and supplement materials are available at https://github.com/I2-Multimedia-Lab/A2S-v3.
Authors: Hongyu Chen, Yiqi Gao, Min Zhou, Peng Wang, Xubin Li, Tiezheng Ge, Bo Zheng
Abstract: Recently, integrating visual controls into text-to-image~(T2I) models, such as ControlNet method, has received significant attention for finer control capabilities. While various training-free methods make efforts to enhance prompt following in T2I models, the issue with visual control is still rarely studied, especially in the scenario that visual controls are misaligned with text prompts. In this paper, we address the challenge of ``Prompt Following With Visual Control" and propose a training-free approach named Mask-guided Prompt Following (MGPF). Object masks are introduced to distinct aligned and misaligned parts of visual controls and prompts. Meanwhile, a network, dubbed as Masked ControlNet, is designed to utilize these object masks for object generation in the misaligned visual control region. Further, to improve attribute matching, a simple yet efficient loss is designed to align the attention maps of attributes with object regions constrained by ControlNet and object masks. The efficacy and superiority of MGPF are validated through comprehensive quantitative and qualitative experiments.
Authors: Shounak Sural (Raj), Nishad Sahu (Raj), Ragunathan (Raj), Rajkumar
Abstract: The fusion of multimodal sensor data streams such as camera images and lidar point clouds plays an important role in the operation of autonomous vehicles (AVs). Robust perception across a range of adverse weather and lighting conditions is specifically required for AVs to be deployed widely. While multi-sensor fusion networks have been previously developed for perception in sunny and clear weather conditions, these methods show a significant degradation in performance under night-time and poor weather conditions. In this paper, we propose a simple yet effective technique called ContextualFusion to incorporate the domain knowledge about cameras and lidars behaving differently across lighting and weather variations into 3D object detection models. Specifically, we design a Gated Convolutional Fusion (GatedConv) approach for the fusion of sensor streams based on the operational context. To aid in our evaluation, we use the open-source simulator CARLA to create a multimodal adverse-condition dataset called AdverseOp3D to address the shortcomings of existing datasets being biased towards daytime and good-weather conditions. Our ContextualFusion approach yields an mAP improvement of 6.2% over state-of-the-art methods on our context-balanced synthetic dataset. Finally, our method enhances state-of-the-art 3D objection performance at night on the real-world NuScenes dataset with a significant mAP improvement of 11.7%.
Authors: Jieru Lin, Danqing Huang, Tiejun Zhao, Dechen Zhan, Chin-Yew Lin
Abstract: A well-executed graphic design typically achieves harmony in two levels, from the fine-grained design elements (color, font and layout) to the overall design. This complexity makes the comprehension of graphic design challenging, for it needs the capability to both recognize the design elements and understand the design. With the rapid development of Multimodal Large Language Models (MLLMs), we establish the DesignProbe, a benchmark to investigate the capability of MLLMs in design. Our benchmark includes eight tasks in total, across both the fine-grained element level and the overall design level. At design element level, we consider both the attribute recognition and semantic understanding tasks. At overall design level, we include style and metaphor. 9 MLLMs are tested and we apply GPT-4 as evaluator. Besides, further experiments indicates that refining prompts can enhance the performance of MLLMs. We first rewrite the prompts by different LLMs and found increased performances appear in those who self-refined by their own LLMs. We then add extra task knowledge in two different ways (text descriptions and image examples), finding that adding images boost much more performance over texts.
Authors: Siyuan Mei, Fuxin Fan, Mareike Thies, Mingxuan Gu, Fabian Wagner, Oliver Aust, Ina Erceg, Zeynab Mirzaei, Georgiana Neag, Yipeng Sun, Yixing Huang, Andreas Maier
Abstract: Recently, X-ray microscopy (XRM) and light-sheet fluorescence microscopy (LSFM) have emerged as two pivotal imaging tools in preclinical research on bone remodeling diseases, offering micrometer-level resolution. Integrating these complementary modalities provides a holistic view of bone microstructures, facilitating function-oriented volume analysis across different disease cycles. However, registering such independently acquired large-scale volumes is extremely challenging under real and reference-free scenarios. This paper presents a fast two-stage pipeline for volume registration of XRM and LSFM. The first stage extracts the surface features and employs two successive point cloud-based methods for coarse alignment. The second stage fine-tunes the initial alignment using a modified cross-correlation method, ensuring precise volumetric registration. Moreover, we propose residual similarity as a novel metric to assess the alignment of two complementary modalities. The results imply robust gradual improvement across the stages. In the end, all correlating microstructures, particularly lacunae in XRM and bone cells in LSFM, are precisely matched, enabling new insights into bone diseases like osteoporosis which are a substantial burden in aging societies.
Authors: Wenjin Hou, Shiming Chen, Shuhuang Chen, Ziming Hong, Yan Wang, Xuetao Feng, Salman Khan, Fahad Shahbaz Khan, Xinge You
Abstract: Generative Zero-shot learning (ZSL) learns a generator to synthesize visual samples for unseen classes, which is an effective way to advance ZSL. However, existing generative methods rely on the conditions of Gaussian noise and the predefined semantic prototype, which limit the generator only optimized on specific seen classes rather than characterizing each visual instance, resulting in poor generalizations (\textit{e.g.}, overfitting to seen classes). To address this issue, we propose a novel Visual-Augmented Dynamic Semantic prototype method (termed VADS) to boost the generator to learn accurate semantic-visual mapping by fully exploiting the visual-augmented knowledge into semantic conditions. In detail, VADS consists of two modules: (1) Visual-aware Domain Knowledge Learning module (VDKL) learns the local bias and global prior of the visual features (referred to as domain visual knowledge), which replace pure Gaussian noise to provide richer prior noise information; (2) Vision-Oriented Semantic Updation module (VOSU) updates the semantic prototype according to the visual representations of the samples. Ultimately, we concatenate their output as a dynamic semantic prototype, which serves as the condition of the generator. Extensive experiments demonstrate that our VADS achieves superior CZSL and GZSL performances on three prominent datasets and outperforms other state-of-the-art methods with averaging increases by 6.4\%, 5.9\% and 4.2\% on SUN, CUB and AWA2, respectively.
Authors: Ziheng Jiao, Hongyuan Zhang, Xuelong Li
Abstract: Although the convolutional neural network (CNN) has achieved excellent performance in vision tasks by extracting the intra-sample representation, it will take a higher training expense because of stacking numerous convolutional layers. Recently, as the bilinear models, graph neural networks (GNN) have succeeded in exploring the underlying topological relationship among the graph data with a few graph neural layers. Unfortunately, it cannot be directly utilized on non-graph data due to the lack of graph structure and has high inference latency on large-scale scenarios. Inspired by these complementary strengths and weaknesses, \textit{we discuss a natural question, how to bridge these two heterogeneous networks?} In this paper, we propose a novel CNN2GNN framework to unify CNN and GNN together via distillation. Firstly, to break the limitations of GNN, a differentiable sparse graph learning module is designed as the head of networks to dynamically learn the graph for inductive learning. Then, a response-based distillation is introduced to transfer the knowledge from CNN to GNN and bridge these two heterogeneous networks. Notably, due to extracting the intra-sample representation of a single instance and the topological relationship among the datasets simultaneously, the performance of distilled ``boosted'' two-layer GNN on Mini-ImageNet is much higher than CNN containing dozens of layers such as ResNet152.
Authors: Teodor Chiaburu, Frank Hau{\ss}er, Felix Bie{\ss}mann
Abstract: Mounting evidence in explainability for artificial intelligence (XAI) research suggests that good explanations should be tailored to individual tasks and should relate to concepts relevant to the task. However, building task specific explanations is time consuming and requires domain expertise which can be difficult to integrate into generic XAI methods. A promising approach towards designing useful task specific explanations with domain experts is based on compositionality of semantic concepts. Here, we present a novel approach that enables domain experts to quickly create concept-based explanations for computer vision tasks intuitively via natural language. Leveraging recent progress in deep generative methods we propose to generate visual concept-based prototypes via text-to-image methods. These prototypes are then used to explain predictions of computer vision models via a simple k-Nearest-Neighbors routine. The modular design of CoProNN is simple to implement, it is straightforward to adapt to novel tasks and allows for replacing the classification and text-to-image models as more powerful models are released. The approach can be evaluated offline against the ground-truth of predefined prototypes that can be easily communicated also to domain experts as they are based on visual concepts. We show that our strategy competes very well with other concept-based XAI approaches on coarse grained image classification tasks and may even outperform those methods on more demanding fine grained tasks. We demonstrate the effectiveness of our method for human-machine collaboration settings in qualitative and quantitative user studies. All code and experimental data can be found in our GitHub $\href{https://github.com/TeodorChiaburu/beexplainable}{repository}$.
Authors: Kexin Meng, Ruirui Li, Daguang Jiang
Abstract: Human pose estimation is a fundamental and challenging task in computer vision. Larger-scale and more accurate keypoint annotations, while helpful for improving the accuracy of supervised pose estimation, are often expensive and difficult to obtain. Semi-supervised pose estimation tries to leverage a large amount of unlabeled data to improve model performance, which can alleviate the problem of insufficient labeled samples. The latest semi-supervised learning usually adopts a strong and weak data augmented teacher-student learning framework to deal with the challenge of "Human postural diversity and its long-tailed distribution". Appropriate data augmentation method is one of the key factors affecting the accuracy and generalization of semi-supervised models. Aiming at the problem that the difference of sample learning is not considered in the fixed keypoint masking augmentation method, this paper proposes an adaptive keypoint masking method, which can fully mine the information in the samples and obtain better estimation performance. In order to further improve the generalization and robustness of the model, this paper proposes a dual-branch data augmentation scheme, which can perform Mixup on samples and features on the basis of adaptive keypoint masking. The effectiveness of the proposed method is verified on COCO and MPII, outperforming the state-of-the-art semi-supervised pose estimation by 5.2% and 0.3%, respectively.
Authors: Xingyue Zhao, Zhongyu Li, Xiangde Luo, Peiqi Li, Peng Huang, Jianwei Zhu, Yang Liu, Jihua Zhu, Meng Yang, Shi Chang, Jun Dong
Abstract: Recent advances in deep learning have greatly facilitated the automated segmentation of ultrasound images, which is essential for nodule morphological analysis. Nevertheless, most existing methods depend on extensive and precise annotations by domain experts, which are labor-intensive and time-consuming. In this study, we suggest using simple aspect ratio annotations directly from ultrasound clinical diagnoses for automated nodule segmentation. Especially, an asymmetric learning framework is developed by extending the aspect ratio annotations with two types of pseudo labels, i.e., conservative labels and radical labels, to train two asymmetric segmentation networks simultaneously. Subsequently, a conservative-radical-balance strategy (CRBS) strategy is proposed to complementally combine radical and conservative labels. An inconsistency-aware dynamically mixed pseudo-labels supervision (IDMPS) module is introduced to address the challenges of over-segmentation and under-segmentation caused by the two types of labels. To further leverage the spatial prior knowledge provided by clinical annotations, we also present a novel loss function namely the clinical anatomy prior loss. Extensive experiments on two clinically collected ultrasound datasets (thyroid and breast) demonstrate the superior performance of our proposed method, which can achieve comparable and even better performance than fully supervised methods using ground truth annotations.
Authors: Brize Ozenne, Martin Norgaard, Cyril Pernet, Melanie Ganz
Abstract: Even though novel imaging techniques have been successful in studying brain structure and function, the measured biological signals are often contaminated by multiple sources of noise, arising due to e.g. head movements of the individual being scanned, limited spatial/temporal resolution, or other issues specific to each imaging technology. Data preprocessing (e.g. denoising) is therefore critical. Preprocessing pipelines have become increasingly complex over the years, but also more flexible, and this flexibility can have a significant impact on the final results and conclusions of a given study. This large parameter space is often referred to as multiverse analyses. Here, we provide conceptual and practical tools for statistical analyses that can aggregate multiple pipeline results along with a new sensitivity analysis testing for hypotheses across pipelines such as "no effect across all pipelines" or "at least one pipeline with no effect". The proposed framework is generic and can be applied to any multiverse scenario, but we illustrate its use based on positron emission tomography data.
Authors: Yugan Chen, Lin Zhao, Yalong Xu, Honglei Zu, Xiaoqi An, Guangyu Li
Abstract: Domain adaptive pose estimation aims to enable deep models trained on source domain (synthesized) datasets produce similar results on the target domain (real-world) datasets. The existing methods have made significant progress by conducting image-level or feature-level alignment. However, only aligning at a single level is not sufficient to fully bridge the domain gap and achieve excellent domain adaptive results. In this paper, we propose a multi-level domain adaptation aproach, which aligns different domains at the image, feature, and pose levels. Specifically, we first utilize image style transer to ensure that images from the source and target domains have a similar distribution. Subsequently, at the feature level, we employ adversarial training to make the features from the source and target domains preserve domain-invariant characeristics as much as possible. Finally, at the pose level, a self-supervised approach is utilized to enable the model to learn diverse knowledge, implicitly addressing the domain gap. Experimental results demonstrate that significant imrovement can be achieved by the proposed multi-level alignment method in pose estimation, which outperforms previous state-of-the-art in human pose by up to 2.4% and animal pose estimation by up to 3.1% for dogs and 1.4% for sheep.
Authors: Haozhe Cheng, Cheng Ju, Haicheng Wang, Jinxiang Liu, Mengting Chen, Qiang Hu, Xiaoyun Zhang, Yanfeng Wang
Abstract: As one of the fundamental video tasks in computer vision, Open-Vocabulary Action Recognition (OVAR) recently gains increasing attention, with the development of vision-language pre-trainings. To enable generalization of arbitrary classes, existing methods treat class labels as text descriptions, then formulate OVAR as evaluating embedding similarity between visual samples and textual classes. However, one crucial issue is completely ignored: the class descriptions given by users may be noisy, e.g., misspellings and typos, limiting the real-world practicality of vanilla OVAR. To fill the research gap, this paper pioneers to evaluate existing methods by simulating multi-level noises of various types, and reveals their poor robustness. To tackle the noisy OVAR task, we further propose one novel DENOISER framework, covering two parts: generation and discrimination. Concretely, the generative part denoises noisy class-text names via one decoding process, i.e., propose text candidates, then utilize inter-modal and intra-modal information to vote for the best. At the discriminative part, we use vanilla OVAR models to assign visual samples to class-text names, thus obtaining more semantics. For optimization, we alternately iterate between generative and discriminative parts for progressive refinements. The denoised text classes help OVAR models classify visual samples more accurately; in return, classified visual samples help better denoising. On three datasets, we carry out extensive experiments to show our superior robustness, and thorough ablations to dissect the effectiveness of each component.
Authors: Ross Greer, Mathias Viborg Andersen, Andreas M{\o}gelmose, Mohan Trivedi
Abstract: Driver activity classification is crucial for ensuring road safety, with applications ranging from driver assistance systems to autonomous vehicle control transitions. In this paper, we present a novel approach leveraging generalizable representations from vision-language models for driver activity classification. Our method employs a Semantic Representation Late Fusion Neural Network (SRLF-Net) to process synchronized video frames from multiple perspectives. Each frame is encoded using a pretrained vision-language encoder, and the resulting embeddings are fused to generate class probability predictions. By leveraging contrastively-learned vision-language representations, our approach achieves robust performance across diverse driver activities. We evaluate our method on the Naturalistic Driving Action Recognition Dataset, demonstrating strong accuracy across many classes. Our results suggest that vision-language representations offer a promising avenue for driver monitoring systems, providing both accuracy and interpretability through natural language descriptors.
Authors: Hoang Chuong Nguyen, Tianyu Wang, Jose M. Alvarez, Miaomiao Liu
Abstract: This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1 remain a critical challenge for these methods due to the inherent ambiguity in depth and motion estimation, resulting in inaccurate depth estimation. This paper proposes a self-supervised training framework exploiting pseudo depth labels for dynamic regions from training data. The key contribution of our framework is to decouple depth estimation for static and dynamic regions of images in the training data. We start with an unsupervised depth estimation approach, which provides reliable depth estimates for static regions and motion cues for dynamic regions and allows us to extract moving object information at the instance level. In the next stage, we use an object network to estimate the depth of those moving objects assuming rigid motions. Then, we propose a new scale alignment module to address the scale ambiguity between estimated depths for static and dynamic regions. We can then use the depth labels generated to train an end-to-end depth estimation network and improve its performance. Extensive experiments on the Cityscapes and KITTI datasets show that our self-training strategy consistently outperforms existing self/unsupervised depth estimation methods.
Authors: Muhammad Ahmad, Manuel Mazzara, Salvatore Distifano
Abstract: Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models. When training, validation, and test sets overlap or share data, it introduces a bias that inflates performance metrics and prevents accurate assessment of a model's true ability to generalize to new examples. This paper presents an innovative disjoint sampling approach for training SOTA models on Hyperspectral image classification (HSIC) tasks. By separating training, validation, and test data without overlap, the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or validation. Experiments demonstrate the approach significantly improves a model's generalization compared to alternatives that include training and validation data in test data. By eliminating data leakage between sets, disjoint sampling provides reliable metrics for benchmarking progress in HSIC. Researchers can have confidence that reported performance truly reflects a model's capabilities for classifying new scenes, not just memorized pixels. This rigorous methodology is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral sensors. The source code is available at https://github.com/mahmad00/Disjoint-Sampling-for-Hyperspectral-Image-Classification.
URLs: https://github.com/mahmad00/Disjoint-Sampling-for-Hyperspectral-Image-Classification.
Authors: Muhammad Ahmad, Muhammad Hassaan Farooq Butt, Manuel Mazzara, Salvatore Distifano
Abstract: The traditional Transformer model encounters challenges with variable-length input sequences, particularly in Hyperspectral Image Classification (HSIC), leading to efficiency and scalability concerns. To overcome this, we propose a pyramid-based hierarchical transformer (PyFormer). This innovative approach organizes input data hierarchically into segments, each representing distinct abstraction levels, thereby enhancing processing efficiency for lengthy sequences. At each level, a dedicated transformer module is applied, effectively capturing both local and global context. Spatial and spectral information flow within the hierarchy facilitates communication and abstraction propagation. Integration of outputs from different levels culminates in the final input representation. Experimental results underscore the superiority of the proposed method over traditional approaches. Additionally, the incorporation of disjoint samples augments robustness and reliability, thereby highlighting the potential of our approach in advancing HSIC. The source code is available at https://github.com/mahmad00/PyFormer.
Authors: Wensheng Pan, Timin Gao, Yan Zhang, Runze Hu, Xiawu Zheng, Enwei Zhang, Yuting Gao, Yutao Liu, Yunhang Shen, Ke Li, Shengchuan Zhang, Liujuan Cao, Rongrong Ji
Abstract: Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Currently, leveraging semantic information to enhance IQA is a crucial research direction. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. However, the generalist nature of these pre-trained Vision-Language (VL) models often renders them suboptimal for IQA-specific tasks. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. Existing prompt-based VL models overly focus on incremental semantic information from text, neglecting the rich insights available from visual data analysis. This imbalance limits their performance improvements in IQA tasks. This paper introduces an innovative multi-modal prompt-based methodology for IQA. Our approach employs carefully crafted prompts that synergistically mine incremental semantic information from both visual and linguistic data. Specifically, in the visual branch, we introduce a multi-layer prompt structure to enhance the VL model's adaptability. In the text branch, we deploy a dual-prompt scheme that steers the model to recognize and differentiate between scene category and distortion type, thereby refining the model's capacity to assess image quality. Our experimental findings underscore the effectiveness of our method over existing Blind Image Quality Assessment (BIQA) approaches. Notably, it demonstrates competitive performance across various datasets. Our method achieves Spearman Rank Correlation Coefficient (SRCC) values of 0.961(surpassing 0.946 in CSIQ) and 0.941 (exceeding 0.930 in KADID), illustrating its robustness and accuracy in diverse contexts.
