Authors: Ghazal Alinezhad Noghre, Armin Danesh Pazho, Hamed Tabkhi
Abstract: Video Anomaly Detection (VAD) represents a challenging and prominent research task within computer vision. In recent years, Pose-based Video Anomaly Detection (PAD) has drawn considerable attention from the research community due to several inherent advantages over pixel-based approaches despite the occasional suboptimal performance. Specifically, PAD is characterized by reduced computational complexity, intrinsic privacy preservation, and the mitigation of concerns related to discrimination and bias against specific demographic groups. This paper introduces TSGAD, a novel human-centric Two-Stream Graph-Improved Anomaly Detection leveraging Variational Autoencoders (VAEs) and trajectory prediction. TSGAD aims to explore the possibility of utilizing VAEs as a new approach for pose-based human-centric VAD alongside the benefits of trajectory prediction. We demonstrate TSGAD's effectiveness through comprehensive experimentation on benchmark datasets. TSGAD demonstrates comparable results with state-of-the-art methods showcasing the potential of adopting variational autoencoders. This suggests a promising direction for future research endeavors. The code base for this work is available at https://github.com/TeCSAR-UNCC/TSGAD.
Authors: Jerry Chun-Wei Lin, Pi-Wei Chen, Chao-Chun Chen
Abstract: Reconstruction networks are prevalently used in unsupervised anomaly and Out-of-Distribution (OOD) detection due to their independence from labeled anomaly data. However, in multi-class datasets, the effectiveness of anomaly detection is often compromised by the models' generalized reconstruction capabilities, which allow anomalies to blend within the expanded boundaries of normality resulting from the added categories, thereby reducing detection accuracy. We introduce the FUTUREG framework, which incorporates two innovative modules: the Feature Purification Module (FPM) and the CFG Decoder. The FPM constrains the normality boundary within the latent space to effectively filter out anomalous features, while the CFG Decoder uses layer-wise encoder representations to guide the reconstruction of filtered features, preserving fine-grained details. Together, these modules enhance the reconstruction error for anomalies, ensuring high-quality reconstructions for normal samples. Our results demonstrate that FUTUREG achieves state-of-the-art performance in multi-class OOD settings and remains competitive in industrial anomaly detection scenarios.
Authors: Areg Karapetyan, Aaron Chung Hin Chow, Samer Madanat
Abstract: In light of growing threats posed by climate change in general and sea level rise (SLR) in particular, the necessity for computationally efficient means to estimate and analyze potential coastal flood hazards has become increasingly pressing. Data-driven supervised learning methods serve as promising candidates that can dramatically expedite the process, thereby eliminating the computational bottleneck associated with traditional physics-based hydrodynamic simulators. Yet, the development of accurate and reliable coastal flood prediction models, especially those based on Deep Learning (DL) techniques, has been plagued with two major issues: (1) the scarcity of training data and (2) the high-dimensional output required for detailed inundation mapping. To remove this barrier, we present a systematic framework for training high-fidelity Deep Vision-based coastal flood prediction models in low-data settings. We test the proposed workflow on different existing vision models, including a fully transformer-based architecture and a Convolutional Neural Network (CNN) with additive attention gates. Additionally, we introduce a deep CNN architecture tailored specifically to the coastal flood prediction problem at hand. The model was designed with a particular focus on its compactness so as to cater to resource-constrained scenarios and accessibility aspects. The performance of the developed DL models is validated against commonly adopted geostatistical regression methods and traditional Machine Learning (ML) approaches, demonstrating substantial improvement in prediction quality. Lastly, we round up the contributions by providing a meticulously curated dataset of synthetic flood inundation maps of Abu Dhabi's coast produced with a physics-based hydrodynamic simulator, which can serve as a benchmark for evaluating future coastal flood prediction models.
Authors: Akshita Gupta, Aditya Arora, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Graham W. Taylor
Abstract: Open-Vocabulary Temporal Action Localization (OVTAL) enables a model to recognize any desired action category in videos without the need to explicitly curate training data for all categories. However, this flexibility poses significant challenges, as the model must recognize not only the action categories seen during training but also novel categories specified at inference. Unlike standard temporal action localization, where training and test categories are predetermined, OVTAL requires understanding contextual cues that reveal the semantics of novel categories. To address these challenges, we introduce OVFormer, a novel open-vocabulary framework extending ActionFormer with three key contributions. First, we employ task-specific prompts as input to a large language model to obtain rich class-specific descriptions for action categories. Second, we introduce a cross-attention mechanism to learn the alignment between class representations and frame-level video features, facilitating the multimodal guided features. Third, we propose a two-stage training strategy which includes training with a larger vocabulary dataset and finetuning to downstream data to generalize to novel categories. OVFormer extends existing TAL methods to open-vocabulary settings. Comprehensive evaluations on the THUMOS14 and ActivityNet-1.3 benchmarks demonstrate the effectiveness of our method. Code and pretrained models will be publicly released.
Authors: Paridhi Singh, Arun Kumar
Abstract: This paper introduces an innovative approach to open world recognition (OWR), where we leverage knowledge acquired from known objects to address the recognition of previously unseen objects. The traditional method of object modeling relies on supervised learning with strict closed-set assumptions, presupposing that objects encountered during inference are already known at the training phase. However, this assumption proves inadequate for real-world scenarios due to the impracticality of accounting for the immense diversity of objects. Our hypothesis posits that object appearances can be represented as collections of "shareable" mid-level features, arranged in constellations to form object instances. By adopting this framework, we can efficiently dissect and represent both known and unknown objects in terms of their appearance cues. Our paper introduces a straightforward yet elegant method for modeling novel or unseen objects, utilizing established appearance cues and accounting for inherent uncertainties. This representation not only enables the detection of out-of-distribution objects or novel categories among unseen objects but also facilitates a deeper level of reasoning, empowering the identification of the superclass to which an unknown instance belongs. This novel approach holds promise for advancing open world recognition in diverse applications.
Authors: Saswat Subhajyoti Mallick, Rahul Goel, Bernhard Kerbl, Francisco Vicente Carrasco, Markus Steinberger, Fernando De La Torre
Abstract: 3D Gaussian Splatting (3DGS) has transformed novel-view synthesis with its fast, interpretable, and high-fidelity rendering. However, its resource requirements limit its usability. Especially on constrained devices, training performance degrades quickly and often cannot complete due to excessive memory consumption of the model. The method converges with an indefinite number of Gaussians -- many of them redundant -- making rendering unnecessarily slow and preventing its usage in downstream tasks that expect fixed-size inputs. To address these issues, we tackle the challenges of training and rendering 3DGS models on a budget. We use a guided, purely constructive densification process that steers densification toward Gaussians that raise the reconstruction quality. Model size continuously increases in a controlled manner towards an exact budget, using score-based densification of Gaussians with training-time priors that measure their contribution. We further address training speed obstacles: following a careful analysis of 3DGS' original pipeline, we derive faster, numerically equivalent solutions for gradient computation and attribute updates, including an alternative parallelization for efficient backpropagation. We also propose quality-preserving approximations where suitable to reduce training time even further. Taken together, these enhancements yield a robust, scalable solution with reduced training times, lower compute and memory requirements, and high quality. Our evaluation shows that in a budgeted setting, we obtain competitive quality metrics with 3DGS while achieving a 4--5x reduction in both model size and training time. With more generous budgets, our measured quality surpasses theirs. These advances open the door for novel-view synthesis in constrained environments, e.g., mobile devices.
Authors: Sandeep Singh Sengar, Aswin Kumar, Owen Singh
Abstract: This study presents a novel driver drowsiness detection system that combines deep learning techniques with the OpenCV framework. The system utilises facial landmarks extracted from the driver's face as input to Convolutional Neural Networks trained to recognise drowsiness patterns. The integration of OpenCV enables real-time video processing, making the system suitable for practical implementation. Extensive experiments on a diverse dataset demonstrate high accuracy, sensitivity, and specificity in detecting drowsiness. The proposed system has the potential to enhance road safety by providing timely alerts to prevent accidents caused by driver fatigue. This research contributes to advancing real-time driver monitoring systems and has implications for automotive safety and intelligent transportation systems. The successful application of deep learning techniques in this context opens up new avenues for future research in driver monitoring and vehicle safety. The implementation code for the paper is available at https://github.com/LUFFY7001/Driver-s-Drowsiness-Detection.
URLs: https://github.com/LUFFY7001/Driver-s-Drowsiness-Detection.
Authors: Sandeep Singh Sengar, Abhishek Kumar, Owen Singh
Abstract: This study presents significant enhancements in human pose estimation using the MediaPipe framework. The research focuses on improving accuracy, computational efficiency, and real-time processing capabilities by comprehensively optimising the underlying algorithms. Novel modifications are introduced that substantially enhance pose estimation accuracy across challenging scenarios, such as dynamic movements and partial occlusions. The improved framework is benchmarked against traditional models, demonstrating considerable precision and computational speed gains. The advancements have wide-ranging applications in augmented reality, sports analytics, and healthcare, enabling more immersive experiences, refined performance analysis, and advanced patient monitoring. The study also explores the integration of these enhancements within mobile and embedded systems, addressing the need for computational efficiency and broader accessibility. The implications of this research set a new benchmark for real-time human pose estimation technologies and pave the way for future innovations in the field. The implementation code for the paper is available at https://github.com/avhixd/Human_pose_estimation.
Authors: Nemin Wu, Qian Cao, Zhangyu Wang, Zeping Liu, Yanlin Qi, Jielu Zhang, Joshua Ni, Xiaobai Yao, Hongxu Ma, Lan Mu, Stefano Ermon, Tanuja Ganu, Akshay Nambi, Ni Lao, Gengchen Mai
Abstract: Spatial representation learning (SRL) aims at learning general-purpose neural network representations from various types of spatial data (e.g., points, polylines, polygons, networks, images, etc.) in their native formats. Learning good spatial representations is a fundamental problem for various downstream applications such as species distribution modeling, weather forecasting, trajectory generation, geographic question answering, etc. Even though SRL has become the foundation of almost all geospatial artificial intelligence (GeoAI) research, we have not yet seen significant efforts to develop an extensive deep learning framework and benchmark to support SRL model development and evaluation. To fill this gap, we propose TorchSpatial, a learning framework and benchmark for location (point) encoding, which is one of the most fundamental data types of spatial representation learning. TorchSpatial contains three key components: 1) a unified location encoding framework that consolidates 15 commonly recognized location encoders, ensuring scalability and reproducibility of the implementations; 2) the LocBench benchmark tasks encompassing 7 geo-aware image classification and 4 geo-aware image regression datasets; 3) a comprehensive suite of evaluation metrics to quantify geo-aware models' overall performance as well as their geographic bias, with a novel Geo-Bias Score metric. Finally, we provide a detailed analysis and insights into the model performance and geographic bias of different location encoders. We believe TorchSpatial will foster future advancement of spatial representation learning and spatial fairness in GeoAI research. The TorchSpatial model framework, LocBench, and Geo-Bias Score evaluation framework are available at https://github.com/seai-lab/TorchSpatial.
Authors: Bronson Brown-deVost, Berat Kurar-Barakat, Nachum Dershowitz
Abstract: This paper presents a customized pipeline for segmenting manuscript fragments from images curated by the Israel Antiquities Authority (IAA). The images present challenges for standard segmentation methods due to the presence of the ruler, color, and plate number bars, as well as a black background that resembles the ink and varying backing substrates. The proposed pipeline, consisting of four steps, addresses these challenges by isolating and solving each difficulty using custom tailored methods. Further, the usage of a multi-step pipeline will surely be helpful from a conceptual standpoint for other image segmentation projects that encounter problems that have proven intractable when applying any of the more commonly used segmentation techniques. In addition, we create a dataset with bar detection and fragment segmentation ground truth and evaluate the pipeline steps qualitatively and quantitatively on it. This dataset is publicly available to support the development of the field. It aims to address the lack of standard sets of fragment images and evaluation metrics and enable researchers to evaluate their methods in a reliable and reproducible manner.
Authors: Zhuo Zheng, Yanfei Zhong, Ailong Ma, Liangpei Zhang
Abstract: Bitemporal supervised learning paradigm always dominates remote sensing change detection using numerous labeled bitemporal image pairs, especially for high spatial resolution (HSR) remote sensing imagery. However, it is very expensive and labor-intensive to label change regions in large-scale bitemporal HSR remote sensing image pairs. In this paper, we propose single-temporal supervised learning (STAR) for universal remote sensing change detection from a new perspective of exploiting changes between unpaired images as supervisory signals. STAR enables us to train a high-accuracy change detector only using unpaired labeled images and can generalize to real-world bitemporal image pairs. To demonstrate the flexibility and scalability of STAR, we design a simple yet unified change detector, termed ChangeStar2, capable of addressing binary change detection, object change detection, and semantic change detection in one architecture. ChangeStar2 achieves state-of-the-art performances on eight public remote sensing change detection datasets, covering above two supervised settings, multiple change types, multiple scenarios. The code is available at https://github.com/Z-Zheng/pytorch-change-models.
Authors: Haofeng Li, Yiming Ouyang, Xiang Wan
Abstract: Recently, self-supervised learning (SSL) methods have been used in pre-training the segmentation models for 2D and 3D medical images. Most of these methods are based on reconstruction, contrastive learning and consistency regularization. However, the spatial correspondence of 2D slices from a 3D medical image has not been fully exploited. In this paper, we propose a novel self-supervised alignment learning framework to pre-train the neural network for medical image segmentation. The proposed framework consists of a new local alignment loss and a global positional loss. We observe that in the same 3D scan, two close 2D slices usually contain similar anatomic structures. Thus, the local alignment loss is proposed to make the pixel-level features of matched structures close to each other. Experimental results show that the proposed alignment learning is competitive with existing self-supervised pre-training approaches on CT and MRI datasets, under the setting of limited annotations.
Authors: Guangzhi Sun, Wenyi Yu, Changli Tang, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, Yuxuan Wang, Chao Zhang
Abstract: Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end av-LLM for video processing, which can understand not only visual frame sequences, audio events and music, but speech as well. To obtain fine-grained temporal information required by speech understanding, while keeping efficient for other video elements, this paper proposes a novel multi-resolution causal Q-Former (MRC Q-Former) structure to connect pre-trained audio-visual encoders and the backbone large language model. Moreover, dedicated training approaches including the diversity loss and the unpaired audio-visual mixed training scheme are proposed to avoid frames or modality dominance. On the introduced speech-audio-visual evaluation benchmark, video-SALMONN achieves more than 25\% absolute accuracy improvements on the video-QA task and over 30\% absolute accuracy improvements on audio-visual QA tasks with human speech. In addition, video-SALMONN demonstrates remarkable video comprehension and reasoning abilities on tasks that are unprecedented by other av-LLMs. Our training code and model checkpoints are available at \texttt{\url{https://github.com/bytedance/SALMONN/}}.
Authors: Tongtong Zhang, Yuanxiang Li
Abstract: Most current NeRF variants for satellites are designed for one specific scene and fall short of generalization to new geometry. Additionally, the RGB images require pan-sharpening as an independent preprocessing step. This paper introduces psPRF, a Planar Neural Radiance Field designed for paired low-resolution RGB (LR-RGB) and high-resolution panchromatic (HR-PAN) images from satellite sensors with Rational Polynomial Cameras (RPC). To capture the cross-modal prior from both of the LR-RGB and HR-PAN images, for the Unet-shaped architecture, we adapt the encoder with explicit spectral-to-spatial convolution (SSConv) to enhance the multimodal representation ability. To support the generalization ability of psRPF across scenes, we adopt projection loss to ensure strong geometry self-supervision. The proposed method is evaluated with the multi-scene WorldView-3 LR-RGB and HR-PAN pairs, and achieves state-of-the-art performance.
Authors: Ali Jamali, Swalpa Kumar Roy, Danfeng Hong, Bing Lu, Pedram Ghamisi
Abstract: Convolutional Neural Networks (CNNs) and vision transformers (ViTs) have shown excellent capability in complex hyperspectral image (HSI) classification. However, these models require a significant number of training data and are computational resources. On the other hand, modern Multi-Layer Perceptrons (MLPs) have demonstrated great classification capability. These modern MLP-based models require significantly less training data compared to CNNs and ViTs, achieving the state-of-the-art classification accuracy. Recently, Kolmogorov-Arnold Networks (KANs) were proposed as viable alternatives for MLPs. Because of their internal similarity to splines and their external similarity to MLPs, KANs are able to optimize learned features with remarkable accuracy in addition to being able to learn new features. Thus, in this study, we assess the effectiveness of KANs for complex HSI data classification. Moreover, to enhance the HSI classification accuracy obtained by the KANs, we develop and propose a Hybrid architecture utilizing 1D, 2D, and 3D KANs. To demonstrate the effectiveness of the proposed KAN architecture, we conducted extensive experiments on three newly created HSI benchmark datasets: QUH-Pingan, QUH-Tangdaowan, and QUH-Qingyun. The results underscored the competitive or better capability of the developed hybrid KAN-based model across these benchmark datasets over several other CNN- and ViT-based algorithms, including 1D-CNN, 2DCNN, 3D CNN, VGG-16, ResNet-50, EfficientNet, RNN, and ViT. The code are publicly available at (https://github.com/aj1365/HSIConvKAN)
Authors: Min Zhao, Hongzhou Zhu, Chendong Xiang, Kaiwen Zheng, Chongxuan Li, Jun Zhu
Abstract: Diffusion models have obtained substantial progress in image-to-video (I2V) generation. However, such models are not fully understood. In this paper, we report a significant but previously overlooked issue in I2V diffusion models (I2V-DMs), namely, conditional image leakage. I2V-DMs tend to over-rely on the conditional image at large time steps, neglecting the crucial task of predicting the clean video from noisy inputs, which results in videos lacking dynamic and vivid motion. We further address this challenge from both inference and training aspects by presenting plug-and-play strategies accordingly. First, we introduce a training-free inference strategy that starts the generation process from an earlier time step to avoid the unreliable late-time steps of I2V-DMs, as well as an initial noise distribution with optimal analytic expressions (Analytic-Init) by minimizing the KL divergence between it and the actual marginal distribution to effectively bridge the training-inference gap. Second, to mitigate conditional image leakage during training, we design a time-dependent noise distribution for the conditional image, which favors high noise levels at large time steps to sufficiently interfere with the conditional image. We validate these strategies on various I2V-DMs using our collected open-domain image benchmark and the UCF101 dataset. Extensive results demonstrate that our methods outperform baselines by producing videos with more dynamic and natural motion without compromising image alignment and temporal consistency. The project page: \url{https://cond-image-leak.github.io/}.
Authors: Rishi Jain, Bohan Yu, Peter Wu, Tejas Prabhune, Gopala Anumanchipalli
Abstract: Accurate modeling of the vocal tract is necessary to construct articulatory representations for interpretable speech processing and linguistics. However, vocal tract modeling is challenging because many internal articulators are occluded from external motion capture technologies. Real-time magnetic resonance imaging (RT-MRI) allows measuring precise movements of internal articulators during speech, but annotated datasets of MRI are limited in size due to time-consuming and computationally expensive labeling methods. We first present a deep labeling strategy for the RT-MRI video using a vision-only segmentation approach. We then introduce a multimodal algorithm using audio to improve segmentation of vocal articulators. Together, we set a new benchmark for vocal tract modeling in MRI video segmentation and use this to release labels for a 75-speaker RT-MRI dataset, increasing the amount of labeled public RT-MRI data of the vocal tract by over a factor of 9. The code and dataset labels can be found at \url{rishiraij.github.io/multimodal-mri-avatar/}.
Authors: Xu Yin, Woobin Im, Dongbo Min, Yuchi Huo, Fei Pan, Sung-Eui Yoon
Abstract: Generating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information. Prevalent class activation map (CAM)-based solutions are challenged to discriminate the foreground (FG) objects from the suspicious background (BG) pixels (a.k.a. co-occurring) and learn the integral object regions. This paper proposes a simple fine-grained background representation (FBR) method to discover and represent diverse BG semantics and address the co-occurring problems. We abandon using the class prototype or pixel-level features for BG representation. Instead, we develop a novel primitive, negative region of interest (NROI), to capture the fine-grained BG semantic information and conduct the pixel-to-NROI contrast to distinguish the confusing BG pixels. We also present an active sampling strategy to mine the FG negatives on-the-fly, enabling efficient pixel-to-pixel intra-foreground contrastive learning to activate the entire object region. Thanks to the simplicity of design and convenience in use, our proposed method can be seamlessly plugged into various models, yielding new state-of-the-art results under various WSSS settings across benchmarks. Leveraging solely image-level (I) labels as supervision, our method achieves 73.2 mIoU and 45.6 mIoU segmentation results on Pascal Voc and MS COCO test sets, respectively. Furthermore, by incorporating saliency maps as an additional supervision signal (I+S), we attain 74.9 mIoU on Pascal Voc test set. Concurrently, our FBR approach demonstrates meaningful performance gains in weakly-supervised instance segmentation (WSIS) tasks, showcasing its robustness and strong generalization capabilities across diverse domains.
Authors: Wenxue Li, Xinyu Xiong, Peng Xia, Lie Ju, Zongyuan Ge
Abstract: Recent advances in large foundation models, such as the Segment Anything Model (SAM), have demonstrated considerable promise across various tasks. Despite their progress, these models still encounter challenges in specialized medical image analysis, especially in recognizing subtle inter-class differences in Diabetic Retinopathy (DR) lesion segmentation. In this paper, we propose a novel framework that customizes SAM for text-prompted DR lesion segmentation, termed TP-DRSeg. Our core idea involves exploiting language cues to inject medical prior knowledge into the vision-only segmentation network, thereby combining the advantages of different foundation models and enhancing the credibility of segmentation. Specifically, to unleash the potential of vision-language models in the recognition of medical concepts, we propose an explicit prior encoder that transfers implicit medical concepts into explicit prior knowledge, providing explainable clues to excavate low-level features associated with lesions. Furthermore, we design a prior-aligned injector to inject explicit priors into the segmentation process, which can facilitate knowledge sharing across multi-modality features and allow our framework to be trained in a parameter-efficient fashion. Experimental results demonstrate the superiority of our framework over other traditional models and foundation model variants.
Authors: Guanqun Wang, Xinyu Wei, Jiaming Liu, Ray Zhang, Yichi Zhang, Kevin Zhang, Maurice Chong, Shanghang Zhang
Abstract: In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception tasks, such as detection and segmentation. However, MLLMs mainly focus on high-level image-text interpretations and struggle with fine-grained visual understanding, and vision perception models usually suffer from open-world distribution shifts due to their limited model capacity. To overcome these challenges, we propose the Mutually Reinforced Multimodal Large Language Model (MR-MLLM), a novel framework that synergistically enhances visual perception and multimodal comprehension. First, a shared query fusion mechanism is proposed to harmonize detailed visual inputs from vision models with the linguistic depth of language models, enhancing multimodal comprehension and vision perception synergistically. Second, we propose the perception-enhanced cross-modal integration method, incorporating novel modalities from vision perception outputs, like object detection bounding boxes, to capture subtle visual elements, thus enriching the understanding of both visual and textual data. In addition, an innovative perception-embedded prompt generation mechanism is proposed to embed perceptual information into the language model's prompts, aligning the responses contextually and perceptually for a more accurate multimodal interpretation. Extensive experiments demonstrate MR-MLLM's superior performance in various multimodal comprehension and vision perception tasks, particularly those requiring corner case vision perception and fine-grained language comprehension.
Authors: Haoyu Zhang, Yuquan Xie, Yisen Feng, Zaijing Li, Meng Liu, Liqiang Nie
Abstract: In this report, we present our champion solution for Ego4D EgoSchema Challenge in CVPR 2024. To deeply integrate the powerful egocentric captioning model and question reasoning model, we propose a novel Hierarchical Comprehension scheme for egocentric video Question Answering, named HCQA. It consists of three stages: Fine-grained Caption Generation, Context-driven Summarization, and Inference-guided Answering. Given a long-form video, HCQA captures local detailed visual information and global summarised visual information via Fine-grained Caption Generation and Context-driven Summarization, respectively. Then in Inference-guided Answering, HCQA utilizes this hierarchical information to reason and answer given question. On the EgoSchema blind test set, HCQA achieves 75% accuracy in answering over 5,000 human curated multiple-choice questions. Our code will be released at https://github.com/Hyu-Zhang/HCQA.
Authors: Yisen Feng, Haoyu Zhang, Yuquan Xie, Zaijing Li, Meng Liu, Liqiang Nie
Abstract: In this report, we present our approach for the Natural Language Query track and Goal Step track of the Ego4D Episodic Memory Benchmark at CVPR 2024. Both challenges require the localization of actions within long video sequences using textual queries. To enhance localization accuracy, our method not only processes the temporal information of videos but also identifies fine-grained objects spatially within the frames. To this end, we introduce a novel approach, termed ObjectNLQ, which incorporates an object branch to augment the video representation with detailed object information, thereby improving grounding efficiency. ObjectNLQ achieves a mean R@1 of 23.15, ranking 2nd in the Natural Language Queries Challenge, and gains 33.00 in terms of the metric R@1, IoU=0.3, ranking 3rd in the Goal Step Challenge. Our code will be released at https://github.com/Yisen-Feng/ObjectNLQ.
Authors: Zhaoxin Hu, Keyan Ren
Abstract: Lack of shape guidance and label jitter caused by information deficiency of weak label are the main problems in 3D weakly-supervised object detection. Current weakly-supervised models often use heuristics or assumptions methods to infer information from weak labels without taking advantage of the inherent clues of weakly-supervised and fully-supervised methods, thus it is difficult to explore a method that combines data utilization efficiency and model accuracy. In an attempt to address these issues, we propose a novel plug-and-in point cloud feature representation network called Multi-scale Mixed Attention (MMA). MMA utilizes adjacency attention within neighborhoods and disparity attention at different density scales to build a feature representation network. The smart feature representation obtained from MMA has shape tendency and object existence area inference, which can constrain the region of the detection boxes, thereby alleviating the problems caused by the information default of weak labels. Extensive experiments show that in indoor weak label scenarios, the fully-supervised network can perform close to that of the weakly-supervised network merely through the improvement of point feature by MMA. At the same time, MMA can turn waste into treasure, reversing the label jitter problem that originally interfered with weakly-supervised detection into the source of data enhancement, strengthening the performance of existing weak supervision detection methods. Our code is available at https://github.com/hzx-9894/MMA.
Authors: Qiao Yu, Xianzhi Li, Yuan Tang, Jinfeng Xu, Long Hu, Yixue Hao, Min Chen
Abstract: Reconstructing textured meshes from colored point clouds is an important but challenging task in 3D graphics and vision. Most existing methods predict colors as implicit functions in 3D or UV space, suffering from blurry textures or the lack of generalization capability. Addressing this, we propose PointDreamer, a novel framework for textured mesh reconstruction from colored point cloud. It produces meshes with enhanced fidelity and clarity by 2D image inpainting, taking advantage of the mature techniques and massive data of 2D vision. Specifically, we first project the input point cloud into 2D space to generate sparse multi-view images, and then inpaint empty pixels utilizing a pre-trained 2D diffusion model. Next, we design a novel Non-Border-First strategy to unproject the colors of the inpainted dense images back to 3D space, thus obtaining the final textured mesh. In this way, our PointDreamer works in a zero-shot manner, requiring no extra training. Extensive qualitative and quantitative experiments on various synthetic and real-scanned datasets show the SoTA performance of PointDreamer, by significantly outperforming baseline methods with 30\% improvement in LPIPS score (from 0.118 to 0.068). Code at: https://github.com/YuQiao0303/PointDreamer.
Authors: Honori Udo, Takafumi Koshinaka
Abstract: We revisit language bottleneck models as an approach to ensuring the explainability of deep learning models for image classification. Because of inevitable information loss incurred in the step of converting images into language, the accuracy of language bottleneck models is considered to be inferior to that of standard black-box models. Recent image captioners based on large-scale foundation models of Vision and Language, however, have the ability to accurately describe images in verbal detail to a degree that was previously believed to not be realistically possible. In a task of disaster image classification, we experimentally show that a language bottleneck model that combines a modern image captioner with a pre-trained language model can achieve image classification accuracy that exceeds that of black-box models. We also demonstrate that a language bottleneck model and a black-box model may be thought to extract different features from images and that fusing the two can create a synergistic effect, resulting in even higher classification accuracy.
Authors: Wei Wang, Yaosen Chen, Yuegen Liu, Qi Yuan, Shubin Yang, Yanru Zhang
Abstract: Video composition is the core task of video editing. Although image composition based on diffusion models has been highly successful, it is not straightforward to extend the achievement to video object composition tasks, which not only exhibit corresponding interaction effects but also ensure that the objects in the composited video maintain motion and identity consistency, which is necessary to composite a physical harmony video. To address this challenge, we propose a Multiple Video Object Composition (MVOC) method based on diffusion models. Specifically, we first perform DDIM inversion on each video object to obtain the corresponding noise features. Secondly, we combine and edit each object by image editing methods to obtain the first frame of the composited video. Finally, we use the image-to-video generation model to composite the video with feature and attention injections in the Video Object Dependence Module, which is a training-free conditional guidance operation for video generation, and enables the coordination of features and attention maps between various objects that can be non-independent in the composited video. The final generative model not only constrains the objects in the generated video to be consistent with the original object motion and identity, but also introduces interaction effects between objects. Extensive experiments have demonstrated that the proposed method outperforms existing state-of-the-art approaches. Project page: https://sobeymil.github.io/mvoc.com.
Authors: Muhammad Saif Ullah Khan, Muhammad Zeshan Afzal, Didier Stricker
Abstract: Reconstructing texture-less surfaces poses unique challenges in computer vision, primarily due to the lack of specialized datasets that cater to the nuanced needs of depth and normals estimation in the absence of textural information. We introduce "Shape2.5D," a novel, large-scale dataset designed to address this gap. Comprising 364k frames spanning 2635 3D models and 48 unique objects, our dataset provides depth and surface normal maps for texture-less object reconstruction. The proposed dataset includes synthetic images rendered with 3D modeling software to simulate various lighting conditions and viewing angles. It also includes a real-world subset comprising 4672 frames captured with a depth camera. Our comprehensive benchmarks, performed using a modified encoder-decoder network, showcase the dataset's capability to support the development of algorithms that robustly estimate depth and normals from RGB images. Our open-source data generation pipeline allows the dataset to be extended and adapted for future research. The dataset is publicly available at \url{https://github.com/saifkhichi96/Shape25D}.
Authors: Shiqi Gao, Huiyu Duan, Xinyue Li, Kang Fu, Yicong Peng, Qihang Xu, Yuanyuan Chang, Jia Wang, Xiongkuo Min, Guangtao Zhai
Abstract: In recent years, learning-based color and tone enhancement methods for photos have become increasingly popular. However, most learning-based image enhancement methods just learn a mapping from one distribution to another based on one dataset, lacking the ability to adjust images continuously and controllably. It is important to enable the learning-based enhancement models to adjust an image continuously, since in many cases we may want to get a slighter or stronger enhancement effect rather than one fixed adjusted result. In this paper, we propose a quality-guided image enhancement paradigm that enables image enhancement models to learn the distribution of images with various quality ratings. By learning this distribution, image enhancement models can associate image features with their corresponding perceptual qualities, which can be used to adjust images continuously according to different quality scores. To validate the effectiveness of our proposed method, a subjective quality assessment experiment is first conducted, focusing on skin tone adjustment in portrait photography. Guided by the subjective quality ratings obtained from this experiment, our method can adjust the skin tone corresponding to different quality requirements. Furthermore, an experiment conducted on 10 natural raw images corroborates the effectiveness of our model in situations with fewer subjects and fewer shots, and also demonstrates its general applicability to natural images. Our project page is https://github.com/IntMeGroup/quality-guided-enhancement .