Authors: Ziqi Xie
Abstract: Learning-based image stitching techniques typically involve three distinct stages: registration, fusion, and rectangling. These stages are often performed sequentially, each trained independently, leading to potential cascading error propagation and complex parameter tuning challenges. In rethinking the mathematical modeling of the fusion and rectangling stages, we discovered that these processes can be effectively combined into a single, variety-intensity inpainting problem. Therefore, we propose the Simple and Robust Stitcher (SRStitcher), an efficient training-free image stitching method that merges the fusion and rectangling stages into a unified model. By employing the weighted mask and large-scale generative model, SRStitcher can solve the fusion and rectangling problems in a single inference, without additional training or fine-tuning of other models. Our method not only simplifies the stitching pipeline but also enhances fault tolerance towards misregistration errors. Extensive experiments demonstrate that SRStitcher outperforms state-of-the-art (SOTA) methods in both quantitative assessments and qualitative evaluations. The code is released at https://github.com/yayoyo66/SRStitcher
Authors: Esam Ghaleb, Ilya Burenko, Marlou Rasenberg, Wim Pouw, Ivan Toni, Peter Uhrig, Anna Wilson, Judith Holler, Asl{\i} \"Ozy\"urek, Raquel Fern\'andez
Abstract: Gestures are inherent to human interaction and often complement speech in face-to-face communication, forming a multimodal communication system. An important task in gesture analysis is detecting a gesture's beginning and end. Research on automatic gesture detection has primarily focused on visual and kinematic information to detect a limited set of isolated or silent gestures with low variability, neglecting the integration of speech and vision signals to detect gestures that co-occur with speech. This work addresses this gap by focusing on co-speech gesture detection, emphasising the synchrony between speech and co-speech hand gestures. We address three main challenges: the variability of gesture forms, the temporal misalignment between gesture and speech onsets, and differences in sampling rate between modalities. We investigate extended speech time windows and employ separate backbone models for each modality to address the temporal misalignment and sampling rate differences. We utilize Transformer encoders in cross-modal and early fusion techniques to effectively align and integrate speech and skeletal sequences. The study results show that combining visual and speech information significantly enhances gesture detection performance. Our findings indicate that expanding the speech buffer beyond visual time segments improves performance and that multimodal integration using cross-modal and early fusion techniques outperforms baseline methods using unimodal and late fusion methods. Additionally, we find a correlation between the models' gesture prediction confidence and low-level speech frequency features potentially associated with gestures. Overall, the study provides a better understanding and detection methods for co-speech gestures, facilitating the analysis of multimodal communication.
Authors: Muhammad Ahmad, Salvatore Distifano, Manuel Mazzara, Adil Mehmood Khan
Abstract: Hyperspectral image classification is a challenging task due to the high dimensionality and complex nature of hyperspectral data. In recent years, deep learning techniques have emerged as powerful tools for addressing these challenges. This survey provides a comprehensive overview of the current trends and future prospects in hyperspectral image classification, focusing on the advancements from deep learning models to the emerging use of transformers. We review the key concepts, methodologies, and state-of-the-art approaches in deep learning for hyperspectral image classification. Additionally, we discuss the potential of transformer-based models in this field and highlight the advantages and challenges associated with these approaches. Comprehensive experimental results have been undertaken using three Hyperspectral datasets to verify the efficacy of various conventional deep-learning models and Transformers. Finally, we outline future research directions and potential applications that can further enhance the accuracy and efficiency of hyperspectral image classification. The Source code is available at https://github.com/mahmad00/Conventional-to-Transformer-for-Hyperspectral-Image-Classification-Survey-2024.
Authors: Ye Zhang, Yifeng Wang, Zijie Fang, Hao Bian, Linghan Cai, Ziyue Wang, Yongbing Zhang
Abstract: Weakly supervised segmentation methods have gained significant attention due to their ability to reduce the reliance on costly pixel-level annotations during model training. However, the current weakly supervised nuclei segmentation approaches typically follow a two-stage pseudo-label generation and network training process. The performance of the nuclei segmentation heavily relies on the quality of the generated pseudo-labels, thereby limiting its effectiveness. This paper introduces a novel domain-adaptive weakly supervised nuclei segmentation framework using cross-task interaction strategies to overcome the challenge of pseudo-label generation. Specifically, we utilize weakly annotated data to train an auxiliary detection task, which assists the domain adaptation of the segmentation network. To enhance the efficiency of domain adaptation, we design a consistent feature constraint module integrating prior knowledge from the source domain. Furthermore, we develop pseudo-label optimization and interactive training methods to improve the domain transfer capability. To validate the effectiveness of our proposed method, we conduct extensive comparative and ablation experiments on six datasets. The results demonstrate the superiority of our approach over existing weakly supervised approaches. Remarkably, our method achieves comparable or even better performance than fully supervised methods. Our code will be released in https://github.com/zhangye-zoe/DAWN.
Authors: Xu Han, Yuan Tang, Zhaoxuan Wang, Xianzhi Li
Abstract: Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state space models (SSM), outperforms Transformer in multiple areas with only linear complexity. However, the straightforward adoption of Mamba does not achieve satisfactory performance on point cloud tasks. In this work, we present Mamba3D, a state space model tailored for point cloud learning to enhance local feature extraction, achieving superior performance, high efficiency, and scalability potential. Specifically, we propose a simple yet effective Local Norm Pooling (LNP) block to extract local geometric features. Additionally, to obtain better global features, we introduce a bidirectional SSM (bi-SSM) with both a token forward SSM and a novel backward SSM that operates on the feature channel. Extensive experimental results show that Mamba3D surpasses Transformer-based counterparts and concurrent works in multiple tasks, with or without pre-training. Notably, Mamba3D achieves multiple SoTA, including an overall accuracy of 92.6% (train from scratch) on the ScanObjectNN and 95.1% (with single-modal pre-training) on the ModelNet40 classification task, with only linear complexity.
Authors: Deheng Zhang, Clara Fernandez-Labrador, Christopher Schroers
Abstract: Creating artistic 3D scenes can be time-consuming and requires specialized knowledge. To address this, recent works such as ARF, use a radiance field-based approach with style constraints to generate 3D scenes that resemble a style image provided by the user. However, these methods lack fine-grained control over the resulting scenes. In this paper, we introduce Controllable Artistic Radiance Fields (CoARF), a novel algorithm for controllable 3D scene stylization. CoARF enables style transfer for specified objects, compositional 3D style transfer and semantic-aware style transfer. We achieve controllability using segmentation masks with different label-dependent loss functions. We also propose a semantic-aware nearest neighbor matching algorithm to improve the style transfer quality. Our extensive experiments demonstrate that CoARF provides user-specified controllability of style transfer and superior style transfer quality with more precise feature matching.
Authors: Niklas Wagner, Felix M\"atzler, Samed R. Vossberg, Helen Schneider, Svetlana Pavlitska, J. Marius Z\"ollner
Abstract: Understanding emotions and expressions is a task of interest across multiple disciplines, especially for improving user experiences. Contrary to the common perception, it has been shown that emotions are not discrete entities but instead exist along a continuum. People understand discrete emotions differently due to a variety of factors, including cultural background, individual experiences, and cognitive biases. Therefore, most approaches to expression understanding, particularly those relying on discrete categories, are inherently biased. In this paper, we present a comparative in-depth analysis of two common datasets (AffectNet and EMOTIC) equipped with the components of the circumplex model of affect. Further, we propose a model for the prediction of facial expressions tailored for lightweight applications. Using a small-scaled MaxViT-based model architecture, we evaluate the impact of discrete expression category labels in training with the continuous valence and arousal labels. We show that considering valence and arousal in addition to discrete category labels helps to significantly improve expression inference. The proposed model outperforms the current state-of-the-art models on AffectNet, establishing it as the best-performing model for inferring valence and arousal achieving a 7% lower RMSE. Training scripts and trained weights to reproduce our results can be found here: https://github.com/wagner-niklas/CAGE_expression_inference.
URLs: https://github.com/wagner-niklas/CAGE_expression_inference.
Authors: Junsong Zhang, Zisong Chen, Chunyu Lin, Lang Nie, Zhijie Shen, Junda Huang, Yao Zhao
Abstract: Panoramic distortion poses a significant challenge in 360 depth estimation, particularly pronounced at the north and south poles. Existing methods either adopt a bi-projection fusion strategy to remove distortions or model long-range dependencies to capture global structures, which can result in either unclear structure or insufficient local perception. In this paper, we propose a spherical geometry transformer, named SGFormer, to address the above issues, with an innovative step to integrate spherical geometric priors into vision transformers. To this end, we retarget the transformer decoder to a spherical prior decoder (termed SPDecoder), which endeavors to uphold the integrity of spherical structures during decoding. Concretely, we leverage bipolar re-projection, circular rotation, and curve local embedding to preserve the spherical characteristics of equidistortion, continuity, and surface distance, respectively. Furthermore, we present a query-based global conditional position embedding to compensate for spatial structure at varying resolutions. It not only boosts the global perception of spatial position but also sharpens the depth structure across different patches. Finally, we conduct extensive experiments on popular benchmarks, demonstrating our superiority over state-of-the-art solutions.
Authors: Yingquan Wang, Pingping Zhang, Dong Wang, Huchuan Lu
Abstract: Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from images captured at different places and times. Recently, object Re-ID has achieved great success with the advances of Vision Transformers (ViT). However, the effects of the global-local relation have not been fully explored in Transformers for object Re-ID. In this work, we first explore the influence of global and local features of ViT and then further propose a novel Global-Local Transformer (GLTrans) for high-performance object Re-ID. We find that the features from last few layers of ViT already have a strong representational ability, and the global and local information can mutually enhance each other. Based on this fact, we propose a Global Aggregation Encoder (GAE) to utilize the class tokens of the last few Transformer layers and learn comprehensive global features effectively. Meanwhile, we propose the Local Multi-layer Fusion (LMF) which leverages both the global cues from GAE and multi-layer patch tokens to explore the discriminative local representations. Extensive experiments demonstrate that our proposed method achieves superior performance on four object Re-ID benchmarks.
Authors: Stuti Pandey, Josh Myers-Dean, Jarek Reynolds, Danna Gurari
Abstract: Lateral flow tests (LFTs) enable rapid, low-cost testing for health conditions including Covid, pregnancy, HIV, and malaria. Automated readers of LFT results can yield many benefits including empowering blind people to independently learn about their health and accelerating data entry for large-scale monitoring (e.g., for pandemics such as Covid) by using only a single photograph per LFT test. Accordingly, we explore the abilities of modern foundation vision language models (VLMs) in interpreting such tests. To enable this analysis, we first create a new labeled dataset with hierarchical segmentations of each LFT test and its nested test result window. We call this dataset LFT-Grounding. Next, we benchmark eight modern VLMs in zero-shot settings for analyzing these images. We demonstrate that current VLMs frequently fail to correctly identify the type of LFT test, interpret the test results, locate the nested result window of the LFT tests, and recognize LFT tests when they partially obfuscated. To facilitate community-wide progress towards automated LFT reading, we publicly release our dataset at https://iamstuti.github.io/lft_grounding_foundation_models/.
URLs: https://iamstuti.github.io/lft_grounding_foundation_models/.
Authors: Felipe Torres, Hanwei Zhang, Ronan Sicre, St\'ephane Ayache, Yannis Avrithis
Abstract: Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map. Additionally, attention-based pooling serves as a form of masking the in feature space. Motivated by this observation, we design an attention-based pooling mechanism intended to replace Global Average Pooling (GAP) at inference. This mechanism, called Cross-Attention Stream (CA-Stream), comprises a stream of cross attention blocks interacting with features at different network depths. CA-Stream enhances interpretability in models, while preserving recognition performance.
Authors: Wen Liang, Peipei Ran, Mengchao Bai, Xiao Liu, P. Bilha Githinji, Wei Zhao, Peiwu Qin
Abstract: Salient object detection (SOD) aims at finding the most salient objects in images and outputs pixel-level binary masks. Transformer-based methods achieve promising performance due to their global semantic understanding, crucial for identifying salient objects. However, these models tend to be large and require numerous training parameters. To better harness the potential of transformers for SOD, we propose a novel parameter-efficient fine-tuning method aimed at reducing the number of training parameters while enhancing the salient object detection capability. Our model, termed EXternal Prompt features Enhanced adapteR Tuning (ExPert), features an encoder-decoder structure with adapters and injectors interspersed between the layers of a frozen transformer encoder. The adapter modules adapt the pre-trained backbone to SOD while the injector modules incorporate external prompt features to enhance the awareness of salient objects. Comprehensive experiments demonstrate the superiority of our method. Surpassing former state-of-the-art (SOTA) models across five SOD datasets, ExPert achieves 0.215 mean absolute error (MAE) in ECSSD dataset with 80.2M trained parameters, 21% better than transformer-based SOTA model and 47% better than CNN-based SOTA model.
Authors: Anahita Fathi Kazerooni, Nastaran Khalili, Deep Gandhi, Xinyang Liu, Zhifan Jiang, Syed Muhammed Anwar, Jake Albrecht, Maruf Adewole, Udunna Anazodo, Hannah Anderson, Sina Bagheri, Ujjwal Baid, Timothy Bergquist, Austin J. Borja, Evan Calabrese, Verena Chung, Gian-Marco Conte, Farouk Dako, James Eddy, Ivan Ezhov, Ariana Familiar, Keyvan Farahani, Anurag Gottipati, Debanjan Haldar, Shuvanjan Haldar, Juan Eugenio Iglesias, Anastasia Janas, Elaine Johansen, Blaise V Jones, Neda Khalili, Florian Kofler, Dominic LaBella, Hollie Anne Lai, Koen Van Leemput, Hongwei Bran Li, Nazanin Maleki, Aaron S McAllister, Zeke Meier, Bjoern Menze, Ahmed W Moawad, Khanak K Nandolia, Julija Pavaine, Marie Piraud, Tina Poussaint, Sanjay P Prabhu, Zachary Reitman, Andres Rodriguez, Jeffrey D Rudie, Mariana Sanchez-Montano, Ibraheem Salman Shaikh, Lubdha M. Shah, Nakul Sheth, Russel Taki Shinohara, Wenxin Tu, Karthik Viswanathan, Chunhao Wang, Jeffrey B Ware, Benedikt Wiestler, Walter Wiggins, Anna Zapaishchykova, Mariam Aboian, Miriam Bornhorst, Peter de Blank, Michelle Deutsch, Maryam Fouladi, Lindsey Hoffman, Benjamin Kann, Margot Lazow, Leonie Mikael, Ali Nabavizadeh, Roger Packer, Spyridon Bakas, Adam Resnick, Brian Rood, Arastoo Vossough, Marius George Linguraru
Abstract: Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge, focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.
Authors: Shuofeng Sun, Yongming Rao, Jiwen Lu, Haibin Yan
Abstract: Numerous prior studies predominantly emphasize constructing relation vectors for individual neighborhood points and generating dynamic kernels for each vector and embedding these into high-dimensional spaces to capture implicit local structures. However, we contend that such implicit high-dimensional structure modeling approch inadequately represents the local geometric structure of point clouds due to the absence of explicit structural information. Hence, we introduce X-3D, an explicit 3D structure modeling approach. X-3D functions by capturing the explicit local structural information within the input 3D space and employing it to produce dynamic kernels with shared weights for all neighborhood points within the current local region. This modeling approach introduces effective geometric prior and significantly diminishes the disparity between the local structure of the embedding space and the original input point cloud, thereby improving the extraction of local features. Experiments show that our method can be used on a variety of methods and achieves state-of-the-art performance on segmentation, classification, detection tasks with lower extra computational cost, such as \textbf{90.7\%} on ScanObjectNN for classification, \textbf{79.2\%} on S3DIS 6 fold and \textbf{74.3\%} on S3DIS Area 5 for segmentation, \textbf{76.3\%} on ScanNetV2 for segmentation and \textbf{64.5\%} mAP , \textbf{46.9\%} mAP on SUN RGB-D and \textbf{69.0\%} mAP , \textbf{51.1\%} mAP on ScanNetV2 . Our code is available at \href{https://github.com/sunshuofeng/X-3D}{https://github.com/sunshuofeng/X-3D}.
URLs: https://github.com/sunshuofeng/X-3D, https://github.com/sunshuofeng/X-3D
Authors: Guoqing Wang, Zhongdao Wang, Pin Tang, Jilai Zheng, Xiangxuan Ren, Bailan Feng, Chao Ma
Abstract: Existing solutions for 3D semantic occupancy prediction typically treat the task as a one-shot 3D voxel-wise segmentation perception problem. These discriminative methods focus on learning the mapping between the inputs and occupancy map in a single step, lacking the ability to gradually refine the occupancy map and the reasonable scene imaginative capacity to complete the local regions somewhere. In this paper, we introduce OccGen, a simple yet powerful generative perception model for the task of 3D semantic occupancy prediction. OccGen adopts a ''noise-to-occupancy'' generative paradigm, progressively inferring and refining the occupancy map by predicting and eliminating noise originating from a random Gaussian distribution. OccGen consists of two main components: a conditional encoder that is capable of processing multi-modal inputs, and a progressive refinement decoder that applies diffusion denoising using the multi-modal features as conditions. A key insight of this generative pipeline is that the diffusion denoising process is naturally able to model the coarse-to-fine refinement of the dense 3D occupancy map, therefore producing more detailed predictions. Extensive experiments on several occupancy benchmarks demonstrate the effectiveness of the proposed method compared to the state-of-the-art methods. For instance, OccGen relatively enhances the mIoU by 9.5%, 6.3%, and 13.3% on nuScenes-Occupancy dataset under the muli-modal, LiDAR-only, and camera-only settings, respectively. Moreover, as a generative perception model, OccGen exhibits desirable properties that discriminative models cannot achieve, such as providing uncertainty estimates alongside its multiple-step predictions.
Authors: Yihao Li, Mostafa El Habib Daho, Pierre-Henri Conze, Rachid Zeghlache, Hugo Le Boit\'e, Ramin Tadayoni, B\'eatrice Cochener, Mathieu Lamard, Gwenol\'e Quellec
Abstract: Multimodal medical imaging plays a pivotal role in clinical diagnosis and research, as it combines information from various imaging modalities to provide a more comprehensive understanding of the underlying pathology. Recently, deep learning-based multimodal fusion techniques have emerged as powerful tools for improving medical image classification. This review offers a thorough analysis of the developments in deep learning-based multimodal fusion for medical classification tasks. We explore the complementary relationships among prevalent clinical modalities and outline three main fusion schemes for multimodal classification networks: input fusion, intermediate fusion (encompassing single-level fusion, hierarchical fusion, and attention-based fusion), and output fusion. By evaluating the performance of these fusion techniques, we provide insight into the suitability of different network architectures for various multimodal fusion scenarios and application domains. Furthermore, we delve into challenges related to network architecture selection, handling incomplete multimodal data management, and the potential limitations of multimodal fusion. Finally, we spotlight the promising future of Transformer-based multimodal fusion techniques and give recommendations for future research in this rapidly evolving field.
Authors: Felipe Torres Figueroa, Hanwei Zhang, Ronan Sicre, Yannis Avrithis, Stephane Ayache
Abstract: This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation. However, it is well understood that gradients are noisy and alternatives like guided backpropagation have been proposed to obtain better visualization at inference. In this work, we present a novel training approach to improve the quality of gradients for interpretability. In particular, we introduce a regularization loss such that the gradient with respect to the input image obtained by standard backpropagation is similar to the gradient obtained by guided backpropagation. We find that the resulting gradient is qualitatively less noisy and improves quantitatively the interpretability properties of different networks, using several interpretability methods.
Authors: Hao Li, Han Liu, Dewei Hu, Jiacheng Wang, Ipek Oguz
Abstract: In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles as sparse prompts, as well as masks as dense prompts. Specifically, PRISM is designed with four principles to achieve robustness: (1) Iterative learning. The model produces segmentations by using visual prompts from previous iterations to achieve progressive improvement. (2) Confidence learning. PRISM employs multiple segmentation heads per input image, each generating a continuous map and a confidence score to optimize predictions. (3) Corrective learning. Following each segmentation iteration, PRISM employs a shallow corrective refinement network to reassign mislabeled voxels. (4) Hybrid design. PRISM integrates hybrid encoders to better capture both the local and global information. Comprehensive validation of PRISM is conducted using four public datasets for tumor segmentation in the colon, pancreas, liver, and kidney, highlighting challenges caused by anatomical variations and ambiguous boundaries in accurate tumor identification. Compared to state-of-the-art methods, both with and without prompt engineering, PRISM significantly improves performance, achieving results that are close to human levels. The code is publicly available at https://github.com/MedICL-VU/PRISM.
Authors: Jinfan Liu, Yichao Yan, Junjie Li, Weiming Zhao, Pengzhi Chu, Xingdong Sheng, Yunhui Liu, Xiaokang Yang
Abstract: Video anomaly detection (VAD) is a challenging task aiming to recognize anomalies in video frames, and existing large-scale VAD researches primarily focus on road traffic and human activity scenes. In industrial scenes, there are often a variety of unpredictable anomalies, and the VAD method can play a significant role in these scenarios. However, there is a lack of applicable datasets and methods specifically tailored for industrial production scenarios due to concerns regarding privacy and security. To bridge this gap, we propose a new dataset, IPAD, specifically designed for VAD in industrial scenarios. The industrial processes in our dataset are chosen through on-site factory research and discussions with engineers. This dataset covers 16 different industrial devices and contains over 6 hours of both synthetic and real-world video footage. Moreover, we annotate the key feature of the industrial process, ie, periodicity. Based on the proposed dataset, we introduce a period memory module and a sliding window inspection mechanism to effectively investigate the periodic information in a basic reconstruction model. Our framework leverages LoRA adapter to explore the effective migration of pretrained models, which are initially trained using synthetic data, into real-world scenarios. Our proposed dataset and method will fill the gap in the field of industrial video anomaly detection and drive the process of video understanding tasks as well as smart factory deployment.
Authors: Ronan Sicre, Hanwei Zhang, Julien Dejasmin, Chiheb Daaloul, St\'ephane Ayache, Thierry Arti\`eres
Abstract: This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system learns and detects parts in the images that are discriminative among categories, without the need for fine-tuning the CNN, making it more scalable than other part-based models. While part-based approaches naturally offer interpretable representations, we propose explanations at image and category levels and introduce specific constraints on the part learning process to make them more discrimative.
Authors: Fan Zhang, Zhi-Qi Cheng, Jian Zhao, Xiaojiang Peng, Xuelong Li
Abstract: Semi-supervised learning has emerged as a promising approach to tackle the challenge of label scarcity in facial expression recognition (FER) task. However, current state-of-the-art methods primarily focus on one side of the coin, i.e., generating high-quality pseudo-labels, while overlooking the other side: enhancing expression-relevant representations. In this paper, we unveil both sides of the coin by proposing a unified framework termed hierarchicaL dEcoupling And Fusing (LEAF) to coordinate expression-relevant representations and pseudo-labels for semi-supervised FER. LEAF introduces a hierarchical expression-aware aggregation strategy that operates at three levels: semantic, instance, and category. (1) At the semantic and instance levels, LEAF decouples representations into expression-agnostic and expression-relevant components, and adaptively fuses them using learnable gating weights. (2) At the category level, LEAF assigns ambiguous pseudo-labels by decoupling predictions into positive and negative parts, and employs a consistency loss to ensure agreement between two augmented views of the same image. Extensive experiments on benchmark datasets demonstrate that by unveiling and harmonizing both sides of the coin, LEAF outperforms state-of-the-art semi-supervised FER methods, effectively leveraging both labeled and unlabeled data. Moreover, the proposed expression-aware aggregation strategy can be seamlessly integrated into existing semi-supervised frameworks, leading to significant performance gains.
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: Xun Wu, Shaohan Huang, Furu Wei
Abstract: Recent studies have demonstrated the exceptional potentials of leveraging human preference datasets to refine text-to-image generative models, enhancing the alignment between generated images and textual prompts. Despite these advances, current human preference datasets are either prohibitively expensive to construct or suffer from a lack of diversity in preference dimensions, resulting in limited applicability for instruction tuning in open-source text-to-image generative models and hinder further exploration. To address these challenges and promote the alignment of generative models through instruction tuning, we leverage multimodal large language models to create VisionPrefer, a high-quality and fine-grained preference dataset that captures multiple preference aspects. We aggregate feedback from AI annotators across four aspects: prompt-following, aesthetic, fidelity, and harmlessness to construct VisionPrefer. To validate the effectiveness of VisionPrefer, we train a reward model VP-Score over VisionPrefer to guide the training of text-to-image generative models and the preference prediction accuracy of VP-Score is comparable to human annotators. Furthermore, we use two reinforcement learning methods to supervised fine-tune generative models to evaluate the performance of VisionPrefer, and extensive experimental results demonstrate that VisionPrefer significantly improves text-image alignment in compositional image generation across diverse aspects, e.g., aesthetic, and generalizes better than previous human-preference metrics across various image distributions. Moreover, VisionPrefer indicates that the integration of AI-generated synthetic data as a supervisory signal is a promising avenue for achieving improved alignment with human preferences in vision generative models.
Authors: Sunan He, Yuxiang Nie, Zhixuan Chen, Zhiyuan Cai, Hongmei Wang, Shu Yang, Hao Chen
Abstract: The rapid advancement of large-scale vision-language models has showcased remarkable capabilities across various tasks. However, the lack of extensive and high-quality image-text data in medicine has greatly hindered the development of large-scale medical vision-language models. In this work, we present a diagnosis-guided bootstrapping strategy that exploits both image and label information to construct vision-language datasets. Based on the constructed dataset, we developed MedDr, a generalist foundation model for healthcare capable of handling diverse medical data modalities, including radiology, pathology, dermatology, retinography, and endoscopy. Moreover, during inference, we propose a simple but effective retrieval-augmented medical diagnosis strategy, which enhances the model's generalization ability. Extensive experiments on visual question answering, medical report generation, and medical image diagnosis demonstrate the superiority of our method.
Authors: Sara Dadjouy, Hedieh Sajedi
Abstract: Medical image analysis is a significant application of artificial intelligence for disease diagnosis. A crucial step in this process is the identification of regions of interest within the images. This task can be automated using object detection algorithms. YOLO and Faster R-CNN are renowned for such algorithms, each with its own strengths and weaknesses. This study aims to explore the advantages of both techniques to select more accurate bounding boxes for gallbladder detection from ultrasound images, thereby enhancing gallbladder cancer classification. A fusion method that leverages the benefits of both techniques is presented in this study. The proposed method demonstrated superior classification performance, with an accuracy of 92.62%, compared to the individual use of Faster R-CNN and YOLOv8, which yielded accuracies of 90.16% and 82.79%, respectively.
Authors: Mingbao Lin, Zhihang Lin, Wengyi Zhan, Liujuan Cao, Rongrong Ji
Abstract: Transforming large pre-trained low-resolution diffusion models to cater to higher-resolution demands, i.e., diffusion extrapolation, significantly improves diffusion adaptability. We propose tuning-free CutDiffusion, aimed at simplifying and accelerating the diffusion extrapolation process, making it more affordable and improving performance. CutDiffusion abides by the existing patch-wise extrapolation but cuts a standard patch diffusion process into an initial phase focused on comprehensive structure denoising and a subsequent phase dedicated to specific detail refinement. Comprehensive experiments highlight the numerous almighty advantages of CutDiffusion: (1) simple method construction that enables a concise higher-resolution diffusion process without third-party engagement; (2) fast inference speed achieved through a single-step higher-resolution diffusion process, and fewer inference patches required; (3) cheap GPU cost resulting from patch-wise inference and fewer patches during the comprehensive structure denoising; (4) strong generation performance, stemming from the emphasis on specific detail refinement.
Authors: Merey Ramazanova, Alejandro Pardo, Bernard Ghanem, Motasem Alfarra
Abstract: Understanding videos that contain multiple modalities is crucial, especially in egocentric videos, where combining various sensory inputs significantly improves tasks like action recognition and moment localization. However, real-world applications often face challenges with incomplete modalities due to privacy concerns, efficiency needs, or hardware issues. Current methods, while effective, often necessitate retraining the model entirely to handle missing modalities, making them computationally intensive, particularly with large training datasets. In this study, we propose a novel approach to address this issue at test time without requiring retraining. We frame the problem as a test-time adaptation task, where the model adjusts to the available unlabeled data at test time. Our method, MiDl~(Mutual information with self-Distillation), encourages the model to be insensitive to the specific modality source present during testing by minimizing the mutual information between the prediction and the available modality. Additionally, we incorporate self-distillation to maintain the model's original performance when both modalities are available. MiDl represents the first self-supervised, online solution for handling missing modalities exclusively at test time. Through experiments with various pretrained models and datasets, MiDl demonstrates substantial performance improvement without the need for retraining.
Authors: Tianwei Zhou, Songbai Tan, Wei Zhou, Yu Luo, Yuan-Gen Wang, Guanghui Yue
Abstract: With the increasing maturity of the text-to-image and image-to-image generative models, AI-generated images (AGIs) have shown great application potential in advertisement, entertainment, education, social media, etc. Although remarkable advancements have been achieved in generative models, very few efforts have been paid to design relevant quality assessment models. In this paper, we propose a novel blind image quality assessment (IQA) network, named AMFF-Net, for AGIs. AMFF-Net evaluates AGI quality from three dimensions, i.e., "visual quality", "authenticity", and "consistency". Specifically, inspired by the characteristics of the human visual system and motivated by the observation that "visual quality" and "authenticity" are characterized by both local and global aspects, AMFF-Net scales the image up and down and takes the scaled images and original-sized image as the inputs to obtain multi-scale features. After that, an Adaptive Feature Fusion (AFF) block is used to adaptively fuse the multi-scale features with learnable weights. In addition, considering the correlation between the image and prompt, AMFF-Net compares the semantic features from text encoder and image encoder to evaluate the text-to-image alignment. We carry out extensive experiments on three AGI quality assessment databases, and the experimental results show that our AMFF-Net obtains better performance than nine state-of-the-art blind IQA methods. The results of ablation experiments further demonstrate the effectiveness of the proposed multi-scale input strategy and AFF block.
Authors: Yu-Jie Liang, Zihan Cao, Liang-Jian Deng, Xiao Wu
Abstract: Recently, implicit neural representations (INR) have made significant strides in various vision-related domains, providing a novel solution for Multispectral and Hyperspectral Image Fusion (MHIF) tasks. However, INR is prone to losing high-frequency information and is confined to the lack of global perceptual capabilities. To address these issues, this paper introduces a Fourier-enhanced Implicit Neural Fusion Network (FeINFN) specifically designed for MHIF task, targeting the following phenomena: The Fourier amplitudes of the HR-HSI latent code and LR-HSI are remarkably similar; however, their phases exhibit different patterns. In FeINFN, we innovatively propose a spatial and frequency implicit fusion function (Spa-Fre IFF), helping INR capture high-frequency information and expanding the receptive field. Besides, a new decoder employing a complex Gabor wavelet activation function, called Spatial-Frequency Interactive Decoder (SFID), is invented to enhance the interaction of INR features. Especially, we further theoretically prove that the Gabor wavelet activation possesses a time-frequency tightness property that favors learning the optimal bandwidths in the decoder. Experiments on two benchmark MHIF datasets verify the state-of-the-art (SOTA) performance of the proposed method, both visually and quantitatively. Also, ablation studies demonstrate the mentioned contributions. The code will be available on Anonymous GitHub (https://anonymous.4open.science/r/FeINFN-15C9/) after possible acceptance.
Authors: Mei Qiu, Wei Lin, Lauren Ann Christopher, Stanley Chien, Yaobin Chen, Shu Hu
Abstract: In the US, thousands of Pan, Tilt, and Zoom (PTZ) traffic cameras monitor highway conditions. There is a great interest in using these highway cameras to gather valuable road traffic data to support traffic analysis and decision-making for highway safety and efficient traffic management. However, there are too many cameras for a few human traffic operators to effectively monitor, so a fully automated solution is desired. This paper introduces a novel system that learns the locations of highway lanes and traffic directions from these camera feeds automatically. It collects real-time, lane-specific traffic data continuously, even adjusting for changes in camera angle or zoom. This facilitates efficient traffic analysis, decision-making, and improved highway safety.
Authors: kaiko. ai, Nanne Aben, Edwin D. de Jong, Ioannis Gatopoulos, Nicolas K\"anzig, Mikhail Karasikov, Axel Lagr\'e, Roman Moser, Joost van Doorn, Fei Tang
Abstract: Driven by the recent advances in deep learning methods and, in particular, by the development of modern self-supervised learning algorithms, increased interest and efforts have been devoted to build foundation models (FMs) for medical images. In this work, we present our scalable training pipeline for large pathology imaging data, and a comprehensive analysis of various hyperparameter choices and training techniques for building pathology FMs. We release and make publicly available the first batch of our pathology FMs (https://github.com/kaiko-ai/towards_large_pathology_fms) trained on open-access TCGA whole slide images, a commonly used collection of pathology images. The experimental evaluation shows that our models reach state-of-the-art performance on various patch-level downstream tasks, ranging from breast cancer subtyping to colorectal nuclear segmentation. Finally, to unify the evaluation approaches used in the field and to simplify future comparisons of different FMs, we present an open-source framework (https://github.com/kaiko-ai/eva) designed for the consistent evaluation of pathology FMs across various downstream tasks.
URLs: https://github.com/kaiko-ai/towards_large_pathology_fms), https://github.com/kaiko-ai/eva)
Authors: Mona Alzahrani, Muhammad Usman, Salma Kammoun, Saeed Anwar, Tarek Helmy
Abstract: Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed by a single image may not be sufficient for accurate decision-making, particularly in complex recognition problems. The utilization of multi-view 3D representations for object recognition has thus far demonstrated the most promising results for achieving state-of-the-art performance. This review paper comprehensively covers recent progress in multi-view 3D object recognition methods for 3D classification and retrieval tasks. Specifically, we focus on deep learning-based and transformer-based techniques, as they are widely utilized and have achieved state-of-the-art performance. We provide detailed information about existing deep learning-based and transformer-based multi-view 3D object recognition models, including the most commonly used 3D datasets, camera configurations and number of views, view selection strategies, pre-trained CNN architectures, fusion strategies, and recognition performance on 3D classification and 3D retrieval tasks. Additionally, we examine various computer vision applications that use multi-view classification. Finally, we highlight key findings and future directions for developing multi-view 3D object recognition methods to provide readers with a comprehensive understanding of the field.
Authors: Peter Kulits, Haiwen Feng, Weiyang Liu, Victoria Abrevaya, Michael J. Black
Abstract: Inverse graphics -- the task of inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics. Disentangling an image into its constituent elements, such as the shape, color, and material properties of the objects of the 3D scene that produced it, requires a comprehensive understanding of the environment. This requirement limits the ability of existing carefully engineered approaches to generalize across domains. Inspired by the zero-shot ability of large language models (LLMs) to generalize to novel contexts, we investigate the possibility of leveraging the broad world knowledge encoded in such models in solving inverse-graphics problems. To this end, we propose the Inverse-Graphics Large Language Model (IG-LLM), an inverse-graphics framework centered around an LLM, that autoregressively decodes a visual embedding into a structured, compositional 3D-scene representation. We incorporate a frozen pre-trained visual encoder and a continuous numeric head to enable end-to-end training. Through our investigation, we demonstrate the potential of LLMs to facilitate inverse graphics through next-token prediction, without the use of image-space supervision. Our analysis opens up new possibilities for precise spatial reasoning about images that exploit the visual knowledge of LLMs. We will release our code and data to ensure the reproducibility of our investigation and to facilitate future research at https://ig-llm.is.tue.mpg.de/
Authors: Pedro C. Neto, Rafael M. Mamede, Carolina Albuquerque, Tiago Gon\c{c}alves, Ana F. Sequeira
Abstract: Face recognition applications have grown in parallel with the size of datasets, complexity of deep learning models and computational power. However, while deep learning models evolve to become more capable and computational power keeps increasing, the datasets available are being retracted and removed from public access. Privacy and ethical concerns are relevant topics within these domains. Through generative artificial intelligence, researchers have put efforts into the development of completely synthetic datasets that can be used to train face recognition systems. Nonetheless, the recent advances have not been sufficient to achieve performance comparable to the state-of-the-art models trained on real data. To study the drift between the performance of models trained on real and synthetic datasets, we leverage a massive attribute classifier (MAC) to create annotations for four datasets: two real and two synthetic. From these annotations, we conduct studies on the distribution of each attribute within all four datasets. Additionally, we further inspect the differences between real and synthetic datasets on the attribute set. When comparing through the Kullback-Leibler divergence we have found differences between real and synthetic samples. Interestingly enough, we have verified that while real samples suffice to explain the synthetic distribution, the opposite could not be further from being true.
Authors: Manyi Yao, Abhishek Aich, Yumin Suh, Amit Roy-Chowdhury, Christian Shelton, Manmohan Chandraker
Abstract: Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge is by adapting the computation level to the specific needs of the input image rather than the current one-size-fits-all approach. To this end, we introduce ECO-M2F or EffiCient TransfOrmer Encoders for Mask2Former-style models. Noting that the encoder module of M2F-style models incur high resource-intensive computations, ECO-M2F provides a strategy to self-select the number of hidden layers in the encoder, conditioned on the input image. To enable this self-selection ability for providing a balance between performance and computational efficiency, we present a three step recipe. The first step is to train the parent architecture to enable early exiting from the encoder. The second step is to create an derived dataset of the ideal number of encoder layers required for each training example. The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on the input image. Additionally, to change the computational-accuracy tradeoff, only steps two and three need to be repeated which significantly reduces retraining time. Experiments on the public datasets show that the proposed approach reduces expected encoder computational cost while maintaining performance, adapts to various user compute resources, is flexible in architecture configurations, and can be extended beyond the segmentation task to object detection.
Authors: Xingguang Zhang, Chih-Hsien Chou
Abstract: When deploying pre-trained video object detectors in real-world scenarios, the domain gap between training and testing data caused by adverse image conditions often leads to performance degradation. Addressing this issue becomes particularly challenging when only the pre-trained model and degraded videos are available. Although various source-free domain adaptation (SFDA) methods have been proposed for single-frame object detectors, SFDA for video object detection (VOD) remains unexplored. Moreover, most unsupervised domain adaptation works for object detection rely on two-stage detectors, while SFDA for one-stage detectors, which are more vulnerable to fine-tuning, is not well addressed in the literature. In this paper, we propose Spatial-Temporal Alternate Refinement with Mean Teacher (STAR-MT), a simple yet effective SFDA method for VOD. Specifically, we aim to improve the performance of the one-stage VOD method, YOLOV, under adverse image conditions, including noise, air turbulence, and haze. Extensive experiments on the ImageNetVOD dataset and its degraded versions demonstrate that our method consistently improves video object detection performance in challenging imaging conditions, showcasing its potential for real-world applications.
Authors: Bin Wang, Zhuangcheng Gu, Chao Xu, Bo Zhang, Botian Shi, Conghui He
Abstract: This paper presents the UniMER dataset to provide the first study on Mathematical Expression Recognition (MER) towards complex real-world scenarios. The UniMER dataset consists of a large-scale training set UniMER-1M offering an unprecedented scale and diversity with one million training instances and a meticulously designed test set UniMER-Test that reflects a diverse range of formula distributions prevalent in real-world scenarios. Therefore, the UniMER dataset enables the training of a robust and high-accuracy MER model and comprehensive evaluation of model performance. Moreover, we introduce the Universal Mathematical Expression Recognition Network (UniMERNet), an innovative framework designed to enhance MER in practical scenarios. UniMERNet incorporates a Length-Aware Module to process formulas of varied lengths efficiently, thereby enabling the model to handle complex mathematical expressions with greater accuracy. In addition, UniMERNet employs our UniMER-1M data and image augmentation techniques to improve the model's robustness under different noise conditions. Our extensive experiments demonstrate that UniMERNet outperforms existing MER models, setting a new benchmark in various scenarios and ensuring superior recognition quality in real-world applications. The dataset and model are available at https://github.com/opendatalab/UniMERNet.