URLs: https://github.com/IntMeGroup/quality-guided-enhancement
Authors: Tianyu Wei, Shanmin Pang, Qi Guo, Yizhuo Ma, Qing Guo
Abstract: Text-to-image diffusion models can create realistic images based on input texts. Users can describe an object to convey their opinions visually. In this work, we unveil a previously unrecognized and latent risk of using diffusion models to generate images; we utilize emotion in the input texts to introduce negative contents, potentially eliciting unfavorable emotions in users. Emotions play a crucial role in expressing personal opinions in our daily interactions, and the inclusion of maliciously negative content can lead users astray, exacerbating negative emotions. Specifically, we identify the emotion-aware backdoor attack (EmoAttack) that can incorporate malicious negative content triggered by emotional texts during image generation. We formulate such an attack as a diffusion personalization problem to avoid extensive model retraining and propose the EmoBooth. Unlike existing personalization methods, our approach fine-tunes a pre-trained diffusion model by establishing a mapping between a cluster of emotional words and a given reference image containing malicious negative content. To validate the effectiveness of our method, we built a dataset and conducted extensive analysis and discussion about its effectiveness. Given consumers' widespread use of diffusion models, uncovering this threat is critical for society.
Authors: Praveen Nagil, Sumit K. Mandal
Abstract: Assistive technology for visually impaired individuals is extremely useful to make them independent of another human being in performing day-to-day chores and instill confidence in them. One of the important aspects of assistive technology is outdoor navigation for visually impaired people. While there exist several techniques for outdoor navigation in the literature, they are mainly limited to obstacle detection. However, navigating a visually impaired person through the sidewalk (while the person is walking outside) is important too. Moreover, the assistive technology should ensure low-energy operation to extend the battery life of the device. Therefore, in this work, we propose an end-to-end technology deployed on an edge device to assist visually impaired people. Specifically, we propose a novel pruning technique for transformer algorithm which detects sidewalk. The pruning technique ensures low latency of execution and low energy consumption when the pruned transformer algorithm is deployed on the edge device. Extensive experimental evaluation shows that our proposed technology provides up to 32.49% improvement in accuracy and 1.4 hours of extension in battery life with respect to a baseline technique.
Authors: Zhenbin Wang, Lei Zhang, Lituan Wang, Zhenwei Zhang
Abstract: Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are the predominant modalities utilized in the field of medical imaging. Although MRI capture the complexity of anatomical structures with greater detail than CT, it entails a higher financial costs and requires longer image acquisition times. In this study, we aim to train latent diffusion model for CT to MRI conversion, replacing the commonly-used U-Net or Transformer backbone with a State-Space Model (SSM) called Mamba that operates on latent patches. First, we noted critical oversights in the scan scheme of most Mamba-based vision methods, including inadequate attention to the spatial continuity of patch tokens and the lack of consideration for their varying importance to the target task. Secondly, extending from this insight, we introduce Diffusion Mamba (DiffMa), employing soft masked to integrate Cross-Sequence Attention into Mamba and conducting selective scan in a spiral manner. Lastly, extensive experiments demonstrate impressive performance by DiffMa in medical image generation tasks, with notable advantages in input scaling efficiency over existing benchmark models. The code and models are available at https://github.com/wongzbb/DiffMa-Diffusion-Mamba
Authors: Oded Rotem, Assaf Zaritsky
Abstract: We recently presented DISentangled COunterfactual Visual interpretER (DISCOVER), a method toward systematic visual interpretability of image-based classification models and demonstrated its applicability to two biomedical domains. Here we demonstrate that DISCOVER can be applied to the domain of natural images. First, DISCOVER visually interpreted the nose size, the muzzle area, and the face size as semantic discriminative visual traits discriminating between facial images of dogs versus cats. Second, DISCOVER visually interpreted the cheeks and jawline, eyebrows and hair, and the eyes, as discriminative facial characteristics. These successful visual interpretations across two natural images domains indicate that DISCOVER is a generalized interpretability method.
Authors: Jialang Xu, Nazir Sirajudeen, Matthew Boal, Nader Francis, Danail Stoyanov, Evangelos Mazomenos
Abstract: Automated detection of surgical errors can improve robotic-assisted surgery. Despite promising progress, existing methods still face challenges in capturing rich temporal context to establish long-term dependencies while maintaining computational efficiency. In this paper, we propose a novel hierarchical model named SEDMamba, which incorporates the selective state space model (SSM) into surgical error detection, facilitating efficient long sequence modelling with linear complexity. SEDMamba enhances selective SSM with bottleneck mechanism and fine-to-coarse temporal fusion (FCTF) to detect and temporally localize surgical errors in long videos. The bottleneck mechanism compresses and restores features within their spatial dimension, thereby reducing computational complexity. FCTF utilizes multiple dilated 1D convolutional layers to merge temporal information across diverse scale ranges, accommodating errors of varying durations. Besides, we deploy an established observational clinical human reliability assessment tool (OCHRA) to annotate the errors of suturing tasks in an open-source radical prostatectomy dataset (SAR-RARP50), constructing the first frame-level in-vivo surgical error detection dataset to support error detection in real-world scenarios. Experimental results demonstrate that our SEDMamba outperforms state-of-the-art methods with at least 1.82% AUC and 3.80% AP performance gain with significantly reduced computational complexity.
Authors: Alvaro Lopez Pellcier, Yi Li, Plamen Angelov
Abstract: Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images. Recent advancements in deep learning-based deepfake detection methods, particularly with diffusion models, have shown remarkable progress. However, there is a growing demand for real-world applications to detect unseen individuals, deepfake techniques, and scenarios. To address this limitation, we propose a Prototype-based Unified Framework for Deepfake Detection (PUDD). PUDD offers a detection system based on similarity, comparing input data against known prototypes for video classification and identifying potential deepfakes or previously unseen classes by analyzing drops in similarity. Our extensive experiments reveal three key findings: (1) PUDD achieves an accuracy of 95.1% on Celeb-DF, outperforming state-of-the-art deepfake detection methods; (2) PUDD leverages image classification as the upstream task during training, demonstrating promising performance in both image classification and deepfake detection tasks during inference; (3) PUDD requires only 2.7 seconds for retraining on new data and emits 10$^{5}$ times less carbon compared to the state-of-the-art model, making it significantly more environmentally friendly.
Authors: Yi Li, Plamen Angelov, Zhengxin Yu, Alvaro Lopez Pellicer, Neeraj Suri
Abstract: As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks. In this paper, we propose a federated adversarial learning-based framework to detect landing runways using paired data comprising of clean local data and its adversarial version. Firstly, the local model is pre-trained on a large-scale lane detection dataset. Then, instead of exploiting large instance-adaptive models, we resort to a parameter-efficient fine-tuning method known as scale and shift deep features (SSF), upon the pre-trained model. Secondly, in each SSF layer, distributions of clean local data and its adversarial version are disentangled for accurate statistics estimation. To the best of our knowledge, this marks the first instance of federated learning work that address the adversarial sample problem in landing runway detection. Our experimental evaluations over both synthesis and real images of Landing Approach Runway Detection (LARD) dataset consistently demonstrate good performance of the proposed federated adversarial learning and robust to adversarial attacks.
Authors: William Stevens, Vishal Urs, Karthik Selvaraj, Gabriel Torres, Gaurish Lakhanpal
Abstract: With the increasing prevalence of autonomous vehicles, it is essential for computer vision algorithms to accurately assess road features in real-time. This study explores the LaneSegNet architecture, a new approach to lane topology prediction which integrates topological information with lane-line data to provide a more contextual understanding of road environments. The LaneSegNet architecture includes a feature extractor, lane encoder, lane decoder, and prediction head, leveraging components from ResNet-50, BEVFormer, and various attention mechanisms. We experimented with optimizations to the LaneSegNet architecture through feature extractor modification and transformer encoder-decoder stack modification. We found that modifying the encoder and decoder stacks offered an interesting tradeoff between training time and prediction accuracy, with certain combinations showing promising results. Our implementation, trained on a single NVIDIA Tesla A100 GPU, found that a 2:4 ratio reduced training time by 22.3% with only a 7.1% drop in mean average precision, while a 4:8 ratio increased training time by only 11.1% but improved mean average precision by a significant 23.7%. These results indicate that strategic hyperparameter tuning can yield substantial improvements depending on the resources of the user. This study provides valuable insights for optimizing LaneSegNet according to available computation power, making it more accessible for users with limited resources and increasing the capabilities for users with more powerful resources.
Authors: Michael A. Lepori, Alexa R. Tartaglini, Wai Keen Vong, Thomas Serre, Brenden M. Lake, Ellie Pavlick
Abstract: Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform tasks that require computing visual relations between objects? Prior efforts to interpret ViTs tend to focus on characterizing relevant low-level visual features. In contrast, we adopt methods from mechanistic interpretability to study the higher-level visual algorithms that ViTs use to perform abstract visual reasoning. We present a case study of a fundamental, yet surprisingly difficult, relational reasoning task: judging whether two visual entities are the same or different. We find that pretrained ViTs fine-tuned on this task often exhibit two qualitatively different stages of processing despite having no obvious inductive biases to do so: 1) a perceptual stage wherein local object features are extracted and stored in a disentangled representation, and 2) a relational stage wherein object representations are compared. In the second stage, we find evidence that ViTs can learn to represent somewhat abstract visual relations, a capability that has long been considered out of reach for artificial neural networks. Finally, we demonstrate that failure points at either stage can prevent a model from learning a generalizable solution to our fairly simple tasks. By understanding ViTs in terms of discrete processing stages, one can more precisely diagnose and rectify shortcomings of existing and future models.
Authors: Yangdi Lu, Wenbo He
Abstract: Deep neural networks has been highly successful in data-intense computer vision applications, while such success relies heavily on the massive and clean data. In real-world scenarios, clean data sometimes is difficult to obtain. For example, in image classification and segmentation tasks, precise annotations of millions samples are generally very expensive and time-consuming. In 3D static scene reconstruction task, most NeRF related methods require the foundational assumption of the static scene (e.g. consistent lighting condition and persistent object positions), which is often violated in real-world scenarios. To address these problem, learning with noisy ground truth (LNGT) has emerged as an effective learning method and shows great potential. In this short survey, we propose a formal definition unify the analysis of LNGT LNGT in the context of different machine learning tasks (classification and regression). Based on this definition, we propose a novel taxonomy to classify the existing work according to the error decomposition with the fundamental definition of machine learning. Further, we provide in-depth analysis on memorization effect and insightful discussion about potential future research opportunities from 2D classification to 3D reconstruction, in the hope of providing guidance to follow-up research.
Authors: Hu Gao, Depeng Dang
Abstract: Stereo image super-resolution (stereoSR) aims to enhance the quality of super-resolution results by incorporating complementary information from an alternative view. Although current methods have shown significant advancements, they typically operate on representations at full resolution to preserve spatial details, facing challenges in accurately capturing contextual information. Simultaneously, they utilize all feature similarities to cross-fuse information from the two views, potentially disregarding the impact of irrelevant information. To overcome this problem, we propose a mixed-scale selective fusion network (MSSFNet) to preserve precise spatial details and incorporate abundant contextual information, and adaptively select and fuse most accurate features from two views to enhance the promotion of high-quality stereoSR. Specifically, we develop a mixed-scale block (MSB) that obtains contextually enriched feature representations across multiple spatial scales while preserving precise spatial details. Furthermore, to dynamically retain the most essential cross-view information, we design a selective fusion attention module (SFAM) that searches and transfers the most accurate features from another view. To learn an enriched set of local and non-local features, we introduce a fast fourier convolution block (FFCB) to explicitly integrate frequency domain knowledge. Extensive experiments show that MSSFNet achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations.
Authors: Mingshu Zhao, Yi Luo, Yong Ouyang
Abstract: In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at capturing global context through self-attention mechanisms, their deployment in resource-limited environments is hindered by computational complexity and latency. Conversely, lightweight CNNs are favored for their parameter efficiency and low latency. This study investigates the complementary advantages of CNNs and ViTs to develop a versatile vision backbone tailored for resource-constrained applications. We introduce RepNeXt, a novel model series integrates multi-scale feature representations and incorporates both serial and parallel structural reparameterization (SRP) to enhance network depth and width without compromising inference speed. Extensive experiments demonstrate RepNeXt's superiority over current leading lightweight CNNs and ViTs, providing advantageous latency across various vision benchmarks. RepNeXt-M4 matches RepViT-M1.5's 82.3\% accuracy on ImageNet within 1.5ms on an iPhone 12, outperforms its AP$^{box}$ by 1.1 on MS-COCO, and reduces parameters by 0.7M. Codes and models are available at https://github.com/suous/RepNeXt.
Authors: Delin Qu, Qizhi Chen, Pingrui Zhang, Xianqiang Gao, Bin Zhao, Dong Wang, Xuelong Li
Abstract: This paper aims to advance the progress of physical world interactive scene reconstruction by extending the interactive object reconstruction from single object level to complex scene level. To this end, we first construct one simulated and one real scene-level physical interaction dataset containing 28 scenes with multiple interactive objects per scene. Furthermore, to accurately model the interactive motions of multiple objects in complex scenes, we propose LiveScene, the first scene-level language-embedded interactive neural radiance field that efficiently reconstructs and controls multiple interactive objects in complex scenes. LiveScene introduces an efficient factorization that decomposes the interactive scene into multiple local deformable fields to separately reconstruct individual interactive objects, achieving the first accurate and independent control on multiple interactive objects in a complex scene. Moreover, we introduce an interaction-aware language embedding method that generates varying language embeddings to localize individual interactive objects under different interactive states, enabling arbitrary control of interactive objects using natural language. Finally, we evaluate LiveScene on the constructed datasets OminiSim and InterReal with various simulated and real-world complex scenes. Extensive experiment results demonstrate that the proposed approach achieves SOTA novel view synthesis and language grounding performance, surpassing existing methods by +9.89, +1.30, and +1.99 in PSNR on CoNeRF Synthetic, OminiSim #chanllenging, and InterReal #chanllenging datasets, and +65.12 of mIOU on OminiSim, respectively. Project page: \href{https://livescenes.github.io}{https://livescenes.github.io}.
URLs: https://livescenes.github.io, https://livescenes.github.io
Authors: Oluwatosin Alabi, Ko Ko Zayar Toe, Zijian Zhou, Charlie Budd, Nicholas Raison, Miaojing Shi, Tom Vercauteren
Abstract: In laparoscopic and robotic surgery, precise tool instance segmentation is an essential technology for advanced computer-assisted interventions. Although publicly available procedures of routine surgeries exist, they often lack comprehensive annotations for tool instance segmentation. Additionally, the majority of standard datasets for tool segmentation are derived from porcine(pig) surgeries. To address this gap, we introduce CholecInstanceSeg, the largest open-access tool instance segmentation dataset to date. Derived from the existing CholecT50 and Cholec80 datasets, CholecInstanceSeg provides novel annotations for laparoscopic cholecystectomy procedures in patients. Our dataset comprises 41.9k annotated frames extracted from 85 clinical procedures and 64.4k tool instances, each labelled with semantic masks and instance IDs. To ensure the reliability of our annotations, we perform extensive quality control, conduct label agreement statistics, and benchmark the segmentation results with various instance segmentation baselines. CholecInstanceSeg aims to advance the field by offering a comprehensive and high-quality open-access dataset for the development and evaluation of tool instance segmentation algorithms.
Authors: In\`es Hyeonsu Kim, JoungBin Lee, Soowon Son, Woojeong Jin, Kyusun Cho, Junyoung Seo, Min-Seop Kwak, Seokju Cho, JeongYeol Baek, Byeongwon Lee, Seungryong Kim
Abstract: Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and scalability in these aspects, hindering the generalization of Re-ID models to new camera systems. Previous methods have attempted to address these issues through data augmentation; however, they rely on human poses already present in the training dataset, failing to effectively reduce the human pose bias in the dataset. We propose Diff-ID, a novel data augmentation approach that incorporates sparse and underrepresented human pose and camera viewpoint examples into the training data, addressing the limited diversity in the original training data distribution. Our objective is to augment a training dataset that enables existing Re-ID models to learn features unbiased by human pose and camera viewpoint variations. To achieve this, we leverage the knowledge of pre-trained large-scale diffusion models. Using the SMPL model, we simultaneously capture both the desired human poses and camera viewpoints, enabling realistic human rendering. The depth information provided by the SMPL model indirectly conveys the camera viewpoints. By conditioning the diffusion model on both the human pose and camera viewpoint concurrently through the SMPL model, we generate realistic images with diverse human poses and camera viewpoints. Qualitative results demonstrate the effectiveness of our method in addressing human pose bias and enhancing the generalizability of Re-ID models compared to other data augmentation-based Re-ID approaches. The performance gains achieved by training Re-ID models on our offline augmented dataset highlight the potential of our proposed framework in improving the scalability and generalizability of person Re-ID models.
Authors: Yueru Luo, Shuguang Cui, Zhen Li
Abstract: Accurate 3D lane estimation is crucial for ensuring safety in autonomous driving. However, prevailing monocular techniques suffer from depth loss and lighting variations, hampering accurate 3D lane detection. In contrast, LiDAR points offer geometric cues and enable precise localization. In this paper, we present DV-3DLane, a novel end-to-end Dual-View multi-modal 3D Lane detection framework that synergizes the strengths of both images and LiDAR points. We propose to learn multi-modal features in dual-view spaces, i.e., perspective view (PV) and bird's-eye-view (BEV), effectively leveraging the modal-specific information. To achieve this, we introduce three designs: 1) A bidirectional feature fusion strategy that integrates multi-modal features into each view space, exploiting their unique strengths. 2) A unified query generation approach that leverages lane-aware knowledge from both PV and BEV spaces to generate queries. 3) A 3D dual-view deformable attention mechanism, which aggregates discriminative features from both PV and BEV spaces into queries for accurate 3D lane detection. Extensive experiments on the public benchmark, OpenLane, demonstrate the efficacy and efficiency of DV-3DLane. It achieves state-of-the-art performance, with a remarkable 11.2 gain in F1 score and a substantial 53.5% reduction in errors. The code is available at \url{https://github.com/JMoonr/dv-3dlane}.
Authors: Hengyu Liu, Yifan Liu, Chenxin Li, Wuyang Li, Yixuan Yuan
Abstract: The advent of 3D Gaussian Splatting (3D-GS) techniques and their dynamic scene modeling variants, 4D-GS, offers promising prospects for real-time rendering of dynamic surgical scenarios. However, the prerequisite for modeling dynamic scenes by a large number of Gaussian units, the high-dimensional Gaussian attributes and the high-resolution deformation fields, all lead to serve storage issues that hinder real-time rendering in resource-limited surgical equipment. To surmount these limitations, we introduce a Lightweight 4D Gaussian Splatting framework (LGS) that can liberate the efficiency bottlenecks of both rendering and storage for dynamic endoscopic reconstruction. Specifically, to minimize the redundancy of Gaussian quantities, we propose Deformation-Aware Pruning by gauging the impact of each Gaussian on deformation. Concurrently, to reduce the redundancy of Gaussian attributes, we simplify the representation of textures and lighting in non-crucial areas by pruning the dimensions of Gaussian attributes. We further resolve the feature field redundancy caused by the high resolution of 4D neural spatiotemporal encoder for modeling dynamic scenes via a 4D feature field condensation. Experiments on public benchmarks demonstrate efficacy of LGS in terms of a compression rate exceeding 9 times while maintaining the pleasing visual quality and real-time rendering efficiency. LGS confirms a substantial step towards its application in robotic surgical services.
Authors: Thomas Stegm\"uller, Tim Lebailly, Nikola Dukic, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars
Abstract: Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle in dense tasks like zero-shot open-vocabulary segmentation. This deficiency is often attributed to the absence of localization cues in captions and the intertwined nature of the learning process, which encompasses both image representation learning and cross-modality alignment. To tackle these issues, we propose SimZSS, a Simple framework for open-vocabulary Zero-Shot Segmentation. The method is founded on two key principles: i) leveraging frozen vision-only models that exhibit spatial awareness while exclusively aligning the text encoder and ii) exploiting the discrete nature of text and linguistic knowledge to pinpoint local concepts within captions. By capitalizing on the quality of the visual representations, our method requires only image-caption pairs datasets and adapts to both small curated and large-scale noisy datasets. When trained on COCO Captions across 8 GPUs, SimZSS achieves state-of-the-art results on 7 out of 8 benchmark datasets in less than 15 minutes.
Authors: Ni Wang, Dongliang Liao, Xing Xu
Abstract: Currently, in the field of video-text retrieval, there are many transformer-based methods. Most of them usually stack frame features and regrade frames as tokens, then use transformers for video temporal modeling. However, they commonly neglect the inferior ability of the transformer modeling local temporal information. To tackle this problem, we propose a transformer variant named Multi-Scale Temporal Difference Transformer (MSTDT). MSTDT mainly addresses the defects of the traditional transformer which has limited ability to capture local temporal information. Besides, in order to better model the detailed dynamic information, we make use of the difference feature between frames, which practically reflects the dynamic movement of a video. We extract the inter-frame difference feature and integrate the difference and frame feature by the multi-scale temporal transformer. In general, our proposed MSTDT consists of a short-term multi-scale temporal difference transformer and a long-term temporal transformer. The former focuses on modeling local temporal information, the latter aims at modeling global temporal information. At last, we propose a new loss to narrow the distance of similar samples. Extensive experiments show that backbone, such as CLIP, with MSTDT has attained a new state-of-the-art result.
Authors: Pengfei Zhang, Chang Li, Yongjun Zhang, Rongjun Qin
Abstract: Remotely sensed image high-accuracy interpretation (RSIHI), including tasks such as semantic segmentation and change detection, faces the three major problems: (1) complementarity problem of spatially stationary-and-non-stationary frequency; (2) edge uncertainty problem caused by down-sampling in the encoder step and intrinsic edge noises; and (3) false detection problem caused by imagery registration error in change detection. To solve the aforementioned problems, an uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the proposed for RSIHI, the superiority of which is as following: (1) a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP) is proposed to enhance the interaction of spatially stationary and non-stationary frequency features to yield high-fidelity edge extraction result. Inspired by HRFormer, SHCP remains the high-frequency stream through the whole encoder-decoder process with parallel high-to-low frequency streams and reduces the edge loss by a downsampling operation; (2) a mask-and-geo-knowledge-based uncertainty diffusion module (MUDM) is proposed to improve the robustness and edge noise resistance. MUDM could further optimize the uncertain region to improve edge extraction result by gradually removing the multiple geo-knowledge-based noises; (3) a semi-pseudo-Siamese UDHF2-Net for change detection task is proposed to reduce the pseudo change by registration error. It adopts semi-pseudo-Siamese architecture to extract above complemental frequency features for adaptively reducing registration differencing, and MUDM to recover the uncertain region by gradually reducing the registration error besides above edge noises. Comprehensive experiments were performed to demonstrate the superiority of UDHF2-Net. Especially ablation experiments indicate the effectiveness of UDHF2-Net.
Authors: Jian Yang, Jiakun Li, Guoming Li, Zhen Shen, Huai-Yu Wu, Zhaoxin Fan, Heng Huang
Abstract: Multi-view hand mesh reconstruction is a critical task for applications in virtual reality and human-computer interaction, but it remains a formidable challenge. Although existing multi-view hand reconstruction methods achieve remarkable accuracy, they typically come with an intensive computational burden that hinders real-time inference. To this end, we propose MLPHand, a novel method designed for real-time multi-view single hand reconstruction. MLP Hand consists of two primary modules: (1) a lightweight MLP-based Skeleton2Mesh model that efficiently recovers hand meshes from hand skeletons, and (2) a multi-view geometry feature fusion prediction module that enhances the Skeleton2Mesh model with detailed geometric information from multiple views. Experiments on three widely used datasets demonstrate that MLPHand can reduce computational complexity by 90% while achieving comparable reconstruction accuracy to existing state-of-the-art baselines.
Authors: Yanming Guo
Abstract: Multimodal multilabel classification (MMC) is a challenging task that aims to design a learning algorithm to handle two data sources, the image and text, and learn a comprehensive semantic feature presentation across the modalities. In this task, we review the extensive number of state-of-the-art approaches in MMC and leverage a novel technique that utilises the Contrastive Language-Image Pre-training (CLIP) as the feature extractor and fine-tune the model by exploring different classification heads, fusion methods and loss functions. Finally, our best result achieved more than 90% F_1 score in the public Kaggle competition leaderboard. This paper provides detailed descriptions of novel training methods and quantitative analysis through the experimental results.
Authors: Maged Badawi, Mohammedyahia Abushanab, Sheethal Bhat, Andreas Maier
Abstract: In this paper, different techniques of few-shot, zero-shot, and regular object detection have been investigated. The need for few-shot learning and zero-shot learning techniques is crucial and arises from the limitations and challenges in traditional machine learning, deep learning, and computer vision methods where they require large amounts of data, plus the poor generalization of those traditional methods. Those techniques can give us prominent results by using only a few training sets reducing the required amounts of data and improving the generalization. This survey will highlight the recent papers of the last three years that introduce the usage of few-shot learning and zero-shot learning techniques in addressing the challenges mentioned earlier. In this paper we reviewed the Zero-shot, few-shot and regular object detection methods and categorized them in an understandable manner. Based on the comparison made within each category. It been found that the approaches are quite impressive. This integrated review of diverse papers on few-shot, zero-shot, and regular object detection reveals a shared focus on advancing the field through novel frameworks and techniques. A noteworthy observation is the scarcity of detailed discussions regarding the difficulties encountered during the development phase. Contributions include the introduction of innovative models, such as ZSD-YOLO and GTNet, often showcasing improvements with various metrics such as mean average precision (mAP),Recall@100 (RE@100), the area under the receiver operating characteristic curve (AUROC) and precision. These findings underscore a collective move towards leveraging vision-language models for versatile applications, with potential areas for future research including a more thorough exploration of limitations and domain-specific adaptations.
Authors: Jan Ignatowicz, Krzysztof Kutt, Grzegorz J. Nalepa
Abstract: Experiments in affective computing are based on stimulus datasets that, in the process of standardization, receive metadata describing which emotions each stimulus evokes. In this paper, we explore an approach to creating stimulus datasets for affective computing using generative adversarial networks (GANs). Traditional dataset preparation methods are costly and time consuming, prompting our investigation of alternatives. We conducted experiments with various GAN architectures, including Deep Convolutional GAN, Conditional GAN, Auxiliary Classifier GAN, Progressive Augmentation GAN, and Wasserstein GAN, alongside data augmentation and transfer learning techniques. Our findings highlight promising advances in the generation of emotionally evocative synthetic images, suggesting significant potential for future research and improvements in this domain.
Authors: Guillaume Jaume, Paul Doucet, Andrew H. Song, Ming Y. Lu, Cristina Almagro-P\'erez, Sophia J. Wagner, Anurag J. Vaidya, Richard J. Chen, Drew F. K. Williamson, Ahrong Kim, Faisal Mahmood
Abstract: Spatial transcriptomics (ST) enables interrogating the molecular composition of tissue with ever-increasing resolution, depth, and sensitivity. However, costs, rapidly evolving technology, and lack of standards have constrained computational methods in ST to narrow tasks and small cohorts. In addition, the underlying tissue morphology as reflected by H&E-stained whole slide images (WSIs) encodes rich information often overlooked in ST studies. Here, we introduce HEST-1k, a collection of 1,108 spatial transcriptomic profiles, each linked to a WSI and metadata. HEST-1k was assembled using HEST-Library from 131 public and internal cohorts encompassing 25 organs, two species (Homo Sapiens and Mus Musculus), and 320 cancer samples from 25 cancer types. HEST-1k processing enabled the identification of 1.5 million expression--morphology pairs and 60 million nuclei. HEST-1k is tested on three use cases: (1) benchmarking foundation models for histopathology (HEST-Benchmark), (2) biomarker identification, and (3) multimodal representation learning. HEST-1k, HEST-Library, and HEST-Benchmark can be freely accessed via https://github.com/mahmoodlab/hest.
Authors: Tong Wei, Philipp Lindenberger, Jiri Matas, Daniel Barath
Abstract: We propose a novel visual place recognition approach, VOP, that efficiently addresses occlusions and complex scenes by shifting from traditional reliance on global image similarities and local features to image overlap prediction. The proposed method enables the identification of visible image sections without requiring expensive feature detection and matching. By focusing on obtaining patch-level embeddings by a Vision Transformer backbone and establishing patch-to-patch correspondences, our approach uses a voting mechanism to assess overlap scores for potential database images, thereby providing a nuanced image retrieval metric in challenging scenarios. VOP leads to more accurate relative pose estimation and localization results on the retrieved image pairs than state-of-the-art baselines on a number of large-scale, real-world datasets. The code is available at https://github.com/weitong8591/vop.
Authors: Zhenxiong Tan, Xingyi Yang, Songhua Liu, Xinchao Wang
Abstract: Diffusion models have recently achieved remarkable results for video generation. Despite the encouraging performances, the generated videos are typically constrained to a small number of frames, resulting in clips lasting merely a few seconds. The primary challenges in producing longer videos include the substantial memory requirements and the extended processing time required on a single GPU. A straightforward solution would be to split the workload across multiple GPUs, which, however, leads to two issues: (1) ensuring all GPUs communicate effectively to share timing and context information, and (2) modifying existing video diffusion models, which are usually trained on short sequences, to create longer videos without additional training. To tackle these, in this paper we introduce Video-Infinity, a distributed inference pipeline that enables parallel processing across multiple GPUs for long-form video generation. Specifically, we propose two coherent mechanisms: Clip parallelism and Dual-scope attention. Clip parallelism optimizes the gathering and sharing of context information across GPUs which minimizes communication overhead, while Dual-scope attention modulates the temporal self-attention to balance local and global contexts efficiently across the devices. Together, the two mechanisms join forces to distribute the workload and enable the fast generation of long videos. Under an 8 x Nvidia 6000 Ada GPU (48G) setup, our method generates videos up to 2,300 frames in approximately 5 minutes, enabling long video generation at a speed 100 times faster than the prior methods.
Authors: Xueyu Liu, Guangze Shi, Rui Wang, Yexin Lai, Jianan Zhang, Lele Sun, Quan Yang, Yongfei Wu, MIng Li, Weixia Han, Wen Zheng
Abstract: Assessment of the glomerular basement membrane (GBM) in transmission electron microscopy (TEM) is crucial for diagnosing chronic kidney disease (CKD). The lack of domain-independent automatic segmentation tools for the GBM necessitates an AI-based solution to automate the process. In this study, we introduce GBMSeg, a training-free framework designed to automatically segment the GBM in TEM images guided only by a one-shot annotated reference. Specifically, GBMSeg first exploits the robust feature matching capabilities of the pretrained foundation model to generate initial prompt points, then introduces a series of novel automatic prompt engineering techniques across the feature and physical space to optimize the prompt scheme. Finally, GBMSeg employs a class-agnostic foundation segmentation model with the generated prompt scheme to obtain accurate segmentation results. Experimental results on our collected 2538 TEM images confirm that GBMSeg achieves superior segmentation performance with a Dice similarity coefficient (DSC) of 87.27% using only one labeled reference image in a training-free manner, outperforming recently proposed one-shot or few-shot methods. In summary, GBMSeg introduces a distinctive automatic prompt framework that facilitates robust domain-independent segmentation performance without training, particularly advancing the automatic prompting of foundation segmentation models for medical images. Future work involves automating the thickness measurement of segmented GBM and quantifying pathological indicators, holding significant potential for advancing pathology assessments in clinical applications. The source code is available on https://github.com/SnowRain510/GBMSeg
Authors: Zhiyuan Chang, Mingyang Li, Junjie Wang, Yi Liu, Qing Wang, Yang Liu
Abstract: Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies. The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt. We first conduct an empirical study on this issue, exploring the prevalence of catastrophic-neglect, potential mitigation strategies with feature enhancement, and the insights gained. Guided by the empirical findings, we propose an automated repair approach named Patcher to address catastrophic-neglect in T2I DMs. Specifically, Patcher first determines whether there are any neglected objects in the prompt, and then applies attention-guided feature enhancement to these neglected objects, resulting in a repaired prompt. Experimental results on three versions of Stable Diffusion demonstrate that Patcher effectively repairs the issue of catastrophic-neglect, achieving 10.1%-16.3% higher Correct Rate in image generation compared to baselines.
Authors: Sandeep Mishra, Oindrila Saha, Alan C. Bovik
Abstract: 3D generation guided by text-to-image diffusion models enables the creation of visually compelling assets. However previous methods explore generation based on image or text. The boundaries of creativity are limited by what can be expressed through words or the images that can be sourced. We present YouDream, a method to generate high-quality anatomically controllable animals. YouDream is guided using a text-to-image diffusion model controlled by 2D views of a 3D pose prior. Our method generates 3D animals that are not possible to create using previous text-to-3D generative methods. Additionally, our method is capable of preserving anatomic consistency in the generated animals, an area where prior text-to-3D approaches often struggle. Moreover, we design a fully automated pipeline for generating commonly found animals. To circumvent the need for human intervention to create a 3D pose, we propose a multi-agent LLM that adapts poses from a limited library of animal 3D poses to represent the desired animal. A user study conducted on the outcomes of YouDream demonstrates the preference of the animal models generated by our method over others. Turntable results and code are released at https://youdream3d.github.io/
Authors: Neng Wang, Ruibin Guo, Chenghao Shi, Hui Zhang, Huimin Lu, Zhiqiang Zheng, Xieyuanli Chen
Abstract: 4D LiDAR semantic segmentation, also referred to as multi-scan semantic segmentation, plays a crucial role in enhancing the environmental understanding capabilities of autonomous vehicles. It entails identifying the semantic category of each point in the LiDAR scan and distinguishing whether it is dynamic, a critical aspect in downstream tasks such as path planning and autonomous navigation. Existing methods for 4D semantic segmentation often rely on computationally intensive 4D convolutions for multi-scan input, resulting in poor real-time performance. In this article, we introduce SegNet4D, a novel real-time multi-scan semantic segmentation method leveraging a projection-based approach for fast motion feature encoding, showcasing outstanding performance. SegNet4D treats 4D semantic segmentation as two distinct tasks: single-scan semantic segmentation and moving object segmentation, each addressed by dedicated head. These results are then fused in the proposed motion-semantic fusion module to achieve comprehensive multi-scan semantic segmentation. Besides, we propose extracting instance information from the current scan and incorporating it into the network for instance-aware segmentation. Our approach exhibits state-of-the-art performance across multiple datasets and stands out as a real-time multi-scan semantic segmentation method. The implementation of SegNet4D will be made available at \url{https://github.com/nubot-nudt/SegNet4D}.
Authors: Tong Qin, Changze Li, Haoyang Ye, Shaowei Wan, Minzhen Li, Hongwei Liu, Ming Yang
Abstract: Recently, Neural Radiance Fields (NeRF) achieved impressive results in novel view synthesis. Block-NeRF showed the capability of leveraging NeRF to build large city-scale models. For large-scale modeling, a mass of image data is necessary. Collecting images from specially designed data-collection vehicles can not support large-scale applications. How to acquire massive high-quality data remains an opening problem. Noting that the automotive industry has a huge amount of image data, crowd-sourcing is a convenient way for large-scale data collection. In this paper, we present a crowd-sourced framework, which utilizes substantial data captured by production vehicles to reconstruct the scene with the NeRF model. This approach solves the key problem of large-scale reconstruction, that is where the data comes from and how to use them. Firstly, the crowd-sourced massive data is filtered to remove redundancy and keep a balanced distribution in terms of time and space. Then a structure-from-motion module is performed to refine camera poses. Finally, images, as well as poses, are used to train the NeRF model in a certain block. We highlight that we present a comprehensive framework that integrates multiple modules, including data selection, sparse 3D reconstruction, sequence appearance embedding, depth supervision of ground surface, and occlusion completion. The complete system is capable of effectively processing and reconstructing high-quality 3D scenes from crowd-sourced data. Extensive quantitative and qualitative experiments were conducted to validate the performance of our system. Moreover, we proposed an application, named first-view navigation, which leveraged the NeRF model to generate 3D street view and guide the driver with a synthesized video.
Authors: Yajing Pei, Shiyu Huang, Yiting Lu, Xin Li, Zhibo Chen
Abstract: User Generated Content (UGC) videos are susceptible to complicated and variant degradations and contents, which prevents the existing blind video quality assessment (BVQA) models from good performance since the lack of the adapability of distortions and contents. To mitigate this, we propose a novel prior-augmented perceptual vision transformer (PriorFormer) for the BVQA of UGC, which boots its adaptability and representation capability for divergent contents and distortions. Concretely, we introduce two powerful priors, i.e., the content and distortion priors, by extracting the content and distortion embeddings from two pre-trained feature extractors. Then we adopt these two powerful embeddings as the adaptive prior tokens, which are transferred to the vision transformer backbone jointly with implicit quality features. Based on the above strategy, the proposed PriorFormer achieves state-of-the-art performance on three public UGC VQA datasets including KoNViD-1K, LIVE-VQC and YouTube-UGC.
Authors: Yuting Mei, Linli Yao, Qin Jin
Abstract: With the surge in the amount of video data, video summarization techniques, including visual-modal(VM) and textual-modal(TM) summarization, are attracting more and more attention. However, unimodal summarization inevitably loses the rich semantics of the video. In this paper, we focus on a more comprehensive video summarization task named Bimodal Semantic Summarization of Videos (BiSSV). Specifically, we first construct a large-scale dataset, BIDS, in (video, VM-Summary, TM-Summary) triplet format. Unlike traditional processing methods, our construction procedure contains a VM-Summary extraction algorithm aiming to preserve the most salient content within long videos. Based on BIDS, we propose a Unified framework UBiSS for the BiSSV task, which models the saliency information in the video and generates a TM-summary and VM-summary simultaneously. We further optimize our model with a list-wise ranking-based objective to improve its capacity to capture highlights. Lastly, we propose a metric, $NDCG_{MS}$, to provide a joint evaluation of the bimodal summary. Experiments show that our unified framework achieves better performance than multi-stage summarization pipelines. Code and data are available at https://github.com/MeiYutingg/UBiSS.
Authors: Aoxiang Ning, Yiting Wei, Minglong Xue, Senming Zhong
Abstract: Although current text detection algorithms demonstrate effectiveness in general scenarios, their performance declines when confronted with artistic-style text featuring complex structures. This paper proposes a method that utilizes Criss-Cross Attention and residual dense block to address the incomplete and misdiagnosis of artistic-style text detection by current algorithms. Specifically, our method mainly consists of a feature extraction backbone, a feature enhancement network, a multi-scale feature fusion module, and a boundary discrimination module. The feature enhancement network significantly enhances the model's perceptual capabilities in complex environments by fusing horizontal and vertical contextual information, allowing it to capture detailed features overlooked in artistic-style text. We incorporate residual dense block into the Feature Pyramid Network to suppress the effect of background noise during feature fusion. Aiming to omit the complex post-processing, we explore a boundary discrimination module that guides the correct generation of boundary proposals. Furthermore, given that movie poster titles often use stylized art fonts, we collected a Movie-Poster dataset to address the scarcity of artistic-style text data. Extensive experiments demonstrate that our proposed method performs superiorly on the Movie-Poster dataset and produces excellent results on multiple benchmark datasets. The code and the Movie-Poster dataset will be available at: https://github.com/biedaxiaohua/Artistic-style-text-detection
URLs: https://github.com/biedaxiaohua/Artistic-style-text-detection
Authors: Yichen Sun, Zhixuan Chu, Zhan Qin, Kui Ren
Abstract: The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, these models are often susceptible in generating contents that contradict the input text, which poses a challenge to their reliability and practical deployment. To address this problem, we introduce a novel diffusion-based framework to significantly enhance the alignment of generated images with their corresponding descriptions, addressing the inconsistency between visual output and textual input. Our framework is built upon a comprehensive analysis of inconsistency phenomena, categorizing them based on their manifestation in the image. Leveraging a state-of-the-art large language module, we first extract objects and construct a knowledge graph to predict the locations of these objects in potentially generated images. We then integrate a state-of-the-art controllable image generation model with a visual text generation module to generate an image that is consistent with the original prompt, guided by the predicted object locations. Through extensive experiments on an advanced multimodal hallucination benchmark, we demonstrate the efficacy of our approach in accurately generating the images without the inconsistency with the original prompt. The code can be accessed via https://github.com/TruthAI-Lab/PCIG.
Authors: Yuxuan Wang, Yueqian Wang, Dongyan Zhao, Cihang Xie, Zilong Zheng
Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have extended their capabilities to video understanding. Yet, these models are often plagued by "hallucinations", where irrelevant or nonsensical content is generated, deviating from the actual video context. This work introduces VideoHallucer, the first comprehensive benchmark for hallucination detection in large video-language models (LVLMs). VideoHallucer categorizes hallucinations into two main types: intrinsic and extrinsic, offering further subcategories for detailed analysis, including object-relation, temporal, semantic detail, extrinsic factual, and extrinsic non-factual hallucinations. We adopt an adversarial binary VideoQA method for comprehensive evaluation, where pairs of basic and hallucinated questions are crafted strategically. By evaluating eleven LVLMs on VideoHallucer, we reveal that i) the majority of current models exhibit significant issues with hallucinations; ii) while scaling datasets and parameters improves models' ability to detect basic visual cues and counterfactuals, it provides limited benefit for detecting extrinsic factual hallucinations; iii) existing models are more adept at detecting facts than identifying hallucinations. As a byproduct, these analyses further instruct the development of our self-PEP framework, achieving an average of 5.38% improvement in hallucination resistance across all model architectures.
Authors: Daniel Wen, Nafisa Hussain
Abstract: Large language models (LLMs) and large visual language models (LVLMs) have been at the forefront of the artificial intelligence field, particularly for tasks like text generation, video captioning, and question-answering. Typically, it is more applicable to train these models on broader knowledge bases or datasets to increase generalizability, learn relationships between topics, and recognize patterns. Instead, we propose to provide instructional datasets specific to the task of each modality within a distinct domain and then fine-tune the parameters of the model using LORA. With our approach, we can eliminate all noise irrelevant to the given task while also ensuring that the model generates with enhanced precision. For this work, we use Video-LLaVA to generate recipes given cooking videos without transcripts. Video-LLaVA's multimodal architecture allows us to provide cooking images to its image encoder, cooking videos to its video encoder, and general cooking questions to its text encoder. Thus, we aim to remove all noise unrelated to cooking while improving our model's capabilities to generate specific ingredient lists and detailed instructions. As a result, our approach to fine-tuning Video-LLaVA leads to gains over the baseline Video-LLaVA by 2% on the YouCook2 dataset. While this may seem like a marginal increase, our model trains on an image instruction dataset 2.5% the size of Video-LLaVA's and a video instruction dataset 23.76% of Video-LLaVA's.
Authors: Yuxin Dai, Qi Wang, Jingsen Zhu, Dianbing Xi, Yuchi Huo, Chen Qian, Ying He
Abstract: We present MIRReS, a novel two-stage inverse rendering framework that jointly reconstructs and optimizes the explicit geometry, material, and lighting from multi-view images. Unlike previous methods that rely on implicit irradiance fields or simplified path tracing algorithms, our method extracts an explicit geometry (triangular mesh) in stage one, and introduces a more realistic physically-based inverse rendering model that utilizes multi-bounce path tracing and Monte Carlo integration. By leveraging multi-bounce path tracing, our method effectively estimates indirect illumination, including self-shadowing and internal reflections, which improves the intrinsic decomposition of shape, material, and lighting. Moreover, we incorporate reservoir sampling into our framework to address the noise in Monte Carlo integration, enhancing convergence and facilitating gradient-based optimization with low sample counts. Through qualitative and quantitative evaluation of several scenarios, especially in challenging scenarios with complex shadows, we demonstrate that our method achieves state-of-the-art performance on decomposition results. Additionally, our optimized explicit geometry enables applications such as scene editing, relighting, and material editing with modern graphics engines or CAD software. The source code is available at https://brabbitdousha.github.io/MIRReS/
Authors: Jaime Corsetti, Davide Boscaini, Francesco Giuliari, Changjae Oh, Andrea Cavallaro, Fabio Poiesi
Abstract: The generalisation to unseen objects in the 6D pose estimation task is very challenging. While Vision-Language Models (VLMs) enable using natural language descriptions to support 6D pose estimation of unseen objects, these solutions underperform compared to model-based methods. In this work we present Horyon, an open-vocabulary VLM-based architecture that addresses relative pose estimation between two scenes of an unseen object, described by a textual prompt only. We use the textual prompt to identify the unseen object in the scenes and then obtain high-resolution multi-scale features. These features are used to extract cross-scene matches for registration. We evaluate our model on a benchmark with a large variety of unseen objects across four datasets, namely REAL275, Toyota-Light, Linemod, and YCB-Video. Our method achieves state-of-the-art performance on all datasets, outperforming by 12.6 in Average Recall the previous best-performing approach.
Authors: Tiange Zhang, Qing Cai, Feng Gao, Lin Qi, Junyu Dong
Abstract: Cross-Domain Few-Shot Learning has witnessed great stride with the development of meta-learning. However, most existing methods pay more attention to learning domain-adaptive inductive bias (meta-knowledge) through feature-wise manipulation or task diversity improvement while neglecting the phenomenon that deep networks tend to rely more on high-frequency cues to make the classification decision, which thus degenerates the robustness of learned inductive bias since high-frequency information is vulnerable and easy to be disturbed by noisy information. Hence in this paper, we make one of the first attempts to propose a Frequency-Aware Prompting method with mutual attention for Cross-Domain Few-Shot classification, which can let networks simulate the human visual perception of selecting different frequency cues when facing new recognition tasks. Specifically, a frequency-aware prompting mechanism is first proposed, in which high-frequency components of the decomposed source image are switched either with normal distribution sampling or zeroing to get frequency-aware augment samples. Then, a mutual attention module is designed to learn generalizable inductive bias under CD-FSL settings. More importantly, the proposed method is a plug-and-play module that can be directly applied to most off-the-shelf CD-FLS methods. Experimental results on CD-FSL benchmarks demonstrate the effectiveness of our proposed method as well as robustly improve the performance of existing CD-FLS methods. Resources at https://github.com/tinkez/FAP_CDFSC.
Authors: Ziyue Wang, Ye Zhang, Yifeng Wang, Linghan Cai, Yongbing Zhang
Abstract: Deep learning has achieved impressive results in nuclei segmentation, but the massive requirement for pixel-wise labels remains a significant challenge. To alleviate the annotation burden, existing methods generate pseudo masks for model training using point labels. However, the generated masks are inevitably different from the ground truth, and these dissimilarities are not handled reasonably during the network training, resulting in the subpar performance of the segmentation model. To tackle this issue, we propose a framework named DoNuSeg, enabling \textbf{D}ynamic pseudo label \textbf{O}ptimization in point-supervised \textbf{Nu}clei \textbf{Seg}mentation. Specifically, DoNuSeg takes advantage of class activation maps (CAMs) to adaptively capture regions with semantics similar to annotated points. To leverage semantic diversity in the hierarchical feature levels, we design a dynamic selection module to choose the optimal one among CAMs from different encoder blocks as pseudo masks. Meanwhile, a CAM-guided contrastive module is proposed to further enhance the accuracy of pseudo masks. In addition to exploiting the semantic information provided by CAMs, we consider location priors inherent to point labels, developing a task-decoupled structure for effectively differentiating nuclei. Extensive experiments demonstrate that DoNuSeg outperforms state-of-the-art point-supervised methods. The code is available at https://github.com/shinning0821/MICCAI24-DoNuSeg.
Authors: Wenwu Yang, Jinyi Yu, Tuo Chen, Zhenguang Liu, Xun Wang, Jianbing Shen
Abstract: Effective expression feature representations generated by a triplet-based deep metric learning are highly advantageous for facial expression recognition (FER). The performance of triplet-based deep metric learning is contingent upon identifying the best threshold for triplet loss. Threshold validation, however, is tough and challenging, as the ideal threshold changes among datasets and even across classes within the same dataset. In this paper, we present the multi-threshold deep metric learning technique, which not only avoids the difficult threshold validation but also vastly increases the capacity of triplet loss learning to construct expression feature representations. We find that each threshold of the triplet loss intrinsically determines a distinctive distribution of inter-class variations and corresponds, thus, to a unique expression feature representation. Therefore, rather than selecting a single optimal threshold from a valid threshold range, we thoroughly sample thresholds across the range, allowing the representation characteristics manifested by thresholds within the range to be fully extracted and leveraged for FER. To realize this approach, we partition the embedding layer of the deep metric learning network into a collection of slices and model training these embedding slices as an end-to-end multi-threshold deep metric learning problem. Each embedding slice corresponds to a sample threshold and is learned by enforcing the corresponding triplet loss, yielding a set of distinct expression features, one for each embedding slice. It makes the embedding layer, which is composed of a set of slices, a more informative and discriminative feature, hence enhancing the FER accuracy. Extensive evaluations demonstrate the superior performance of the proposed approach on both posed and spontaneous facial expression datasets.
Authors: Shilei Cao, Yan Liu, Juepeng Zheng, Weijia Li, Runmin Dong, Haohuan Fu
Abstract: For real-world applications, neural network models are commonly deployed in dynamic environments, where the distribution of the target domain undergoes temporal changes. Continual Test-Time Adaptation (CTTA) has recently emerged as a promising technique to gradually adapt a source-trained model to test data drawn from a continually changing target domain. Despite recent advancements in addressing CTTA, two critical issues remain: 1) The use of a fixed threshold for pseudo-labeling in existing methodologies leads to the generation of low-quality pseudo-labels, as model confidence varies across categories and domains; 2) While current solutions utilize stochastic parameter restoration to mitigate catastrophic forgetting, their capacity to preserve critical information is undermined by its intrinsic randomness. To tackle these challenges, we present CTAOD, aiming to enhance the performance of detection models in CTTA scenarios. Inspired by prior CTTA works for effective adaptation, CTAOD is founded on the mean-teacher framework, characterized by three core components. Firstly, the object-level contrastive learning module tailored for object detection extracts object-level features using the teacher's region of interest features and optimizes them through contrastive learning. Secondly, the dynamic threshold strategy updates the category-specific threshold based on predicted confidence scores to improve the quality of pseudo-labels. Lastly, we design a data-driven stochastic restoration mechanism to selectively reset inactive parameters using the gradients as weights for a random mask matrix, thereby ensuring the retention of essential knowledge. We demonstrate the effectiveness of our approach on four CTTA tasks for object detection, where CTAOD outperforms existing methods, especially achieving a 3.0 mAP improvement on the Cityscapes-to-Cityscapes-C CTTA task.
Authors: Qu Yang, Mang Ye, Bo Du
Abstract: Multi-modal large language models (MLLMs) have achieved remarkable performance on objective multimodal perception tasks, but their ability to interpret subjective, emotionally nuanced multimodal content remains largely unexplored. Thus, it impedes their ability to effectively understand and react to the intricate emotions expressed by humans through multimodal media. To bridge this gap, we introduce EmoBench, the first comprehensive benchmark designed specifically to evaluate the emotional capabilities of MLLMs across five popular emotional tasks, using a diverse dataset of 287k images and videos paired with corresponding textual instructions. Meanwhile, we propose EmoLLM, a novel model for multimodal emotional understanding, incorporating with two core techniques. 1) Multi-perspective Visual Projection, it captures diverse emotional cues from visual data from multiple perspectives. 2) EmoPrompt, it guides MLLMs to reason about emotions in the correct direction. Experimental results demonstrate that EmoLLM significantly elevates multimodal emotional understanding performance, with an average improvement of 12.1% across multiple foundation models on EmoBench. Our work contributes to the advancement of MLLMs by facilitating a deeper and more nuanced comprehension of intricate human emotions, paving the way for the development of artificial emotional intelligence capabilities with wide-ranging applications in areas such as human-computer interaction, mental health support, and empathetic AI systems. Code, data, and model will be released.
Authors: Mingrui Wu, Jiayi Ji, Oucheng Huang, Jiale Li, Yuhang Wu, Xiaoshuai Sun, Rongrong Ji
Abstract: The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations, which can be easily alleviated by introducing object detectors. However, these efforts neglect hallucinations in inter-object relationships, which is essential for visual comprehension. In this work, we introduce R-Bench, a novel benchmark for evaluating Vision Relationship Hallucination. R-Bench features image-level questions that focus on the existence of relationships and instance-level questions that assess local visual comprehension. We identify three types of relationship co-occurrences that lead to hallucinations: relationship-relationship, subject-relationship, and relationship-object. The visual instruction tuning dataset's long-tail distribution significantly impacts LVLMs' understanding of visual relationships. Furthermore, our analysis reveals that current LVLMs tend to disregard visual content and overly rely on the common sense knowledge of Large Language Models. They also struggle with reasoning about spatial relationships based on contextual information.
Authors: Junxiong Lin, Zeng Tao, Xuan Tong, Xinji Mai, Haoran Wang, Boyang Wang, Yan Wang, Qing Zhao, Jiawen Yu, Yuxuan Lin, Shaoqi Yan, Shuyong Gao, Wenqiang Zhang
Abstract: The problem of blind image super-resolution aims to recover high-resolution (HR) images from low-resolution (LR) images with unknown degradation modes. Most existing methods model the image degradation process using blur kernels. However, this explicit modeling approach struggles to cover the complex and varied degradation processes encountered in the real world, such as high-order combinations of JPEG compression, blur, and noise. Implicit modeling for the degradation process can effectively overcome this issue, but a key challenge of implicit modeling is the lack of accurate ground truth labels for the degradation process to conduct supervised training. To overcome this limitations inherent in implicit modeling, we propose an \textbf{U}ncertainty-based degradation representation for blind \textbf{S}uper-\textbf{R}esolution framework (\textbf{USR}). By suppressing the uncertainty of local degradation representations in images, USR facilitated self-supervised learning of degradation representations. The USR consists of two components: Adaptive Uncertainty-Aware Degradation Extraction (AUDE) and a feature extraction network composed of Variable Depth Dynamic Convolution (VDDC) blocks. To extract Uncertainty-based Degradation Representation from LR images, the AUDE utilizes the Self-supervised Uncertainty Contrast module with Uncertainty Suppression Loss to suppress the inherent model uncertainty of the Degradation Extractor. Furthermore, VDDC block integrates degradation information through dynamic convolution. Rhe VDDC also employs an Adaptive Intensity Scaling operation that adaptively adjusts the degradation representation according to the network hierarchy, thereby facilitating the effective integration of degradation information. Quantitative and qualitative experiments affirm the superiority of our approach.
Authors: Haoran Wang, Xinji Mai, Zeng Tao, Xuan Tong, Junxiong Lin, Yan Wang, Jiawen Yu, Boyang Wang, Shaoqi Yan, Qing Zhao, Ziheng Zhou, Shuyong Gao, Wenqiang Zhang
Abstract: The contemporary state-of-the-art of Dynamic Facial Expression Recognition (DFER) technology facilitates remarkable progress by deriving emotional mappings of facial expressions from video content, underpinned by training on voluminous datasets. Yet, the DFER datasets encompass a substantial volume of noise data. Noise arises from low-quality captures that defy logical labeling, and instances that suffer from mislabeling due to annotation bias, engendering two principal types of uncertainty: the uncertainty regarding data usability and the uncertainty concerning label reliability. Addressing the two types of uncertainty, we have meticulously crafted a two-stage framework aiming at \textbf{S}eeking \textbf{C}ertain data \textbf{I}n extensive \textbf{U}ncertain data (SCIU). This initiative aims to purge the DFER datasets of these uncertainties, thereby ensuring that only clean, verified data is employed in training processes. To mitigate the issue of low-quality samples, we introduce the Coarse-Grained Pruning (CGP) stage, which assesses sample weights and prunes those deemed unusable due to their low weight. For samples with incorrect annotations, the Fine-Grained Correction (FGC) stage evaluates prediction stability to rectify mislabeled data. Moreover, SCIU is conceived as a universally compatible, plug-and-play framework, tailored to integrate seamlessly with prevailing DFER methodologies. Rigorous experiments across prevalent DFER datasets and against numerous benchmark methods substantiates SCIU's capacity to markedly elevate performance metrics.
Authors: Shuwei Shi, Wenbo Li, Yuechen Zhang, Jingwen He, Biao Gong, Yinqiang Zheng
Abstract: Diffusion models excel at producing high-quality images; however, scaling to higher resolutions, such as 4K, often results in over-smoothed content, structural distortions, and repetitive patterns. To this end, we introduce ResMaster, a novel, training-free method that empowers resolution-limited diffusion models to generate high-quality images beyond resolution restrictions. Specifically, ResMaster leverages a low-resolution reference image created by a pre-trained diffusion model to provide structural and fine-grained guidance for crafting high-resolution images on a patch-by-patch basis. To ensure a coherent global structure, ResMaster meticulously aligns the low-frequency components of high-resolution patches with the low-resolution reference at each denoising step. For fine-grained guidance, tailored image prompts based on the low-resolution reference and enriched textual prompts produced by a vision-language model are incorporated. This approach could significantly mitigate local pattern distortions and improve detail refinement. Extensive experiments validate that ResMaster sets a new benchmark for high-resolution image generation and demonstrates promising efficiency. The project page is https://shuweis.github.io/ResMaster .
Authors: Aiwen Jiang, Zhi Wei, Long Peng, Feiqiang Liu, Wenbo Li, Mingwen Wang
Abstract: Image super-resolution pursuits reconstructing high-fidelity high-resolution counterpart for low-resolution image. In recent years, diffusion-based models have garnered significant attention due to their capabilities with rich prior knowledge. The success of diffusion models based on general text prompts has validated the effectiveness of textual control in the field of text2image. However, given the severe degradation commonly presented in low-resolution images, coupled with the randomness characteristics of diffusion models, current models struggle to adequately discern semantic and degradation information within severely degraded images. This often leads to obstacles such as semantic loss, visual artifacts, and visual hallucinations, which pose substantial challenges for practical use. To address these challenges, this paper proposes to leverage degradation-aligned language prompt for accurate, fine-grained, and high-fidelity image restoration. Complementary priors including semantic content descriptions and degradation prompts are explored. Specifically, on one hand, image-restoration prompt alignment decoder is proposed to automatically discern the degradation degree of LR images, thereby generating beneficial degradation priors for image restoration. On the other hand, much richly tailored descriptions from pretrained multimodal large language model elicit high-level semantic priors closely aligned with human perception, ensuring fidelity control for image restoration. Comprehensive comparisons with state-of-the-art methods have been done on several popular synthetic and real-world benchmark datasets. The quantitative and qualitative analysis have demonstrated that the proposed method achieves a new state-of-the-art perceptual quality level, especially in real-world cases based on reference-free metrics.
Authors: Alvaro Lopez Pellicer, Kittipos Giatgong, Yi Li, Neeraj Suri, Plamen Angelov
Abstract: As the use of Deep Neural Networks (DNNs) becomes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges. The state-of-the-art offers discrete solutions aimed to tackle individual issues covering specific adversarial attack scenarios, classification or evolving learning. However, real-world systems need to be able to detect and recover from a wide range of adversarial attacks without sacrificing classification accuracy and to flexibly act in {\bf unseen} scenarios. In this paper, UNICAD, is proposed as a novel framework that integrates a variety of techniques to provide an adaptive solution. For the targeted image classification, UNICAD achieves accurate image classification, detects unseen classes, and recovers from adversarial attacks using Prototype and Similarity-based DNNs with denoising autoencoders. Our experiments performed on the CIFAR-10 dataset highlight UNICAD's effectiveness in adversarial mitigation and unseen class classification, outperforming traditional models.
Authors: Xiaowen Ma, Rongrong Lian, Zhenkai Wu, Hongbo Guo, Mengting Ma, Sensen Wu, Zhenhong Du, Siyang Song, Wei Zhang
Abstract: Remote sensing images usually characterized by complex backgrounds, scale and orientation variations, and large intra-class variance. General semantic segmentation methods usually fail to fully investigate the above issues, and thus their performances on remote sensing image segmentation are limited. In this paper, we propose our LOGCAN++, a semantic segmentation model customized for remote sensing images, which is made up of a Global Class Awareness (GCA) module and several Local Class Awareness (LCA) modules. The GCA module captures global representations for class-level context modeling to reduce the interference of background noise. The LCA module generates local class representations as intermediate perceptual elements to indirectly associate pixels with the global class representations, targeting at dealing with the large intra-class variance problem. In particular, we introduce affine transformations in the LCA module for adaptive extraction of local class representations to effectively tolerate scale and orientation variations in remotely sensed images. Extensive experiments on three benchmark datasets show that our LOGCAN++ outperforms current mainstream general and remote sensing semantic segmentation methods and achieves a better trade-off between speed and accuracy. Code is available at https://github.com/xwmaxwma/rssegmentation.
Authors: Theresa Follath, David Mickisch, Jan Hemmerling, Stefan Erasmi, Marcel Schwieder, Beg\"um Demir
Abstract: Using images acquired by different satellite sensors has shown to improve classification performance in the framework of crop mapping from satellite image time series (SITS). Existing state-of-the-art architectures use self-attention mechanisms to process the temporal dimension and convolutions for the spatial dimension of SITS. Motivated by the success of purely attention-based architectures in crop mapping from single-modal SITS, we introduce several multi-modal multi-temporal transformer-based architectures. Specifically, we investigate the effectiveness of Early Fusion, Cross Attention Fusion and Synchronized Class Token Fusion within the Temporo-Spatial Vision Transformer (TSViT). Experimental results demonstrate significant improvements over state-of-the-art architectures with both convolutional and self-attention components.
Authors: Zhaohui Chen, Elyas Asadi Shamsabadi, Sheng Jiang, Luming Shen, Daniel Dias-da-Costa
Abstract: Convolutional neural networks (CNNs) and Transformers have shown advanced accuracy in crack detection under certain conditions. Yet, the fixed local attention can compromise the generalisation of CNNs, and the quadratic complexity of the global self-attention restricts the practical deployment of Transformers. Given the emergence of the new-generation architecture of Mamba, this paper proposes a Vision Mamba (VMamba)-based framework for crack segmentation on concrete, asphalt, and masonry surfaces, with high accuracy, generalisation, and less computational complexity. Having 15.6% - 74.5% fewer parameters, the encoder-decoder network integrated with VMamba could obtain up to 2.8% higher mDS than representative CNN-based models while showing about the same performance as Transformer-based models. Moreover, the VMamba-based encoder-decoder network could process high-resolution image input with up to 90.6% lower floating-point operations.