Authors: Cameron Smith, David Charatan, Ayush Tewari, Vincent Sitzmann
Abstract: This paper introduces FlowMap, an end-to-end differentiable method that solves for precise camera poses, camera intrinsics, and per-frame dense depth of a video sequence. Our method performs per-video gradient-descent minimization of a simple least-squares objective that compares the optical flow induced by depth, intrinsics, and poses against correspondences obtained via off-the-shelf optical flow and point tracking. Alongside the use of point tracks to encourage long-term geometric consistency, we introduce differentiable re-parameterizations of depth, intrinsics, and pose that are amenable to first-order optimization. We empirically show that camera parameters and dense depth recovered by our method enable photo-realistic novel view synthesis on 360-degree trajectories using Gaussian Splatting. Our method not only far outperforms prior gradient-descent based bundle adjustment methods, but surprisingly performs on par with COLMAP, the state-of-the-art SfM method, on the downstream task of 360-degree novel view synthesis (even though our method is purely gradient-descent based, fully differentiable, and presents a complete departure from conventional SfM).
Authors: Lahav Lipson, Jia Deng
Abstract: We introduce a new system for Multi-Session SLAM, which tracks camera motion across multiple disjoint videos under a single global reference. Our approach couples the prediction of optical flow with solver layers to estimate camera pose. The backbone is trained end-to-end using a novel differentiable solver for wide-baseline two-view pose. The full system can connect disjoint sequences, perform visual odometry, and global optimization. Compared to existing approaches, our design is accurate and robust to catastrophic failures. Code is available at github.com/princeton-vl/MultiSlam_DiffPose
Authors: Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu
Abstract: Radiance fields have demonstrated impressive performance in synthesizing lifelike 3D talking heads. However, due to the difficulty in fitting steep appearance changes, the prevailing paradigm that presents facial motions by directly modifying point appearance may lead to distortions in dynamic regions. To tackle this challenge, we introduce TalkingGaussian, a deformation-based radiance fields framework for high-fidelity talking head synthesis. Leveraging the point-based Gaussian Splatting, facial motions can be represented in our method by applying smooth and continuous deformations to persistent Gaussian primitives, without requiring to learn the difficult appearance change like previous methods. Due to this simplification, precise facial motions can be synthesized while keeping a highly intact facial feature. Under such a deformation paradigm, we further identify a face-mouth motion inconsistency that would affect the learning of detailed speaking motions. To address this conflict, we decompose the model into two branches separately for the face and inside mouth areas, therefore simplifying the learning tasks to help reconstruct more accurate motion and structure of the mouth region. Extensive experiments demonstrate that our method renders high-quality lip-synchronized talking head videos, with better facial fidelity and higher efficiency compared with previous methods.
Authors: Zehuan Huang, Hongxing Fan, Lipeng Wang, Lu Sheng
Abstract: Recent advancements in controllable human image generation have led to zero-shot generation using structural signals (e.g., pose, depth) or facial appearance. Yet, generating human images conditioned on multiple parts of human appearance remains challenging. Addressing this, we introduce Parts2Whole, a novel framework designed for generating customized portraits from multiple reference images, including pose images and various aspects of human appearance. To achieve this, we first develop a semantic-aware appearance encoder to retain details of different human parts, which processes each image based on its textual label to a series of multi-scale feature maps rather than one image token, preserving the image dimension. Second, our framework supports multi-image conditioned generation through a shared self-attention mechanism that operates across reference and target features during the diffusion process. We enhance the vanilla attention mechanism by incorporating mask information from the reference human images, allowing for the precise selection of any part. Extensive experiments demonstrate the superiority of our approach over existing alternatives, offering advanced capabilities for multi-part controllable human image customization. See our project page at https://huanngzh.github.io/Parts2Whole/.
Authors: Wanrong Zhu, Jennifer Healey, Ruiyi Zhang, William Yang Wang, Tong Sun
Abstract: Recent advancements in instruction-following models have made user interactions with models more user-friendly and efficient, broadening their applicability. In graphic design, non-professional users often struggle to create visually appealing layouts due to limited skills and resources. In this work, we introduce a novel multimodal instruction-following framework for layout planning, allowing users to easily arrange visual elements into tailored layouts by specifying canvas size and design purpose, such as for book covers, posters, brochures, or menus. We developed three layout reasoning tasks to train the model in understanding and executing layout instructions. Experiments on two benchmarks show that our method not only simplifies the design process for non-professionals but also surpasses the performance of few-shot GPT-4V models, with mIoU higher by 12% on Crello. This progress highlights the potential of multimodal instruction-following models to automate and simplify the design process, providing an approachable solution for a wide range of design tasks on visually-rich documents.
Authors: Jingyang Lin, Yingda Xia, Jianpeng Zhang, Ke Yan, Le Lu, Jiebo Luo, Ling Zhang
Abstract: Medical Vision-Language Pretraining (Med-VLP) establishes a connection between visual content from medical images and the relevant textual descriptions. Existing Med-VLP methods primarily focus on 2D images depicting a single body part, notably chest X-rays. In this paper, we extend the scope of Med-VLP to encompass 3D images, specifically targeting full-body scenarios, by using a multimodal dataset of CT images and reports. Compared with the 2D counterpart, 3D VLP is required to effectively capture essential semantics from significantly sparser representation in 3D imaging. In this paper, we introduce CT-GLIP (Grounded Language-Image Pretraining with CT scans), a novel method that constructs organ-level image-text pairs to enhance multimodal contrastive learning, aligning grounded visual features with precise diagnostic text. Additionally, we developed an abnormality dictionary to augment contrastive learning with diverse negative samples. Our method, trained on a multimodal CT dataset comprising 44,011 organ-level vision-text pairs from 17,702 patients across 104 organs, demonstrates it can identify organs and abnormalities in a zero-shot manner using natural languages. The performance of CT-GLIP is validated on a separate test set of 1,130 patients, focusing on the 16 most frequent abnormalities across 7 organs. The experimental results show our model's superior performance over the standard CLIP framework across zero-shot and fine-tuning scenarios, using both CNN and ViT architectures.
Authors: Xuanhua He, Quande Liu, Shengju Qian, Xin Wang, Tao Hu, Ke Cao, Keyu Yan, Man Zhou, Jie Zhang
Abstract: Generating high fidelity human video with specified identities has attracted significant attention in the content generation community. However, existing techniques struggle to strike a balance between training efficiency and identity preservation, either requiring tedious case-by-case finetuning or usually missing the identity details in video generation process. In this study, we present ID-Animator, a zero-shot human-video generation approach that can perform personalized video generation given single reference facial image without further training. ID-Animator inherits existing diffusion-based video generation backbones with a face adapter to encode the ID-relevant embeddings from learnable facial latent queries. To facilitate the extraction of identity information in video generation, we introduce an ID-oriented dataset construction pipeline, which incorporates decoupled human attribute and action captioning technique from a constructed facial image pool. Based on this pipeline, a random face reference training method is further devised to precisely capture the ID-relevant embeddings from reference images, thus improving the fidelity and generalization capacity of our model for ID-specific video generation. Extensive experiments demonstrate the superiority of ID-Animator to generate personalized human videos over previous models. Moreover, our method is highly compatible with popular pre-trained T2V models like animatediff and various community backbone models, showing high extendability in real-world applications for video generation where identity preservation is highly desired. Our codes and checkpoints will be released at https://github.com/ID-Animator/ID-Animator.
Authors: Xiangyu Xu, Lijuan Liu, Shuicheng Yan
Abstract: Existing Transformers for monocular 3D human shape and pose estimation typically have a quadratic computation and memory complexity with respect to the feature length, which hinders the exploitation of fine-grained information in high-resolution features that is beneficial for accurate reconstruction. In this work, we propose an SMPL-based Transformer framework (SMPLer) to address this issue. SMPLer incorporates two key ingredients: a decoupled attention operation and an SMPL-based target representation, which allow effective utilization of high-resolution features in the Transformer. In addition, based on these two designs, we also introduce several novel modules including a multi-scale attention and a joint-aware attention to further boost the reconstruction performance. Extensive experiments demonstrate the effectiveness of SMPLer against existing 3D human shape and pose estimation methods both quantitatively and qualitatively. Notably, the proposed algorithm achieves an MPJPE of 45.2 mm on the Human3.6M dataset, improving upon Mesh Graphormer by more than 10% with fewer than one-third of the parameters. Code and pretrained models are available at https://github.com/xuxy09/SMPLer.
Authors: Jason Wu, Yi-Hao Peng, Amanda Li, Amanda Swearngin, Jeffrey P. Bigham, Jeffrey Nichols
Abstract: User interface (UI) design is a difficult yet important task for ensuring the usability, accessibility, and aesthetic qualities of applications. In our paper, we develop a machine-learned model, UIClip, for assessing the design quality and visual relevance of a UI given its screenshot and natural language description. To train UIClip, we used a combination of automated crawling, synthetic augmentation, and human ratings to construct a large-scale dataset of UIs, collated by description and ranked by design quality. Through training on the dataset, UIClip implicitly learns properties of good and bad designs by i) assigning a numerical score that represents a UI design's relevance and quality and ii) providing design suggestions. In an evaluation that compared the outputs of UIClip and other baselines to UIs rated by 12 human designers, we found that UIClip achieved the highest agreement with ground-truth rankings. Finally, we present three example applications that demonstrate how UIClip can facilitate downstream applications that rely on instantaneous assessment of UI design quality: i) UI code generation, ii) UI design tips generation, and iii) quality-aware UI example search.
Authors: Marek Wodzinski, Niccol\`o Marini, Manfredo Atzori, Henning M\"uller
Abstract: DeeperHistReg is a software framework dedicated to registering whole slide images (WSIs) acquired using multiple stains. It allows one to perform the preprocessing, initial alignment, and nonrigid registration of WSIs acquired using multiple stains (e.g. hematoxylin \& eosin, immunochemistry). The framework implements several state-of-the-art registration algorithms and provides an interface to operate on arbitrary resolution of the WSIs (up to 200k x 200k). The framework is extensible and new algorithms can be easily integrated by other researchers. The framework is available both as a PyPI package and as a Docker container.
Authors: Cyprien Arnold, Philippe Jouvet, Lama Seoud
Abstract: Thermal imaging plays a crucial role in various applications, but the inherent low resolution of commonly available infrared (IR) cameras limits its effectiveness. Conventional super-resolution (SR) methods often struggle with thermal images due to their lack of high-frequency details. Guided SR leverages information from a high-resolution image, typically in the visible spectrum, to enhance the reconstruction of a high-res IR image from the low-res input. Inspired by SwinFusion, we propose SwinFuSR, a guided SR architecture based on Swin transformers. In real world scenarios, however, the guiding modality (e.g. RBG image) may be missing, so we propose a training method that improves the robustness of the model in this case. Our method has few parameters and outperforms state of the art models in terms of Peak Signal to Noise Ratio (PSNR) and Structural SIMilarity (SSIM). In Track 2 of the PBVS 2024 Thermal Image Super-Resolution Challenge, it achieves 3rd place in the PSNR metric. Our code and pretained weights are available at https://github.com/VisionICLab/SwinFuSR.
Authors: Hikmat Khan, Nidhal Carla Bouaynaya, Ghulam Rasool
Abstract: Artificial intelligence (AI) and neuroscience share a rich history, with advancements in neuroscience shaping the development of AI systems capable of human-like knowledge retention. Leveraging insights from neuroscience and existing research in adversarial and continual learning, we introduce a novel framework comprising two core concepts: feature distillation and re-consolidation. Our framework, named Robust Rehearsal, addresses the challenge of catastrophic forgetting inherent in continual learning (CL) systems by distilling and rehearsing robust features. Inspired by the mammalian brain's memory consolidation process, Robust Rehearsal aims to emulate the rehearsal of distilled experiences during learning tasks. Additionally, it mimics memory re-consolidation, where new experiences influence the integration of past experiences to mitigate forgetting. Extensive experiments conducted on CIFAR10, CIFAR100, and real-world helicopter attitude datasets showcase the superior performance of CL models trained with Robust Rehearsal compared to baseline methods. Furthermore, examining different optimization training objectives-joint, continual, and adversarial learning-we highlight the crucial role of feature learning in model performance. This underscores the significance of rehearsing CL-robust samples in mitigating catastrophic forgetting. In conclusion, aligning CL approaches with neuroscience insights offers promising solutions to the challenge of catastrophic forgetting, paving the way for more robust and human-like AI systems.
Authors: Yang Chen, Ruituo Wu, Yipeng Liu, Ce Zhu
Abstract: Implicit neural representations (INR) suffer from worsening spectral bias, which results in overly smooth solutions to the inverse problem. To deal with this problem, we propose a universal framework for processing inverse problems called \textbf{High-Order Implicit Neural Representations (HOIN)}. By refining the traditional cascade structure to foster high-order interactions among features, HOIN enhances the model's expressive power and mitigates spectral bias through its neural tangent kernel's (NTK) strong diagonal properties, accelerating and optimizing inverse problem resolution. By analyzing the model's expression space, high-order derivatives, and the NTK matrix, we theoretically validate the feasibility of HOIN. HOIN realizes 1 to 3 dB improvements in most inverse problems, establishing a new state-of-the-art recovery quality and training efficiency, thus providing a new general paradigm for INR and paving the way for it to solve the inverse problem.
Authors: Raehyuk Jung, Hyojun Go, Jaehyuk Yi, Jiho Jang, Daniel Kim, Jay Suh, Aiden Lee, Cooper Han, Jae Lee, Jeff Kim, Jin-Young Kim, Junwan Kim, Kyle Park, Lucas Lee, Mars Ha, Minjoon Seo, Abraham Jo, Ed Park, Hassan Kianinejad, SJ Kim, Tony Moon, Wade Jeong, Andrei Popescu, Esther Kim, EK Yoon, Genie Heo, Henry Choi, Jenna Kang, Kevin Han, Noah Seo, Sunny Nguyen, Ryan Won, Yeonhoo Park, Anthony Giuliani, Dave Chung, Hans Yoon, James Le, Jenny Ahn, June Lee, Maninder Saini, Meredith Sanders, Soyoung Lee, Sue Kim, Travis Couture
Abstract: This technical report introduces Pegasus-1, a multimodal language model specialized in video content understanding and interaction through natural language. Pegasus-1 is designed to address the unique challenges posed by video data, such as interpreting spatiotemporal information, to offer nuanced video content comprehension across various lengths. This technical report overviews Pegasus-1's architecture, training strategies, and its performance in benchmarks on video conversation, zero-shot video question answering, and video summarization. We also explore qualitative characteristics of Pegasus-1 , demonstrating its capabilities as well as its limitations, in order to provide readers a balanced view of its current state and its future direction.
Authors: Yunming Zhang, Dengpan Ye, Sipeng Shen, Caiyun Xie, Ziyi Liu, Jiacheng Deng, Long Tang
Abstract: The wide deployment of Face Recognition (FR) systems poses risks of privacy leakage. One countermeasure to address this issue is adversarial attacks, which deceive malicious FR searches but simultaneously interfere the normal identity verification of trusted authorizers. In this paper, we propose the first Double Privacy Guard (DPG) scheme based on traceable adversarial watermarking. DPG employs a one-time watermark embedding to deceive unauthorized FR models and allows authorizers to perform identity verification by extracting the watermark. Specifically, we propose an information-guided adversarial attack against FR models. The encoder embeds an identity-specific watermark into the deep feature space of the carrier, guiding recognizable features of the image to deviate from the source identity. We further adopt a collaborative meta-optimization strategy compatible with sub-tasks, which regularizes the joint optimization direction of the encoder and decoder. This strategy enhances the representation of universal carrier features, mitigating multi-objective optimization conflicts in watermarking. Experiments confirm that DPG achieves significant attack success rates and traceability accuracy on state-of-the-art FR models, exhibiting remarkable robustness that outperforms the existing privacy protection methods using adversarial attacks and deep watermarking, or simple combinations of the two. Our work potentially opens up new insights into proactive protection for FR privacy.
Authors: Siyin Wang, Chao-Han Huck Yang, Ji Wu, Chao Zhang
Abstract: Large language models (LLMs) can adapt to new tasks through in-context learning (ICL) based on a few examples presented in dialogue history without any model parameter update. Despite such convenience, the performance of ICL heavily depends on the quality of the in-context examples presented, which makes the in-context example selection approach a critical choice. This paper proposes a novel Bayesian in-Context example Selection method (ByCS) for ICL. Extending the inference probability conditioned on in-context examples based on Bayes' theorem, ByCS focuses on the inverse inference conditioned on test input. Following the assumption that accurate inverse inference probability (likelihood) will result in accurate inference probability (posterior), in-context examples are selected based on their inverse inference results. Diverse and extensive cross-tasking and cross-modality experiments are performed with speech, text, and image examples. Experimental results show the efficacy and robustness of our ByCS method on various models, tasks and modalities.
Authors: Bo Lin, Yingjing Xu, Xuanwen Bao, Zhou Zhao, Zuyong Zhang, Zhouyang Wang, Jie Zhang, Shuiguang Deng, Jianwei Yin
Abstract: With the continuous advancement of vision language models (VLMs) technology, remarkable research achievements have emerged in the dermatology field, the fourth most prevalent human disease category. However, despite these advancements, VLM still faces "hallucination" in dermatological diagnosis, and due to the inherent complexity of dermatological conditions, existing tools offer relatively limited support for user comprehension. We propose SkinGEN, a diagnosis-to-generation framework that leverages the stable diffusion (SD) method to generate reference demonstrations from diagnosis results provided by VLM, thereby enhancing the visual explainability for users. Through extensive experiments with Low-Rank Adaptation (LoRA), we identify optimal strategies for skin condition image generation. We conduct a user study with 32 participants evaluating both the system performance and explainability. Results demonstrate that SkinGEN significantly improves users' comprehension of VLM predictions and fosters increased trust in the diagnostic process. This work paves the way for more transparent and user-centric VLM applications in dermatology and beyond.
Authors: Aojun Lu, Tao Feng, Hangjie Yuan, Xiaotian Song, Yanan Sun
Abstract: Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, width, and components) in contributing to CL. This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL. This work considers architecture design at the network scaling level, i.e., width and depth, and also at the network components, i.e., skip connections, global pooling layers, and down-sampling. In both cases, we first derive insights through systematically exploring how architectural designs affect CL. Then, grounded in these insights, we craft a specialized search space for CL and further propose a simple yet effective ArchCraft method to steer a CL-friendly architecture, namely, this method recrafts AlexNet/ResNet into AlexAC/ResAC. Experimental validation across various CL settings and scenarios demonstrates that improved architectures are parameter-efficient, achieving state-of-the-art performance of CL while being 86%, 61%, and 97% more compact in terms of parameters than the naive CL architecture in Class IL and Task IL. Code is available at https://github.com/byyx666/ArchCraft.
Authors: Zhengzheng Tu, Le Gu, Xixi Wang, Bo Jiang
Abstract: Segment Anything Model (SAM) has recently achieved amazing results in the field of natural image segmentation. However, it is not effective for medical image segmentation, owing to the large domain gap between natural and medical images. In this paper, we mainly focus on ultrasound image segmentation. As we know that it is very difficult to train a foundation model for ultrasound image data due to the lack of large-scale annotated ultrasound image data. To address these issues, in this paper, we develop a novel Breast Ultrasound SAM Adapter, termed Breast Ultrasound Segment Anything Model (BUSSAM), which migrates the SAM to the field of breast ultrasound image segmentation by using the adapter technique. To be specific, we first design a novel CNN image encoder, which is fully trained on the BUS dataset. Our CNN image encoder is more lightweight, and focuses more on features of local receptive field, which provides the complementary information to the ViT branch in SAM. Then, we design a novel Cross-Branch Adapter to allow the CNN image encoder to fully interact with the ViT image encoder in SAM module. Finally, we add both of the Position Adapter and the Feature Adapter to the ViT branch to fine-tune the original SAM. The experimental results on AMUBUS and BUSI datasets demonstrate that our proposed model outperforms other medical image segmentation models significantly. Our code will be available at: https://github.com/bscs12/BUSSAM.
Authors: Kaikai Deng, Dong Zhao, Wenxin Zheng, Yue Ling, Kangwen Yin, Huadong Ma
Abstract: Millimeter wave radar is gaining traction recently as a promising modality for enabling pervasive and privacy-preserving gesture recognition. However, the lack of rich and fine-grained radar datasets hinders progress in developing generalized deep learning models for gesture recognition across various user postures (e.g., standing, sitting), positions, and scenes. To remedy this, we resort to designing a software pipeline that exploits wealthy 2D videos to generate realistic radar data, but it needs to address the challenge of simulating diversified and fine-grained reflection properties of user gestures. To this end, we design G3R with three key components: (i) a gesture reflection point generator expands the arm's skeleton points to form human reflection points; (ii) a signal simulation model simulates the multipath reflection and attenuation of radar signals to output the human intensity map; (iii) an encoder-decoder model combines a sampling module and a fitting module to address the differences in number and distribution of points between generated and real-world radar data for generating realistic radar data. We implement and evaluate G3R using 2D videos from public data sources and self-collected real-world radar data, demonstrating its superiority over other state-of-the-art approaches for gesture recognition.