Authors: Yirui Chen, Xudong Huang, Quan Zhang, Wei Li, Mingjian Zhu, Qiangyu Yan, Simiao Li, Hanting Chen, Hailin Hu, Jie Yang, Wei Liu, Jie Hu
Abstract: The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location(IMDL). However, the lack of a large-scale data foundation makes IMDL task unattainable. In this paper, a local manipulation pipeline is designed, incorporating the powerful SAM, ChatGPT and generative models. Upon this basis, We propose the GIM dataset, which has the following advantages: 1) Large scale, including over one million pairs of AI-manipulated images and real images. 2) Rich Image Content, encompassing a broad range of image classes 3) Diverse Generative Manipulation, manipulated images with state-of-the-art generators and various manipulation tasks. The aforementioned advantages allow for a more comprehensive evaluation of IMDL methods, extending their applicability to diverse images. We introduce two benchmark settings to evaluate the generalization capability and comprehensive performance of baseline methods. In addition, we propose a novel IMDL framework, termed GIMFormer, which consists of a ShadowTracer, Frequency-Spatial Block (FSB), and a Multi-window Anomalous Modelling (MWAM) Module. Extensive experiments on the GIM demonstrate that GIMFormer surpasses previous state-of-the-art works significantly on two different benchmarks.
Authors: Yuhang Ma, Wenting Xu, Jiji Tang, Qinfeng Jin, Rongsheng Zhang, Zeng Zhao, Changjie Fan, Zhipeng Hu
Abstract: Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have encountered challenges in preserving characters with high-fidelity consistency due to inadequate feature extraction and concept confusion of reference characters. Therefore, we propose Character-Adapter, a plug-and-play framework designed to generate images that preserve the details of reference characters, ensuring high-fidelity consistency. Character-Adapter employs prompt-guided segmentation to ensure fine-grained regional features of reference characters and dynamic region-level adapters to mitigate concept confusion. Extensive experiments are conducted to validate the effectiveness of Character-Adapter. Both quantitative and qualitative results demonstrate that Character-Adapter achieves the state-of-the-art performance of consistent character generation, with an improvement of 24.8% compared with other methods
Authors: Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski
Abstract: Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to those corruptions but may harm performance on clean images and other types of distortion. In this paper, we introduce an alternative approach that improves the robustness of DNNs to a wide range of corruptions without compromising accuracy on clean images. We first demonstrate that input perturbations can be mimicked by multiplicative perturbations in the weight space. Leveraging this, we propose Data Augmentation via Multiplicative Perturbation (DAMP), a training method that optimizes DNNs under random multiplicative weight perturbations. We also examine the recently proposed Adaptive Sharpness-Aware Minimization (ASAM) and show that it optimizes DNNs under adversarial multiplicative weight perturbations. Experiments on image classification datasets (CIFAR-10/100, TinyImageNet and ImageNet) and neural network architectures (ResNet50, ViT-S/16) show that DAMP enhances model generalization performance in the presence of corruptions across different settings. Notably, DAMP is able to train a ViT-S/16 on ImageNet from scratch, reaching the top-1 error of 23.7% which is comparable to ResNet50 without extensive data augmentations.
Authors: Ivan Kirillov, Denis Parkhomenko, Kirill Chernyshev, Alexander Pletnev, Yibo Shi, Kai Lin, Dmitry Babin
Abstract: Learned video compression methods already outperform VVC in the low-delay (LD) case, but the random-access (RA) scenario remains challenging. Most works on learned RA video compression either use HEVC as an anchor or compare it to VVC in specific test conditions, using RGB-PSNR metric instead of Y-PSNR and avoiding comprehensive evaluation. Here, we present an end-to-end learned video codec for random access that combines training on long sequences of frames, rate allocation designed for hierarchical coding and content adaptation on inference. We show that under common test conditions (JVET-CTC), it achieves results comparable to VTM (VVC reference software) in terms of YUV-PSNR BD-Rate on some classes of videos, and outperforms it on almost all test sets in terms of VMAF BD-Rate. On average it surpasses open LD and RA end-to-end solutions in terms of VMAF and YUV BD-Rates.
Authors: Zhiyu Tan, Xiaomeng Yang, Luozheng Qin, Mengping Yang, Cheng Zhang, Hao Li
Abstract: The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics that can guide the optimization of the models. In this paper, we propose EvalAlign, a metric characterized by its accuracy, stability, and fine granularity. Our approach leverages the capabilities of Multimodal Large Language Models (MLLMs) pre-trained on extensive datasets. We develop evaluation protocols that focus on two key dimensions: image faithfulness and text-image alignment. Each protocol comprises a set of detailed, fine-grained instructions linked to specific scoring options, enabling precise manual scoring of the generated images. We Supervised Fine-Tune (SFT) the MLLM to align closely with human evaluative judgments, resulting in a robust evaluation model. Our comprehensive tests across 24 text-to-image generation models demonstrate that EvalAlign not only provides superior metric stability but also aligns more closely with human preferences than existing metrics, confirming its effectiveness and utility in model assessment.
Authors: Yirui Chen, Pengjin Wei, Zhenhuan Liu, Bingchao Wang, Jie Yang, Wei Liu
Abstract: Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume and a 2D encoder-decoder structure to conduct traversability classification instead of the widely used 3D convolutions. This results in less computational cost while even better performance is achieved at the same time. We then propose a new spatio-temporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds, and this makes our module able to assess distant areas more accurately. Comprehensive experimental results on augmented Semantic KITTI and RELLIS-3D datasets show that our method is able to achieve superior performance over existing approaches both quantitatively and quantitatively.
Authors: Alexandre Fournier-Mongieux, Michael Soumm, Adrian Popescu, Bertrand Luvison, Herv\'e Le Borgne
Abstract: Face recognition and verification are two computer vision tasks whose performance has progressed with the introduction of deep representations. However, ethical, legal, and technical challenges due to the sensitive character of face data and biases in real training datasets hinder their development. Generative AI addresses privacy by creating fictitious identities, but fairness problems persist. We promote fairness by introducing a demographic attributes balancing mechanism in generated training datasets. We experiment with an existing real dataset, three generated training datasets, and the balanced versions of a diffusion-based dataset. We propose a comprehensive evaluation that considers accuracy and fairness equally and includes a rigorous regression-based statistical analysis of attributes. The analysis shows that balancing reduces demographic unfairness. Also, a performance gap persists despite generation becoming more accurate with time. The proposed balancing method and comprehensive verification evaluation promote fairer and transparent face recognition and verification.
Authors: Muhammad Mohsin, Xianlai Zeng, Stefano Rovetta, Francesco Masulli
Abstract: The waste of electrical and electronic equipment has been increased due to the fast evolution of technology products and competition of many IT sectors. Every year millions of tons of electronic waste are thrown into the environment which causes high consequences for human health. Therefore, it is crucial to control this waste flow using technology, especially using Artificial Intelligence but also reclamation of critical raw materials for new production processes. In this paper, we focused on the measurement of recyclability of waste electronic components (WECs) from waste printed circuit boards (WPCBs) using mathematical innovation model. This innovative approach evaluates both the recyclability and recycling difficulties of WECs, integrating an AI model for improved disassembly and sorting. Assessing the recyclability of individual electronic components present on WPCBs provides insight into the recovery potential of valuable materials and indicates the level of complexity involved in recycling in terms of economic worth and production utility. This novel measurement approach helps AI models in accurately determining the number of classes to be identified and sorted during the automated disassembly of discarded PCBs. It also facilitates the model in iterative training and validation of individual electronic components.
Authors: Sifan Wu, Zhenguang Liu, Beibei Zhang, Roger Zimmermann, Zhongjie Ba, Xiaosong Zhang, Kui Ren
Abstract: Human motion copy is an intriguing yet challenging task in artificial intelligence and computer vision, which strives to generate a fake video of a target person performing the motion of a source person. The problem is inherently challenging due to the subtle human-body texture details to be generated and the temporal consistency to be considered. Existing approaches typically adopt a conventional GAN with an L1 or L2 loss to produce the target fake video, which intrinsically necessitates a large number of training samples that are challenging to acquire. Meanwhile, current methods still have difficulties in attaining realistic image details and temporal consistency, which unfortunately can be easily perceived by human observers. Motivated by this, we try to tackle the issues from three aspects: (1) We constrain pose-to-appearance generation with a perceptual loss and a theoretically motivated Gromov-Wasserstein loss to bridge the gap between pose and appearance. (2) We present an episodic memory module in the pose-to-appearance generation to propel continuous learning that helps the model learn from its past poor generations. We also utilize geometrical cues of the face to optimize facial details and refine each key body part with a dedicated local GAN. (3) We advocate generating the foreground in a sequence-to-sequence manner rather than a single-frame manner, explicitly enforcing temporal inconsistency. Empirical results on five datasets, iPER, ComplexMotion, SoloDance, Fish, and Mouse datasets, demonstrate that our method is capable of generating realistic target videos while precisely copying motion from a source video. Our method significantly outperforms state-of-the-art approaches and gains 7.2% and 12.4% improvements in PSNR and FID respectively.
Authors: Sishun Pan, Tingmin Li, Yang Yang
Abstract: In this paper, we introduce our approach to the 5th CLVision Challenge, which presents distinctive challenges beyond traditional class incremental learning. Unlike standard settings, this competition features the recurrence of previously encountered classes and includes unlabeled data that may contain Out-of-Distribution (OOD) categories. Our approach is based on Winning Subnetworks to allocate independent parameter spaces for each task addressing the catastrophic forgetting problem in class incremental learning and employ three training strategies: supervised classification learning, unsupervised contrastive learning, and pseudo-label classification learning to fully utilize the information in both labeled and unlabeled data, enhancing the classification performance of each subnetwork. Furthermore, during the inference stage, we have devised an interaction strategy between subnetworks, where the prediction for a specific class of a particular sample is the average logits across different subnetworks corresponding to that class, leveraging the knowledge learned from different subnetworks on recurring classes to improve classification accuracy. These strategies can be simultaneously applied to the three scenarios of the competition, effectively solving the difficulties in the competition scenarios. Experimentally, our method ranks first in both the pre-selection and final evaluation stages, with an average accuracy of 0.4535 during the preselection stage and an average accuracy of 0.4805 during the final evaluation stage.
Authors: Lu Zhang, Tiancheng Zhao, Heting Ying, Yibo Ma, Kyusong Lee
Abstract: Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding. However, processing extensive videos such as 24-hour CCTV footage or full-length films presents significant challenges due to the vast data and processing demands. Traditional methods, like extracting key frames or converting frames to text, often result in substantial information loss. To address these shortcomings, we develop OmAgent, efficiently stores and retrieves relevant video frames for specific queries, preserving the detailed content of videos. Additionally, it features an Divide-and-Conquer Loop capable of autonomous reasoning, dynamically invoking APIs and tools to enhance query processing and accuracy. This approach ensures robust video understanding, significantly reducing information loss. Experimental results affirm OmAgent's efficacy in handling various types of videos and complex tasks. Moreover, we have endowed it with greater autonomy and a robust tool-calling system, enabling it to accomplish even more intricate tasks.
Authors: Jianning Deng, Kartic Subr, Hakan Bilen
Abstract: We propose a novel unsupervised method to learn the pose and part-segmentation of articulated objects with rigid parts. Given two observations of an object in different articulation states, our method learns the geometry and appearance of object parts by using an implicit model from the first observation, distils the part segmentation and articulation from the second observation while rendering the latter observation. Additionally, to tackle the complexities in the joint optimization of part segmentation and articulation, we propose a voxel grid-based initialization strategy and a decoupled optimization procedure. Compared to the prior unsupervised work, our model obtains significantly better performance, and generalizes to objects with multiple parts while it can be efficiently from few views for the latter observation.
Authors: Yuming Zhang, Shouxin Zhang, Peizhe Wang, Feiyu Zhu, Dongzhi Guan, Jiabin Liu, Changpeng Cai
Abstract: End-to-end (E2E) training approaches are commonly plagued by high memory consumption, reduced efficiency in training, challenges in model parallelization, and suboptimal biocompatibility. Local learning is considered a novel interactive training method that holds promise as an alternative to E2E. Nonetheless, conventional local learning methods fall short in achieving high model accuracy due to inadequate local inter-module interactions. In this paper, we introduce a new model known as the Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network (MLAAN). MLAAN features an innovative supervised local learning approach coupled with a robust reinforcement module. This dual-component design enables the MLAAN to integrate smoothly with established local learning techniques, thereby enhancing the efficacy of the foundational methods. The method simultaneously acquires the local and global features of the model separately by constructing an independent auxiliary network and a cascade auxiliary network on the one hand and incorporates a leap augmented module, which serves to counteract the reduced learning capacity often associated with weaker supervision. This architecture not only augments the exchange of information amongst the local modules but also effectively mitigates the model's tendency toward myopia. The experimental evaluations conducted on four benchmark datasets, CIFAR-10, STL-10, SVHN, and ImageNet, demonstrate that the integration of MLAAN with existing supervised local learning methods significantly enhances the original methodologies. Of particular note, MLAAN enables local learning methods to comprehensively outperform end-to-end training approaches in terms of optimal performance while saving GPU memory.
Authors: Mohammad Belal (Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates), Taimur Hassan (Abu Dhabi University, Abu Dhabi, United Arab Emirates), Abdelfatah Ahmed (Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates), Ahmad Aljarah (Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates), Nael Alsheikh (Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates), Irfan Hussain (Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates)
Abstract: Human activity recognition (HAR) is a crucial area of research that involves understanding human movements using computer and machine vision technology. Deep learning has emerged as a powerful tool for this task, with models such as Convolutional Neural Networks (CNNs) and Transformers being employed to capture various aspects of human motion. One of the key contributions of this work is the demonstration of the effectiveness of feature fusion in improving HAR accuracy by capturing spatial and temporal features, which has important implications for the development of more accurate and robust activity recognition systems. The study uses sensory data from HuGaDB, PKU-MMD, LARa, and TUG datasets. Two model, the PO-MS-GCN and a Transformer were trained and evaluated, with PO-MS-GCN outperforming state-of-the-art models. HuGaDB and TUG achieved high accuracies and f1-scores, while LARa and PKU-MMD had lower scores. Feature fusion improved results across datasets.
Authors: Jun Fu, Wei Zhou, Qiuping Jiang, Hantao Liu, Guangtao Zhai
Abstract: Recently, textual prompt tuning has shown inspirational performance in adapting Contrastive Language-Image Pre-training (CLIP) models to natural image quality assessment. However, such uni-modal prompt learning method only tunes the language branch of CLIP models. This is not enough for adapting CLIP models to AI generated image quality assessment (AGIQA) since AGIs visually differ from natural images. In addition, the consistency between AGIs and user input text prompts, which correlates with the perceptual quality of AGIs, is not investigated to guide AGIQA. In this letter, we propose vision-language consistency guided multi-modal prompt learning for blind AGIQA, dubbed CLIP-AGIQA. Specifically, we introduce learnable textual and visual prompts in language and vision branches of CLIP models, respectively. Moreover, we design a text-to-image alignment quality prediction task, whose learned vision-language consistency knowledge is used to guide the optimization of the above multi-modal prompts. Experimental results on two public AGIQA datasets demonstrate that the proposed method outperforms state-of-the-art quality assessment models. The source code is available at https://github.com/JunFu1995/CLIP-AGIQA.
Authors: Min-Seop Kwak, Donghoon Ahn, Ines Hyeonsu Kim, Jin-wha Kim, Seungryong Kim
Abstract: Score distillation sampling (SDS), the methodology in which the score from pretrained 2D diffusion models is distilled into 3D representation, has recently brought significant advancements in text-to-3D generation task. However, this approach is still confronted with critical geometric inconsistency problems such as the Janus problem. Starting from a hypothesis that such inconsistency problems may be induced by multiview inconsistencies between 2D scores predicted from various viewpoints, we introduce GSD, a simple and general plug-and-play framework for incorporating 3D consistency and therefore geometry awareness into the SDS process. Our methodology is composed of three components: 3D consistent noising, designed to produce 3D consistent noise maps that perfectly follow the standard Gaussian distribution, geometry-based gradient warping for identifying correspondences between predicted gradients of different viewpoints, and novel gradient consistency loss to optimize the scene geometry toward producing more consistent gradients. We demonstrate that our method significantly improves performance, successfully addressing the geometric inconsistency problems in text-to-3D generation task with minimal computation cost and being compatible with existing score distillation-based models. Our project page is available at https://ku-cvlab.github.io/GSD/.
Authors: Jinkun Hao, Junshu Tang, Jiangning Zhang, Ran Yi, Yijia Hong, Moran Li, Weijian Cao, Yating Wang, Lizhuang Ma
Abstract: While recent works have achieved great success on one-shot 3D common object generation, high quality and fidelity 3D head generation from a single image remains a great challenge. Previous text-based methods for generating 3D heads were limited by text descriptions and image-based methods struggled to produce high-quality head geometry. To handle this challenging problem, we propose a novel framework, Portrait3D, to generate high-quality 3D heads while preserving their identities. Our work incorporates the identity information of the portrait image into three parts: 1) geometry initialization, 2) geometry sculpting, and 3) texture generation stages. Given a reference portrait image, we first align the identity features with text features to realize ID-aware guidance enhancement, which contains the control signals representing the face information. We then use the canny map, ID features of the portrait image, and a pre-trained text-to-normal/depth diffusion model to generate ID-aware geometry supervision, and 3D-GAN inversion is employed to generate ID-aware geometry initialization. Furthermore, with the ability to inject identity information into 3D head generation, we use ID-aware guidance to calculate ID-aware Score Distillation (ISD) for geometry sculpting. For texture generation, we adopt the ID Consistent Texture Inpainting and Refinement which progressively expands the view for texture inpainting to obtain an initialization UV texture map. We then use the id-aware guidance to provide image-level supervision for noisy multi-view images to obtain a refined texture map. Extensive experiments demonstrate that we can generate high-quality 3D heads with accurate geometry and texture from single in-the-wild portrait images. The project page is at https://jinkun-hao.github.io/Portrait3D/.
Authors: Yizheng Wu, Zhiyu Pan, Kewei Wang, Xingyi Li, Jiahao Cui, Liwen Xiao, Guosheng Lin, Zhiguo Cao
Abstract: Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches. Code is available: https://github.com/W1zheng/InsTeacher3D.
Authors: Abhi Kamboj
Abstract: The transformer neural network architecture allows for autoregressive sequence-to-sequence modeling through the use of attention layers. It was originally created with the application of machine translation but has revolutionized natural language processing. Recently, transformers have also been applied across a wide variety of pattern recognition tasks, particularly in computer vision. In this literature review, we describe major advances in computer vision utilizing transformers. We then focus specifically on Multi-Object Tracking (MOT) and discuss how transformers are increasingly becoming competitive in state-of-the-art MOT works, yet still lag behind traditional deep learning methods.
Authors: Yufei Liu, Junshu Tang, Chu Zheng, Shijie Zhang, Jinkun Hao, Junwei Zhu, Dongjin Huang
Abstract: High-fidelity 3D garment synthesis from text is desirable yet challenging for digital avatar creation. Recent diffusion-based approaches via Score Distillation Sampling (SDS) have enabled new possibilities but either intricately couple with human body or struggle to reuse. We introduce ClotheDreamer, a 3D Gaussian-based method for generating wearable, production-ready 3D garment assets from text prompts. We propose a novel representation Disentangled Clothe Gaussian Splatting (DCGS) to enable separate optimization. DCGS represents clothed avatar as one Gaussian model but freezes body Gaussian splats. To enhance quality and completeness, we incorporate bidirectional SDS to supervise clothed avatar and garment RGBD renderings respectively with pose conditions and propose a new pruning strategy for loose clothing. Our approach can also support custom clothing templates as input. Benefiting from our design, the synthetic 3D garment can be easily applied to virtual try-on and support physically accurate animation. Extensive experiments showcase our method's superior and competitive performance. Our project page is at https://ggxxii.github.io/clothedreamer.
Authors: Zixuan Li
Abstract: This paper explores the application of the GPT-4V(ision) large visual language model to autonomous driving in mining environments, where traditional systems often falter in understanding intentions and making accurate decisions during emergencies. GPT-4V introduces capabilities for visual question answering and complex scene comprehension, addressing challenges in these specialized settings.Our evaluation focuses on its proficiency in scene understanding, reasoning, and driving functions, with specific tests on its ability to recognize and interpret elements such as pedestrians, various vehicles, and traffic devices. While GPT-4V showed robust comprehension and decision-making skills, it faced difficulties in accurately identifying specific vehicle types and managing dynamic interactions. Despite these challenges, its effective navigation and strategic decision-making demonstrate its potential as a reliable agent for autonomous driving in the complex conditions of mining environments, highlighting its adaptability and operational viability in industrial settings.
Authors: Xiaohao Xu, Tianyi Zhang, Sibo Wang, Xiang Li, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Xiaonan Huang
Abstract: Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy. While real-world datasets are invaluable, simulation-based benchmarks offer a scalable approach for robustness evaluations. However, the creation of a challenging and controllable noisy world with diverse perturbations remains under-explored. To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations. The pipeline comprises a comprehensive taxonomy of sensor and motion perturbations for embodied multi-modal (specifically RGB-D) sensing, categorized by their sources and propagation order, allowing for procedural composition. We also provide a toolbox for synthesizing these perturbations, enabling the transformation of clean environments into challenging noisy simulations. Utilizing the pipeline, we instantiate the large-scale Noisy-Replica benchmark, which includes diverse perturbation types, to evaluate the risk tolerance of existing advanced RGB-D SLAM models. Our extensive analysis uncovers the susceptibilities of both neural (NeRF and Gaussian Splatting -based) and non-neural SLAM models to disturbances, despite their demonstrated accuracy in standard benchmarks. Our code is publicly available at https://github.com/Xiaohao-Xu/SLAM-under-Perturbation.
URLs: https://github.com/Xiaohao-Xu/SLAM-under-Perturbation.
Authors: Peiyuan Zhang, Kaichen Zhang, Bo Li, Guangtao Zeng, Jingkang Yang, Yuanhan Zhang, Ziyue Wang, Haoran Tan, Chunyuan Li, Ziwei Liu
Abstract: Video sequences offer valuable temporal information, but existing large multimodal models (LMMs) fall short in understanding extremely long videos. Many works address this by reducing the number of visual tokens using visual resamplers. Alternatively, in this paper, we approach this problem from the perspective of the language model. By simply extrapolating the context length of the language backbone, we enable LMMs to comprehend orders of magnitude more visual tokens without any video training. We call this phenomenon long context transfer and carefully ablate its properties. To effectively measure LMMs' ability to generalize to long contexts in the vision modality, we develop V-NIAH (Visual Needle-In-A-Haystack), a purely synthetic long vision benchmark inspired by the language model's NIAH test. Our proposed Long Video Assistant (LongVA) can process 2000 frames or over 200K visual tokens without additional complexities. With its extended context length, LongVA achieves state-of-the-art performance on Video-MME among 7B-scale models by densely sampling more input frames. Our work is open-sourced at https://github.com/EvolvingLMMs-Lab/LongVA.
Authors: Yuang Peng, Yuxin Cui, Haomiao Tang, Zekun Qi, Runpei Dong, Jing Bai, Chunrui Han, Zheng Ge, Xiangyu Zhang, Shu-Tao Xia
Abstract: Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive function in creatively generating personalized content. However, current evaluations either are automated but misalign with humans or require human evaluations that are time-consuming and expensive. In this work, we present DreamBench++, a human-aligned benchmark automated by advanced multimodal GPT models. Specifically, we systematically design the prompts to let GPT be both human-aligned and self-aligned, empowered with task reinforcement. Further, we construct a comprehensive dataset comprising diverse images and prompts. By benchmarking 7 modern generative models, we demonstrate that DreamBench++ results in significantly more human-aligned evaluation, helping boost the community with innovative findings.
Authors: Shengbang Tong, Ellis Brown, Penghao Wu, Sanghyun Woo, Manoj Middepogu, Sai Charitha Akula, Jihan Yang, Shusheng Yang, Adithya Iyer, Xichen Pan, Austin Wang, Rob Fergus, Yann LeCun, Saining Xie
Abstract: We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design choices for vision components are often insufficiently explored and disconnected from visual representation learning research. This gap hinders accurate sensory grounding in real-world scenarios. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations, offering new insights into different models and architectures -- self-supervised, strongly supervised, or combinations thereof -- based on experiments with over 20 vision encoders. We critically examine existing MLLM benchmarks, addressing the difficulties involved in consolidating and interpreting results from various tasks, and introduce a new vision-centric benchmark, CV-Bench. To further improve visual grounding, we propose the Spatial Vision Aggregator (SVA), a dynamic and spatially-aware connector that integrates high-resolution vision features with LLMs while reducing the number of tokens. Additionally, we discuss the curation of high-quality visual instruction-tuning data from publicly available sources, emphasizing the importance of data source balancing and distribution ratio. Collectively, Cambrian-1 not only achieves state-of-the-art performance but also serves as a comprehensive, open cookbook for instruction-tuned MLLMs. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes. We hope our release will inspire and accelerate advancements in multimodal systems and visual representation learning.
Authors: Haonan Qiu, Zhaoxi Chen, Zhouxia Wang, Yingqing He, Menghan Xia, Ziwei Liu
Abstract: Diffusion model has demonstrated remarkable capability in video generation, which further sparks interest in introducing trajectory control into the generation process. While existing works mainly focus on training-based methods (e.g., conditional adapter), we argue that diffusion model itself allows decent control over the generated content without requiring any training. In this study, we introduce a tuning-free framework to achieve trajectory-controllable video generation, by imposing guidance on both noise construction and attention computation. Specifically, 1) we first show several instructive phenomenons and analyze how initial noises influence the motion trajectory of generated content. 2) Subsequently, we propose FreeTraj, a tuning-free approach that enables trajectory control by modifying noise sampling and attention mechanisms. 3) Furthermore, we extend FreeTraj to facilitate longer and larger video generation with controllable trajectories. Equipped with these designs, users have the flexibility to provide trajectories manually or opt for trajectories automatically generated by the LLM trajectory planner. Extensive experiments validate the efficacy of our approach in enhancing the trajectory controllability of video diffusion models.
Authors: Chongjie Ye, Lingteng Qiu, Xiaodong Gu, Qi Zuo, Yushuang Wu, Zilong Dong, Liefeng Bo, Yuliang Xiu, Xiaoguang Han
Abstract: This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized by repurposing diffusion priors. However, previous attempts still struggle with stochastic inference, conflicting with the deterministic nature of the Image2Normal task, and costly ensembling step, which slows down the estimation process. Our method, StableNormal, mitigates the stochasticity of the diffusion process by reducing inference variance, thus producing "Stable-and-Sharp" normal estimates without any additional ensembling process. StableNormal works robustly under challenging imaging conditions, such as extreme lighting, blurring, and low quality. It is also robust against transparent and reflective surfaces, as well as cluttered scenes with numerous objects. Specifically, StableNormal employs a coarse-to-fine strategy, which starts with a one-step normal estimator (YOSO) to derive an initial normal guess, that is relatively coarse but reliable, then followed by a semantic-guided refinement process (SG-DRN) that refines the normals to recover geometric details. The effectiveness of StableNormal is demonstrated through competitive performance in standard datasets such as DIODE-indoor, iBims, ScannetV2 and NYUv2, and also in various downstream tasks, such as surface reconstruction and normal enhancement. These results evidence that StableNormal retains both the "stability" and "sharpness" for accurate normal estimation. StableNormal represents a baby attempt to repurpose diffusion priors for deterministic estimation. To democratize this, code and models have been publicly available in hf.co/Stable-X
Authors: Jierun Chen, Fangyun Wei, Jinjing Zhao, Sizhe Song, Bohuai Wu, Zhuoxuan Peng, S. -H. Gary Chan, Hongyang Zhang
Abstract: Referring expression comprehension (REC) involves localizing a target instance based on a textual description. Recent advancements in REC have been driven by large multimodal models (LMMs) like CogVLM, which achieved 92.44% accuracy on RefCOCO. However, this study questions whether existing benchmarks such as RefCOCO, RefCOCO+, and RefCOCOg, capture LMMs' comprehensive capabilities. We begin with a manual examination of these benchmarks, revealing high labeling error rates: 14% in RefCOCO, 24% in RefCOCO+, and 5% in RefCOCOg, which undermines the authenticity of evaluations. We address this by excluding problematic instances and reevaluating several LMMs capable of handling the REC task, showing significant accuracy improvements, thus highlighting the impact of benchmark noise. In response, we introduce Ref-L4, a comprehensive REC benchmark, specifically designed to evaluate modern REC models. Ref-L4 is distinguished by four key features: 1) a substantial sample size with 45,341 annotations; 2) a diverse range of object categories with 365 distinct types and varying instance scales from 30 to 3,767; 3) lengthy referring expressions averaging 24.2 words; and 4) an extensive vocabulary comprising 22,813 unique words. We evaluate a total of 24 large models on Ref-L4 and provide valuable insights. The cleaned versions of RefCOCO, RefCOCO+, and RefCOCOg, as well as our Ref-L4 benchmark and evaluation code, are available at https://github.com/JierunChen/Ref-L4.
Authors: Jesse Atuhurra, Iqra Ali, Tatsuya Hiraoka, Hidetaka Kamigaito, Tomoya Iwakura, Taro Watanabe
Abstract: Large language models (LLMs) have increased interest in vision language models (VLMs), which process image-text pairs as input. Studies investigating the visual understanding ability of VLMs have been proposed, but such studies are still preliminary because existing datasets do not permit a comprehensive evaluation of the fine-grained visual linguistic abilities of VLMs across multiple languages. To further explore the strengths of VLMs, such as GPT-4V \cite{openai2023GPT4}, we developed new datasets for the systematic and qualitative analysis of VLMs. Our contribution is four-fold: 1) we introduced nine vision-and-language (VL) tasks (including object recognition, image-text matching, and more) and constructed multilingual visual-text datasets in four languages: English, Japanese, Swahili, and Urdu through utilizing templates containing \textit{questions} and prompting GPT4-V to generate the \textit{answers} and the \textit{rationales}, 2) introduced a new VL task named \textit{unrelatedness}, 3) introduced rationales to enable human understanding of the VLM reasoning process, and 4) employed human evaluation to measure the suitability of proposed datasets for VL tasks. We show that VLMs can be fine-tuned on our datasets. Our work is the first to conduct such analyses in Swahili and Urdu. Also, it introduces \textit{rationales} in VL analysis, which played a vital role in the evaluation.
Authors: Alexander Messick
Abstract: I explore the mathematical transformation that occurs in color coordinate space when physically mixing paints of two different colors. I tested 120 pairs of 16 paint colors and used a linear regression to find the most accurate combination of input parameters, both in RGB space and several other color spaces. I found that the fit with the strongest coefficient of determination was a geometrically symmetrized linear combination of the colors in CIEXYZ space, while this same mapping in RGB space returns a better mean squared error.