Authors: Sassan Mokhtar, Eugenio Chisari, Nick Heppert, Abhinav Valada
Abstract: Precisely grasping and reconstructing articulated objects is key to enabling general robotic manipulation. In this paper, we propose CenterArt, a novel approach for simultaneous 3D shape reconstruction and 6-DoF grasp estimation of articulated objects. CenterArt takes RGB-D images of the scene as input and first predicts the shape and joint codes through an encoder. The decoder then leverages these codes to reconstruct 3D shapes and estimate 6-DoF grasp poses of the objects. We further develop a mechanism for generating a dataset of 6-DoF grasp ground truth poses for articulated objects. CenterArt is trained on realistic scenes containing multiple articulated objects with randomized designs, textures, lighting conditions, and realistic depths. We perform extensive experiments demonstrating that CenterArt outperforms existing methods in accuracy and robustness.
Authors: Libang Chen, Jun Yang, Lingye Chen, Yuyang Shui, Yikun Liu, Jianying Zhou
Abstract: Recording and identifying faint objects through atmospheric scattering media by an optical system are fundamentally interesting and technologically important. In this work, we introduce a comprehensive model that incorporates contributions from target characteristics, atmospheric effects, imaging system, digital processing, and visual perception to assess the ultimate perceptible limit of geometrical imaging, specifically the angular resolution at the boundary of visible distance. The model allows to reevaluate the effectiveness of conventional imaging recording, processing, and perception and to analyze the limiting factors that constrain image recognition capabilities in atmospheric media. The simulations were compared with the experimental results measured in a fog chamber and outdoor settings. The results reveal general good agreement between analysis and experimental, pointing out the way to harnessing the physical limit for optical imaging in scattering media. An immediate application of the study is the extension of the image range by an amount of 1.2 times with noise reduction via multi-frame averaging, hence greatly enhancing the capability of optical imaging in the atmosphere.
Authors: Rui Chen, Mingyi Shi, Shaoli Huang, Ping Tan, Taku Komura, Xuelin Chen
Abstract: We present a novel character control framework that effectively utilizes motion diffusion probabilistic models to generate high-quality and diverse character animations, responding in real-time to a variety of dynamic user-supplied control signals. At the heart of our method lies a transformer-based Conditional Autoregressive Motion Diffusion Model (CAMDM), which takes as input the character's historical motion and can generate a range of diverse potential future motions conditioned on high-level, coarse user control. To meet the demands for diversity, controllability, and computational efficiency required by a real-time controller, we incorporate several key algorithmic designs. These include separate condition tokenization, classifier-free guidance on past motion, and heuristic future trajectory extension, all designed to address the challenges associated with taming motion diffusion probabilistic models for character control. As a result, our work represents the first model that enables real-time generation of high-quality, diverse character animations based on user interactive control, supporting animating the character in multiple styles with a single unified model. We evaluate our method on a diverse set of locomotion skills, demonstrating the merits of our method over existing character controllers. Project page and source codes: https://aiganimation.github.io/CAMDM/
Authors: Suyeon Shin, Sujin jeon, Junghyun Kim, Gi-Cheon Kang, Byoung-Tak Zhang
Abstract: Embodied Instruction Following (EIF) is the task of executing natural language instructions by navigating and interacting with objects in 3D environments. One of the primary challenges in EIF is compositional task planning, which is often addressed with supervised or in-context learning with labeled data. To this end, we introduce the Socratic Planner, the first zero-shot planning method that infers without the need for any training data. Socratic Planner first decomposes the instructions into substructural information of the task through self-questioning and answering, translating it into a high-level plan, i.e., a sequence of subgoals. Subgoals are executed sequentially, with our visually grounded re-planning mechanism adjusting plans dynamically through a dense visual feedback. We also introduce an evaluation metric of high-level plans, RelaxedHLP, for a more comprehensive evaluation. Experiments demonstrate the effectiveness of the Socratic Planner, achieving competitive performance on both zero-shot and few-shot task planning in the ALFRED benchmark, particularly excelling in tasks requiring higher-dimensional inference. Additionally, a precise adjustments in the plan were achieved by incorporating environmental visual information.
Authors: Michal Nazarczuk, Jan Kristof Behrens, Karla Stepanova, Matej Hoffmann, Krystian Mikolajczyk
Abstract: Embodied reasoning systems integrate robotic hardware and cognitive processes to perform complex tasks typically in response to a natural language query about a specific physical environment. This usually involves changing the belief about the scene or physically interacting and changing the scene (e.g. 'Sort the objects from lightest to heaviest'). In order to facilitate the development of such systems we introduce a new simulating environment that makes use of MuJoCo physics engine and high-quality renderer Blender to provide realistic visual observations that are also accurate to the physical state of the scene. Together with the simulator we propose a new benchmark composed of 10 classes of multi-step reasoning scenarios that require simultaneous visual and physical measurements. Finally, we develop a new modular Closed Loop Interactive Reasoning (CLIER) approach that takes into account the measurements of non-visual object properties, changes in the scene caused by external disturbances as well as uncertain outcomes of robotic actions. We extensively evaluate our reasoning approach in simulation and in the real world manipulation tasks with a success rate above 76% and 64%, respectively.
Authors: Junli Ren, Yikai Liu, Yingru Dai, Guijin Wang
Abstract: Legged navigation is typically examined within open-world, off-road, and challenging environments. In these scenarios, estimating external disturbances requires a complex synthesis of multi-modal information. This underlines a major limitation in existing works that primarily focus on avoiding obstacles. In this work, we propose TOP-Nav, a novel legged navigation framework that integrates a comprehensive path planner with Terrain awareness, Obstacle avoidance and close-loop Proprioception. TOP-Nav underscores the synergies between vision and proprioception in both path and motion planning. Within the path planner, we present and integrate a terrain estimator that enables the robot to select waypoints on terrains with higher traversability while effectively avoiding obstacles. In the motion planning level, we not only implement a locomotion controller to track the navigation commands, but also construct a proprioception advisor to provide motion evaluations for the path planner. Based on the close-loop motion feedback, we make online corrections for the vision-based terrain and obstacle estimations. Consequently, TOP-Nav achieves open-world navigation that the robot can handle terrains or disturbances beyond the distribution of prior knowledge and overcomes constraints imposed by visual conditions. Building upon extensive experiments conducted in both simulation and real-world environments, TOP-Nav demonstrates superior performance in open-world navigation compared to existing methods.
Authors: Matt Y Cheung, Tucker J Netherton, Laurence E Court, Ashok Veeraraghavan, Guha Balakrishnan
Abstract: Recent advancements in machine learning have led to novel imaging systems and algorithms that address ill-posed problems. Assessing their trustworthiness and understanding how to deploy them safely at test time remains an important and open problem. We propose a method that leverages conformal prediction to retrieve upper/lower bounds and statistical inliers/outliers of reconstructions based on the prediction intervals of downstream metrics. We apply our method to sparse-view CT for downstream radiotherapy planning and show 1) that metric-guided bounds have valid coverage for downstream metrics while conventional pixel-wise bounds do not and 2) anatomical differences of upper/lower bounds between metric-guided and pixel-wise methods. Our work paves the way for more meaningful reconstruction bounds. Code available at https://github.com/matthewyccheung/conformal-metric
Authors: Robik Shrestha, Kushal Kafle, Christopher Kanan
Abstract: Existing Visual Question Answering (VQA) methods tend to exploit dataset biases and spurious statistical correlations, instead of producing right answers for the right reasons. To address this issue, recent bias mitigation methods for VQA propose to incorporate visual cues (e.g., human attention maps) to better ground the VQA models, showcasing impressive gains. However, we show that the performance improvements are not a result of improved visual grounding, but a regularization effect which prevents over-fitting to linguistic priors. For instance, we find that it is not actually necessary to provide proper, human-based cues; random, insensible cues also result in similar improvements. Based on this observation, we propose a simpler regularization scheme that does not require any external annotations and yet achieves near state-of-the-art performance on VQA-CPv2.
Authors: Jiachen Kang, Wenjing Jia, Xiangjian He
Abstract: The existing deep learning models suffer from out-of-distribution (o.o.d.) performance drop in computer vision tasks. In comparison, humans have a remarkable ability to interpret images, even if the scenes in the images are rare, thanks to the systematicity of acquired knowledge. This work focuses on 1) the acquisition of systematic knowledge of 2D transformations, and 2) architectural components that can leverage the learned knowledge in image classification tasks in an o.o.d. setting. With a new training methodology based on synthetic datasets that are constructed under the causal framework, the deep neural networks acquire knowledge from semantically different domains (e.g. even from noise), and exhibit certain level of systematicity in parameter estimation experiments. Based on this, a novel architecture is devised consisting of a classifier, an estimator and an identifier (abbreviated as "CED"). By emulating the "hypothesis-verification" process in human visual perception, CED improves the classification accuracy significantly on test sets under covariate shift.
Authors: Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Salih Atici, Ahmet Enis Cetin
Abstract: In this paper, we propose a set of transform-based neural network layers as an alternative to the $3\times3$ Conv2D layers in Convolutional Neural Networks (CNNs). The proposed layers can be implemented based on orthogonal transforms such as the Discrete Cosine Transform (DCT), Hadamard transform (HT), and biorthogonal Block Wavelet Transform (BWT). Furthermore, by taking advantage of the convolution theorems, convolutional filtering operations are performed in the transform domain using element-wise multiplications. Trainable soft-thresholding layers, that remove noise in the transform domain, bring nonlinearity to the transform domain layers. Compared to the Conv2D layer, which is spatial-agnostic and channel-specific, the proposed layers are location-specific and channel-specific. Moreover, these proposed layers reduce the number of parameters and multiplications significantly while improving the accuracy results of regular ResNets on the ImageNet-1K classification task. Furthermore, they can be inserted with a batch normalization layer before the global average pooling layer in the conventional ResNets as an additional layer to improve classification accuracy.
Authors: Jingyang Lin, Hang Hua, Ming Chen, Yikang Li, Jenhao Hsiao, Chiuman Ho, Jiebo Luo
Abstract: Video summarization aims to distill the most important information from a source video to produce either an abridged clip or a textual narrative. Traditionally, different methods have been proposed depending on whether the output is a video or text, thus ignoring the correlation between the two semantically related tasks of visual summarization and textual summarization. We propose a new joint video and text summarization task. The goal is to generate both a shortened video clip along with the corresponding textual summary from a long video, collectively referred to as a cross-modal summary. The generated shortened video clip and text narratives should be semantically well aligned. To this end, we first build a large-scale human-annotated dataset -- VideoXum (X refers to different modalities). The dataset is reannotated based on ActivityNet. After we filter out the videos that do not meet the length requirements, 14,001 long videos remain in our new dataset. Each video in our reannotated dataset has human-annotated video summaries and the corresponding narrative summaries. We then design a novel end-to-end model -- VTSUM-BILP to address the challenges of our proposed task. Moreover, we propose a new metric called VT-CLIPScore to help evaluate the semantic consistency of cross-modality summary. The proposed model achieves promising performance on this new task and establishes a benchmark for future research.
Authors: Dong Huo, Jian Wang, Yiming Qian, Yee-Hong Yang
Abstract: This paper tackles spectral reflectance recovery (SRR) from RGB images. Since capturing ground-truth spectral reflectance and camera spectral sensitivity are challenging and costly, most existing approaches are trained on synthetic images and utilize the same parameters for all unseen testing images, which are suboptimal especially when the trained models are tested on real images because they never exploit the internal information of the testing images. To address this issue, we adopt a self-supervised meta-auxiliary learning (MAXL) strategy that fine-tunes the well-trained network parameters with each testing image to combine external with internal information. To the best of our knowledge, this is the first work that successfully adapts the MAXL strategy to this problem. Instead of relying on naive end-to-end training, we also propose a novel architecture that integrates the physical relationship between the spectral reflectance and the corresponding RGB images into the network based on our mathematical analysis. Besides, since the spectral reflectance of a scene is independent to its illumination while the corresponding RGB images are not, we recover the spectral reflectance of a scene from its RGB images captured under multiple illuminations to further reduce the unknown. Qualitative and quantitative evaluations demonstrate the effectiveness of our proposed network and of the MAXL. Our code and data are available at https://github.com/Dong-Huo/SRR-MAXL.
Authors: Jiachen Kang, Wenjing Jia, Xiangjian He, Kin Man Lam
Abstract: Self-supervised representation learning (SSRL) has gained increasing attention in point cloud understanding, in addressing the challenges posed by 3D data scarcity and high annotation costs. This paper presents PCExpert, a novel SSRL approach that reinterprets point clouds as "specialized images". This conceptual shift allows PCExpert to leverage knowledge derived from large-scale image modality in a more direct and deeper manner, via extensively sharing the parameters with a pre-trained image encoder in a multi-way Transformer architecture. The parameter sharing strategy, combined with a novel pretext task for pre-training, i.e., transformation estimation, empowers PCExpert to outperform the state of the arts in a variety of tasks, with a remarkable reduction in the number of trainable parameters. Notably, PCExpert's performance under LINEAR fine-tuning (e.g., yielding a 90.02% overall accuracy on ScanObjectNN) has already approached the results obtained with FULL model fine-tuning (92.66%), demonstrating its effective and robust representation capability.
Authors: Esam Ghaleb, Ilya Burenko, Marlou Rasenberg, Wim Pouw, Peter Uhrig, Judith Holler, Ivan Toni, Asl{\i} \"Ozy\"urek, Raquel Fern\'andez
Abstract: Gestures are integral components of face-to-face communication. They unfold over time, often following predictable movement phases of preparation, stroke, and retraction. Yet, the prevalent approach to automatic gesture detection treats the problem as binary classification, classifying a segment as either containing a gesture or not, thus failing to capture its inherently sequential and contextual nature. To address this, we introduce a novel framework that reframes the task as a multi-phase sequence labeling problem rather than binary classification. Our model processes sequences of skeletal movements over time windows, uses Transformer encoders to learn contextual embeddings, and leverages Conditional Random Fields to perform sequence labeling. We evaluate our proposal on a large dataset of diverse co-speech gestures in task-oriented face-to-face dialogues. The results consistently demonstrate that our method significantly outperforms strong baseline models in detecting gesture strokes. Furthermore, applying Transformer encoders to learn contextual embeddings from movement sequences substantially improves gesture unit detection. These results highlight our framework's capacity to capture the fine-grained dynamics of co-speech gesture phases, paving the way for more nuanced and accurate gesture detection and analysis.
Authors: Qinfeng Zhu, Lei Fan, Ningxin Weng
Abstract: Deep learning (DL) has become one of the mainstream and effective methods for point cloud analysis tasks such as detection, segmentation and classification. To reduce overfitting during training DL models and improve model performance especially when the amount and/or diversity of training data are limited, augmentation is often crucial. Although various point cloud data augmentation methods have been widely used in different point cloud processing tasks, there are currently no published systematic surveys or reviews of these methods. Therefore, this article surveys these methods, categorizing them into a taxonomy framework that comprises basic and specialized point cloud data augmentation methods. Through a comprehensive evaluation of these augmentation methods, this article identifies their potentials and limitations, serving as a useful reference for choosing appropriate augmentation methods. In addition, potential directions for future research are recommended. This survey contributes to providing a holistic overview of the current state of point cloud data augmentation, promoting its wider application and development.
Authors: Zhong-Yu Li, Bo-Wen Yin, Yongxiang Liu, Li Liu, Ming-Ming Cheng
Abstract: Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous architectures has not been well exploited in self-supervised learning. Thus, we propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model. In this process, HSSL endows the base model with new characteristics in a representation learning way without structural changes. To comprehensively understand the HSSL, we conduct experiments on various heterogeneous pairs containing a base model and an auxiliary head. We discover that the representation quality of the base model moves up as their architecture discrepancy grows. This observation motivates us to propose a search strategy that quickly determines the most suitable auxiliary head for a specific base model to learn and several simple but effective methods to enlarge the model discrepancy. The HSSL is compatible with various self-supervised methods, achieving superior performances on various downstream tasks, including image classification, semantic segmentation, instance segmentation, and object detection. Our source code will be made publicly available.
Authors: Binglun Wang, Niladri Shekhar Dutt, Niloy J. Mitra
Abstract: Neural Radiance Fields (NeRFs) have recently emerged as a popular option for photo-realistic object capture due to their ability to faithfully capture high-fidelity volumetric content even from handheld video input. Although much research has been devoted to efficient optimization leading to real-time training and rendering, options for interactive editing NeRFs remain limited. We present a very simple but effective neural network architecture that is fast and efficient while maintaining a low memory footprint. This architecture can be incrementally guided through user-friendly image-based edits. Our representation allows straightforward object selection via semantic feature distillation at the training stage. More importantly, we propose a local 3D-aware image context to facilitate view-consistent image editing that can then be distilled into fine-tuned NeRFs, via geometric and appearance adjustments. We evaluate our setup on a variety of examples to demonstrate appearance and geometric edits and report 10-30x speedup over concurrent work focusing on text-guided NeRF editing. Video results can be seen on our project webpage at https://proteusnerf.github.io.
Authors: Xiao Lin, Deming Wang, Guangliang Zhou, Chengju Liu, Qijun Chen
Abstract: Estimating the 6D object pose is an essential task in many applications. Due to the lack of depth information, existing RGB-based methods are sensitive to occlusion and illumination changes. How to extract and utilize the geometry features in depth information is crucial to achieve accurate predictions. To this end, we propose TransPose, a novel 6D pose framework that exploits Transformer Encoder with geometry-aware module to develop better learning of point cloud feature representations. Specifically, we first uniformly sample point cloud and extract local geometry features with the designed local feature extractor base on graph convolution network. To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information. Finally, we introduce geometry-aware module in Transformer Encoder, which to form an effective constrain for point cloud feature learning and makes the global information exchange more tightly coupled with point cloud tasks. Extensive experiments indicate the effectiveness of TransPose, our pose estimation pipeline achieves competitive results on three benchmark datasets.
Authors: Ryusei Uramune, Sei Ikeda, Hiroki Ishizuka, Osamu Oshiro
Abstract: This study proposes a novel self-calibration method for eye tracking in a virtual reality (VR) headset. The proposed method is based on the assumptions that the user's viewpoint can freely move and that the points of regard (PoRs) from different viewpoints are distributed within a small area on an object surface during visual fixation. In the method, fixations are first detected from the time-series data of uncalibrated gaze directions using an extension of the I-VDT (velocity and dispersion threshold identification) algorithm to a three-dimensional (3D) scene. Then, the calibration parameters are optimized by minimizing the sum of a dispersion metrics of the PoRs. The proposed method can potentially identify the optimal calibration parameters representing the user-dependent offset from the optical axis to the visual axis without explicit user calibration, image processing, or marker-substitute objects. For the gaze data of 18 participants walking in two VR environments with many occlusions, the proposed method achieved an accuracy of 2.1$^\circ$, which was significantly lower than the average offset. Our method is the first self-calibration method with an average error lower than 3$^\circ$ in 3D environments. Further, the accuracy of the proposed method can be improved by up to 1.2$^\circ$ by refining the fixation detection or optimization algorithm.
Authors: Armin Danesh Pazho, Ghazal Alinezhad Noghre, Vinit Katariya, Hamed Tabkhi
Abstract: Enhancing roadway safety has become an essential computer vision focus area for Intelligent Transportation Systems (ITS). As a part of ITS, Vehicle Trajectory Prediction (VTP) aims to forecast a vehicle's future positions based on its past and current movements. VTP is a pivotal element for road safety, aiding in applications such as traffic management, accident prevention, work-zone safety, and energy optimization. While most works in this field focus on autonomous driving, with the growing number of surveillance cameras, another sub-field emerges for surveillance VTP with its own set of challenges. In this paper, we introduce VT-Former, a novel transformer-based VTP approach for highway safety and surveillance. In addition to utilizing transformers to capture long-range temporal patterns, a new Graph Attentive Tokenization (GAT) module has been proposed to capture intricate social interactions among vehicles. This study seeks to explore both the advantages and the limitations inherent in combining transformer architecture with graphs for VTP. Our investigation, conducted across three benchmark datasets from diverse surveillance viewpoints, showcases the State-of-the-Art (SotA) or comparable performance of VT-Former in predicting vehicle trajectories. This study underscores the potential of VT-Former and its architecture, opening new avenues for future research and exploration.
Authors: Jiaxi Lv, Yi Huang, Mingfu Yan, Jiancheng Huang, Jianzhuang Liu, Yifan Liu, Yafei Wen, Xiaoxin Chen, Shifeng Chen
Abstract: Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Specifically, GPT4Motion employs GPT-4 to generate a Blender script based on a user textual prompt, which commands Blender's built-in physics engine to craft fundamental scene components that encapsulate coherent physical motions across frames. Then these components are inputted into Stable Diffusion to generate a video aligned with the textual prompt. Experimental results on three basic physical motion scenarios, including rigid object drop and collision, cloth draping and swinging, and liquid flow, demonstrate that GPT4Motion can generate high-quality videos efficiently in maintaining motion coherency and entity consistency. GPT4Motion offers new insights in text-to-video research, enhancing its quality and broadening its horizon for further explorations.
Authors: Jixuan Leng, Yijiang Li, Haohan Wang
Abstract: Domain Generalization (DG), a crucial research area, seeks to train models across multiple domains and test them on unseen ones. In this paper, we introduce a novel approach, namely, Selective Cross-Modality Distillation for Domain Generalization (SCMD). SCMD leverages the capabilities of large vision-language models, specifically CLIP, to train a more efficient model, ensuring it acquires robust generalization capabilities across unseen domains. Our primary contribution is a unique selection framework strategically designed to identify hard-to-learn samples for distillation. In parallel, we introduce a novel cross-modality module that seamlessly combines the projected features of the student model with the text embeddings from CLIP, ensuring the alignment of similarity distributions. We assess SCMD's performance on various benchmarks, where it empowers a ResNet50 to deliver state-of-the-art performance, surpassing existing domain generalization methods. Furthermore, we provide a theoretical analysis of our selection strategy, offering deeper insight into its effectiveness and potential in the field of DG.
Authors: Siteng Huang, Biao Gong, Yutong Feng, Xi Chen, Yuqian Fu, Yu Liu, Donglin Wang
Abstract: This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data and generalize it to unseen humans or even animals. Experimental results show that existing subject-driven customization methods fail to learn the representative characteristics of actions and struggle in decoupling actions from context features, including appearance. To overcome the preference for low-level features and the entanglement of high-level features, we propose an inversion-based method Action-Disentangled Identifier (ADI) to learn action-specific identifiers from the exemplar images. ADI first expands the semantic conditioning space by introducing layer-wise identifier tokens, thereby increasing the representational richness while distributing the inversion across different features. Then, to block the inversion of action-agnostic features, ADI extracts the gradient invariance from the constructed sample triples and masks the updates of irrelevant channels. To comprehensively evaluate the task, we present an ActionBench that includes a variety of actions, each accompanied by meticulously selected samples. Both quantitative and qualitative results show that our ADI outperforms existing baselines in action-customized T2I generation. Our project page is at https://adi-t2i.github.io/ADI.
Authors: R\'emi Kazmierczak, Elo\"ise Berthier, Goran Frehse, Gianni Franchi
Abstract: In this paper, we introduce an explainable algorithm designed from a multi-modal foundation model, that performs fast and explainable image classification. Drawing inspiration from CLIP-based Concept Bottleneck Models (CBMs), our method creates a latent space where each neuron is linked to a specific word. Observing that this latent space can be modeled with simple distributions, we use a Mixture of Gaussians (MoG) formalism to enhance the interpretability of this latent space. Then, we introduce CLIP-QDA, a classifier that only uses statistical values to infer labels from the concepts. In addition, this formalism allows for both local and global explanations. These explanations come from the inner design of our architecture, our work is part of a new family of greybox models, combining performances of opaque foundation models and the interpretability of transparent models. Our empirical findings show that in instances where the MoG assumption holds, CLIP-QDA achieves similar accuracy with state-of-the-art methods CBMs. Our explanations compete with existing XAI methods while being faster to compute.
Authors: Michael A. Alcorn, Noah Schwartz
Abstract: To achieve strong real world performance, neural networks must be trained on large, diverse datasets; however, obtaining and annotating such datasets is costly and time-consuming, particularly for 3D point clouds. In this paper, we describe Paved2Paradise, a simple, cost-effective approach for generating fully labeled, diverse, and realistic lidar datasets from scratch, all while requiring minimal human annotation. Our key insight is that, by deliberately collecting separate "background" and "object" datasets (i.e., "factoring the real world"), we can intelligently combine them to produce a combinatorially large and diverse training set. The Paved2Paradise pipeline thus consists of four steps: (1) collecting copious background data, (2) recording individuals from the desired object class(es) performing different behaviors in an isolated environment (like a parking lot), (3) bootstrapping labels for the object dataset, and (4) generating samples by placing objects at arbitrary locations in backgrounds. To demonstrate the utility of Paved2Paradise, we generated synthetic datasets for two tasks: (1) human detection in orchards (a task for which no public data exists) and (2) pedestrian detection in urban environments. Qualitatively, we find that a model trained exclusively on Paved2Paradise synthetic data is highly effective at detecting humans in orchards, including when individuals are heavily occluded by tree branches. Quantitatively, a model trained on Paved2Paradise data that sources backgrounds from KITTI performs comparably to a model trained on the actual dataset. These results suggest the Paved2Paradise synthetic data pipeline can help accelerate point cloud model development in sectors where acquiring lidar datasets has previously been cost-prohibitive.
Authors: Lingmin Ran, Xiaodong Cun, Jia-Wei Liu, Rui Zhao, Song Zijie, Xintao Wang, Jussi Keppo, Mike Zheng Shou
Abstract: We introduce X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules (e.g., ControlNet, LoRA) to work directly with the upgraded text-to-image diffusion model (e.g., SDXL) without further retraining. We achieve this goal by training an additional network to control the frozen upgraded model with the new text-image data pairs. In detail, X-Adapter keeps a frozen copy of the old model to preserve the connectors of different plugins. Additionally, X-Adapter adds trainable mapping layers that bridge the decoders from models of different versions for feature remapping. The remapped features will be used as guidance for the upgraded model. To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model. After training, we also introduce a two-stage denoising strategy to align the initial latents of X-Adapter and the upgraded model. Thanks to our strategies, X-Adapter demonstrates universal compatibility with various plugins and also enables plugins of different versions to work together, thereby expanding the functionalities of diffusion community. To verify the effectiveness of the proposed method, we conduct extensive experiments and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.
Authors: Xu Shi, Wei Yao, Chuanchen Luo, Junran Peng, Hongwen Zhang, Yunlian Sun
Abstract: Recently, significant progress has been made in text-based motion generation, enabling the generation of diverse and high-quality human motions that conform to textual descriptions. However, generating motions beyond the distribution of original datasets remains challenging, i.e., zero-shot generation. By adopting a divide-and-conquer strategy, we propose a new framework named Fine-Grained Human Motion Diffusion Model (FG-MDM) for zero-shot human motion generation. Specifically, we first parse previous vague textual annotations into fine-grained descriptions of different body parts by leveraging a large language model. We then use these fine-grained descriptions to guide a transformer-based diffusion model, which further adopts a design of part tokens. FG-MDM can generate human motions beyond the scope of original datasets owing to descriptions that are closer to motion essence. Our experimental results demonstrate the superiority of FG-MDM over previous methods in zero-shot settings. We will release our fine-grained textual annotations for HumanML3D and KIT.
Authors: Kang Ge, Chen Wang, Yutao Guo, Yansong Tang, Zhenzhong Hu, Hongbing Chen
Abstract: Large-scale foundation models have become the mainstream deep learning method, while in civil engineering, the scale of AI models is strictly limited. In this work, a vision foundation model is introduced for crack segmentation. Two parameter-efficient fine-tuning methods, adapter and low-rank adaptation, are adopted to fine-tune the foundation model in semantic segmentation: the Segment Anything Model (SAM). The fine-tuned CrackSAM shows excellent performance on different scenes and materials. To test the zero-shot performance of the proposed method, two unique datasets related to road and exterior wall cracks are collected, annotated and open-sourced, for a total of 810 images. Comparative experiments are conducted with twelve mature semantic segmentation models. On datasets with artificial noise and previously unseen datasets, the performance of CrackSAM far exceeds that of all state-of-the-art models. CrackSAM exhibits remarkable superiority, particularly under challenging conditions such as dim lighting, shadows, road markings, construction joints, and other interference factors. These cross-scenario results demonstrate the outstanding zero-shot capability of foundation models and provide new ideas for developing vision models in civil engineering.
Authors: Kuan-Chih Huang, Yi-Hsuan Tsai, Ming-Hsuan Yang
Abstract: Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we employ visual data from three perspectives to establish connections between 2D and 3D domains. First, we design a feature-level constraint to align LiDAR and image features based on object-aware regions. Second, the output-level constraint is developed to enforce the overlap between 2D and projected 3D box estimations. Finally, the training-level constraint is utilized by producing accurate and consistent 3D pseudo-labels that align with the visual data. We conduct extensive experiments on the KITTI dataset to validate the effectiveness of the proposed three constraints. Without using any 3D labels, our method achieves favorable performance against state-of-the-art approaches and is competitive with the method that uses 500-frame 3D annotations. Code and models will be made publicly available at https://github.com/kuanchihhuang/VG-W3D.
Authors: Yue Yang, Fan-Yun Sun, Luca Weihs, Eli VanderBilt, Alvaro Herrasti, Winson Han, Jiajun Wu, Nick Haber, Ranjay Krishna, Lingjie Liu, Chris Callison-Burch, Mark Yatskar, Aniruddha Kembhavi, Christopher Clark
Abstract: 3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To mitigate this limitation, we present Holodeck, a system that generates 3D environments to match a user-supplied prompt fully automatedly. Holodeck can generate diverse scenes, e.g., arcades, spas, and museums, adjust the designs for styles, and can capture the semantics of complex queries such as "apartment for a researcher with a cat" and "office of a professor who is a fan of Star Wars". Holodeck leverages a large language model (i.e., GPT-4) for common sense knowledge about what the scene might look like and uses a large collection of 3D assets from Objaverse to populate the scene with diverse objects. To address the challenge of positioning objects correctly, we prompt GPT-4 to generate spatial relational constraints between objects and then optimize the layout to satisfy those constraints. Our large-scale human evaluation shows that annotators prefer Holodeck over manually designed procedural baselines in residential scenes and that Holodeck can produce high-quality outputs for diverse scene types. We also demonstrate an exciting application of Holodeck in Embodied AI, training agents to navigate in novel scenes like music rooms and daycares without human-constructed data, which is a significant step forward in developing general-purpose embodied agents.
Authors: Yanting Zhang, Shuanghong Wang, Qingxiang Wang, Cairong Yan, Rui Fan
Abstract: Ensuring driving safety for autonomous vehicles has become increasingly crucial, highlighting the need for systematic tracking of on-road pedestrians. Most vehicles are equipped with visual sensors, however, the large-scale visual data has not been well studied yet. Multi-target multi-camera (MTMC) tracking systems are composed of two modules: single-camera tracking (SCT) and inter-camera tracking (ICT). To reliably coordinate between them, MTMC tracking has been a very complicated task, while tracking across multiple moving cameras makes it even more challenging. In this paper, we focus on multi-target multi-moving-camera (MTMMC) tracking, which is attracting increasing attention from the research community. Observing there are few datasets for MTMMC tracking, we collect a new dataset, called Multi-Moving-Camera Track (MMCT), which contains sequences under various driving scenarios. To address the common problems of identity switch easily faced by most existing SCT trackers, especially for moving cameras due to ego-motion between the camera and targets, a lightweight appearance-free global link model, called Linker, is proposed to mitigate the identity switch by associating two disjoint tracklets of the same target into a complete trajectory within the same camera. Incorporated with Linker, existing SCT trackers generally obtain a significant improvement. Moreover, to alleviate the impact of the image style variations caused by different cameras, a color transfer module is effectively incorporated to extract cross-camera consistent appearance features for pedestrian association across moving cameras for ICT, resulting in a much improved MTMMC tracking system, which can constitute a step further towards coordinated mining of multiple moving cameras. The project page is available at https://dhu-mmct.github.io/.
Authors: Mingyu Liu, Ekim Yurtsever, Jonathan Fossaert, Xingcheng Zhou, Walter Zimmer, Yuning Cui, Bare Luka Zagar, Alois C. Knoll
Abstract: Autonomous driving has rapidly developed and shown promising performance due to recent advances in hardware and deep learning techniques. High-quality datasets are fundamental for developing reliable autonomous driving algorithms. Previous dataset surveys either focused on a limited number or lacked detailed investigation of dataset characteristics. To this end, we present an exhaustive study of 265 autonomous driving datasets from multiple perspectives, including sensor modalities, data size, tasks, and contextual conditions. We introduce a novel metric to evaluate the impact of datasets, which can also be a guide for creating new datasets. Besides, we analyze the annotation processes, existing labeling tools, and the annotation quality of datasets, showing the importance of establishing a standard annotation pipeline. On the other hand, we thoroughly analyze the impact of geographical and adversarial environmental conditions on the performance of autonomous driving systems. Moreover, we exhibit the data distribution of several vital datasets and discuss their pros and cons accordingly. Finally, we discuss the current challenges and the development trend of the future autonomous driving datasets.
Authors: Ziying Song, Guoxing Zhang, Lin Liu, Lei Yang, Shaoqing Xu, Caiyan Jia, Feiyang Jia, Li Wang
Abstract: Multi-modal 3D object detectors are dedicated to exploring secure and reliable perception systems for autonomous driving (AD).Although achieving state-of-the-art (SOTA) performance on clean benchmark datasets, they tend to overlook the complexity and harsh conditions of real-world environments. With the emergence of visual foundation models (VFMs), opportunities and challenges are presented for improving the robustness and generalization of multi-modal 3D object detection in AD. Therefore, we propose RoboFusion, a robust framework that leverages VFMs like SAM to tackle out-of-distribution (OOD) noise scenarios. We first adapt the original SAM for AD scenarios named SAM-AD. To align SAM or SAM-AD with multi-modal methods, we then introduce AD-FPN for upsampling the image features extracted by SAM. We employ wavelet decomposition to denoise the depth-guided images for further noise reduction and weather interference. At last, we employ self-attention mechanisms to adaptively reweight the fused features, enhancing informative features while suppressing excess noise. In summary, RoboFusion significantly reduces noise by leveraging the generalization and robustness of VFMs, thereby enhancing the resilience of multi-modal 3D object detection. Consequently, RoboFusion achieves SOTA performance in noisy scenarios, as demonstrated by the KITTI-C and nuScenes-C benchmarks. Code is available at https://github.com/adept-thu/RoboFusion.
Authors: Qiao Jin, Fangyuan Chen, Yiliang Zhou, Ziyang Xu, Justin M. Cheung, Robert Chen, Ronald M. Summers, Justin F. Rousseau, Peiyun Ni, Marc J Landsman, Sally L. Baxter, Subhi J. Al'Aref, Yijia Li, Alex Chen, Josef A. Brejt, Michael F. Chiang, Yifan Peng, Zhiyong Lu
Abstract: Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges - an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V performs comparatively to human physicians regarding multi-choice accuracy (81.6% vs. 77.8%). GPT-4V also performs well in cases where physicians incorrectly answer, with over 78% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (35.5%), most prominent in image comprehension (27.2%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such multimodal AI models into clinical workflows.
Authors: Yixu Feng, Cheng Zhang, Pei Wang, Peng Wu, Qingsen Yan, Yanning Zhang
Abstract: Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images. Most existing methods learn the mapping function between low/normal-light images by Deep Neural Networks (DNNs) on sRGB and HSV color space. Nevertheless, enhancement involves amplifying image signals, and applying these color spaces to low-light images with a low signal-to-noise ratio can introduce sensitivity and instability into the enhancement process. Consequently, this results in the presence of color artifacts and brightness artifacts in the enhanced images. To alleviate this problem, we propose a novel trainable color space, named Horizontal/Vertical-Intensity (HVI). It not only decouples brightness and color from RGB channels to mitigate the instability during enhancement but also adapts to low-light images in different illumination ranges due to the trainable parameters. Further, we design a novel Color and Intensity Decoupling Network (CIDNet) with two branches dedicated to processing the decoupled image brightness and color in the HVI space. Within CIDNet, we introduce the Lightweight Cross-Attention (LCA) module to facilitate interaction between image structure and content information in both branches, while also suppressing noise in low-light images. Finally, we conducted 22 quantitative and qualitative experiments to show that the proposed CIDNet outperforms the state-of-the-art methods on 11 datasets. The code is available at https://github.com/Fediory/HVI-CIDNet.
Authors: Matthieu Vilain, R\'emi Giraud, Hugo Germain, Guillaume Bourmaud
Abstract: Semi-dense detector-free approaches (SDF), such as LoFTR, are currently among the most popular image matching methods. While SDF methods are trained to establish correspondences between two images, their performances are almost exclusively evaluated using relative pose estimation metrics. Thus, the link between their ability to establish correspondences and the quality of the resulting estimated pose has thus far received little attention. This paper is a first attempt to study this link. We start with proposing a novel structured attention-based image matching architecture (SAM). It allows us to show a counter-intuitive result on two datasets (MegaDepth and HPatches): on the one hand SAM either outperforms or is on par with SDF methods in terms of pose/homography estimation metrics, but on the other hand SDF approaches are significantly better than SAM in terms of matching accuracy. We then propose to limit the computation of the matching accuracy to textured regions, and show that in this case SAM often surpasses SDF methods. Our findings highlight a strong correlation between the ability to establish accurate correspondences in textured regions and the accuracy of the resulting estimated pose/homography. Our code will be made available.
Authors: Jisu Nam, Heesu Kim, DongJae Lee, Siyoon Jin, Seungryong Kim, Seunggyu Chang
Abstract: The objective of text-to-image (T2I) personalization is to customize a diffusion model to a user-provided reference concept, generating diverse images of the concept aligned with the target prompts. Conventional methods representing the reference concepts using unique text embeddings often fail to accurately mimic the appearance of the reference. To address this, one solution may be explicitly conditioning the reference images into the target denoising process, known as key-value replacement. However, prior works are constrained to local editing since they disrupt the structure path of the pre-trained T2I model. To overcome this, we propose a novel plug-in method, called DreamMatcher, which reformulates T2I personalization as semantic matching. Specifically, DreamMatcher replaces the target values with reference values aligned by semantic matching, while leaving the structure path unchanged to preserve the versatile capability of pre-trained T2I models for generating diverse structures. We also introduce a semantic-consistent masking strategy to isolate the personalized concept from irrelevant regions introduced by the target prompts. Compatible with existing T2I models, DreamMatcher shows significant improvements in complex scenarios. Intensive analyses demonstrate the effectiveness of our approach.
Authors: Danyang Hou, Liang Pang, Huawei Shen, Xueqi Cheng
Abstract: Video Corpus Moment Retrieval (VCMR) is a new video retrieval task aimed at retrieving a relevant moment from a large corpus of untrimmed videos using a text query. The relevance between the video and query is partial, mainly evident in two aspects:~(1)~Scope: The untrimmed video contains many frames, but not all are relevant to the query. Strong relevance is typically observed only within the relevant moment.~(2)~Modality: The relevance of the query varies with different modalities. Action descriptions align more with visual elements, while character conversations are more related to textual information.Existing methods often treat all video contents equally, leading to sub-optimal moment retrieval. We argue that effectively capturing the partial relevance between the query and video is essential for the VCMR task. To this end, we propose a Partial Relevance Enhanced Model~(PREM) to improve VCMR. VCMR involves two sub-tasks: video retrieval and moment localization. To align with their distinct objectives, we implement specialized partial relevance enhancement strategies. For video retrieval, we introduce a multi-modal collaborative video retriever, generating different query representations for the two modalities by modality-specific pooling, ensuring a more effective match. For moment localization, we propose the focus-then-fuse moment localizer, utilizing modality-specific gates to capture essential content. We also introduce relevant content-enhanced training methods for both retriever and localizer to enhance the ability of model to capture relevant content. Experimental results on TVR and DiDeMo datasets show that the proposed model outperforms the baselines, achieving a new state-of-the-art of VCMR. The code is available at \url{https://github.com/hdy007007/PREM}.