Authors: Xingjian Hu, Baole Wei, Liangcai Gao
Abstract: Text line detection is a key task in historical document analysis facing many challenges of arbitrary-shaped text lines, dense texts, and text lines with high aspect ratios, etc. In this paper, we propose a general framework for historical document text detection (SegHist), enabling existing segmentation-based text detection methods to effectively address the challenges, especially text lines with high aspect ratios. Integrating the SegHist framework with the commonly used method DB++, we develop DB-SegHist. This approach achieves \ac{SOTA} on the \ac{CHDAC}, MTHv2, and competitive results on \ac{HDRC} datasets, with a significant improvement of 1.19\% on the most challenging \ac{CHDAC} dataset which features more text lines with high aspect ratios. Moreover, our method attains \ac{SOTA} on rotated MTHv2 and rotated \ac{HDRC}, demonstrating its rotational robustness. The code is available at https://github.com/LumionHXJ/SegHist.
Authors: Asmail Muftah, S M Schirmer, Frank C Langbein
Abstract: Magnetic resonance imaging (MRI) has become a crucial tool in the diagnosis and staging of prostate cancer, owing to its superior tissue contrast. However, it also creates large volumes of data that must be assessed by trained experts, a time-consuming and laborious task. This has prompted the development of machine learning tools for the automation of Prostate cancer (PCa) risk classification based on multiple MRI modalities (T2W, ADC, and high-b-value DWI). Understanding and interpreting the predictions made by the models, however, remains a challenge. We analyze Random Forests (RF) and Support Vector Machines (SVM), for two complementary datasets, the public Prostate-X dataset, and an in-house, mostly early-stage PCa dataset to elucidate the contributions made by first-order statistical features, Haralick texture features, and local binary patterns to the classification. Using correlation analysis and Shapley impact scores, we find that many of the features typically used are strongly correlated, and that the majority of features have negligible impact on the classification. We identify a small set of features that determine the classification outcome, which may aid the development of explainable AI approaches.
Authors: Hyeyoon Lee, Kanghyun Choi, Dain Kwon, Sunjong Park, Mayoore Selvarasa Jaiswal, Noseong Park, Jonghyun Choi, Jinho Lee
Abstract: Recent advances in adversarial robustness rely on an abundant set of training data, where using external or additional datasets has become a common setting. However, in real life, the training data is often kept private for security and privacy issues, while only the pretrained weight is available to the public. In such scenarios, existing methods that assume accessibility to the original data become inapplicable. Thus we investigate the pivotal problem of data-free adversarial robustness, where we try to achieve adversarial robustness without accessing any real data. Through a preliminary study, we highlight the severity of the problem by showing that robustness without the original dataset is difficult to achieve, even with similar domain datasets. To address this issue, we propose DataFreeShield, which tackles the problem from two perspectives: surrogate dataset generation and adversarial training using the generated data. Through extensive validation, we show that DataFreeShield outperforms baselines, demonstrating that the proposed method sets the first entirely data-free solution for the adversarial robustness problem.
Authors: Mojtaba Safari, Zach Eidex, Shaoyan Pan, Richard L. J. Qiu, Xiaofeng Yang
Abstract: Purpose: To propose a self-supervised deep learning-based compressed sensing MRI (DL-based CS-MRI) method named "Adaptive Self-Supervised Consistency Guided Diffusion Model (ASSCGD)" to accelerate data acquisition without requiring fully sampled datasets. Materials and Methods: We used the fastMRI multi-coil brain axial T2-weighted (T2-w) dataset from 1,376 cases and single-coil brain quantitative magnetization prepared 2 rapid acquisition gradient echoes (MP2RAGE) T1 maps from 318 cases to train and test our model. Robustness against domain shift was evaluated using two out-of-distribution (OOD) datasets: multi-coil brain axial postcontrast T1 -weighted (T1c) dataset from 50 cases and axial T1-weighted (T1-w) dataset from 50 patients. Data were retrospectively subsampled at acceleration rates R in {2x, 4x, 8x}. ASSCGD partitions a random sampling pattern into two disjoint sets, ensuring data consistency during training. We compared our method with ReconFormer Transformer and SS-MRI, assessing performance using normalized mean squared error (NMSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM). Statistical tests included one-way analysis of variance (ANOVA) and multi-comparison Tukey's Honesty Significant Difference (HSD) tests. Results: ASSCGD preserved fine structures and brain abnormalities visually better than comparative methods at R = 8x for both multi-coil and single-coil datasets. It achieved the lowest NMSE at R in {4x, 8x}, and the highest PSNR and SSIM values at all acceleration rates for the multi-coil dataset. Similar trends were observed for the single-coil dataset, though SSIM values were comparable to ReconFormer at R in {2x, 8x}. These results were further confirmed by the voxel-wise correlation scatter plots. OOD results showed significant (p << 10^-5 ) improvements in undersampled image quality after reconstruction.
Authors: Parastoo Sotoudeh Sharifi, M. Omair Ahmad, M. N. S. Swamy
Abstract: Recent advancements in deep learning (DL) have significantly advanced medical image analysis. In the field of medical image processing, particularly in histopathology image analysis, the variation in staining protocols and differences in scanners present significant domain shift challenges, undermine the generalization capabilities of models to the data from unseen domains, prompting the need for effective domain generalization (DG) strategies to improve the consistency and reliability of automated cancer detection tools in diagnostic decision-making. In this paper, we introduce Pathology Weight Averaging (PathoWAve), a multi-source DG strategy for addressing domain shift phenomenon of DL models in histopathology image analysis. Integrating specific weight averaging technique with parallel training trajectories and a strategically combination of regular augmentations with histopathology-specific data augmentation methods, PathoWAve enables a comprehensive exploration and precise convergence within the loss landscape. This method significantly enhanced generalization capabilities of DL models across new, unseen histopathology domains. To the best of our knowledge, PathoWAve is the first proposed weight averaging method for DG in histopathology image analysis. Our quantitative results on Camelyon17 WILDS dataset demonstrate PathoWAve's superiority over previous proposed methods to tackle the domain shift phenomenon in histopathology image processing. Our code is available at \url{https://github.com/ParastooSotoudeh/PathoWAve}.
Authors: Han Liu, Hao Li, Jiacheng Wang, Yubo Fan, Zhoubing Xu, Ipek Oguz
Abstract: Fluorescence labeling is the standard approach to reveal cellular structures and other subcellular constituents for microscopy images. However, this invasive procedure may perturb or even kill the cells and the procedure itself is highly time-consuming and complex. Recently, in silico labeling has emerged as a promising alternative, aiming to use machine learning models to directly predict the fluorescently labeled images from label-free microscopy. In this paper, we propose a deep learning-based in silico labeling method for the Light My Cells challenge. Built upon pix2pix, our proposed method can be trained using the partially labeled datasets with an adaptive loss. Moreover, we explore the effectiveness of several training strategies to handle different input modalities, such as training them together or separately. The results show that our method achieves promising performance for in silico labeling. Our code is available at https://github.com/MedICL-VU/LightMyCells.
Authors: Piumi Sandarenu, Julia Chen, Iveta Slapetova, Lois Browne, Peter H. Graham, Alexander Swarbrick, Ewan K. A. Millar, Yang Song, Erik Meijering
Abstract: Advancements in digital imaging technologies have sparked increased interest in using multiplexed immunofluorescence (mIF) images to visualise and identify the interactions between specific immunophenotypes with the tumour microenvironment at the cellular level. Current state-of-the-art multiplexed immunofluorescence image analysis pipelines depend on cell feature representations characterised by morphological and stain intensity-based metrics generated using simple statistical and machine learning-based tools. However, these methods are not capable of generating complex representations of cells. We propose a deep learning-based cell feature extraction model using a variational autoencoder with supervision using a latent subspace to extract cell features in mIF images. We perform cell phenotype classification using a cohort of more than 44,000 multiplexed immunofluorescence cell image patches extracted across 1,093 tissue microarray cores of breast cancer patients, to demonstrate the success of our model against current and alternative methods.
Authors: Anoop Cherian, Kuan-Chuan Peng, Suhas Lohit, Joanna Matthiesen, Kevin Smith, Joshua B. Tenenbaum
Abstract: Recent years have seen a significant progress in the general-purpose problem solving abilities of large vision and language models (LVLMs), such as ChatGPT, Gemini, etc.; some of these breakthroughs even seem to enable AI models to outperform human abilities in varied tasks that demand higher-order cognitive skills. Are the current large AI models indeed capable of generalized problem solving as humans do? A systematic analysis of AI capabilities for joint vision and text reasoning, however, is missing in the current scientific literature. In this paper, we make an effort towards filling this gap, by evaluating state-of-the-art LVLMs on their mathematical and algorithmic reasoning abilities using visuo-linguistic problems from children's Olympiads. Specifically, we consider problems from the Mathematical Kangaroo (MK) Olympiad, which is a popular international competition targeted at children from grades 1-12, that tests children's deeper mathematical abilities using puzzles that are appropriately gauged to their age and skills. Using the puzzles from MK, we created a dataset, dubbed SMART-840, consisting of 840 problems from years 2020-2024. With our dataset, we analyze LVLMs power on mathematical reasoning; their responses on our puzzles offer a direct way to compare against that of children. Our results show that modern LVLMs do demonstrate increasingly powerful reasoning skills in solving problems for higher grades, but lack the foundations to correctly answer problems designed for younger children. Further analysis shows that there is no significant correlation between the reasoning capabilities of AI models and that of young children, and their capabilities appear to be based on a different type of reasoning than the cumulative knowledge that underlies children's mathematics and logic skills.
Authors: Lorenzo Basile, Santiago Acevedo, Luca Bortolussi, Fabio Anselmi, Alex Rodriguez
Abstract: To gain insight into the mechanisms behind machine learning methods, it is crucial to establish connections among the features describing data points. However, these correlations often exhibit a high-dimensional and strongly nonlinear nature, which makes them challenging to detect using standard methods. This paper exploits the entanglement between intrinsic dimensionality and correlation to propose a metric that quantifies the (potentially nonlinear) correlation between high-dimensional manifolds. We first validate our method on synthetic data in controlled environments, showcasing its advantages and drawbacks compared to existing techniques. Subsequently, we extend our analysis to large-scale applications in neural network representations. Specifically, we focus on latent representations of multimodal data, uncovering clear correlations between paired visual and textual embeddings, whereas existing methods struggle significantly in detecting similarity. Our results indicate the presence of highly nonlinear correlation patterns between latent manifolds.
Authors: Shyam Gupta, Dhanisha Sharma
Abstract: The manual examination of X-ray images for fractures is a time-consuming process that is prone to human error. In this work, we introduce a robust yet simple training loop for the classification of fractures, which significantly outperforms existing methods. Our method achieves superior performance in less than ten epochs and utilizes the latest dataset to deliver the best-performing model for this task. We emphasize the importance of training deep learning models responsibly and efficiently, as well as the critical role of selecting high-quality datasets.
Authors: Benjamin Hou, Sung-Won Lee, Jung-Min Lee, Christopher Koh, Jing Xiao, Perry J. Pickhardt, Ronald M. Summers
Abstract: Purpose: To evaluate the performance of an automated deep learning method in detecting ascites and subsequently quantifying its volume in patients with liver cirrhosis and ovarian cancer. Materials and Methods: This retrospective study included contrast-enhanced and non-contrast abdominal-pelvic CT scans of patients with cirrhotic ascites and patients with ovarian cancer from two institutions, National Institutes of Health (NIH) and University of Wisconsin (UofW). The model, trained on The Cancer Genome Atlas Ovarian Cancer dataset (mean age, 60 years +/- 11 [s.d.]; 143 female), was tested on two internal (NIH-LC and NIH-OV) and one external dataset (UofW-LC). Its performance was measured by the Dice coefficient, standard deviations, and 95% confidence intervals, focusing on ascites volume in the peritoneal cavity. Results: On NIH-LC (25 patients; mean age, 59 years +/- 14 [s.d.]; 14 male) and NIH-OV (166 patients; mean age, 65 years +/- 9 [s.d.]; all female), the model achieved Dice scores of 0.855 +/- 0.061 (CI: 0.831-0.878) and 0.826 +/- 0.153 (CI: 0.764-0.887), with median volume estimation errors of 19.6% (IQR: 13.2-29.0) and 5.3% (IQR: 2.4-9.7) respectively. On UofW-LC (124 patients; mean age, 46 years +/- 12 [s.d.]; 73 female), the model had a Dice score of 0.830 +/- 0.107 (CI: 0.798-0.863) and median volume estimation error of 9.7% (IQR: 4.5-15.1). The model showed strong agreement with expert assessments, with r^2 values of 0.79, 0.98, and 0.97 across the test sets. Conclusion: The proposed deep learning method performed well in segmenting and quantifying the volume of ascites in concordance with expert radiologist assessments.
Authors: Mrinal Kanti Dhar, Chuanbo Wang, Yash Patel, Taiyu Zhang, Jeffrey Niezgoda, Sandeep Gopalakrishnan, Keke Chen, Zeyun Yu
Abstract: Identifying individual tissues, so-called tissue segmentation, in diabetic foot ulcer (DFU) images is a challenging task and little work has been published, largely due to the limited availability of a clinical image dataset. To address this gap, we have created a DFUTissue dataset for the research community to evaluate wound tissue segmentation algorithms. The dataset contains 110 images with tissues labeled by wound experts and 600 unlabeled images. Additionally, we conducted a pilot study on segmenting wound characteristics including fibrin, granulation, and callus using deep learning. Due to the limited amount of annotated data, our framework consists of both supervised learning (SL) and semi-supervised learning (SSL) phases. In the SL phase, we propose a hybrid model featuring a Mix Transformer (MiT-b3) in the encoder and a CNN in the decoder, enhanced by the integration of a parallel spatial and channel squeeze-and-excitation (P-scSE) module known for its efficacy in improving boundary accuracy. The SSL phase employs a pseudo-labeling-based approach, iteratively identifying and incorporating valuable unlabeled images to enhance overall segmentation performance. Comparative evaluations with state-of-the-art methods are conducted for both SL and SSL phases. The SL achieves a Dice Similarity Coefficient (DSC) of 84.89%, which has been improved to 87.64% in the SSL phase. Furthermore, the results are benchmarked against two widely used SSL approaches: Generative Adversarial Networks and Cross-Consistency Training. Additionally, our hybrid model outperforms the state-of-the-art methods with a 92.99% DSC in performing binary segmentation of DFU wound areas when tested on the Chronic Wound dataset. Codes and data are available at https://github.com/uwm-bigdata/DFUTissueSegNet.
Authors: Lujun Gui, Chuyang Ye, Tianyi Yan
Abstract: Contrast-enhanced magnetic resonance imaging (MRI) is pivotal in the pipeline of brain tumor segmentation and analysis. Gadolinium-based contrast agents, as the most commonly used contrast agents, are expensive and may have potential side effects, and it is desired to obtain contrast-enhanced brain tumor MRI scans without the actual use of contrast agents. Deep learning methods have been applied to synthesize virtual contrast-enhanced MRI scans from non-contrast images. However, as this synthesis problem is inherently ill-posed, these methods fall short in producing high-quality results. In this work, we propose Conditional Autoregressive Vision Model (CAVM) for improving the synthesis of contrast-enhanced brain tumor MRI. As the enhancement of image intensity grows with a higher dose of contrast agents, we assume that it is less challenging to synthesize a virtual image with a lower dose, where the difference between the contrast-enhanced and non-contrast images is smaller. Thus, CAVM gradually increases the contrast agent dosage and produces higher-dose images based on previous lower-dose ones until the final desired dose is achieved. Inspired by the resemblance between the gradual dose increase and the Chain-of-Thought approach in natural language processing, CAVM uses an autoregressive strategy with a decomposition tokenizer and a decoder. Specifically, the tokenizer is applied to obtain a more compact image representation for computational efficiency, and it decomposes the image into dose-variant and dose-invariant tokens. Then, a masked self-attention mechanism is developed for autoregression that gradually increases the dose of the virtual image based on the dose-variant tokens. Finally, the updated dose-variant tokens corresponding to the desired dose are decoded together with dose-invariant tokens to produce the final contrast-enhanced MRI.
Authors: Sukanya Patra, Nicolas Sournac, Souhaib Ben Taieb
Abstract: Concentrated Solar Power (CSP) plants store energy by heating a storage medium with an array of mirrors that focus sunlight onto solar receivers atop a central tower. Operating at high temperatures these receivers face risks such as freezing, deformation, and corrosion, leading to operational failures, downtime, or costly equipment damage. We study the problem of anomaly detection (AD) in sequences of thermal images collected over a year from an operational CSP plant. These images are captured at irregular intervals ranging from one to five minutes throughout the day by infrared cameras mounted on solar receivers. Our goal is to develop a method to extract useful representations from high-dimensional thermal images for AD. It should be able to handle temporal features of the data, which include irregularity, temporal dependency between images and non-stationarity due to a strong daily seasonal pattern. The co-occurrence of low-temperature anomalies that resemble normal images from the start and the end of the operational cycle with high-temperature anomalies poses an additional challenge. We first evaluate state-of-the-art deep image-based AD methods, which have been shown to be effective in deriving meaningful image representations for the detection of anomalies. Then, we introduce a forecasting-based AD method that predicts future thermal images from past sequences and timestamps via a deep sequence model. This method effectively captures specific temporal data features and distinguishes between difficult-to-detect temperature-based anomalies. Our experiments demonstrate the effectiveness of our approach compared to multiple SOTA baselines across multiple evaluation metrics. We have also successfully deployed our solution on five months of unseen data, providing critical insights for the maintenance of the CSP plant. Our code is available at: https://tinyurl.com/ForecastAD
Authors: Ruisheng Gao, Zeyu Xiao, Zhiwei Xiong
Abstract: Transformer-based methods have demonstrated impressive performance in 4D light field (LF) super-resolution by effectively modeling long-range spatial-angular correlations, but their quadratic complexity hinders the efficient processing of high resolution 4D inputs, resulting in slow inference speed and high memory cost. As a compromise, most prior work adopts a patch-based strategy, which fails to leverage the full information from the entire input LFs. The recently proposed selective state-space model, Mamba, has gained popularity for its efficient long-range sequence modeling. In this paper, we propose a Mamba-based Light Field Super-Resolution method, named MLFSR, by designing an efficient subspace scanning strategy. Specifically, we tokenize 4D LFs into subspace sequences and conduct bi-directional scanning on each subspace. Based on our scanning strategy, we then design the Mamba-based Global Interaction (MGI) module to capture global information and the local Spatial- Angular Modulator (SAM) to complement local details. Additionally, we introduce a Transformer-to-Mamba (T2M) loss to further enhance overall performance. Extensive experiments on public benchmarks demonstrate that MLFSR surpasses CNN-based models and rivals Transformer-based methods in performance while maintaining higher efficiency. With quicker inference speed and reduced memory demand, MLFSR facilitates full-image processing of high-resolution 4D LFs with enhanced performance.
Authors: Chen Wang, Kaiyi Ji, Junyi Geng, Zhongqiang Ren, Taimeng Fu, Fan Yang, Yifan Guo, Haonan He, Xiangyu Chen, Zitong Zhan, Qiwei Du, Shaoshu Su, Bowen Li, Yuheng Qiu, Yi Du, Qihang Li, Yifan Yang, Xiao Lin, Zhipeng Zhao
Abstract: Data-driven methods such as reinforcement and imitation learning have achieved remarkable success in robot autonomy. However, their data-centric nature still hinders them from generalizing well to ever-changing environments. Moreover, collecting large datasets for robotic tasks is often impractical and expensive. To overcome these challenges, we introduce a new self-supervised neural-symbolic (NeSy) computational framework, imperative learning (IL), for robot autonomy, leveraging the generalization abilities of symbolic reasoning. The framework of IL consists of three primary components: a neural module, a reasoning engine, and a memory system. We formulate IL as a special bilevel optimization (BLO), which enables reciprocal learning over the three modules. This overcomes the label-intensive obstacles associated with data-driven approaches and takes advantage of symbolic reasoning concerning logical reasoning, physical principles, geometric analysis, etc. We discuss several optimization techniques for IL and verify their effectiveness in five distinct robot autonomy tasks including path planning, rule induction, optimal control, visual odometry, and multi-robot routing. Through various experiments, we show that IL can significantly enhance robot autonomy capabilities and we anticipate that it will catalyze further research across diverse domains.
Authors: Omkar Joglekar, Tal Lancewicki, Shir Kozlovsky, Vladimir Tchuiev, Zohar Feldman, Dotan Di Castro
Abstract: Large Language Models (LLMs) and strong vision models have enabled rapid research and development in the field of Vision-Language-Action models that enable robotic control. The main objective of these methods is to develop a generalist policy that can control robots with various embodiments. However, in industrial robotic applications such as automated assembly and disassembly, some tasks, such as insertion, demand greater accuracy and involve intricate factors like contact engagement, friction handling, and refined motor skills. Implementing these skills using a generalist policy is challenging because these policies might integrate further sensory data, including force or torque measurements, for enhanced precision. In our method, we present a global control policy based on LLMs that can transfer the control policy to a finite set of skills that are specifically trained to perform high-precision tasks through dynamic context switching. The integration of LLMs into this framework underscores their significance in not only interpreting and processing language inputs but also in enriching the control mechanisms for diverse and intricate robotic operations.
Authors: Noa Cahan, Eyal Klang, Galit Aviram, Yiftach Barash, Eli Konen, Raja Giryes, Hayit Greenspan
Abstract: Chest X-rays or chest radiography (CXR), commonly used for medical diagnostics, typically enables limited imaging compared to computed tomography (CT) scans, which offer more detailed and accurate three-dimensional data, particularly contrast-enhanced scans like CT Pulmonary Angiography (CTPA). However, CT scans entail higher costs, greater radiation exposure, and are less accessible than CXRs. In this work we explore cross-modal translation from a 2D low contrast-resolution X-ray input to a 3D high contrast and spatial-resolution CTPA scan. Driven by recent advances in generative AI, we introduce a novel diffusion-based approach to this task. We evaluate the models performance using both quantitative metrics and qualitative feedback from radiologists, ensuring diagnostic relevance of the generated images. Furthermore, we employ the synthesized 3D images in a classification framework and show improved AUC in a PE categorization task, using the initial CXR input. The proposed method is generalizable and capable of performing additional cross-modality translations in medical imaging. It may pave the way for more accessible and cost-effective advanced diagnostic tools. The code for this project is available: https://github.com/NoaCahan/X-ray2CTPA .
Authors: Haifan Gong, Wenhao Huang, Huan Zhang, Yu Wang, Xiang Wan, Hong Shen, Guanbin Li, Haofeng Li
Abstract: Automatic segmentation of the bronchial tree from CT imaging is important, as it provides structural information for disease diagnosis. Despite the merits of previous automatic bronchus segmentation methods, they have paied less attention to the issue we term as \textit{Intensity Confusion}, wherein the intensity values of certain background voxels approach those of the foreground voxels within bronchi. Conversely, the intensity values of some foreground voxels are nearly identical to those of background voxels. This proximity in intensity values introduces significant challenges to neural network methodologies. To address the issue, we introduce a novel Intensity-Distance Guided loss function, which assigns adaptive weights to different image voxels for mining hard samples that cause the intensity confusion. The proposed loss estimates the voxel-level hardness of samples, on the basis of the following intensity and distance priors. We regard a voxel as a hard sample if it is in: (1) the background and has an intensity value close to the bronchus region; (2) the bronchus region and is of higher intensity than most voxels inside the bronchus; (3) the background region and at a short distance from the bronchus. Extensive experiments not only show the superiority of our method compared with the state-of-the-art methods, but also verify that tackling the intensity confusion issue helps to significantly improve bronchus segmentation. Project page: https://github.com/lhaof/ICM.
Authors: Sheng Zhang, Yang Nan, Yingying Fang, Shiyi Wang, Xiaodan Xing, Zhifan Gao, Guang Yang
Abstract: Automatic lung organ segmentation on CT images is crucial for lung disease diagnosis. However, the unlimited voxel values and class imbalance of lung organs can lead to false-negative/positive and leakage issues in advanced methods. Additionally, some slender lung organs are easily lost during the recycled down/up-sample procedure, e.g., bronchioles & arterioles, causing severe discontinuity issue. Inspired by these, this paper introduces an effective lung organ segmentation method called Fuzzy Attention-based Border Rendering (FABR) network. Since fuzzy logic can handle the uncertainty in feature extraction, hence the fusion of deep networks and fuzzy sets should be a viable solution for better performance. Meanwhile, unlike prior top-tier methods that operate on all regular dense points, our FABR depicts lung organ regions as cube-trees, focusing only on recycle-sampled border vulnerable points, rendering the severely discontinuous, false-negative/positive organ regions with a novel Global-Local Cube-tree Fusion (GLCF) module. All experimental results, on four challenging datasets of airway & artery, demonstrate that our method can achieve the favorable performance significantly.
Authors: Ozan Vardal, Richard Hawkins, Colin Paterson, Chiara Picardi, Daniel Omeiza, Lars Kunze, Ibrahim Habli
Abstract: For machine learning components used as part of autonomous systems (AS) in carrying out critical tasks it is crucial that assurance of the models can be maintained in the face of post-deployment changes (such as changes in the operating environment of the system). A critical part of this is to be able to monitor when the performance of the model at runtime (as a result of changes) poses a safety risk to the system. This is a particularly difficult challenge when ground truth is unavailable at runtime. In this paper we introduce a process for creating safety monitors for ML components through the use of degraded datasets and machine learning. The safety monitor that is created is deployed to the AS in parallel to the ML component to provide a prediction of the safety risk associated with the model output. We demonstrate the viability of our approach through some initial experiments using publicly available speed sign datasets.
Authors: Kishaan Jeeveswaran, Elahe Arani, Bahram Zonooz
Abstract: Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation drift, which refers to the phenomenon of learned representations undergoing changes as the model adapts to new tasks, can help alleviate catastrophic forgetting. In this study, we propose a novel DIL method named DARE, featuring a three-stage training process: Divergence, Adaptation, and REfinement. This process gradually adapts the representations associated with new tasks into the feature space spanned by samples from previous tasks, simultaneously integrating task-specific decision boundaries. Additionally, we introduce a novel strategy for buffer sampling and demonstrate the effectiveness of our proposed method, combined with this sampling strategy, in reducing representation drift within the feature encoder. This contribution effectively alleviates catastrophic forgetting across multiple DIL benchmarks. Furthermore, our approach prevents sudden representation drift at task boundaries, resulting in a well-calibrated DIL model that maintains the performance on previous tasks.
Authors: Kwang-Hyun Uhm, Seung-Won Jung, Sung-Hoo Hong, Sung-Jea Ko
Abstract: Multi-phase computed tomography (CT) has been widely used for the preoperative diagnosis of kidney cancer due to its non-invasive nature and ability to characterize renal lesions. However, since enhancement patterns of renal lesions across CT phases are different even for the same lesion type, the visual assessment by radiologists suffers from inter-observer variability in clinical practice. Although deep learning-based approaches have been recently explored for differential diagnosis of kidney cancer, they do not explicitly model the relationships between CT phases in the network design, limiting the diagnostic performance. In this paper, we propose a novel lesion-aware cross-phase attention network (LACPANet) that can effectively capture temporal dependencies of renal lesions across CT phases to accurately classify the lesions into five major pathological subtypes from time-series multi-phase CT images. We introduce a 3D inter-phase lesion-aware attention mechanism to learn effective 3D lesion features that are used to estimate attention weights describing the inter-phase relations of the enhancement patterns. We also present a multi-scale attention scheme to capture and aggregate temporal patterns of lesion features at different spatial scales for further improvement. Extensive experiments on multi-phase CT scans of kidney cancer patients from the collected dataset demonstrate that our LACPANet outperforms state-of-the-art approaches in diagnostic accuracy.
Authors: Daniel Wen
Abstract: In this research, we explore different ways to improve generative adversarial networks for video super-resolution tasks from a base single image super-resolution GAN model. Our primary objective is to identify potential techniques that enhance these models and to analyze which of these techniques yield the most significant improvements. We evaluate our results using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Our findings indicate that the most effective techniques include temporal smoothing, long short-term memory (LSTM) layers, and a temporal loss function. The integration of these methods results in an 11.97% improvement in PSNR and an 8% improvement in SSIM compared to the baseline video super-resolution generative adversarial network (GAN) model. This substantial improvement suggests potential further applications to enhance current state-of-the-art models.
Authors: Junjie Chen, Subin Huang
Abstract: The prevalence of sarcasm in social media, conveyed through text-image combinations, presents significant challenges for sentiment analysis and intention mining. Current multi-modal sarcasm detection methods have been proven to struggle with biases from spurious cues, leading to a superficial understanding of the complex interactions between text and image. To address these issues, we propose InterCLIP-MEP, a robust framework for multi-modal sarcasm detection. InterCLIP-MEP introduces a refined variant of CLIP, Interactive CLIP (InterCLIP), as the backbone, enhancing sample representations by embedding cross-modality information in each encoder. Furthermore, a novel training strategy is designed to adapt InterCLIP for a Memory-Enhanced Predictor (MEP). MEP uses dynamic dual-channel memory to store valuable historical knowledge of test samples and then leverages this memory as a non-parametric classifier to derive the final prediction. By using InterCLIP to encode text-image interactions more effectively and incorporating MEP, InterCLIP-MEP offers a more robust recognition of multi-modal sarcasm. Experiments demonstrate that InterCLIP-MEP achieves state-of-the-art performance on the MMSD2.0 benchmark. Code and data are available at [https://github.com/CoderChen01/InterCLIP-MEP](https://github.com/CoderChen01/InterCLIP-MEP).
URLs: https://github.com/CoderChen01/InterCLIP-MEP](https://github.com/CoderChen01/InterCLIP-MEP).
Authors: Jamie Burke, Samuel Gibbon, Justin Engelmann, Adam Threlfall, Ylenia Giarratano, Charlene Hamid, Stuart King, Ian J. C. MacCormick, Tom MacGillivray
Abstract: Purpose: To describe SLOctolyzer: an open-source analysis toolkit for en face retinal vessels appearing in infrared reflectance scanning laser ophthalmoscopy (SLO) images. Methods: SLOctolyzer includes two main modules: segmentation and measurement. The segmentation module use deep learning methods to delineate retinal anatomy, while the measurement module quantifies key retinal vascular features such as vessel complexity, density, tortuosity, and calibre. We evaluate the segmentation module using unseen data and measure its reproducibility. Results: SLOctolyzer's segmentation module performed well against unseen internal test data (Dice for all-vessels, 0.9097; arteries, 0.8376; veins, 0.8525; optic disc, 0.9430; fovea, 0.8837). External validation against severe retinal pathology showed decreased performance (Dice for arteries, 0.7180; veins, 0.7470; optic disc, 0.9032). SLOctolyzer had good reproducibility (mean difference for fractal dimension, -0.0007; vessel density, -0.0003; vessel calibre, -0.3154 $\mu$m; tortuosity density, 0.0013). SLOctolyzer can process a macula-centred SLO image in under 20 seconds and a disc-centred SLO image in under 30 seconds using a standard laptop CPU. Conclusions: To our knowledge, SLOctolyzer is the first open-source tool to convert raw SLO images into reproducible and clinically meaningful retinal vascular parameters. SLO images are captured simultaneous to optical coherence tomography (OCT), and we believe our software will be useful for extracting retinal vascular measurements from large OCT image sets and linking them to ocular or systemic diseases. It requires no specialist knowledge or proprietary software, and allows manual correction of segmentations and re-computing of vascular metrics. SLOctolyzer is freely available at https://github.com/jaburke166/SLOctolyzer.