Authors: Delong Chen, Samuel Cahyawijaya, Jianfeng Liu, Baoyuan Wang, Pascale Fung
Abstract: Transformer-based vision models typically tokenize images into fixed-size square patches as input units, which lacks the adaptability to image content and overlooks the inherent pixel grouping structure. Inspired by the subword tokenization widely adopted in language models, we propose an image tokenizer at a subobject level, where the subobjects are represented by semantically meaningful image segments obtained by segmentation models (e.g., segment anything models). To implement a learning system based on subobject tokenization, we first introduced a Direct Segment Anything Model (DirectSAM) that efficiently produces comprehensive segmentation of subobjects, then embed subobjects into compact latent vectors and fed them into a large language model for vision language learning. Empirical results demonstrated that our subobject-level tokenization significantly facilitates efficient learning of translating images into object and attribute descriptions compared to the traditional patch-level tokenization. Codes and models are open-sourced at https://github.com/ChenDelong1999/subobjects.
Authors: Ailin Deng, Zhirui Chen, Bryan Hooi
Abstract: Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality. Current approaches often rely on the model's token likelihoods or other internal information, instruction tuning on additional datasets, or incorporating complex external tools. We first perform empirical analysis on sentence-level LVLM hallucination, finding that CLIP similarity to the image acts as a stronger and more robust indicator of hallucination compared to token likelihoods. Motivated by this, we introduce our CLIP-Guided Decoding (CGD) approach, a straightforward but effective training-free approach to reduce object hallucination at decoding time. CGD uses CLIP to guide the model's decoding process by enhancing visual grounding of generated text with the image. Experiments demonstrate that CGD effectively mitigates object hallucination across multiple LVLM families while preserving the utility of text generation. Codes are available at https://github.com/d-ailin/CLIP-Guided-Decoding.
Authors: Shuai Tan, Bin Ji, Ye Pan
Abstract: Generating emotional talking faces is a practical yet challenging endeavor. To create a lifelike avatar, we draw upon two critical insights from a human perspective: 1) The connection between audio and the non-deterministic facial dynamics, encompassing expressions, blinks, poses, should exhibit synchronous and one-to-many mapping. 2) Vibrant expressions are often accompanied by emotion-aware high-definition (HD) textures and finely detailed teeth. However, both aspects are frequently overlooked by existing methods. To this end, this paper proposes using normalizing Flow and Vector-Quantization modeling to produce emotional talking faces that satisfy both insights concurrently (FlowVQTalker). Specifically, we develop a flow-based coefficient generator that encodes the dynamics of facial emotion into a multi-emotion-class latent space represented as a mixture distribution. The generation process commences with random sampling from the modeled distribution, guided by the accompanying audio, enabling both lip-synchronization and the uncertain nonverbal facial cues generation. Furthermore, our designed vector-quantization image generator treats the creation of expressive facial images as a code query task, utilizing a learned codebook to provide rich, high-quality textures that enhance the emotional perception of the results. Extensive experiments are conducted to showcase the effectiveness of our approach.
Authors: Feng Cheng, Ziyang Wang, Yi-Lin Sung, Yan-Bo Lin, Mohit Bansal, Gedas Bertasius
Abstract: We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually arriving datasets, (iii) handle inputs from unknown datasets during inference, and (iv) enable knowledge sharing across similar dataset domains. Given a set of continually streaming VidQA datasets, we sequentially train dataset-specific adapters for each dataset while freezing the parameters of a large pretrained video-language backbone. During inference, given a video-question sample from an unknown domain, our method first uses the proposed non-parametric router function to compute a probability for each adapter, reflecting how relevant that adapter is to the current video-question input instance. Subsequently, the proposed dynamic adapter merging scheme aggregates all the adapter weights into a new adapter instance tailored for that particular test sample to compute the final VidQA prediction, mitigating the impact of inaccurate router predictions and facilitating knowledge sharing across domains. Our DAM model outperforms prior state-of-the-art continual learning approaches by 9.1% while exhibiting 1.9% less forgetting on 6 VidQA datasets spanning various domains. We further extend DAM to continual image classification and image QA and outperform prior methods by a large margin. The code is publicly available at: https://github.com/klauscc/DAM
Authors: Ashish Sinha, Ghassan Hamarneh
Abstract: Anatomical trees play a central role in clinical diagnosis and treatment planning. However, accurately representing anatomical trees is challenging due to their varying and complex topology and geometry. Traditional methods for representing tree structures, captured using medical imaging, while invaluable for visualizing vascular and bronchial networks, exhibit drawbacks in terms of limited resolution, flexibility, and efficiency. Recently, implicit neural representations (INRs) have emerged as a powerful tool for representing shapes accurately and efficiently. We propose a novel approach for representing anatomical trees using INR, while also capturing the distribution of a set of trees via denoising diffusion in the space of INRs. We accurately capture the intricate geometries and topologies of anatomical trees at any desired resolution. Through extensive qualitative and quantitative evaluation, we demonstrate high-fidelity tree reconstruction with arbitrary resolution yet compact storage, and versatility across anatomical sites and tree complexities.
Authors: Yinggui Wang, Yuanqing Huang, Jianshu Li, Le Yang, Kai Song, Lei Wang
Abstract: The utilization of personal sensitive data in training face recognition (FR) models poses significant privacy concerns, as adversaries can employ model inversion attacks (MIA) to infer the original training data. Existing defense methods, such as data augmentation and differential privacy, have been employed to mitigate this issue. However, these methods often fail to strike an optimal balance between privacy and accuracy. To address this limitation, this paper introduces an adaptive hybrid masking algorithm against MIA. Specifically, face images are masked in the frequency domain using an adaptive MixUp strategy. Unlike the traditional MixUp algorithm, which is predominantly used for data augmentation, our modified approach incorporates frequency domain mixing. Previous studies have shown that increasing the number of images mixed in MixUp can enhance privacy preservation but at the expense of reduced face recognition accuracy. To overcome this trade-off, we develop an enhanced adaptive MixUp strategy based on reinforcement learning, which enables us to mix a larger number of images while maintaining satisfactory recognition accuracy. To optimize privacy protection, we propose maximizing the reward function (i.e., the loss function of the FR system) during the training of the strategy network. While the loss function of the FR network is minimized in the phase of training the FR network. The strategy network and the face recognition network can be viewed as antagonistic entities in the training process, ultimately reaching a more balanced trade-off. Experimental results demonstrate that our proposed hybrid masking scheme outperforms existing defense algorithms in terms of privacy preservation and recognition accuracy against MIA.
Authors: Jiacheng Zhang, Jiaming Li, Xiangru Lin, Wei Zhang, Xiao Tan, Junyu Han, Errui Ding, Jingdong Wang, Guanbin Li
Abstract: We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D attributes and the tendency of depth supervision derived from pseudo-labels to be noisy, leading to significant optimization conflicts with other reliable forms of supervision. We introduce a novel decoupled pseudo-labeling (DPL) approach for SSM3OD. Our approach features a Decoupled Pseudo-label Generation (DPG) module, designed to efficiently generate pseudo-labels by separately processing 2D and 3D attributes. This module incorporates a unique homography-based method for identifying dependable pseudo-labels in BEV space, specifically for 3D attributes. Additionally, we present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and removing conflicting gradients. This dual decoupling strategy-at both the pseudo-label generation and gradient levels-significantly improves the utilization of pseudo-labels in SSM3OD. Our comprehensive experiments on the KITTI benchmark demonstrate the superiority of our method over existing approaches.
Authors: Andrea Atzori, Fadi Boutros, Naser Damer, Gianni Fenu, Mirko Marras
Abstract: Recent advances in deep face recognition have spurred a growing demand for large, diverse, and manually annotated face datasets. Acquiring authentic, high-quality data for face recognition has proven to be a challenge, primarily due to privacy concerns. Large face datasets are primarily sourced from web-based images, lacking explicit user consent. In this paper, we examine whether and how synthetic face data can be used to train effective face recognition models with reduced reliance on authentic images, thereby mitigating data collection concerns. First, we explored the performance gap among recent state-of-the-art face recognition models, trained with synthetic data only and authentic (scarce) data only. Then, we deepened our analysis by training a state-of-the-art backbone with various combinations of synthetic and authentic data, gaining insights into optimizing the limited use of the latter for verification accuracy. Finally, we assessed the effectiveness of data augmentation approaches on synthetic and authentic data, with the same goal in mind. Our results highlighted the effectiveness of FR trained on combined datasets, particularly when combined with appropriate augmentation techniques.
Authors: Pengxiao Han, Changkun Ye, Jieming Zhou, Jing Zhang, Jie Hong, Xuesong Li
Abstract: Long-tailed imbalance distribution is a common issue in practical computer vision applications. Previous works proposed methods to address this problem, which can be categorized into several classes: re-sampling, re-weighting, transfer learning, and feature augmentation. In recent years, diffusion models have shown an impressive generation ability in many sub-problems of deep computer vision. However, its powerful generation has not been explored in long-tailed problems. We propose a new approach, the Latent-based Diffusion Model for Long-tailed Recognition (LDMLR), as a feature augmentation method to tackle the issue. First, we encode the imbalanced dataset into features using the baseline model. Then, we train a Denoising Diffusion Implicit Model (DDIM) using these encoded features to generate pseudo-features. Finally, we train the classifier using the encoded and pseudo-features from the previous two steps. The model's accuracy shows an improvement on the CIFAR-LT and ImageNet-LT datasets by using the proposed method.
Authors: Tong Zhao, Lei Yang, Yichen Xie, Mingyu Ding, Masayoshi Tomizuka, Yintao Wei
Abstract: Road surface conditions, especially geometry profiles, enormously affect driving performance of autonomous vehicles. Vision-based online road reconstruction promisingly captures road information in advance. Existing solutions like monocular depth estimation and stereo matching suffer from modest performance. The recent technique of Bird's-Eye-View (BEV) perception provides immense potential to more reliable and accurate reconstruction. This paper uniformly proposes two simple yet effective models for road elevation reconstruction in BEV named RoadBEV-mono and RoadBEV-stereo, which estimate road elevation with monocular and stereo images, respectively. The former directly fits elevation values based on voxel features queried from image view, while the latter efficiently recognizes road elevation patterns based on BEV volume representing discrepancy between left and right voxel features. Insightful analyses reveal their consistence and difference with perspective view. Experiments on real-world dataset verify the models' effectiveness and superiority. Elevation errors of RoadBEV-mono and RoadBEV-stereo achieve 1.83cm and 0.50cm, respectively. The estimation performance improves by 50\% in BEV based on monocular image. Our models are promising for practical applications, providing valuable references for vision-based BEV perception in autonomous driving. The code is released at https://github.com/ztsrxh/RoadBEV.
Authors: William Ljungbergh, Adam Tonderski, Joakim Johnander, Holger Caesar, Kalle {\AA}str\"om, Michael Felsberg, Christoffer Petersson
Abstract: We present a versatile NeRF-based simulator for testing autonomous driving (AD) software systems, designed with a focus on sensor-realistic closed-loop evaluation and the creation of safety-critical scenarios. The simulator learns from sequences of real-world driving sensor data and enables reconfigurations and renderings of new, unseen scenarios. In this work, we use our simulator to test the responses of AD models to safety-critical scenarios inspired by the European New Car Assessment Programme (Euro NCAP). Our evaluation reveals that, while state-of-the-art end-to-end planners excel in nominal driving scenarios in an open-loop setting, they exhibit critical flaws when navigating our safety-critical scenarios in a closed-loop setting. This highlights the need for advancements in the safety and real-world usability of end-to-end planners. By publicly releasing our simulator and scenarios as an easy-to-run evaluation suite, we invite the research community to explore, refine, and validate their AD models in controlled, yet highly configurable and challenging sensor-realistic environments. Code and instructions can be found at https://github.com/atonderski/neuro-ncap
Authors: Bor-Shiun Wang, Chien-Yi Wang, Wei-Chen Chiu
Abstract: Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model training. Although being effective in bridging the semantic gap between a model's latent space and human interpretation, these explanation methods only partially reveal the model's decision-making process. The outcome is typically limited to high-level semantics derived from the last feature map. We argue that the explanations lacking insights into the decision processes at low and mid-level features are neither fully faithful nor useful. Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model. MCPNet autonomously learns meaningful concept prototypes across multiple feature map levels using Centered Kernel Alignment (CKA) loss and an energy-based weighted PCA mechanism, and it does so without reliance on predefined concept labels. Further, we propose a novel classifier paradigm that learns and aligns multi-level concept prototype distributions for classification purposes via Class-aware Concept Distribution (CCD) loss. Our experiments reveal that our proposed MCPNet while being adaptable to various model architectures, offers comprehensive multi-level explanations while maintaining classification accuracy. Additionally, its concept distribution-based classification approach shows improved generalization capabilities in few-shot classification scenarios.
Authors: Xuelong Li, Hongjun An, Guangying Li, Xing Wang, Guanghua Cheng, Zhe Sun
Abstract: In this paper, we introduce StreakNet-Arch, a novel signal processing architecture designed for Underwater Carrier LiDAR-Radar (UCLR) imaging systems, to address the limitations in scatter suppression and real-time imaging. StreakNet-Arch formulates the signal processing as a real-time, end-to-end binary classification task, enabling real-time image acquisition. To achieve this, we leverage Self-Attention networks and propose a novel Double Branch Cross Attention (DBC-Attention) mechanism that surpasses the performance of traditional methods. Furthermore, we present a method for embedding streak-tube camera images into attention networks, effectively acting as a learned bandpass filter. To facilitate further research, we contribute a publicly available streak-tube camera image dataset. The dataset contains 2,695,168 real-world underwater 3D point cloud data. These advancements significantly improve UCLR capabilities, enhancing its performance and applicability in underwater imaging tasks. The source code and dataset can be found at https://github.com/BestAnHongjun/StreakNet .
Authors: Manideep Reddy Aliminati, Bharatesh Chakravarthi, Aayush Atul Verma, Arpitsinh Vaghela, Hua Wei, Xuesong Zhou, Yezhou Yang
Abstract: Recently, event-based vision sensors have gained attention for autonomous driving applications, as conventional RGB cameras face limitations in handling challenging dynamic conditions. However, the availability of real-world and synthetic event-based vision datasets remains limited. In response to this gap, we present SEVD, a first-of-its-kind multi-view ego, and fixed perception synthetic event-based dataset using multiple dynamic vision sensors within the CARLA simulator. Data sequences are recorded across diverse lighting (noon, nighttime, twilight) and weather conditions (clear, cloudy, wet, rainy, foggy) with domain shifts (discrete and continuous). SEVD spans urban, suburban, rural, and highway scenes featuring various classes of objects (car, truck, van, bicycle, motorcycle, and pedestrian). Alongside event data, SEVD includes RGB imagery, depth maps, optical flow, semantic, and instance segmentation, facilitating a comprehensive understanding of the scene. Furthermore, we evaluate the dataset using state-of-the-art event-based (RED, RVT) and frame-based (YOLOv8) methods for traffic participant detection tasks and provide baseline benchmarks for assessment. Additionally, we conduct experiments to assess the synthetic event-based dataset's generalization capabilities. The dataset is available at https://eventbasedvision.github.io/SEVD
Authors: Qiangang Du, Jinlong Peng, Changan Wang, Xu Chen, Qingdong He, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
Abstract: Change detection aims to identify remote sense object changes by analyzing data between bitemporal image pairs. Due to the large temporal and spatial span of data collection in change detection image pairs, there are often a significant amount of task-specific and task-agnostic noise. Previous effort has focused excessively on denoising, with this goes a great deal of loss of fine-grained information. In this paper, we revisit the importance of fine-grained features in change detection and propose a series of operations for fine-grained information compensation and noise decoupling (FINO). First, the context is utilized to compensate for the fine-grained information in the feature space. Next, a shape-aware and a brightness-aware module are designed to improve the capacity for representation learning. The shape-aware module guides the backbone for more precise shape estimation, guiding the backbone network in extracting object shape features. The brightness-aware module learns a overall brightness estimation to improve the model's robustness to task-agnostic noise. Finally, a task-specific noise decoupling structure is designed as a way to improve the model's ability to separate noise interference from feature similarity. With these training schemes, our proposed method achieves new state-of-the-art (SOTA) results in multiple change detection benchmarks. The code will be made available.
Authors: Qiangang Du, Jinlong Peng, Xu Chen, Qingdong He, Liren He, Qiang Nie, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
Abstract: Change detection is widely applied in remote sensing image analysis. Existing methods require training models separately for each dataset, which leads to poor domain generalization. Moreover, these methods rely heavily on large amounts of high-quality pair-labelled data for training, which is expensive and impractical. In this paper, we propose a multimodal contrastive learning (ChangeCLIP) based on visual-language pre-training for change detection domain generalization. Additionally, we propose a dynamic context optimization for prompt learning. Meanwhile, to address the data dependency issue of existing methods, we introduce a single-temporal and controllable AI-generated training strategy (SAIN). This allows us to train the model using a large number of single-temporal images without image pairs in the real world, achieving excellent generalization. Extensive experiments on series of real change detection datasets validate the superiority and strong generalization of ChangeCLIP, outperforming state-of-the-art change detection methods. Code will be available.
Authors: Xi Chen (Zhejiang University), Sida Peng (Zhejiang University), Dongchen Yang (Zhejiang University), Yuan Liu (The University of Hong Kong), Bowen Pan (Tao Technology Department, Alibaba Group), Chengfei Lv (Tao Technology Department, Alibaba Group), Xiaowei Zhou (Zhejiang University)
Abstract: This paper aims to recover object materials from posed images captured under an unknown static lighting condition. Recent methods solve this task by optimizing material parameters through differentiable physically based rendering. However, due to the coupling between object geometry, materials, and environment lighting, there is inherent ambiguity during the inverse rendering process, preventing previous methods from obtaining accurate results. To overcome this ill-posed problem, our key idea is to learn the material prior with a generative model for regularizing the optimization process. We observe that the general rendering equation can be split into diffuse and specular shading terms, and thus formulate the material prior as diffusion models of albedo and specular. Thanks to this design, our model can be trained using the existing abundant 3D object data, and naturally acts as a versatile tool to resolve the ambiguity when recovering material representations from RGB images. In addition, we develop a coarse-to-fine training strategy that leverages estimated materials to guide diffusion models to satisfy multi-view consistent constraints, leading to more stable and accurate results. Extensive experiments on real-world and synthetic datasets demonstrate that our approach achieves state-of-the-art performance on material recovery. The code will be available at https://zju3dv.github.io/IntrinsicAnything.
Authors: Sina Sharifi, Taha Entesari, Bardia Safaei, Vishal M. Patel, Mahyar Fazlyab
Abstract: One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution. Addressing this issue is known as Out-of-Distribution (OOD) detection. Many state-of-the-art OOD methods employ an auxiliary dataset as a surrogate for OOD data during training to achieve improved performance. However, these methods fail to fully exploit the local information embedded in the auxiliary dataset. In this work, we propose the idea of leveraging the information embedded in the gradient of the loss function during training to enable the network to not only learn a desired OOD score for each sample but also to exhibit similar behavior in a local neighborhood around each sample. We also develop a novel energy-based sampling method to allow the network to be exposed to more informative OOD samples during the training phase. This is especially important when the auxiliary dataset is large. We demonstrate the effectiveness of our method through extensive experiments on several OOD benchmarks, improving the existing state-of-the-art FPR95 by 4% on our ImageNet experiment. We further provide a theoretical analysis through the lens of certified robustness and Lipschitz analysis to showcase the theoretical foundation of our work. We will publicly release our code after the review process.