Authors: Yujin Baek, ChaeHun Park, Jaeseok Kim, Yu-Jung Heo, Du-Seong Chang, Jaegul Choo
Abstract: To create culturally inclusive vision-language models (VLMs), the foremost requirement is developing a test benchmark that can diagnose the models' ability to respond to questions reflecting cultural elements. This paper addresses the necessity for such benchmarks, noting that existing research has relied on human annotators' manual efforts, which impedes diversity and efficiency. We propose a semi-automated pipeline for constructing cultural VLM benchmarks to enhance diversity and efficiency. This pipeline leverages human-VLM collaboration, where VLMs generate questions based on guidelines, human-annotated examples, and image-wise relevant knowledge, which are then reviewed by native speakers for quality and cultural relevance. The effectiveness of our adaptable pipeline is demonstrated through a specific application: creating a dataset tailored to Korean culture, dubbed K-Viscuit. The resulting benchmark features two types of questions: Type 1 questions measure visual recognition abilities, while Type 2 assess fine-grained visual reasoning skills. This ensures a thorough diagnosis of VLM models across various aspects. Our evaluation using K-Viscuit revealed that open-source models notably lag behind proprietary models in understanding Korean culture, highlighting areas for improvement. We provided diverse analyses of VLM performance across different cultural aspects. Besides, we explored the potential of incorporating external knowledge retrieval to enhance the generation process, suggesting future directions for improving cultural interpretation ability of VLMs. Our dataset and code will be made publicly available.
Authors: Johannes P\"oppelbaum, Andreas Schwung
Abstract: In this paper, we propose novel quaternion activation functions where we modify either the quaternion magnitude or the phase, as an alternative to the commonly used split activation functions. We define criteria that are relevant for quaternion activation functions, and subsequently we propose our novel activation functions based on this analysis. Instead of applying a known activation function like the ReLU or Tanh on the quaternion elements separately, these activation functions consider the quaternion properties and respect the quaternion space $\mathbb{H}$. In particular, all quaternion components are utilized to calculate all output components, carrying out the benefit of the Hamilton product in e.g. the quaternion convolution to the activation functions. The proposed activation functions can be incorporated in arbitrary quaternion valued neural networks trained with gradient descent techniques. We further discuss the derivatives of the proposed activation functions where we observe beneficial properties for the activation functions affecting the phase. Specifically, they prove to be sensitive on basically the whole input range, thus improved gradient flow can be expected. We provide an elaborate experimental evaluation of our proposed quaternion activation functions including comparison with the split ReLU and split Tanh on two image classification tasks using the CIFAR-10 and SVHN dataset. There, especially the quaternion activation functions affecting the phase consistently prove to provide better performance.
Authors: Wolong Xing, Zhenkui Shi, Hongyan Peng, Xiantao Hu, Xianxian Li
Abstract: Federated learning enables distributed clients to collaborate on training while storing their data locally to protect client privacy. However, due to the heterogeneity of data, models, and devices, the final global model may need to perform better for tasks on each client. Communication bottlenecks, data heterogeneity, and model heterogeneity have been common challenges in federated learning. In this work, we considered a label distribution skew problem, a type of data heterogeneity easily overlooked. In the context of classification, we propose a personalized federated learning approach called pFedPM. In our process, we replace traditional gradient uploading with feature uploading, which helps reduce communication costs and allows for heterogeneous client models. These feature representations play a role in preserving privacy to some extent. We use a hyperparameter $a$ to mix local and global features, which enables us to control the degree of personalization. We also introduced a relation network as an additional decision layer, which provides a non-linear learnable classifier to predict labels. Experimental results show that, with an appropriate setting of $a$, our scheme outperforms several recent FL methods on MNIST, FEMNIST, and CRIFAR10 datasets and achieves fewer communications.
Authors: You-Wei Luo, Chuan-Xian Ren
Abstract: As a crucial step toward real-world learning scenarios with changing environments, dataset shift theory and invariant representation learning algorithm have been extensively studied to relax the identical distribution assumption in classical learning setting. Among the different assumptions on the essential of shifting distributions, generalized label shift (GLS) is the latest developed one which shows great potential to deal with the complex factors within the shift. In this paper, we aim to explore the limitations of current dataset shift theory and algorithm, and further provide new insights by presenting a comprehensive understanding of GLS. From theoretical aspect, two informative generalization bounds are derived, and the GLS learner is proved to be sufficiently close to optimal target model from the Bayesian perspective. The main results show the insufficiency of invariant representation learning, and prove the sufficiency and necessity of GLS correction for generalization, which provide theoretical supports and innovations for exploring generalizable model under dataset shift. From methodological aspect, we provide a unified view of existing shift correction frameworks, and propose a kernel embedding-based correction algorithm (KECA) to minimize the generalization error and achieve successful knowledge transfer. Both theoretical results and extensive experiment evaluations demonstrate the sufficiency and necessity of GLS correction for addressing dataset shift and the superiority of proposed algorithm.
Authors: Remi Laumont, Yiqiu Dong, Martin Skovgaard Andersen
Abstract: This paper studies two classes of sampling methods for the solution of inverse problems, namely Randomize-Then-Optimize (RTO), which is rooted in sensitivity analysis, and Langevin methods, which are rooted in the Bayesian framework. The two classes of methods correspond to different assumptions and yield samples from different target distributions. We highlight the main conceptual and theoretical differences between the two approaches and compare them from a practical point of view by tackling two classical inverse problems in imaging: deblurring and inpainting. We show that the choice of the sampling method has a significant impact on the quality of the reconstruction and that the RTO method is more robust to the choice of the parameters.
Authors: Nicolas Zilberstein, Morteza Mardani, Santiago Segarra
Abstract: Score distillation sampling has been pivotal for integrating diffusion models into generation of complex visuals. Despite impressive results it suffers from mode collapse and lack of diversity. To cope with this challenge, we leverage the gradient flow interpretation of score distillation to propose Repulsive Score Distillation (RSD). In particular, we propose a variational framework based on repulsion of an ensemble of particles that promotes diversity. Using a variational approximation that incorporates a coupling among particles, the repulsion appears as a simple regularization that allows interaction of particles based on their relative pairwise similarity, measured e.g., via radial basis kernels. We design RSD for both unconstrained and constrained sampling scenarios. For constrained sampling we focus on inverse problems in the latent space that leads to an augmented variational formulation, that strikes a good balance between compute, quality and diversity. Our extensive experiments for text-to-image generation, and inverse problems demonstrate that RSD achieves a superior trade-off between diversity and quality compared with state-of-the-art alternatives.
Authors: Vincent Loos, Rohit Pardasani, Navchetan Awasthi
Abstract: Medical image segmentation is a critical task in healthcare applications, and U-Nets have demonstrated promising results. This work delves into the understudied aspect of receptive field (RF) size and its impact on the U-Net and Attention U-Net architectures. This work explores several critical elements including the relationship between RF size, characteristics of the region of interest, and model performance, as well as the balance between RF size and computational costs for U-Net and Attention U-Net methods for different datasets. This work also proposes a mathematical notation for representing the theoretical receptive field (TRF) of a given layer in a network and proposes two new metrics - effective receptive field (ERF) rate and the Object rate to quantify the fraction of significantly contributing pixels within the ERF against the TRF area and assessing the relative size of the segmentation object compared to the TRF size respectively. The results demonstrate that there exists an optimal TRF size that successfully strikes a balance between capturing a wider global context and maintaining computational efficiency, thereby optimizing model performance. Interestingly, a distinct correlation is observed between the data complexity and the required TRF size; segmentation based solely on contrast achieved peak performance even with smaller TRF sizes, whereas more complex segmentation tasks necessitated larger TRFs. Attention U-Net models consistently outperformed their U-Net counterparts, highlighting the value of attention mechanisms regardless of TRF size. These novel insights present an invaluable resource for developing more efficient U-Net-based architectures for medical imaging and pave the way for future exploration. A tool is also developed that calculates the TRF for a U-Net (and Attention U-Net) model, and also suggest an appropriate TRF size for a given model and dataset.
Authors: Pierangela Bruno, Edoardo De Rose, Carlo Adornetto, Francesco Calimeri, Sandro Donato, Raffaele Giuseppe Agostino, Daniela Amelio, Riccardo Barberi, Maria Carmela Cerra, Maria Caterina Crocco, Mariacristina Filice, Raffaele Filosa, Gianluigi Greco, Sandra Imbrogno, Vincenzo Formoso
Abstract: X-ray computed microtomography ({\mu}-CT) is a non-destructive technique that can generate high-resolution 3D images of the internal anatomy of medical and biological samples. These images enable clinicians to examine internal anatomy and gain insights into the disease or anatomical morphology. However, extracting relevant information from 3D images requires semantic segmentation of the regions of interest, which is usually done manually and results time-consuming and tedious. In this work, we propose a novel framework that uses a convolutional neural network (CNN) to automatically segment the full morphology of the heart of Carassius auratus. The framework employs an optimized 2D CNN architecture that can infer a 3D segmentation of the sample, avoiding the high computational cost of a 3D CNN architecture. We tackle the challenges of handling large and high-resoluted image data (over a thousand pixels in each dimension) and a small training database (only three samples) by proposing a standard protocol for data normalization and processing. Moreover, we investigate how the noise, contrast, and spatial resolution of the sample and the training of the architecture are affected by the reconstruction technique, which depends on the number of input images. Experiments show that our framework significantly reduces the time required to segment new samples, allowing a faster microtomography analysis of the Carassius auratus heart shape. Furthermore, our framework can work with any bio-image (biological and medical) from {\mu}-CT with high-resolution and small dataset size
Authors: Yuning Du, Rohan Dharmakumar, Sotirios A. Tsaftaris
Abstract: Despite the high diagnostic accuracy of Magnetic Resonance Imaging (MRI), using MRI as a Point-of-Care (POC) disease identification tool poses significant accessibility challenges due to the use of high magnetic field strength and lengthy acquisition times. We ask a simple question: Can we dynamically optimise acquired samples, at the patient level, according to an (automated) downstream decision task, while discounting image reconstruction? We propose an ML-based framework that learns an active sampling strategy, via reinforcement learning, at a patient-level to directly infer disease from undersampled k-space. We validate our approach by inferring Meniscus Tear in undersampled knee MRI data, where we achieve diagnostic performance comparable with ML-based diagnosis, using fully sampled k-space data. We analyse task-specific sampling policies, showcasing the adaptability of our active sampling approach. The introduced frugal sampling strategies have the potential to reduce high field strength requirements that in turn strengthen the viability of MRI-based POC disease identification and associated preliminary screening tools.
Authors: Katherine M. Collins, Najoung Kim, Yonatan Bitton, Verena Rieser, Shayegan Omidshafiei, Yushi Hu, Sherol Chen, Senjuti Dutta, Minsuk Chang, Kimin Lee, Youwei Liang, Georgina Evans, Sahil Singla, Gang Li, Adrian Weller, Junfeng He, Deepak Ramachandran, Krishnamurthy Dj Dvijotham
Abstract: Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This paper investigates the effectiveness of fine-grained feedback which captures nuanced distinctions in image quality and prompt-alignment, compared to traditional coarse-grained feedback (for example, thumbs up/down or ranking between a set of options). While fine-grained feedback holds promise, particularly for systems catering to diverse societal preferences, we show that demonstrating its superiority to coarse-grained feedback is not automatic. Through experiments on real and synthetic preference data, we surface the complexities of building effective models due to the interplay of model choice, feedback type, and the alignment between human judgment and computational interpretation. We identify key challenges in eliciting and utilizing fine-grained feedback, prompting a reassessment of its assumed benefits and practicality. Our findings -- e.g., that fine-grained feedback can lead to worse models for a fixed budget, in some settings; however, in controlled settings with known attributes, fine grained rewards can indeed be more helpful -- call for careful consideration of feedback attributes and potentially beckon novel modeling approaches to appropriately unlock the potential value of fine-grained feedback in-the-wild.
Authors: Jingru Fu, Simone Bendazzoli, \"Orjan Smedby, Rodrigo Moreno
Abstract: Significant advances have been made toward building accurate automatic segmentation models for adult gliomas. However, the performance of these models often degrades when applied to pediatric glioma due to their imaging and clinical differences (domain shift). Obtaining sufficient annotated data for pediatric glioma is typically difficult because of its rare nature. Also, manual annotations are scarce and expensive. In this work, we propose Domain-Adapted nnU-Net (DA-nnUNet) to perform unsupervised domain adaptation from adult glioma (source domain) to pediatric glioma (target domain). Specifically, we add a domain classifier connected with a gradient reversal layer (GRL) to a backbone nnU-Net. Once the classifier reaches a very high accuracy, the GRL is activated with the goal of transferring domain-invariant features from the classifier to the segmentation model while preserving segmentation accuracy on the source domain. The accuracy of the classifier slowly degrades to chance levels. No annotations are used in the target domain. The method is compared to 8 different supervised models using BraTS-Adult glioma (N=1251) and BraTS-PED glioma data (N=99). The proposed method shows notable performance enhancements in the tumor core (TC) region compared to the model that only uses adult data: ~32% better Dice scores and ~20 better 95th percentile Hausdorff distances. Moreover, our unsupervised approach shows no statistically significant difference compared to the practical upper bound model using manual annotations from both datasets in TC region. The code is shared at https://github.com/Fjr9516/DA_nnUNet.
Authors: Aditya Sharma, Michael Saxon, William Yang Wang
Abstract: We present LoCoVQA, a dynamic benchmark generator for evaluating long-context extractive reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical reasoning, VQA, and character recognition tasks with increasingly long visual contexts composed of both in-distribution and out-of-distribution distractor images. Across these tasks, a diverse set of VLMs rapidly lose performance as the visual context length grows, often exhibiting a striking exponential decay trend. This test assesses how well VLMs can ignore irrelevant information when answering queries -- a task that is quite easy for language models (LMs) in the text domain -- demonstrating that current state-of-the-art VLMs lack this essential capability for many long-context applications.
Authors: Junbang Liang, Ruoshi Liu, Ege Ozguroglu, Sruthi Sudhakar, Achal Dave, Pavel Tokmakov, Shuran Song, Carl Vondrick
Abstract: A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale datasets of internet videos. In this paper, we propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. At test time, we generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot. Our key insight is that using common tools allows us to effortlessly bridge the embodiment gap between the human hand and the robot manipulator. We evaluate our approach on four tasks of increasing complexity and demonstrate that harnessing internet-scale generative models allows the learned policy to achieve a significantly higher degree of generalization than existing behavior cloning approaches.
Authors: Peng Liu, Xiaoxiao Zhou, Yangjunyi Li, El Basha Mohammad D, Ruogu Fang
Abstract: While the depth of convolutional neural networks has attracted substantial attention in the deep learning research, the width of these networks has recently received greater interest. The width of networks, defined as the size of the receptive fields and the density of the channels, has demonstrated crucial importance in low-level vision tasks such as image denoising and restoration. However, the limited generalization ability, due to the increased width of networks, creates a bottleneck in designing wider networks. In this paper, we propose the Deep Regulated Convolutional Network (RC-Net), a deep network composed of regulated sub-network blocks cascaded by skip-connections, to overcome this bottleneck. Specifically, the Regulated Convolution block (RC-block), featured by a combination of large and small convolution filters, balances the effectiveness of prominent feature extraction and the generalization ability of the network. RC-Nets have several compelling advantages: they embrace diversified features through large-small filter combinations, alleviate the hazy boundary and blurred details in image denoising and super-resolution problems, and stabilize the learning process. Our proposed RC-Nets outperform state-of-the-art approaches with significant performance gains in various image restoration tasks while demonstrating promising generalization ability. The code is available at https://github.com/cswin/RC-Nets.
Authors: Zhihang Yuan, Chenhao Xue, Yiqi Chen, Qiang Wu, Guangyu Sun
Abstract: Quantization is one of the most effective methods to compress neural networks, which has achieved great success on convolutional neural networks (CNNs). Recently, vision transformers have demonstrated great potential in computer vision. However, previous post-training quantization methods performed not well on vision transformer, resulting in more than 1% accuracy drop even in 8-bit quantization. Therefore, we analyze the problems of quantization on vision transformers. We observe the distributions of activation values after softmax and GELU functions are quite different from the Gaussian distribution. We also observe that common quantization metrics, such as MSE and cosine distance, are inaccurate to determine the optimal scaling factor. In this paper, we propose the twin uniform quantization method to reduce the quantization error on these activation values. And we propose to use a Hessian guided metric to evaluate different scaling factors, which improves the accuracy of calibration at a small cost. To enable the fast quantization of vision transformers, we develop an efficient framework, PTQ4ViT. Experiments show the quantized vision transformers achieve near-lossless prediction accuracy (less than 0.5% drop at 8-bit quantization) on the ImageNet classification task.
Authors: Hao Shi, Qi Jiang, Kailun Yang, Xiaoting Yin, Ze Wang, Kaiwei Wang
Abstract: Vision sensors are widely applied in vehicles, robots, and roadside infrastructure. However, due to limitations in hardware cost and system size, camera Field-of-View (FoV) is often restricted and may not provide sufficient coverage. Nevertheless, from a spatiotemporal perspective, it is possible to obtain information beyond the camera's physical FoV from past video streams. In this paper, we propose the concept of online video inpainting for autonomous vehicles to expand the field of view, thereby enhancing scene visibility, perception, and system safety. To achieve this, we introduce the FlowLens architecture, which explicitly employs optical flow and implicitly incorporates a novel clip-recurrent transformer for feature propagation. FlowLens offers two key features: 1) FlowLens includes a newly designed Clip-Recurrent Hub with 3D-Decoupled Cross Attention (DDCA) to progressively process global information accumulated over time. 2) It integrates a multi-branch Mix Fusion Feed Forward Network (MixF3N) to enhance the precise spatial flow of local features. To facilitate training and evaluation, we derive the KITTI360 dataset with various FoV mask, which covers both outer- and inner FoV expansion scenarios. We also conduct both quantitative assessments and qualitative comparisons of beyond-FoV semantics and beyond-FoV object detection across different models. We illustrate that employing FlowLens to reconstruct unseen scenes even enhances perception within the field of view by providing reliable semantic context. Extensive experiments and user studies involving offline and online video inpainting, as well as beyond-FoV perception tasks, demonstrate that FlowLens achieves state-of-the-art performance. The source code and dataset are made publicly available at https://github.com/MasterHow/FlowLens.
Authors: Mingqi Jiang, Saeed Khorram, Li Fuxin
Abstract: In order to gain insights about the decision-making of different visual recognition backbones, we propose two methodologies, sub-explanation counting and cross-testing, that systematically applies deep explanation algorithms on a dataset-wide basis, and compares the statistics generated from the amount and nature of the explanations. These methodologies reveal the difference among networks in terms of two properties called compositionality and disjunctivism. Transformers and ConvNeXt are found to be more compositional, in the sense that they jointly consider multiple parts of the image in building their decisions, whereas traditional CNNs and distilled transformers are less compositional and more disjunctive, which means that they use multiple diverse but smaller set of parts to achieve a confident prediction. Through further experiments, we pinpointed the choice of normalization to be especially important in the compositionality of a model, in that batch normalization leads to less compositionality while group and layer normalization lead to more. Finally, we also analyze the features shared by different backbones and plot a landscape of different models based on their feature-use similarity.
Authors: Zihua Wang, Xu Yang, Hanwang Zhang, Haiyang Xu, Ming Yan, Fei Huang, Yu Zhang
Abstract: We propose a novel Transformer-based image-to-text generation model termed as \textbf{ACF} that adaptively clusters vision patches into object regions and language words into phrases to implicitly learn object-phrase alignments for better visual-text coherence. To achieve this, we design a novel self-attention layer that applies self-attention over the elements in a local cluster window instead of the whole sequence. The window size is softly decided by a clustering matrix that is calculated by the current input data and thus this process is adaptive. By stacking these revised self-attention layers to construct ACF, the small clusters in the lower layers can be grouped into a bigger cluster, \eg vision/language. ACF clusters small objects/phrases into bigger ones. In this gradual clustering process, a parsing tree is generated which embeds the hierarchical knowledge of the input sequence. As a result, by using ACF to build the vision encoder and language decoder, the hierarchical object-phrase alignments are embedded and then transferred from vision to language domains in two popular image-to-text tasks: Image captioning and Visual Question Answering. The experiment results demonstrate the effectiveness of ACF, which outperforms most SOTA captioning and VQA models and achieves comparable scores compared with some large-scale pre-trained models. Our code is available \href{https://github.com/ZihuaEvan/ACFModel/}{[here]}.
Authors: Abhishek Arora, Xinmei Yang, Shao-Yu Jheng, Melissa Dell
Abstract: Many applications require linking individuals, firms, or locations across datasets. Most widely used methods, especially in social science, do not employ deep learning, with record linkage commonly approached using string matching techniques. Moreover, existing methods do not exploit the inherently multimodal nature of documents. In historical record linkage applications, documents are typically noisily transcribed by optical character recognition (OCR). Linkage with just OCR'ed texts may fail due to noise, whereas linkage with just image crops may also fail because vision models lack language understanding (e.g., of abbreviations or other different ways of writing firm names). To leverage multimodal learning, this study develops CLIPPINGS (Contrastively LInking Pooled Pre-trained Embeddings). CLIPPINGS aligns symmetric vision and language bi-encoders, through contrastive language-image pre-training on document images and their corresponding OCR'ed texts. It then contrastively learns a metric space where the pooled image-text embedding for a given instance is close to embeddings in the same class (e.g., the same firm or location) and distant from embeddings of a different class. Data are linked by treating linkage as a nearest neighbor retrieval problem with the multimodal embeddings. CLIPPINGS outperforms widely used string matching methods by a wide margin in linking mid-20th century Japanese firms across financial documents. A purely self-supervised model - trained only by aligning the embeddings for the image crop of a firm name and its corresponding OCR'ed text - also outperforms popular string matching methods. Fascinatingly, a multimodally pre-trained vision-only encoder outperforms a unimodally pre-trained vision-only encoder, illustrating the power of multimodal pre-training even if only one modality is available for linking at inference time.
Authors: Ruotong Wang, Hongrui Chen, Zihao Zhu, Li Liu, Baoyuan Wu
Abstract: Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on benign samples, dubbed \textit{backdoor attack}. Currently, implementing backdoor attacks in physical scenarios still faces significant challenges. Physical attacks are labor-intensive and time-consuming, and the triggers are selected in a manual and heuristic way. Moreover, expanding digital attacks to physical scenarios faces many challenges due to their sensitivity to visual distortions and the absence of counterparts in the real world. To address these challenges, we define a novel trigger called the \textbf{V}isible, \textbf{S}emantic, \textbf{S}ample-Specific, and \textbf{C}ompatible (VSSC) trigger, to achieve effective, stealthy and robust simultaneously, which can also be effectively deployed in the physical scenario using corresponding objects. To implement the VSSC trigger, we propose an automated pipeline comprising three modules: a trigger selection module that systematically identifies suitable triggers leveraging large language models, a trigger insertion module that employs generative models to seamlessly integrate triggers into images, and a quality assessment module that ensures the natural and successful insertion of triggers through vision-language models. Extensive experimental results and analysis validate the effectiveness, stealthiness, and robustness of the VSSC trigger. It can not only maintain robustness under visual distortions but also demonstrates strong practicality in the physical scenario. We hope that the proposed VSSC trigger and implementation approach could inspire future studies on designing more practical triggers in backdoor attacks.
Authors: Zhengyue Zhao, Jinhao Duan, Xing Hu, Kaidi Xu, Chenan Wang, Rui Zhang, Zidong Du, Qi Guo, Yunji Chen
Abstract: Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright infringement, and sensitive data leakage. To tackle these issues, we propose a method, Unlearnable Diffusion Perturbation, to safeguard images from unauthorized exploitation. Our approach involves designing an algorithm to generate sample-wise perturbation noise for each image to be protected. This imperceptible protective noise makes the data almost unlearnable for diffusion models, i.e., diffusion models trained or fine-tuned on the protected data cannot generate high-quality and diverse images related to the protected training data. Theoretically, we frame this as a max-min optimization problem and introduce EUDP, a noise scheduler-based method to enhance the effectiveness of the protective noise. We evaluate our methods on both Denoising Diffusion Probabilistic Model and Latent Diffusion Models, demonstrating that training diffusion models on the protected data lead to a significant reduction in the quality of the generated images. Especially, the experimental results on Stable Diffusion demonstrate that our method effectively safeguards images from being used to train Diffusion Models in various tasks, such as training specific objects and styles. This achievement holds significant importance in real-world scenarios, as it contributes to the protection of privacy and copyright against AI-generated content.
Authors: Michael P. J. Camilleri, Rasneer S. Bains, Christopher K. I. Williams
Abstract: Behavioural experiments often happen in specialised arenas, but this may confound the analysis. To address this issue, we provide tools to study mice in the home-cage environment, equipping biologists with the possibility to capture the temporal aspect of the individual's behaviour and model the interaction and interdependence between cage-mates with minimal human intervention. Our main contribution is the novel Group Behaviour Model (GBM) which summarises the joint behaviour of groups of mice across cages, using a permutation matrix to match the mouse identities in each cage to the model. In support of the above, we also (a) developed the Activity Labelling Module (ALM) to automatically classify mouse behaviour from video, and (b) released two datasets, ABODe for training behaviour classifiers and IMADGE for modelling behaviour.
Authors: Francesco Barbato, Elena Camuffo, Simone Milani, Pietro Zanuttigh
Abstract: State-of-the-art multimodal semantic segmentation strategies combining LiDAR and color data are usually designed on top of asymmetric information-sharing schemes and assume that both modalities are always available. This strong assumption may not hold in real-world scenarios, where sensors are prone to failure or can face adverse conditions that make the acquired information unreliable. This problem is exacerbated when continual learning scenarios are considered since they have stringent data reliability constraints. In this work, we re-frame the task of multimodal semantic segmentation by enforcing a tightly coupled feature representation and a symmetric information-sharing scheme, which allows our approach to work even when one of the input modalities is missing. We also introduce an ad-hoc class-incremental continual learning scheme, proving our approach's effectiveness and reliability even in safety-critical settings, such as autonomous driving. We evaluate our approach on the SemanticKITTI dataset, achieving impressive performances.
Authors: Niklas Deckers, Julia Peters, Martin Potthast
Abstract: Prompt engineering is still the primary way for users of generative text-to-image models to manipulate generated images in a targeted way. Based on treating the model as a continuous function and by passing gradients between the image space and the prompt embedding space, we propose and analyze a new method to directly manipulate the embedding of a prompt instead of the prompt text. We then derive three practical interaction tools to support users with image generation: (1) Optimization of a metric defined in the image space that measures, for example, the image style. (2) Supporting a user in creative tasks by allowing them to navigate in the image space along a selection of directions of "near" prompt embeddings. (3) Changing the embedding of the prompt to include information that a user has seen in a particular seed but has difficulty describing in the prompt. Compared to prompt engineering, user-driven prompt embedding manipulation enables a more fine-grained, targeted control that integrates a user's intentions. Our user study shows that our methods are considered less tedious and that the resulting images are often preferred.
Authors: Xiujun Shu, Wei Wen, Liangsheng Xu, Ruizhi Qiao, Taian Guo, Hanjun Li, Bei Gan, Xiao Wang, Xing Sun
Abstract: Video temporal character grouping locates appearing moments of major characters within a video according to their identities. To this end, recent works have evolved from unsupervised clustering to graph-based supervised clustering. However, graph methods are built upon the premise of fixed affinity graphs, bringing many inexact connections. Besides, they extract multi-modal features with kinds of models, which are unfriendly to deployment. In this paper, we present a unified and dynamic graph (UniDG) framework for temporal character grouping. This is accomplished firstly by a unified representation network that learns representations of multiple modalities within the same space and still preserves the modality's uniqueness simultaneously. Secondly, we present a dynamic graph clustering where the neighbors of different quantities are dynamically constructed for each node via a cyclic matching strategy, leading to a more reliable affinity graph. Thirdly, a progressive association method is introduced to exploit spatial and temporal contexts among different modalities, allowing multi-modal clustering results to be well fused. As current datasets only provide pre-extracted features, we evaluate our UniDG method on a collected dataset named MTCG, which contains each character's appearing clips of face and body and speaking voice tracks. We also evaluate our key components on existing clustering and retrieval datasets to verify the generalization ability. Experimental results manifest that our method can achieve promising results and outperform several state-of-the-art approaches.
Authors: Eva Pachetti, Sara Colantonio
Abstract: The lack of annotated medical images limits the performance of deep learning models, which usually need large-scale labelled datasets. Few-shot learning techniques can reduce data scarcity issues and enhance medical image analysis, especially with meta-learning. This systematic review gives a comprehensive overview of few-shot learning in medical imaging. We searched the literature systematically and selected 80 relevant articles published from 2018 to 2023. We clustered the articles based on medical outcomes, such as tumour segmentation, disease classification, and image registration; anatomical structure investigated (i.e. heart, lung, etc.); and the meta-learning method used. For each cluster, we examined the papers' distributions and the results provided by the state-of-the-art. In addition, we identified a generic pipeline shared among all the studies. The review shows that few-shot learning can overcome data scarcity in most outcomes and that meta-learning is a popular choice to perform few-shot learning because it can adapt to new tasks with few labelled samples. In addition, following meta-learning, supervised learning and semi-supervised learning stand out as the predominant techniques employed to tackle few-shot learning challenges in medical imaging and also best performing. Lastly, we observed that the primary application areas predominantly encompass cardiac, pulmonary, and abdominal domains. This systematic review aims to inspire further research to improve medical image analysis and patient care.
Authors: Gregor Lenz, Garrick Orchard, Sadique Sheik
Abstract: Spiking neural networks (SNNs) promise ultra-low-power applications by exploiting temporal and spatial sparsity. The number of binary activations, called spikes, is proportional to the power consumed when executed on neuromorphic hardware. Training such SNNs using backpropagation through time for vision tasks that rely mainly on spatial features is computationally costly. Training a stateless artificial neural network (ANN) to then convert the weights to an SNN is a straightforward alternative when it comes to image recognition datasets. Most conversion methods rely on rate coding in the SNN to represent ANN activation, which uses enormous amounts of spikes and, therefore, energy to encode information. Recently, temporal conversion methods have shown promising results requiring significantly fewer spikes per neuron, but sometimes complex neuron models. We propose a temporal ANN-to-SNN conversion method, which we call Quartz, that is based on the time to first spike (TTFS). Quartz achieves high classification accuracy and can be easily implemented on neuromorphic hardware while using the least amount of synaptic operations and memory accesses. It incurs a cost of two additional synapses per neuron compared to previous temporal conversion methods, which are readily available on neuromorphic hardware. We benchmark Quartz on MNIST, CIFAR10, and ImageNet in simulation to show the benefits of our method and follow up with an implementation on Loihi, a neuromorphic chip by Intel. We provide evidence that temporal coding has advantages in terms of power consumption, throughput, and latency for similar classification accuracy. Our code and models are publicly available.