Authors: Da Chang, Yu Li
Abstract: With the continuous development of Optical Character Recognition (OCR) and the expansion of application fields, text recognition in complex scenes has become a key challenge. Factors such as multiple fonts, mixed scenes and complex layouts seriously affect the recognition accuracy of traditional OCR models. Although OCR models based on deep learning have performed well in specific fields or similar datasets in recent years, the generalization ability and robustness of the model are still a big challenge when facing complex environments with multiple scenes. Furthermore, training an OCR model from scratch or fine-tuning all parameters is very demanding on computing resources and inference time, which limits the flexibility of its application. This study focuses on a fundamental aspect of mixed text recognition in response to the challenges mentioned above, which involves effectively fine-tuning the pre-trained basic OCR model to demonstrate exceptional performance across various downstream tasks. To this end, we propose a parameter-efficient mixed text recognition method based on pre-trained OCR Transformer, namely DLoRA-TrOCR. This method embeds DoRA into the image encoder and LoRA into the internal structure of the text decoder, enabling efficient parameter fine-tuning for downstream tasks. Experiments show that compared to similar parameter adjustment methods, our model DLoRA-TrOCR has the smallest number of parameters and performs better. It can achieve state-of-the-art performance on complex scene datasets involving simultaneous recognition of mixed handwritten, printed and street view texts.
Authors: Haoyu Zheng, Wenqiao Zhang, Yaoke Wang, Hao Zhou, Jiang Liu, Juncheng Li, Zheqi Lv, Siliang Tang, Yueting Zhuang
Abstract: Revolutionary advancements in text-to-image models have unlocked new dimensions for sophisticated content creation, e.g., text-conditioned image editing, allowing us to edit the diverse images that convey highly complex visual concepts according to the textual guidance. Despite being promising, existing methods focus on texture- or non-rigid-based visual manipulation, which struggles to produce the fine-grained animation of smooth text-conditioned image morphing without fine-tuning, i.e., due to their highly unstructured latent space. In this paper, we introduce a tuning-free LLM-driven attention control framework, encapsulated by the progressive process of LLM planning, prompt-Aware editing, StablE animation geneRation, abbreviated as LASER. LASER employs a large language model (LLM) to refine coarse descriptions into detailed prompts, guiding pre-trained text-to-image models for subsequent image generation. We manipulate the model's spatial features and self-attention mechanisms to maintain animation integrity and enable seamless morphing directly from text prompts, eliminating the need for additional fine-tuning or annotations. Our meticulous control over spatial features and self-attention ensures structural consistency in the images. This paper presents a novel framework integrating LLMs with text-to-image models to create high-quality animations from a single text input. We also propose a Text-conditioned Image-to-Animation Benchmark to validate the effectiveness and efficacy of LASER. Extensive experiments demonstrate that LASER produces impressive, consistent, and efficient results in animation generation, positioning it as a powerful tool for advanced digital content creation.
Authors: Haoyan Gong, Yuzheng Feng, Zhenrong Zhang, Xianxu Hou, Jingxin Liu, Siqi Huang, Hongbin Liu
Abstract: Vehicle license plate recognition is a crucial task in intelligent traffic management systems. However, the challenge of achieving accurate recognition persists due to motion blur from fast-moving vehicles. Despite the widespread use of image synthesis approaches in existing deblurring and recognition algorithms, their effectiveness in real-world scenarios remains unproven. To address this, we introduce the first large-scale license plate deblurring dataset named License Plate Blur (LPBlur), captured by a dual-camera system and processed through a post-processing pipeline to avoid misalignment issues. Then, we propose a License Plate Deblurring Generative Adversarial Network (LPDGAN) to tackle the license plate deblurring: 1) a Feature Fusion Module to integrate multi-scale latent codes; 2) a Text Reconstruction Module to restore structure through textual modality; 3) a Partition Discriminator Module to enhance the model's perception of details in each letter. Extensive experiments validate the reliability of the LPBlur dataset for both model training and testing, showcasing that our proposed model outperforms other state-of-the-art motion deblurring methods in realistic license plate deblurring scenarios. The dataset and code are available at https://github.com/haoyGONG/LPDGAN.
Authors: Yunlong Ran, Yanxu Li, Qi Ye, Yuchi Huo, Zechun Bai, Jiahao Sun, Jiming Chen
Abstract: Neural radiance field (NeRF) has achieved impressive results in high-quality 3D scene reconstruction. However, NeRF heavily relies on precise camera poses. While recent works like BARF have introduced camera pose optimization within NeRF, their applicability is limited to simple trajectory scenes. Existing methods struggle while tackling complex trajectories involving large rotations. To address this limitation, we propose CT-NeRF, an incremental reconstruction optimization pipeline using only RGB images without pose and depth input. In this pipeline, we first propose a local-global bundle adjustment under a pose graph connecting neighboring frames to enforce the consistency between poses to escape the local minima caused by only pose consistency with the scene structure. Further, we instantiate the consistency between poses as a reprojected geometric image distance constraint resulting from pixel-level correspondences between input image pairs. Through the incremental reconstruction, CT-NeRF enables the recovery of both camera poses and scene structure and is capable of handling scenes with complex trajectories. We evaluate the performance of CT-NeRF on two real-world datasets, NeRFBuster and Free-Dataset, which feature complex trajectories. Results show CT-NeRF outperforms existing methods in novel view synthesis and pose estimation accuracy.
Authors: Chen Xu, Tianhui Song, Weixin Feng, Xubin Li, Tiezheng Ge, Bo Zheng, Limin Wang
Abstract: Diffusion models have significantly advanced the state of the art in image, audio, and video generation tasks. However, their applications in practical scenarios are hindered by slow inference speed. Drawing inspiration from the approximation strategies utilized in consistency models, we propose the Sub-path Linear Approximation Model (SLAM), which accelerates diffusion models while maintaining high-quality image generation. SLAM treats the PF-ODE trajectory as a series of PF-ODE sub-paths divided by sampled points, and harnesses sub-path linear (SL) ODEs to form a progressive and continuous error estimation along each individual PF-ODE sub-path. The optimization on such SL-ODEs allows SLAM to construct denoising mappings with smaller cumulative approximated errors. An efficient distillation method is also developed to facilitate the incorporation of more advanced diffusion models, such as latent diffusion models. Our extensive experimental results demonstrate that SLAM achieves an efficient training regimen, requiring only 6 A100 GPU days to produce a high-quality generative model capable of 2 to 4-step generation with high performance. Comprehensive evaluations on LAION, MS COCO 2014, and MS COCO 2017 datasets also illustrate that SLAM surpasses existing acceleration methods in few-step generation tasks, achieving state-of-the-art performance both on FID and the quality of the generated images.
Authors: Jaeho Shin, Seungsang Yun, Ayoung Kim
Abstract: RGB-D cameras are crucial in robotic perception, given their ability to produce images augmented with depth data. However, their limited FOV often requires multiple cameras to cover a broader area. In multi-camera RGB-D setups, the goal is typically to reduce camera overlap, optimizing spatial coverage with as few cameras as possible. The extrinsic calibration of these systems introduces additional complexities. Existing methods for extrinsic calibration either necessitate specific tools or highly depend on the accuracy of camera motion estimation. To address these issues, we present PeLiCal, a novel line-based calibration approach for RGB-D camera systems exhibiting limited overlap. Our method leverages long line features from surroundings, and filters out outliers with a novel convergence voting algorithm, achieving targetless, real-time, and outlier-robust performance compared to existing methods. We open source our implementation on https://github.com/joomeok/PeLiCal.git.
Authors: Hai Ci, Pei Yang, Yiren Song, Mike Zheng Shou
Abstract: We revisit Tree-Ring Watermarking, a recent diffusion model watermarking method that demonstrates great robustness to various attacks. We conduct an in-depth study on it and reveal that the distribution shift unintentionally introduced by the watermarking process, apart from watermark pattern matching, contributes to its exceptional robustness. Our investigation further exposes inherent flaws in its original design, particularly in its ability to identify multiple distinct keys, where distribution shift offers no assistance. Based on these findings and analysis, we present RingID for enhanced multi-key identification. It consists of a novel multi-channel heterogeneous watermarking approach designed to seamlessly amalgamate distinctive advantages from diverse watermarks. Coupled with a series of suggested enhancements, RingID exhibits substantial advancements in multi-key identification. Github Page: https://github.com/showlab/RingID
Authors: Robik Shrestha, Kushal Kafle, Christopher Kanan
Abstract: A critical problem in deep learning is that systems learn inappropriate biases, resulting in their inability to perform well on minority groups. This has led to the creation of multiple algorithms that endeavor to mitigate bias. However, it is not clear how effective these methods are. This is because study protocols differ among papers, systems are tested on datasets that fail to test many forms of bias, and systems have access to hidden knowledge or are tuned specifically to the test set. To address this, we introduce an improved evaluation protocol, sensible metrics, and a new dataset, which enables us to ask and answer critical questions about bias mitigation algorithms. We evaluate seven state-of-the-art algorithms using the same network architecture and hyperparameter selection policy across three benchmark datasets. We introduce a new dataset called Biased MNIST that enables assessment of robustness to multiple bias sources. We use Biased MNIST and a visual question answering (VQA) benchmark to assess robustness to hidden biases. Rather than only tuning to the test set distribution, we study robustness across different tuning distributions, which is critical because for many applications the test distribution may not be known during development. We find that algorithms exploit hidden biases, are unable to scale to multiple forms of bias, and are highly sensitive to the choice of tuning set. Based on our findings, we implore the community to adopt more rigorous assessment of future bias mitigation methods. All data, code, and results are publicly available at: https://github.com/erobic/bias-mitigators.
Authors: Chaoyue Ding, Kunchi Li, Jun Wan, Shan Yu
Abstract: Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data learning between the learned and new classes because of the limited storage memory. In this work, we present a simple but effective approach to tackle these two factors. First, we employ a re-sampling strategy and Mixup K}nowledge D}istillation (Re-MKD) to improve the performances of KD, which would greatly alleviate the overfitting problem. Specifically, we combine mixup and re-sampling strategies to synthesize adequate data used in KD training that are more consistent with the latent distribution between the learned and new classes. Second, we propose a novel incremental influence balance (IIB) method for CIL to tackle the classification of imbalanced data by extending the influence balance method into the CIL setting, which re-weights samples by their influences to create a proper decision boundary. With these two improvements, we present the effective decision boundary learning algorithm (EDBL) which improves the performance of KD and deals with the imbalanced data learning simultaneously. Experiments show that the proposed EDBL achieves state-of-the-art performances on several CIL benchmarks.
Authors: Shangyang Min, Hassan B. Ebadian, Tuka Alhanai, Mohammad Mahdi Ghassemi
Abstract: Feature-Imitating-Networks (FINs) are neural networks that are first trained to approximate closed-form statistical features (e.g. Entropy), and then embedded into other networks to enhance their performance. In this work, we perform the first evaluation of FINs for biomedical image processing tasks. We begin by training a set of FINs to imitate six common radiomics features, and then compare the performance of larger networks (with and without embedding the FINs) for three experimental tasks: COVID-19 detection from CT scans, brain tumor classification from MRI scans, and brain-tumor segmentation from MRI scans. We found that models embedded with FINs provided enhanced performance for all three tasks when compared to baseline networks without FINs, even when those baseline networks had more parameters. Additionally, we found that models embedded with FINs converged faster and more consistently compared to baseline networks with similar or greater representational capacity. The results of our experiments provide evidence that FINs may offer state-of-the-art performance for a variety of other biomedical image processing tasks.
Authors: Weijie Chen, Yuhang Wang, Lin Yao
Abstract: Due to the extremely low signal-to-noise ratio (SNR) and unknown poses (projection angles and image shifts) in cryo-electron microscopy (cryo-EM) experiments, reconstructing 3D volumes from 2D images is very challenging. In addition to these challenges, heterogeneous cryo-EM reconstruction requires conformational classification. In popular cryo-EM reconstruction algorithms, poses and conformation classification labels must be predicted for every input cryo-EM image, which can be computationally costly for large datasets. An emerging class of methods adopted the amortized inference approach. In these methods, only a subset of the input dataset is needed to train neural networks for the estimation of poses and conformations. Once trained, these neural networks can make pose/conformation predictions and 3D reconstructions at low cost for the entire dataset during inference. Unfortunately, when facing heterogeneous reconstruction tasks, it is hard for current amortized-inference-based methods to effectively estimate the conformational distribution and poses from entangled latent variables. Here, we propose a self-supervised variational autoencoder architecture called "HetACUMN" based on amortized inference. We employed an auxiliary conditional pose prediction task by inverting the order of encoder-decoder to explicitly enforce the disentanglement of conformation and pose predictions. Results on simulated datasets show that HetACUMN generated more accurate conformational classifications than other amortized or non-amortized methods. Furthermore, we show that HetACUMN is capable of performing heterogeneous 3D reconstructions of a real experimental dataset.
Authors: Eleonora Lopez, Filippo Betello, Federico Carmignani, Eleonora Grassucci, Danilo Comminiello
Abstract: Breast cancer is the most widespread neoplasm among women and early detection of this disease is critical. Deep learning techniques have become of great interest to improve diagnostic performance. However, distinguishing between malignant and benign masses in whole mammograms poses a challenge, as they appear nearly identical to an untrained eye, and the region of interest (ROI) constitutes only a small fraction of the entire image. In this paper, we propose a framework, parameterized hypercomplex attention maps (PHAM), to overcome these problems. Specifically, we deploy an augmentation step based on computing attention maps. Then, the attention maps are used to condition the classification step by constructing a multi-dimensional input comprised of the original breast cancer image and the corresponding attention map. In this step, a parameterized hypercomplex neural network (PHNN) is employed to perform breast cancer classification. The framework offers two main advantages. First, attention maps provide critical information regarding the ROI and allow the neural model to concentrate on it. Second, the hypercomplex architecture has the ability to model local relations between input dimensions thanks to hypercomplex algebra rules, thus properly exploiting the information provided by the attention map. We demonstrate the efficacy of the proposed framework on both mammography images as well as histopathological ones. We surpass attention-based state-of-the-art networks and the real-valued counterpart of our approach. The code of our work is available at https://github.com/ispamm/AttentionBCS.
Authors: Adrian Celaya, Keegan Kirk, David Fuentes, Beatrice Riviere
Abstract: In recent years, there has been a growing interest in leveraging deep learning and neural networks to address scientific problems, particularly in solving partial differential equations (PDEs). However, many neural network-based methods like PINNs rely on auto differentiation and sampling collocation points, leading to a lack of interpretability and lower accuracy than traditional numerical methods. As a result, we propose a fully unsupervised approach, requiring no training data, to estimate finite difference solutions for PDEs directly via small linear convolutional neural networks. Our proposed approach uses substantially fewer parameters than similar finite difference-based approaches while also demonstrating comparable accuracy to the true solution for several selected elliptic and parabolic problems compared to the finite difference method.
Authors: Da-Wei Zhou, Hai-Long Sun, Jingyi Ning, Han-Jia Ye, De-Chuan Zhan
Abstract: Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of former knowledge when learning new ones. Typical CL methods build the model from scratch to grow with incoming data. However, the advent of the pre-trained model (PTM) era has sparked immense research interest, particularly in leveraging PTMs' robust representational capabilities. This paper presents a comprehensive survey of the latest advancements in PTM-based CL. We categorize existing methodologies into three distinct groups, providing a comparative analysis of their similarities, differences, and respective advantages and disadvantages. Additionally, we offer an empirical study contrasting various state-of-the-art methods to highlight concerns regarding fairness in comparisons. The source code to reproduce these evaluations is available at: https://github.com/sun-hailong/LAMDA-PILOT
Authors: Kangle Deng, Timothy Omernick, Alexander Weiss, Deva Ramanan, Jun-Yan Zhu, Tinghui Zhou, Maneesh Agrawala
Abstract: Manually creating textures for 3D meshes is time-consuming, even for expert visual content creators. We propose a fast approach for automatically texturing an input 3D mesh based on a user-provided text prompt. Importantly, our approach disentangles lighting from surface material/reflectance in the resulting texture so that the mesh can be properly relit and rendered in any lighting environment. We introduce LightControlNet, a new text-to-image model based on the ControlNet architecture, which allows the specification of the desired lighting as a conditioning image to the model. Our text-to-texture pipeline then constructs the texture in two stages. The first stage produces a sparse set of visually consistent reference views of the mesh using LightControlNet. The second stage applies a texture optimization based on Score Distillation Sampling (SDS) that works with LightControlNet to increase the texture quality while disentangling surface material from lighting. Our algorithm is significantly faster than previous text-to-texture methods, while producing high-quality and relightable textures.
Authors: Qinglong Meng, Chongkun Xia, Xueqian Wang
Abstract: Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution and the data distribution, flow-based models might perform badly. 2) Discrete data might make flow-based models collapse into a degenerate mixture of point masses. To sidestep such two issues, we propose PaddingFlow, a novel dequantization method, which improves normalizing flows with padding-dimensional noise. To implement PaddingFlow, only the dimension of normalizing flows needs to be modified. Thus, our method is easy to implement and computationally cheap. Moreover, the padding-dimensional noise is only added to the padding dimension, which means PaddingFlow can dequantize without changing data distributions. Implementing existing dequantization methods needs to change data distributions, which might degrade performance. We validate our method on the main benchmarks of unconditional density estimation, including five tabular datasets and four image datasets for Variational Autoencoder (VAE) models, and the Inverse Kinematics (IK) experiments which are conditional density estimation. The results show that PaddingFlow can perform better in all experiments in this paper, which means PaddingFlow is widely suitable for various tasks. The code is available at: https://github.com/AdamQLMeng/PaddingFlow.
Authors: Yifei Wang, Qi Zhang, Yaoyu Guo, Yisen Wang
Abstract: Deep representations have shown promising performance when transferred to downstream tasks in a black-box manner. Yet, their inherent lack of interpretability remains a significant challenge, as these features are often opaque to human understanding. In this paper, we propose Non-negative Contrastive Learning (NCL), a renaissance of Non-negative Matrix Factorization (NMF) aimed at deriving interpretable features. The power of NCL lies in its enforcement of non-negativity constraints on features, reminiscent of NMF's capability to extract features that align closely with sample clusters. NCL not only aligns mathematically well with an NMF objective but also preserves NMF's interpretability attributes, resulting in a more sparse and disentangled representation compared to standard contrastive learning (CL). Theoretically, we establish guarantees on the identifiability and downstream generalization of NCL. Empirically, we show that these advantages enable NCL to outperform CL significantly on feature disentanglement, feature selection, as well as downstream classification tasks. At last, we show that NCL can be easily extended to other learning scenarios and benefit supervised learning as well. Code is available at https://github.com/PKU-ML/non_neg.
Authors: Yuwei Sun, Ippei Fujisawa, Arthur Juliani, Jun Sakuma, Ryota Kanai
Abstract: Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task knowledge interferes with previously learned knowledge. We propose Remembering Transformer, inspired by the brain's Complementary Learning Systems (CLS), to tackle this issue. Remembering Transformer employs a mixture-of-adapters and a generative model-based routing mechanism to alleviate CF by dynamically routing task data to relevant adapters. Our approach demonstrated a new SOTA performance in various vision continual learning tasks and great parameter efficiency.
Authors: Yong Liu, Mengtian Kang, Shuo Gao, Chi Zhang, Ying Liu, Shiming Li, Yue Qi, Arokia Nathan, Wenjun Xu, Chenyu Tang, Edoardo Occhipinti, Mayinuer Yusufu, Ningli Wang, Weiling Bai, Luigi Occhipinti
Abstract: Fundus diseases are major causes of visual impairment and blindness worldwide, especially in underdeveloped regions, where the shortage of ophthalmologists hinders timely diagnosis. AI-assisted fundus image analysis has several advantages, such as high accuracy, reduced workload, and improved accessibility, but it requires a large amount of expert-annotated data to build reliable models. To address this dilemma, we propose a general self-supervised machine learning framework that can handle diverse fundus diseases from unlabeled fundus images. Our method's AUC surpasses existing supervised approaches by 15.7%, and even exceeds performance of a single human expert. Furthermore, our model adapts well to various datasets from different regions, races, and heterogeneous image sources or qualities from multiple cameras or devices. Our method offers a label-free general framework to diagnose fundus diseases, which could potentially benefit telehealth programs for early screening of people at risk of vision loss.