Authors: Mihir Prabhudesai, Anirudh Goyal, Deepak Pathak, Katerina Fragkiadaki
Abstract: Text-to-image diffusion models have recently emerged at the forefront of image generation, powered by very large-scale unsupervised or weakly supervised text-to-image training datasets. Due to their unsupervised training, controlling their behavior in downstream tasks, such as maximizing human-perceived image quality, image-text alignment, or ethical image generation, is difficult. Recent works finetune diffusion models to downstream reward functions using vanilla reinforcement learning, notorious for the high variance of the gradient estimators. In this paper, we propose AlignProp, a method that aligns diffusion models to downstream reward functions using end-to-end backpropagation of the reward gradient through the denoising process. While naive implementation of such backpropagation would require prohibitive memory resources for storing the partial derivatives of modern text-to-image models, AlignProp finetunes low-rank adapter weight modules and uses gradient checkpointing, to render its memory usage viable. We test AlignProp in finetuning diffusion models to various objectives, such as image-text semantic alignment, aesthetics, compressibility and controllability of the number of objects present, as well as their combinations. We show AlignProp achieves higher rewards in fewer training steps than alternatives, while being conceptually simpler, making it a straightforward choice for optimizing diffusion models for differentiable reward functions of interest. Code and Visualization results are available at https://align-prop.github.io/.
Authors: Xingcheng Zhou, Mingyu Liu, Ekim Yurtsever, Bare Luka Zagar, Walter Zimmer, Hu Cao, Alois C. Knoll
Abstract: The applications of Vision-Language Models (VLMs) in the field of Autonomous Driving (AD) have attracted widespread attention due to their outstanding performance and the ability to leverage Large Language Models (LLMs). By incorporating language data, driving systems can gain a better understanding of real-world environments, thereby enhancing driving safety and efficiency. In this work, we present a comprehensive and systematic survey of the advances in vision language models in this domain, encompassing perception and understanding, navigation and planning, decision-making and control, end-to-end autonomous driving, and data generation. We introduce the mainstream VLM tasks in AD and the commonly utilized metrics. Additionally, we review current studies and applications in various areas and summarize the existing language-enhanced autonomous driving datasets thoroughly. Lastly, we discuss the benefits and challenges of VLMs in AD and provide researchers with the current research gaps and future trends.
Authors: Xiaodan Du, Nicholas Kolkin, Greg Shakhnarovich, Anand Bhattad
Abstract: Generative models excel at creating images that closely mimic real scenes, suggesting they inherently encode scene representations. We introduce Intrinsic LoRA (I-LoRA), a general approach that uses Low-Rank Adaptation (LoRA) to discover scene intrinsics such as normals, depth, albedo, and shading from a wide array of generative models. I-LoRA is lightweight, adding minimally to the model's parameters and requiring very small datasets for this knowledge discovery. Our approach, applicable to Diffusion models, GANs, and Autoregressive models alike, generates intrinsics using the same output head as the original images. Through control experiments, we establish a correlation between the generative model's quality and the extracted intrinsics' accuracy. Finally, scene intrinsics obtained by our method with just hundreds to thousands of labeled images, perform on par with those from supervised methods trained on millions of labeled examples.
Authors: Zhengyue Zhao, Jinhao Duan, Kaidi Xu, Chenan Wang, Rui Zhang, Zidong Du, Qi Guo, Xing Hu
Abstract: Stable Diffusion has established itself as a foundation model in generative AI artistic applications, receiving widespread research and application. Some recent fine-tuning methods have made it feasible for individuals to implant personalized concepts onto the basic Stable Diffusion model with minimal computational costs on small datasets. However, these innovations have also given rise to issues like facial privacy forgery and artistic copyright infringement. In recent studies, researchers have explored the addition of imperceptible adversarial perturbations to images to prevent potential unauthorized exploitation and infringements when personal data is used for fine-tuning Stable Diffusion. Although these studies have demonstrated the ability to protect images, it is essential to consider that these methods may not be entirely applicable in real-world scenarios. In this paper, we systematically evaluate the use of perturbations to protect images within a practical threat model. The results suggest that these approaches may not be sufficient to safeguard image privacy and copyright effectively. Furthermore, we introduce a purification method capable of removing protected perturbations while preserving the original image structure to the greatest extent possible. Experiments reveal that Stable Diffusion can effectively learn from purified images over all protective methods.
Authors: Zirui Wang, Zhizhou Sha, Zheng Ding, Yilin Wang, Zhuowen Tu
Abstract: We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. Despite its tremendous success, the standard denoising process in the Latent Diffusion Model takes text prompts as conditions only, absent explicit constraint for the consistency between the text prompts and the image contents, leading to unsatisfactory results for composing multiple object categories. TokenCompose aims to improve multi-category instance composition by introducing the token-wise consistency terms between the image content and object segmentation maps in the finetuning stage. TokenCompose can be applied directly to the existing training pipeline of text-conditioned diffusion models without extra human labeling information. By finetuning Stable Diffusion, the model exhibits significant improvements in multi-category instance composition and enhanced photorealism for its generated images. Project link: https://mlpc-ucsd.github.io/TokenCompose
Authors: Kun Yuan, Manasi Kattel, Joel L. Lavanchy, Nassir Navab, Vinkle Srivastav, Nicolas Padoy
Abstract: Modern operating room is becoming increasingly complex, requiring innovative intra-operative support systems. While the focus of surgical data science has largely been on video analysis, integrating surgical computer vision with language capabilities is emerging as a necessity. Our work aims to advance Visual Question Answering (VQA) in the surgical context with scene graph knowledge, addressing two main challenges in the current surgical VQA systems: removing question-condition bias in the surgical VQA dataset and incorporating scene-aware reasoning in the surgical VQA model design. First, we propose a Surgical Scene Graph-based dataset, SSG-QA, generated by employing segmentation and detection models on publicly available datasets. We build surgical scene graphs using spatial and action information of instruments and anatomies. These graphs are fed into a question engine, generating diverse QA pairs. Our SSG-QA dataset provides a more complex, diverse, geometrically grounded, unbiased, and surgical action-oriented dataset compared to existing surgical VQA datasets. We then propose SSG-QA-Net, a novel surgical VQA model incorporating a lightweight Scene-embedded Interaction Module (SIM), which integrates geometric scene knowledge in the VQA model design by employing cross-attention between the textual and the scene features. Our comprehensive analysis of the SSG-QA dataset shows that SSG-QA-Net outperforms existing methods across different question types and complexities. We highlight that the primary limitation in the current surgical VQA systems is the lack of scene knowledge to answer complex queries. We present a novel surgical VQA dataset and model and show that results can be significantly improved by incorporating geometric scene features in the VQA model design. The source code and the dataset will be made publicly available at: https://github.com/CAMMA-public/SSG-QA
Authors: Ying Wang, Tim G. J. Rudner, Andrew Gordon Wilson
Abstract: Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability. To improve the interpretability of vision-language models such as CLIP, we propose a multi-modal information bottleneck (M2IB) approach that learns latent representations that compress irrelevant information while preserving relevant visual and textual features. We demonstrate how M2IB can be applied to attribution analysis of vision-language pretrained models, increasing attribution accuracy and improving the interpretability of such models when applied to safety-critical domains such as healthcare. Crucially, unlike commonly used unimodal attribution methods, M2IB does not require ground truth labels, making it possible to audit representations of vision-language pretrained models when multiple modalities but no ground-truth data is available. Using CLIP as an example, we demonstrate the effectiveness of M2IB attribution and show that it outperforms gradient-based, perturbation-based, and attention-based attribution methods both qualitatively and quantitatively.
Authors: Vardaan Pahuja, Weidi Luo, Yu Gu, Cheng-Hao Tu, Hong-You Chen, Tanya Berger-Wolf, Charles Stewart, Song Gao, Wei-Lun Chao, Yu Su
Abstract: Camera traps are valuable tools in animal ecology for biodiversity monitoring and conservation. However, challenges like poor generalization to deployment at new unseen locations limit their practical application. Images are naturally associated with heterogeneous forms of context possibly in different modalities. In this work, we leverage the structured context associated with the camera trap images to improve out-of-distribution generalization for the task of species identification in camera traps. For example, a photo of a wild animal may be associated with information about where and when it was taken, as well as structured biology knowledge about the animal species. While typically overlooked by existing work, bringing back such context offers several potential benefits for better image understanding, such as addressing data scarcity and enhancing generalization. However, effectively integrating such heterogeneous context into the visual domain is a challenging problem. To address this, we propose a novel framework that reformulates species classification as link prediction in a multimodal knowledge graph (KG). This framework seamlessly integrates various forms of multimodal context for visual recognition. We apply this framework for out-of-distribution species classification on the iWildCam2020-WILDS and Snapshot Mountain Zebra datasets and achieve competitive performance with state-of-the-art approaches. Furthermore, our framework successfully incorporates biological taxonomy for improved generalization and enhances sample efficiency for recognizing under-represented species.
Authors: Brian B. Moser, Arundhati S. Shanbhag, Federico Raue, Stanislav Frolov, Sebastian Palacio, Andreas Dengel
Abstract: Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the realism of those produced by previous generative methods. Despite their promising results, they also come with new challenges that need further research: high computational demands, comparability, lack of explainability, color shifts, and more. Unfortunately, entry into this field is overwhelming because of the abundance of publications. To address this, we provide a unified recount of the theoretical foundations underlying DMs applied to image SR and offer a detailed analysis that underscores the unique characteristics and methodologies within this domain, distinct from broader existing reviews in the field. This survey articulates a cohesive understanding of DM principles and explores current research avenues, including alternative input domains, conditioning techniques, guidance mechanisms, corruption spaces, and zero-shot learning approaches. By offering a detailed examination of the evolution and current trends in image SR through the lens of DMs, this survey sheds light on the existing challenges and charts potential future directions, aiming to inspire further innovation in this rapidly advancing area.
Authors: Justin Tebbe, Jawad Tayyub
Abstract: Diffusion models have found valuable applications in anomaly detection by capturing the nominal data distribution and identifying anomalies via reconstruction. Despite their merits, they struggle to localize anomalies of varying scales, especially larger anomalies such as entire missing components. Addressing this, we present a novel framework that enhances the capability of diffusion models, by extending the previous introduced implicit conditioning approach Meng et al. (2022) in three significant ways. First, we incorporate a dynamic step size computation that allows for variable noising steps in the forward process guided by an initial anomaly prediction. Second, we demonstrate that denoising an only scaled input, without any added noise, outperforms conventional denoising process. Third, we project images in a latent space to abstract away from fine details that interfere with reconstruction of large missing components. Additionally, we propose a fine-tuning mechanism that facilitates the model to effectively grasp the nuances of the target domain. Our method undergoes rigorous evaluation on prominent anomaly detection datasets VisA, BTAD and MVTec yielding strong performance. Importantly, our framework effectively localizes anomalies regardless of their scale, marking a pivotal advancement in diffusion-based anomaly detection.
Authors: Dongqi Fan, Ting Yue, Xin Zhao, Renjing Xu, Liang Chang
Abstract: Recently, there have been significant advancements in Image Restoration based on CNN and transformer. However, the inherent characteristics of the Image Restoration task are often overlooked in many works. They, instead, tend to focus on the basic block design and stack numerous such blocks to the model, leading to parameters redundant and computations unnecessary. Thus, the efficiency of the image restoration is hindered. In this paper, we propose a Lightweight Baseline network for Image Restoration called LIR to efficiently restore the image and remove degradations. First of all, through an ingenious structural design, LIR removes the degradations existing in the local and global residual connections that are ignored by modern networks. Then, a Lightweight Adaptive Attention (LAA) Block is introduced which is mainly composed of proposed Adaptive Filters and Attention Blocks. The proposed Adaptive Filter is used to adaptively extract high-frequency information and enhance object contours in various IR tasks, and Attention Block involves a novel Patch Attention module to approximate the self-attention part of the transformer. On the deraining task, our LIR achieves the state-of-the-art Structure Similarity Index Measure (SSIM) and comparable performance to state-of-the-art models on Peak Signal-to-Noise Ratio (PSNR). For denoising, dehazing, and deblurring tasks, LIR also achieves a comparable performance to state-of-the-art models with a parameter size of about 30\%. In addition, it is worth noting that our LIR produces better visual results that are more in line with the human aesthetic.
Authors: Hamed Amini Amirkolaee, Miaojing Shi, Lianghua He, Mark Mulligan
Abstract: The process of estimating and counting tree density using only a single aerial or satellite image is a difficult task in the fields of photogrammetry and remote sensing. However, it plays a crucial role in the management of forests. The huge variety of trees in varied topography severely hinders tree counting models to perform well. The purpose of this paper is to propose a framework that is learnt from the source domain with sufficient labeled trees and is adapted to the target domain with only a limited number of labeled trees. Our method, termed as AdaTreeFormer, contains one shared encoder with a hierarchical feature extraction scheme to extract robust features from the source and target domains. It also consists of three subnets: two for extracting self-domain attention maps from source and target domains respectively and one for extracting cross-domain attention maps. For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains. We also adopt adversarial learning into the framework to further reduce the gap between source and target domains. Our AdaTreeFormer is evaluated on six designed domain adaptation tasks using three tree counting datasets, \ie Jiangsu, Yosemite, and London. Experimental results show that AdaTreeFormer significantly surpasses the state of the art, \eg in the cross domain from the Yosemite to Jiangsu dataset, it achieves a reduction of 15.9 points in terms of the absolute counting errors and an increase of 10.8\% in the accuracy of the detected trees' locations. The codes and datasets are available at \emph{\color{magenta}{https://github.com/HAAClassic/AdaTreeFormer}}.
Authors: Shivang Chopra, Suraj Kothawade, Houda Aynaou, Aman Chadha
Abstract: This paper introduces a novel approach to leverage the generalizability of Diffusion Models for Source-Free Domain Adaptation (DM-SFDA). Our proposed DMSFDA method involves fine-tuning a pre-trained text-to-image diffusion model to generate source domain images using features from the target images to guide the diffusion process. Specifically, the pre-trained diffusion model is fine-tuned to generate source samples that minimize entropy and maximize confidence for the pre-trained source model. We then use a diffusion model-based image mixup strategy to bridge the domain gap between the source and target domains. We validate our approach through comprehensive experiments across a range of datasets, including Office-31 [39], Office-Home [48], and VisDA [35]. The results demonstrate significant improvements in SFDA performance, highlighting the potential of diffusion models in generating contextually relevant, domain-specific images.
Authors: Shubhabrata Mukherjee, Cory Beard, Zhu Li
Abstract: Low-light conditions and occluded scenarios impede object detection in real-world Internet of Things (IoT) applications like autonomous vehicles and security systems. While advanced machine learning models strive for accuracy, their computational demands clash with the limitations of resource-constrained devices, hampering real-time performance. In our current research, we tackle this challenge, by introducing ``YOLO Phantom", one of the smallest YOLO models ever conceived. YOLO Phantom utilizes the novel Phantom Convolution block, achieving comparable accuracy to the latest YOLOv8n model while simultaneously reducing both parameters and model size by 43\%, resulting in a significant 19\% reduction in Giga Floating-Point Operations (GFLOPs). YOLO Phantom leverages transfer learning on our multimodal RGB-infrared dataset to address low-light and occlusion issues, equipping it with robust vision under adverse conditions. Its real-world efficacy is demonstrated on an IoT platform with advanced low-light and RGB cameras, seamlessly connecting to an AWS-based notification endpoint for efficient real-time object detection. Benchmarks reveal a substantial boost of 17\% and 14\% in frames per second (FPS) for thermal and RGB detection, respectively, compared to the baseline YOLOv8n model. For community contribution, both the code and the multimodal dataset are available on GitHub.
Authors: Zi Ye, Tianxiang Chen, Fangyijie Wang, Hanwei Zhang, Lijun Zhang
Abstract: In pediatric cardiology, the accurate and immediate assessment of cardiac function through echocardiography is crucial since it can determine whether urgent intervention is required in many emergencies. However, echocardiography is characterized by ambiguity and heavy background noise interference, causing more difficulty in accurate segmentation. Present methods lack efficiency and are prone to mistakenly segmenting some background noise areas, such as the left ventricular area, due to noise disturbance. To address these issues, we introduce P-Mamba, which integrates the Mixture of Experts (MoE) concept for efficient pediatric echocardiographic left ventricular segmentation. Specifically, we utilize the recently proposed ViM layers from the vision mamba to enhance our model's computational and memory efficiency while modeling global dependencies.In the DWT-based Perona-Malik Diffusion (PMD) Block, we devise a PMD Block for noise suppression while preserving the left ventricle's local shape cues. Consequently, our proposed P-Mamba innovatively combines the PMD's noise suppression and local feature extraction capabilities with Mamba's efficient design for global dependency modeling. We conducted segmentation experiments on two pediatric ultrasound datasets and a general ultrasound dataset, namely Echonet-dynamic, and achieved state-of-the-art (SOTA) results. Leveraging the strengths of the P-Mamba block, our model demonstrates superior accuracy and efficiency compared to established models, including vision transformers with quadratic and linear computational complexity.
Authors: Xiaoyu Tian, Junru Gu, Bailin Li, Yicheng Liu, Yang Wang, Zhiyong Zhao, Kun Zhan, Peng Jia, Xianpeng Lang, Hang Zhao
Abstract: A primary hurdle of autonomous driving in urban environments is understanding complex and long-tail scenarios, such as challenging road conditions and delicate human behaviors. We introduce DriveVLM, an autonomous driving system leveraging Vision-Language Models (VLMs) for enhanced scene understanding and planning capabilities. DriveVLM integrates a unique combination of reasoning modules for scene description, scene analysis, and hierarchical planning. Furthermore, recognizing the limitations of VLMs in spatial reasoning and heavy computational requirements, we propose DriveVLM-Dual, a hybrid system that synergizes the strengths of DriveVLM with the traditional autonomous driving pipeline. Experiments on both the nuScenes dataset and our SUP-AD dataset demonstrate the efficacy of DriveVLM and DriveVLM-Dual in handling complex and unpredictable driving conditions. Finally, we deploy the DriveVLM-Dual on a production vehicle, verifying it is effective in real-world autonomous driving environments.
Authors: Lvmin Zhang, Maneesh Agrawala
Abstract: We present LayerDiffuse, an approach enabling large-scale pretrained latent diffusion models to generate transparent images. The method allows generation of single transparent images or of multiple transparent layers. The method learns a "latent transparency" that encodes alpha channel transparency into the latent manifold of a pretrained latent diffusion model. It preserves the production-ready quality of the large diffusion model by regulating the added transparency as a latent offset with minimal changes to the original latent distribution of the pretrained model. In this way, any latent diffusion model can be converted into a transparent image generator by finetuning it with the adjusted latent space. We train the model with 1M transparent image layer pairs collected using a human-in-the-loop collection scheme. We show that latent transparency can be applied to different open source image generators, or be adapted to various conditional control systems to achieve applications like foreground/background-conditioned layer generation, joint layer generation, structural control of layer contents, etc. A user study finds that in most cases (97%) users prefer our natively generated transparent content over previous ad-hoc solutions such as generating and then matting. Users also report the quality of our generated transparent images is comparable to real commercial transparent assets like Adobe Stock.
Authors: Katia Genovese
Abstract: Camera calibration is a process of paramount importance in computer vision applications that require accurate quantitative measurements. The popular method developed by Zhang relies on the use of a large number of images of a planar grid of fiducial points captured in multiple poses. Although flexible and easy to implement, Zhang's method has some limitations. The simultaneous optimization of the entire parameter set, including the coefficients of a predefined distortion model, may result in poor distortion correction at the image boundaries or in miscalculation of the intrinsic parameters, even with a reasonably small reprojection error. Indeed, applications involving image stitching (e.g. multi-camera systems) require accurate mapping of distortion up to the outermost regions of the image. Moreover, intrinsic parameters affect the accuracy of camera pose estimation, which is fundamental for applications such as vision servoing in robot navigation and automated assembly. This paper proposes a method for estimating the complete set of calibration parameters from a single image of a planar speckle pattern covering the entire sensor. The correspondence between image points and physical points on the calibration target is obtained using Digital Image Correlation. The effective focal length and the extrinsic parameters are calculated separately after a prior evaluation of the principal point. At the end of the procedure, a dense and uniform model-free distortion map is obtained over the entire image. Synthetic data with different noise levels were used to test the feasibility of the proposed method and to compare its metrological performance with Zhang's method. Real-world tests demonstrate the potential of the developed method to reveal aspects of the image formation that are hidden by averaging over multiple images.
Authors: Zhende Song, Chenchen Wang, Jiamu Sheng, Chi Zhang, Gang Yu, Jiayuan Fan, Tao Chen
Abstract: Development of multimodal models has marked a significant step forward in how machines understand videos. These models have shown promise in analyzing short video clips. However, when it comes to longer formats like movies, they often fall short. The main hurdles are the lack of high-quality, diverse video data and the intensive work required to collect or annotate such data. In face of these challenges, we propose MovieLLM, a novel framework designed to synthesize consistent and high-quality video data for instruction tuning. The pipeline is carefully designed to control the style of videos by improving textual inversion technique with powerful text generation capability of GPT-4. As the first framework to do such thing, our approach stands out for its flexibility and scalability, empowering users to create customized movies with only one description. This makes it a superior alternative to traditional data collection methods. Our extensive experiments validate that the data produced by MovieLLM significantly improves the performance of multimodal models in understanding complex video narratives, overcoming the limitations of existing datasets regarding scarcity and bias.
Authors: Tianxiang Chen, Zi Ye, Zhentao Tan, Tao Gong, Yue Wu, Qi Chu, Bin Liu, Nenghai Yu, Jieping Ye
Abstract: Recently, infrared small target detection (ISTD) has made significant progress, thanks to the development of basic models. Specifically, the models combining CNNs with transformers can successfully extract both local and global features. However, the disadvantage of the transformer is also inherited, i.e., the quadratic computational complexity to sequence length. Inspired by the recent basic model with linear complexity for long-distance modeling, Mamba, we explore the potential of this state space model for ISTD task in terms of effectiveness and efficiency in the paper. However, directly applying Mamba achieves suboptimal performances due to the insufficient harnessing of local features, which are imperative for detecting small targets. Instead, we tailor a nested structure, Mamba-in-Mamba (MiM-ISTD), for efficient ISTD. It consists of Outer and Inner Mamba blocks to adeptly capture both global and local features. Specifically, we treat the local patches as "visual sentences" and use the Outer Mamba to explore the global information. We then decompose each visual sentence into sub-patches as "visual words" and use the Inner Mamba to further explore the local information among words in the visual sentence with negligible computational costs. By aggregating the visual word and visual sentence features, our MiM-ISTD can effectively explore both global and local information. Experiments on NUAA-SIRST and IRSTD-1k show the superior accuracy and efficiency of our method. Specifically, MiM-ISTD is $8 \times$ faster than the SOTA method and reduces GPU memory usage by 62.2$\%$ when testing on $2048 \times 2048$ images, overcoming the computation and memory constraints on high-resolution infrared images.
Authors: Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz, Ying Wei
Abstract: Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the best of both worlds, meta-tuning introduces a subsequent optimization stage of foundation models but has so far only shown limited success and crucially tends to underperform on out-of-distribution (OOD) tasks. In this paper, we introduce Sparse MetA-Tuning (SMAT), a method inspired by sparse mixture-of-experts approaches and trained to isolate subsets of pre-trained parameters automatically for meta-tuning on each task. SMAT successfully overcomes OOD sensitivity and delivers on the promise of enhancing the transfer abilities of vision foundation models beyond parameter-efficient fine-tuning. We establish new state-of-the-art results on a challenging combination of Meta-Dataset augmented with additional OOD tasks in both zero-shot and gradient-based adaptation settings. In addition, we provide a thorough analysis of the superiority of learned over hand-designed sparsity patterns for sparse expert methods and the pivotal importance of the sparsity level in balancing between in-distribution and out-of-distribution generalization. Our code is publicly available.
Authors: Hongxiang Zhao, Xili Dai, Jianan Wang, Shengbang Tong, Jingyuan Zhang, Weida Wang, Lei Zhang, Yi Ma
Abstract: Large image diffusion models have demonstrated zero-shot capability in novel view synthesis (NVS). However, existing diffusion-based NVS methods struggle to generate novel views that are accurately consistent with the corresponding ground truth poses and appearances, even on the training set. This consequently limits the performance of downstream tasks, such as image-to-multiview generation and 3D reconstruction. We realize that such inconsistency is largely due to the fact that it is difficult to enforce accurate pose and appearance alignment directly in the diffusion training, as mostly done by existing methods such as Zero123. To remedy this problem, we propose Ctrl123, a closed-loop transcription-based NVS diffusion method that enforces alignment between the generated view and ground truth in a pose-sensitive feature space. Our extensive experiments demonstrate the effectiveness of Ctrl123 on the tasks of NVS and 3D reconstruction, achieving significant improvements in both multiview-consistency and pose-consistency over existing methods.
Authors: Mrityunjoy Gain, Avi Deb Raha, Rameswar Debnath
Abstract: In this paper, we formulate the colorization problem into a multinomial classification problem and then apply a weighted function to classes. We propose a set of formulas to transform color values into color classes and vice versa. To optimize the classes, we experiment with different bin sizes for color class transformation. Observing class appearance, standard deviation, and model parameters on various extremely large-scale real-time images in practice we propose 532 color classes for our classification task. During training, we propose a class-weighted function based on true class appearance in each batch to ensure proper saturation of individual objects. We adjust the weights of the major classes, which are more frequently observed, by lowering them, while escalating the weights of the minor classes, which are less commonly observed. In our class re-weight formula, we propose a hyper-parameter for finding the optimal trade-off between the major and minor appeared classes. As we apply regularization to enhance the stability of the minor class, occasional minor noise may appear at the object's edges. We propose a novel object-selective color harmonization method empowered by the Segment Anything Model (SAM) to refine and enhance these edges. We propose two new color image evaluation metrics, the Color Class Activation Ratio (CCAR), and the True Activation Ratio (TAR), to quantify the richness of color components. We compare our proposed model with state-of-the-art models using six different dataset: Place, ADE, Celeba, COCO, Oxford 102 Flower, and ImageNet, in qualitative and quantitative approaches. The experimental results show that our proposed model outstrips other models in visualization, CNR and in our proposed CCAR and TAR measurement criteria while maintaining satisfactory performance in regression (MSE, PSNR), similarity (SSIM, LPIPS, UIUI), and generative criteria (FID).
Authors: Yuxuan Li, Xiang Li, Yimian Dai, Qibin Hou, Li Liu, Yongxiang Liu, Ming-Ming Cheng, Jian Yang
Abstract: Remote sensing images pose distinct challenges for downstream tasks due to their inherent complexity. While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios. Such prior knowledge can be useful because remote sensing objects may be mistakenly recognized without referencing a sufficiently long-range context, which can vary for different objects. This paper considers these priors and proposes a lightweight Large Selective Kernel Network (LSKNet) backbone. LSKNet can dynamically adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios. To our knowledge, large and selective kernel mechanisms have not been previously explored in remote sensing images. Without bells and whistles, our lightweight LSKNet sets new state-of-the-art scores on standard remote sensing classification, object detection and semantic segmentation benchmarks. Our comprehensive analysis further validated the significance of the identified priors and the effectiveness of LSKNet. The code is available at https://github.com/zcablii/LSKNet.
Authors: Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu
Abstract: While recent Transformer-based architectures generate improved deblurring outcomes than prior convolutional neural networks (CNNs), the large model size and heavy computational cost are still two bothersome issues which have not been fully resolved. Besides, the existing state-of-the-art (SOTA) approach trained on synthetic datasets may not perform well on a broad range of unseen real-world deblurring scenarios. To this end, we propose DeblurDiNAT, a compact and robust encoder-decoder Transformer which efficiently restores clean images from blurred ones. We adopt an alternating dilation factor structure to learn local and global blur patterns. Also, we observe that Transformers with conventional self-attention layers do not always produce good deblurred results. To solve this problem, we propose a channel modulation self-attention (CMSA) block, where a local cross-channel learner (LCCL) is utilized to capture channel relationships. In addition, we present a divide and multiply feed-forward network (DMFN) allowing fast feature propagation. Moreover, we design a lightweight dual-stage feature fusion (LDFF) module to introduce non-linearity. Comprehensive experimental results show that the proposed DeblurDiNAT provides a significant performance boost without a noticeable increase in computational cost over the baseline, and achieves SOTA performance on mainstream image deblurring datasets. Compared to nearest competitors, our space-efficient and time-saving model demonstrates a stronger generalization ability with 3%-68% fewer parameters and produces deblurred images that are visually closer to the ground truth.
Authors: Qiang Hu, Zhenyu Yi, Ying Zhou, Ting Li, Fan Huang, Mei Liu, Qiang Li, Zhiwei Wang
Abstract: We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the box edges must precisely touch the target boundaries, MonoBox leverages imprecisely-annotated boxes to achieve robust pixel-wise segmentation. The 'linchpin' is that, within the noisy zones around box edges, MonoBox discards the traditional misguiding multiple-instance learning loss, and instead optimizes a carefully-designed objective, termed monotonicity constraint. Along directions transitioning from the foreground to background, this new constraint steers responses to adhere to a trend of monotonically decreasing values. Consequently, the originally unreliable learning within the noisy zones is transformed into a correct and effective monotonicity optimization. Moreover, an adaptive label correction is introduced, enabling MonoBox to enhance the tightness of box annotations using predicted masks from the previous epoch and dynamically shrink the noisy zones as training progresses. We verify MonoBox in the box-supervised segmentation task of polyps, where satisfying box-tightness is challenging due to the vague boundaries between the polyp and normal tissues. Experiments on both public synthetic and in-house real noisy datasets demonstrate that MonoBox exceeds other anti-noise state-of-the-arts by improving Dice by at least 5.5% and 3.3%, respectively. Codes are at https://github.com/Huster-Hq/MonoBox.
Authors: Jinbae Im, JeongYeon Nam, Nokyung Park, Hyungmin Lee, Seunghyun Park
Abstract: Scene Graph Generation (SGG) is a challenging task of detecting objects and predicting relationships between objects. After DETR was developed, one-stage SGG models based on a one-stage object detector have been actively studied. However, complex modeling is used to predict the relationship between objects, and the inherent relationship between object queries learned in the multi-head self-attention of the object detector has been neglected. We propose a lightweight one-stage SGG model that extracts the relation graph from the various relationships learned in the multi-head self-attention layers of the DETR decoder. By fully utilizing the self-attention by-products, the relation graph can be extracted effectively with a shallow relation extraction head. Considering the dependency of the relation extraction task on the object detection task, we propose a novel relation smoothing technique that adjusts the relation label adaptively according to the quality of the detected objects. By the relation smoothing, the model is trained according to the continuous curriculum that focuses on object detection task at the beginning of training and performs multi-task learning as the object detection performance gradually improves. Furthermore, we propose a connectivity prediction task that predicts whether a relation exists between object pairs as an auxiliary task of the relation extraction. We demonstrate the effectiveness and efficiency of our method for the Visual Genome and Open Image V6 datasets. Our code is publicly available at https://github.com/naver-ai/egtr.
Authors: Owen Oertell, Jonathan D. Chang, Yiyi Zhang, Kiant\'e Brantley, Wen Sun
Abstract: Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies inherit the same iterative sampling process of diffusion models that causes slow generation. To overcome this limitation, consistency models proposed learning a new class of generative models that directly map noise to data, resulting in a model that can generate an image in as few as one sampling iteration. In this work, to optimize text-to-image generative models for task specific rewards and enable fast training and inference, we propose a framework for fine-tuning consistency models via RL. Our framework, called Reinforcement Learning for Consistency Model (RLCM), frames the iterative inference process of a consistency model as an RL procedure. Comparing to RL finetuned diffusion models, RLCM trains significantly faster, improves the quality of the generation measured under the reward objectives, and speeds up the inference procedure by generating high quality images with as few as two inference steps. Experimentally, we show that RLCM can adapt text-to-image consistency models to objectives that are challenging to express with prompting, such as image compressibility, and those derived from human feedback, such as aesthetic quality. Our code is available at https://rlcm.owenoertell.com.
Authors: Gianluca Barone, Aashrit Cunchala, Rudy Nunez
Abstract: Standard classification theory assumes that the distribution of images in the test and training sets are identical. Unfortunately, real-life scenarios typically feature unseen data ("out-of-distribution data") which is different from data in the training distribution("in-distribution"). This issue is most prevalent in social justice problems where data from under-represented groups may appear in the test data without representing an equal proportion of the training data. This may result in a model returning confidently wrong decisions and predictions. We are interested in the following question: Can the performance of a neural network improve on facial images of out-of-distribution data when it is trained simultaneously on multiple datasets of in-distribution data? We approach this problem by incorporating the Outlier Exposure model and investigate how the model's performance changes when other datasets of facial images were implemented. We observe that the accuracy and other metrics of the model can be increased by applying Outlier Exposure, incorporating a trainable weight parameter to increase the machine's emphasis on outlier images, and by re-weighting the importance of different class labels. We also experimented with whether sorting the images and determining outliers via image features would have more of an effect on the metrics than sorting by average pixel value. Our goal was to make models not only more accurate but also more fair by scanning a more expanded range of images. We also tested the datasets in reverse order to see whether a more fair dataset with balanced features has an effect on the model's accuracy.
Authors: Johannes Hoster, Sara Al-Sayed, Felix Biessmann, Alexander Glaser, Kristian Hildebrand, Igor Moric, Tuong Vy Nguyen
Abstract: Satellite imagery is regarded as a great opportunity for citizen-based monitoring of activities of interest. Relevant imagery may however not be available at sufficiently high resolution, quality, or cadence -- let alone be uniformly accessible to open-source analysts. This limits an assessment of the true long-term potential of citizen-based monitoring of nuclear activities using publicly available satellite imagery. In this article, we demonstrate how modern game engines combined with advanced machine-learning techniques can be used to generate synthetic imagery of sites of interest with the ability to choose relevant parameters upon request; these include time of day, cloud cover, season, or level of activity onsite. At the same time, resolution and off-nadir angle can be adjusted to simulate different characteristics of the satellite. While there are several possible use-cases for synthetic imagery, here we focus on its usefulness to support tabletop exercises in which simple monitoring scenarios can be examined to better understand verification capabilities enabled by new satellite constellations and very short revisit times.
Authors: Ye Mao, Junpeng Jing, Krystian Mikolajczyk
Abstract: Recent open-world 3D representation learning methods using Vision-Language Models (VLMs) to align 3D data with image-text information have shown superior 3D zero-shot performance. However, CAD-rendered images for this alignment often lack realism and texture variation, compromising alignment robustness. Moreover, the volume discrepancy between 3D and 2D pretraining datasets highlights the need for effective strategies to transfer the representational abilities of VLMs to 3D learning. In this paper, we present OpenDlign, a novel open-world 3D model using depth-aligned images generated from a diffusion model for robust multimodal alignment. These images exhibit greater texture diversity than CAD renderings due to the stochastic nature of the diffusion model. By refining the depth map projection pipeline and designing depth-specific prompts, OpenDlign leverages rich knowledge in pre-trained VLM for 3D representation learning with streamlined fine-tuning. Our experiments show that OpenDlign achieves high zero-shot and few-shot performance on diverse 3D tasks, despite only fine-tuning 6 million parameters on a limited ShapeNet dataset. In zero-shot classification, OpenDlign surpasses previous models by 8.0% on ModelNet40 and 16.4% on OmniObject3D. Additionally, using depth-aligned images for multimodal alignment consistently enhances the performance of other state-of-the-art models.
Authors: Dong Lao, Congli Wang, Alex Wong, Stefano Soatto
Abstract: We describe a method for recovering the irradiance underlying a collection of images corrupted by atmospheric turbulence. Since supervised data is often technically impossible to obtain, assumptions and biases have to be imposed to solve this inverse problem, and we choose to model them explicitly. Rather than initializing a latent irradiance ("template") by heuristics to estimate deformation, we select one of the images as a reference, and model the deformation in this image by the aggregation of the optical flow from it to other images, exploiting a prior imposed by Central Limit Theorem. Then with a novel flow inversion module, the model registers each image TO the template but WITHOUT the template, avoiding artifacts related to poor template initialization. To illustrate the robustness of the method, we simply (i) select the first frame as the reference and (ii) use the simplest optical flow to estimate the warpings, yet the improvement in registration is decisive in the final reconstruction, as we achieve state-of-the-art performance despite its simplicity. The method establishes a strong baseline that can be further improved by integrating it seamlessly into more sophisticated pipelines, or with domain-specific methods if so desired.
Authors: Jiawei Shi, Hui Deng, Yuchao Dai
Abstract: Even though Non-rigid Structure-from-Motion (NRSfM) has been extensively studied and great progress has been made, there are still key challenges that hinder their broad real-world applications: 1) the inherent motion/rotation ambiguity requires either explicit camera motion recovery with extra constraint or complex Procrustean Alignment; 2) existing low-rank modeling of the global shape can over-penalize drastic deformations in the 3D shape sequence. This paper proposes to resolve the above issues from a spatial-temporal modeling perspective. First, we propose a novel Temporally-smooth Procrustean Alignment module that estimates 3D deforming shapes and adjusts the camera motion by aligning the 3D shape sequence consecutively. Our new alignment module remedies the requirement of complex reference 3D shape during alignment, which is more conductive to non-isotropic deformation modeling. Second, we propose a spatial-weighted approach to enforce the low-rank constraint adaptively at different locations to accommodate drastic spatially-variant deformation reconstruction better. Our modeling outperform existing low-rank based methods, and extensive experiments across different datasets validate the effectiveness of our method.
Authors: Kaiyu Li, Xiangyong Cao, Yupeng Deng, Junmin Liu, Deyu Meng, Zhi Wang
Abstract: Change Detection (CD) aims to identify pixels with semantic changes between images. However, annotating massive numbers of pixel-level images is labor-intensive and costly, especially for multi-temporal images, which require pixel-wise comparisons by human experts. Considering the excellent performance of visual language models (VLMs) for zero-shot, open-vocabulary, etc. with prompt-based reasoning, it is promising to utilize VLMs to make better CD under limited labeled data. In this paper, we propose a VLM guidance-based semi-supervised CD method, namely DiffMatch. The insight of DiffMatch is to synthesize free change labels using VLMs to provide additional supervision signals for unlabeled data. However, almost all current VLMs are designed for single-temporal images and cannot be directly applied to bi- or multi-temporal images. Motivated by this, we first propose a VLM-based mixed change event generation (CEG) strategy to yield pseudo labels for unlabeled CD data. Since the additional supervised signals provided by these VLM-driven pseudo labels may conflict with the pseudo labels from the consistency regularization paradigm (e.g. FixMatch), we propose the dual projection head for de-entangling different signal sources. Further, we explicitly decouple the bi-temporal images semantic representation through two auxiliary segmentation decoders, which are also guided by VLM. Finally, to make the model more adequately capture change representations, we introduce metric-aware supervision by feature-level contrastive loss in auxiliary branches. Extensive experiments show the advantage of DiffMatch. For instance, DiffMatch improves the FixMatch baseline by +5.3 IoU on WHU-CD and by +2.4 IoU on LEVIR-CD with 5% labels. In addition, our CEG strategy, in an un-supervised manner, can achieve performance far superior to state-of-the-art un-supervised CD methods.
Authors: Zhizhen Zhang, Ning Wang, Haojie Li, Zhihui Wang
Abstract: Semantic location prediction aims to derive meaningful location insights from multimodal social media posts, offering a more contextual understanding of daily activities than using GPS coordinates. This task faces significant challenges due to the noise and modality heterogeneity in "text-image" posts. Existing methods are generally constrained by inadequate feature representations and modal interaction, struggling to effectively reduce noise and modality heterogeneity. To address these challenges, we propose a Similarity-Guided Multimodal Fusion Transformer (SG-MFT) for predicting the semantic locations of users from their multimodal posts. First, we incorporate high-quality text and image representations by utilizing a pre-trained large vision-language model. Then, we devise a Similarity-Guided Interaction Module (SIM) to alleviate modality heterogeneity and noise interference by incorporating both coarse-grained and fine-grained similarity guidance for improving modality interactions. Specifically, we propose a novel similarity-aware feature interpolation attention mechanism at the coarse-grained level, leveraging modality-wise similarity to mitigate heterogeneity and reduce noise within each modality. At the fine-grained level, we utilize a similarity-aware feed-forward block and element-wise similarity to further address the issue of modality heterogeneity. Finally, building upon pre-processed features with minimal noise and modal interference, we devise a Similarity-aware Fusion Module (SFM) to fuse two modalities with a cross-attention mechanism. Comprehensive experimental results clearly demonstrate the superior performance of our proposed method.
Authors: Hongsheng Wang, Weiyue Zhang, Sihao Liu, Xinrui Zhou, Jing Li, Zhanyun Tang, Shengyu Zhang, Fei Wu, Feng Lin
Abstract: Although 3D Gaussian Splatting (3DGS) has recently made progress in 3D human reconstruction, it primarily relies on 2D pixel-level supervision, overlooking the geometric complexity and topological relationships of different body parts. To address this gap, we introduce the Hierarchical Graph Human Gaussian Control (HUGS) framework for achieving high-fidelity 3D human reconstruction. Our approach involves leveraging explicitly semantic priors of body parts to ensure the consistency of geometric topology, thereby enabling the capture of the complex geometrical and topological associations among body parts. Additionally, we disentangle high-frequency features from global human features to refine surface details in body parts. Extensive experiments demonstrate that our method exhibits superior performance in human body reconstruction, particularly in enhancing surface details and accurately reconstructing body part junctions. Codes are available at https://wanghongsheng01.github.io/HUGS/.
Authors: Hongsheng Wang, Xiang Cai, Xi Sun, Jinhong Yue, Zhanyun Tang, Shengyu Zhang, Feng Lin, Fei Wu
Abstract: Single-view clothed human reconstruction holds a central position in virtual reality applications, especially in contexts involving intricate human motions. It presents notable challenges in achieving realistic clothing deformation. Current methodologies often overlook the influence of motion on surface deformation, resulting in surfaces lacking the constraints imposed by global motion. To overcome these limitations, we introduce an innovative framework, Motion-Based 3D Clo}thed Humans Synthesis (MOSS), which employs kinematic information to achieve motion-aware Gaussian split on the human surface. Our framework consists of two modules: Kinematic Gaussian Locating Splatting (KGAS) and Surface Deformation Detector (UID). KGAS incorporates matrix-Fisher distribution to propagate global motion across the body surface. The density and rotation factors of this distribution explicitly control the Gaussians, thereby enhancing the realism of the reconstructed surface. Additionally, to address local occlusions in single-view, based on KGAS, UID identifies significant surfaces, and geometric reconstruction is performed to compensate for these deformations. Experimental results demonstrate that MOSS achieves state-of-the-art visual quality in 3D clothed human synthesis from monocular videos. Notably, we improve the Human NeRF and the Gaussian Splatting by 33.94% and 16.75% in LPIPS* respectively. Codes are available at https://wanghongsheng01.github.io/MOSS/.
Authors: Hao Liu, Yang Yang, Yunxia Liu
Abstract: Face Super-Resolution (FSR) aims to recover high-resolution (HR) face images from low-resolution (LR) ones. Despite the progress made by convolutional neural networks in FSR, the results of existing approaches are not ideal due to their low reconstruction efficiency and insufficient utilization of prior information. Considering that faces are highly structured objects, effectively leveraging facial priors to improve FSR results is a worthwhile endeavor. This paper proposes a novel network architecture called W-Net to address this challenge. W-Net leverages meticulously designed Parsing Block to fully exploit the resolution potential of LR image. We use this parsing map as an attention prior, effectively integrating information from both the parsing map and LR images. Simultaneously, we perform multiple fusions in various dimensions through the W-shaped network structure combined with the LPF(LR-Parsing Map Fusion Module). Additionally, we utilize a facial parsing graph as a mask, assigning different weights and loss functions to key facial areas to balance the performance of our reconstructed facial images between perceptual quality and pixel accuracy. We conducted extensive comparative experiments, not only limited to conventional facial super-resolution metrics but also extending to downstream tasks such as facial recognition and facial keypoint detection. The experiments demonstrate that W-Net exhibits outstanding performance in quantitative metrics, visual quality, and downstream tasks.
Authors: Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang
Abstract: Diffusion-based text-to-image generation models trained on extensive text-image pairs have shown the capacity to generate photorealistic images consistent with textual descriptions. However, a significant limitation of these models is their slow sample generation, which requires iterative refinement through the same network. In this paper, we enhance Score identity Distillation (SiD) by developing long and short classifier-free guidance (LSG) to efficiently distill pretrained Stable Diffusion models without using real training data. SiD aims to optimize a model-based explicit score matching loss, utilizing a score-identity-based approximation alongside the proposed LSG for practical computation. By training exclusively with fake images synthesized with its one-step generator, SiD equipped with LSG rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Specifically, its data-free distillation of Stable Diffusion 1.5 achieves a record low FID of 8.15 on the COCO-2014 validation set, with a CLIP score of 0.304 at an LSG scale of 1.5, and a FID of 9.56 with a CLIP score of 0.313 at an LSG scale of 2. Our SiD-LSG code and distilled one-step text-to-image generators are available at https://github.com/mingyuanzhou/SiD-LSG
Authors: Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
Abstract: We interpret the function of individual neurons in CLIP by automatically describing them using text. Analyzing the direct effects (i.e. the flow from a neuron through the residual stream to the output) or the indirect effects (overall contribution) fails to capture the neurons' function in CLIP. Therefore, we present the "second-order lens", analyzing the effect flowing from a neuron through the later attention heads, directly to the output. We find that these effects are highly selective: for each neuron, the effect is significant for <2% of the images. Moreover, each effect can be approximated by a single direction in the text-image space of CLIP. We describe neurons by decomposing these directions into sparse sets of text representations. The sets reveal polysemantic behavior - each neuron corresponds to multiple, often unrelated, concepts (e.g. ships and cars). Exploiting this neuron polysemy, we mass-produce "semantic" adversarial examples by generating images with concepts spuriously correlated to the incorrect class. Additionally, we use the second-order effects for zero-shot segmentation and attribute discovery in images. Our results indicate that a scalable understanding of neurons can be used for model deception and for introducing new model capabilities.
Authors: Ge Ya Luo, Zhi Hao Luo, Anthony Gosselin, Alexia Jolicoeur-Martineau, Christopher Pal
Abstract: With recent advances in video prediction, controllable video generation has been attracting more attention. Generating high fidelity videos according to simple and flexible conditioning is of particular interest. To this end, we propose a controllable video generation model using pixel level renderings of 2D or 3D bounding boxes as conditioning. In addition, we also create a bounding box predictor that, given the initial and ending frames' bounding boxes, can predict up to 15 bounding boxes per frame for all the frames in a 25-frame clip. We perform experiments across 3 well-known AV video datasets: KITTI, Virtual-KITTI 2 and BDD100k.
Authors: Changsong Liu, Wei Zhang, Yanyan Liu, Yuming Li, Mingyang Li, Wenlin Li, Yimeng Fan, Liang Zhang
Abstract: Edge detection is a fundamental task in computer vision. It has made great progress under the development of deep convolutional neural networks (DCNNs), some of which have achieved a beyond human-level performance. However, recent top-performing edge detection methods tend to generate thick and noisy edge lines. In this work, we solve this problem from two aspects: (1) leveraging the precise edge pixel location characteristics of second-order image derivatives, and (2) alleviating the issue of imbalanced pixel distribution. We propose a second-order derivative-based multi-scale contextual enhancement module (SDMC) to help the model locate true edge pixels accurately and construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue. We test our method on three standard benchmarks and the experiment results illustrate that our method can make the output edge maps crisp and achieves a top performance among several state-of-the-art methods on the BSDS500 dataset (ODS F-score in standard evaluation is 0.829, in crispness evaluation is 0.720), NYUD-V2 dataset (ODS F-score in standard evaluation is 0.768, in crispness evaluation is 0.546), and BIPED dataset (ODS F-score in standard evaluation is 0.903).
Authors: Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu, Bang Liu, Yoshua Bengio
Abstract: We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
Authors: Mu Wang
Abstract: The problem of Domain Adaptive in the field of Object Detection involves the transfer of object detection models from labeled source domains to unannotated target domains. Recent advancements in this field aim to address domain discrepancies by aligning pixel-pairs across domains within a non-Euclidean graphical space, thereby minimizing semantic distribution variance. Despite their remarkable achievements, these methods often use coarse semantic representations to model graphs, mainly due to ignoring non-informative elements and failing to focus on precise semantic alignment. Additionally, the generation of coarse graphs inherently introduces abnormal nodes, posing challenges and potentially biasing domain adaptation outcomes. Consequently, we propose a framework, which utilizes the Graph Generation to enhance the quality of DAOD (\method{}). Specifically, we introduce a Node Refinement module that utilizes a memory bank to reconstruct noisy sampled nodes while applying contrastive regularization to noisy features. To enhance semantic alignment, we propose separating domain-specific styles from category invariance encoded within graph covariances, which allows us to selectively remove domain-specific styles while preserving category-invariant information, thus facilitating more accurate semantic alignment across different domains. Furthermore, we propose a Graph Optimization adaptor, leveraging variational inference to mitigate the impact of abnormal nodes. Extensive experimentation across three adaptation benchmarks validates that \method{} achieves state-of-the-art performance in the task of unsupervised domain adaptation.
Authors: Yunfeng Li, Bo Wang, Jiuran Sun, Xueyi Wu, Ye Li
Abstract: Vision camera and sonar are naturally complementary in the underwater environment. Combining the information from two modalities will promote better observation of underwater targets. However, this problem has not received sufficient attention in previous research. Therefore, this paper introduces a new challenging RGB-Sonar (RGB-S) tracking task and investigates how to achieve efficient tracking of an underwater target through the interaction of RGB and sonar modalities. Specifically, we first propose an RGBS50 benchmark dataset containing 50 sequences and more than 87000 high-quality annotated bounding boxes. Experimental results show that the RGBS50 benchmark poses a challenge to currently popular SOT trackers. Second, we propose an RGB-S tracker called SCANet, which includes a spatial cross-attention module (SCAM) consisting of a novel spatial cross-attention layer and two independent global integration modules. The spatial cross-attention is used to overcome the problem of spatial misalignment of between RGB and sonar images. Third, we propose a SOT data-based RGB-S simulation training method (SRST) to overcome the lack of RGB-S training datasets. It converts RGB images into sonar-like saliency images to construct pseudo-data pairs, enabling the model to learn the semantic structure of RGB-S-like data. Comprehensive experiments show that the proposed spatial cross-attention effectively achieves the interaction between RGB and sonar modalities and SCANet achieves state-of-the-art performance on the proposed benchmark. The code is available at https://github.com/LiYunfengLYF/RGBS50.
Authors: Chao Wang, Krzysztof Wolski, Bernhard Kerbl, Ana Serrano, Mojtaba Bemana, Hans-Peter Seidel, Karol Myszkowski, Thomas Leimk\"uhler
Abstract: Radiance field methods represent the state of the art in reconstructing complex scenes from multi-view photos. However, these reconstructions often suffer from one or both of the following limitations: First, they typically represent scenes in low dynamic range (LDR), which restricts their use to evenly lit environments and hinders immersive viewing experiences. Secondly, their reliance on a pinhole camera model, assuming all scene elements are in focus in the input images, presents practical challenges and complicates refocusing during novel-view synthesis. Addressing these limitations, we present a lightweight method based on 3D Gaussian Splatting that utilizes multi-view LDR images of a scene with varying exposure times, apertures, and focus distances as input to reconstruct a high-dynamic-range (HDR) radiance field. By incorporating analytical convolutions of Gaussians based on a thin-lens camera model as well as a tonemapping module, our reconstructions enable the rendering of HDR content with flexible refocusing capabilities. We demonstrate that our combined treatment of HDR and depth of field facilitates real-time cinematic rendering, outperforming the state of the art.
Authors: Yufan Zhu, Chongzhi Ran, Mingtao Feng, Weisheng Dong, Antonio M. L\'opez, Guangming Shi
Abstract: Virtual engines have the capability to generate dense depth maps for various synthetic scenes, making them invaluable for training depth estimation models. However, synthetic colors often exhibit significant discrepancies compared to real-world colors, thereby posing challenges for depth estimation in real-world scenes, particularly in complex and uncertain environments encountered in unsupervised monocular depth estimation tasks. To address this issue, we propose Back2Color, a framework that predicts realistic colors from depth utilizing a model trained on real-world data, thus facilitating the transformation of synthetic colors into real-world counterparts. Additionally, by employing the Syn-Real CutMix method for joint training with both real-world unsupervised and synthetic supervised depth samples, we achieve improved performance in monocular depth estimation for real-world scenes. Moreover, to comprehensively address the impact of non-rigid motions on depth estimation, we propose an auto-learning uncertainty temporal-spatial fusion method (Auto-UTSF), which integrates the benefits of unsupervised learning in both temporal and spatial dimensions. Furthermore, we design a depth estimation network (VADepth) based on the Vision Attention Network. Our Back2Color framework demonstrates state-of-the-art performance, as evidenced by improvements in performance metrics and the production of fine-grained details in our predictions, particularly on challenging datasets such as Cityscapes for unsupervised depth estimation.
Authors: Wei Jin, Jun Zhou, Nannan Li, Haba Madeline, Xiuping Liu
Abstract: In recent years, deep learning-based point cloud normal estimation has made great progress. However, existing methods mainly rely on the PCPNet dataset, leading to overfitting. In addition, the correlation between point clouds with different noise scales remains unexplored, resulting in poor performance in cross-domain scenarios. In this paper, we explore the consistency of intrinsic features learned from clean and noisy point clouds using an Asymmetric Siamese Network architecture. By applying reasonable constraints between features extracted from different branches, we enhance the quality of normal estimation. Moreover, we introduce a novel multi-view normal estimation dataset that includes a larger variety of shapes with different noise levels. Evaluation of existing methods on this new dataset reveals their inability to adapt to different types of shapes, indicating a degree of overfitting. Extensive experiments show that the proposed dataset poses significant challenges for point cloud normal estimation and that our feature constraint mechanism effectively improves upon existing methods and reduces overfitting in current architectures.
Authors: Zhe Yuan, Jianqi Shi, Yanhong Huang
Abstract: Computer-aided design (CAD) tools are utilized in the manufacturing industry for modeling everything from cups to spacecraft. These programs are complex to use and typically require years of training and experience to master. Structured and well-constrained 2D sketches and 3D constructions are crucial components of CAD modeling. A well-executed CAD model can be seamlessly integrated into the manufacturing process, thereby enhancing production efficiency. Deep generative models of 3D shapes and 3D object reconstruction models have garnered significant research interest. However, most of these models are represented in discrete forms. Moreover, the few models based on CAD operations often have substantial input restrictions. In this work, we fine-tuned pre-trained models to create OpenECAD (0.55B, 0.89B, 2.4B, 3.2B and 4.2B), leveraging the visual, logical, coding, and general capabilities of visual language models. OpenECAD can process images of 3D designs as input and generate highly structured 2D sketches and 3D construction commands. These outputs can be directly used with existing CAD tools' APIs to generate project files. To train our network, we created a new CAD dataset. This dataset is based on existing public CAD datasets, with adjustments and augmentations to meet the requirements of VLM training.
Authors: Gengyuan Zhang, Mang Ling Ada Fok, Yan Xia, Yansong Tang, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu
Abstract: Video understanding is a pivotal task in the digital era, yet the dynamic and multievent nature of videos makes them labor-intensive and computationally demanding to process. Thus, localizing a specific event given a semantic query has gained importance in both user-oriented applications like video search and academic research into video foundation models. A significant limitation in current research is that semantic queries are typically in natural language that depicts the semantics of the target event. This setting overlooks the potential for multimodal semantic queries composed of images and texts. To address this gap, we introduce a new benchmark, ICQ, for localizing events in videos with multimodal queries, along with a new evaluation dataset ICQ-Highlight. Our new benchmark aims to evaluate how well models can localize an event given a multimodal semantic query that consists of a reference image, which depicts the event, and a refinement text to adjust the images' semantics. To systematically benchmark model performance, we include 4 styles of reference images and 5 types of refinement texts, allowing us to explore model performance across different domains. We propose 3 adaptation methods that tailor existing models to our new setting and evaluate 10 SOTA models, ranging from specialized to large-scale foundation models. We believe this benchmark is an initial step toward investigating multimodal queries in video event localization.
Authors: Akshat Dave, Tianyi Zhang, Aaron Young, Ramesh Raskar, Wolfgang Heidrich, Ashok Veeraraghavan
Abstract: Photoelasticity enables full-field stress analysis in transparent objects through stress-induced birefringence. Existing techniques are limited to 2D slices and require destructively slicing the object. Recovering the internal 3D stress distribution of the entire object is challenging as it involves solving a tensor tomography problem and handling phase wrapping ambiguities. We introduce NeST, an analysis-by-synthesis approach for reconstructing 3D stress tensor fields as neural implicit representations from polarization measurements. Our key insight is to jointly handle phase unwrapping and tensor tomography using a differentiable forward model based on Jones calculus. Our non-linear model faithfully matches real captures, unlike prior linear approximations. We develop an experimental multi-axis polariscope setup to capture 3D photoelasticity and experimentally demonstrate that NeST reconstructs the internal stress distribution for objects with varying shape and force conditions. Additionally, we showcase novel applications in stress analysis, such as visualizing photoelastic fringes by virtually slicing the object and viewing photoelastic fringes from unseen viewpoints. NeST paves the way for scalable non-destructive 3D photoelastic analysis.
Authors: Rishabh Mondal, Shataxi Dubey, Vannsh Jani, Shrimay Shah, Suraj Jaiswal, Zeel B Patel, Nipun Batra
Abstract: Air pollution kills 7 million people annually. The brick manufacturing industry accounts for 8%-14% of air pollution in the densely populated Indo-Gangetic plain. Due to the unorganized nature of brick kilns, policy violation detection, such as proximity to human habitats, remains challenging. While previous studies have utilized computer vision-based machine learning methods for brick kiln detection from satellite imagery, they utilize proprietary satellite data and rarely focus on compliance with government policies. In this research, we introduce a scalable framework for brick kiln detection and automatic compliance monitoring. We use Google Maps Static API to download the satellite imagery followed by the YOLOv8x model for detection. We identified and hand-verified 19579 new brick kilns across 9 states within the Indo-Gangetic plain. Furthermore, we automate and test the compliance to the policies affecting human habitats, rivers and hospitals. Our results show that a substantial number of brick kilns do not meet the compliance requirements. Our framework offers a valuable tool for governments worldwide to automate and enforce policy regulations for brick kilns, addressing critical environmental and public health concerns.
Authors: Haiguang Wang, Yu Wu, Mengxia Wu, Cao Min, Min Zhang
Abstract: Text-based person search aims at retrieving images of a particular person based on a given textual description. A common solution for this task is to directly match the entire images and texts, i.e., global alignment, which fails to deal with discerning specific details that discriminate against appearance-similar people. As a result, some works shift their attention towards local alignment. One group matches fine-grained parts using forward attention weights of the transformer yet underutilizes information. Another implicitly conducts local alignment by reconstructing masked parts based on unmasked context yet with a biased masking strategy. All limit performance improvement. This paper proposes the Local Alignment from Image-Phrase modeling (LAIP) framework, with Bidirectional Attention-weighted local alignment (BidirAtt) and Mask Phrase Modeling (MPM) module.BidirAtt goes beyond the typical forward attention by considering the gradient of the transformer as backward attention, utilizing two-sided information for local alignment. MPM focuses on mask reconstruction within the noun phrase rather than the entire text, ensuring an unbiased masking strategy. Extensive experiments conducted on the CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets demonstrate the superiority of the LAIP framework over existing methods.
Authors: Jianan Jiang, Di Wu, Zhilin Jiang, Weiren Yu
Abstract: Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) aims to minimize the distance between sketches and corresponding images in the embedding space. However, scalability is hindered by the growing complexity of solutions, mainly due to the abstract nature of fine-grained sketches. In this paper, we propose a simple yet efficient approach to narrow the gap between the two modes. It mainly facilitates unified mutual information sharing both intra- and inter-samples, rather than treating them as a single feature alignment problem between modalities. Specifically, our approach includes: (i) Employing dual weight-sharing networks to optimize alignment within sketch and image domain, which also effectively mitigates model learning saturation issues. (ii) Introducing an objective optimization function based on contrastive loss to enhance the model's ability to align features intra- and inter-samples. (iii) Presenting a learnable TRSM combined of self-attention and cross-attention to promote feature representations among tokens, further enhancing sample alignment in the embedding space. Our framework achieves excellent results on CNN- and ViT-based backbones. Extensive experiments demonstrate its superiority over existing methods. We also introduce Cloths-V1, the first professional fashion sketches and images dataset, utilized to validate our method and will be beneficial for other applications.
Authors: Lingjie Kong, Kai Wu, Xiaobin Hu, Wenhui Han, Jinlong Peng, Chengming Xu, Donghao Luo, Jiangning Zhang, Chengjie Wang, Yanwei Fu
Abstract: Text-to-image based object customization, aiming to generate images with the same identity (ID) as objects of interest in accordance with text prompts and reference images, has made significant progress. However, recent customizing research is dominated by specialized tasks, such as human customization or virtual try-on, leaving a gap in general object customization. To this end, we introduce AnyMaker, an innovative zero-shot object customization framework capable of generating general objects with high ID fidelity and flexible text editability. The efficacy of AnyMaker stems from its novel general ID extraction, dual-level ID injection, and ID-aware decoupling. Specifically, the general ID extraction module extracts sufficient ID information with an ensemble of self-supervised models to tackle the diverse customization tasks for general objects. Then, to provide the diffusion UNet with the extracted ID as much while not damaging the text editability in the generation process, we design a global-local dual-level ID injection module, in which the global-level semantic ID is injected into text descriptions while the local-level ID details are injected directly into the model through newly added cross-attention modules. In addition, we propose an ID-aware decoupling module to disentangle ID-related information from non-ID elements in the extracted representations for high-fidelity generation of both identity and text descriptions. To validate our approach and boost the research of general object customization, we create the first large-scale general ID dataset, Multi-Category ID-Consistent (MC-IDC) dataset, with 315k text-image samples and 10k categories. Experiments show that AnyMaker presents remarkable performance in general object customization and outperforms specialized methods in corresponding tasks. Code and dataset will be released soon.
Authors: Bingling Li, Shengyi Chen, Luchao Wang, Kaimin Liao, Sijie Yan, Yuanjun Xiong
Abstract: In this work, we explore the possibility of training high-parameter 3D Gaussian splatting (3DGS) models on large-scale, high-resolution datasets. We design a general model parallel training method for 3DGS, named RetinaGS, which uses a proper rendering equation and can be applied to any scene and arbitrary distribution of Gaussian primitives. It enables us to explore the scaling behavior of 3DGS in terms of primitive numbers and training resolutions that were difficult to explore before and surpass previous state-of-the-art reconstruction quality. We observe a clear positive trend of increasing visual quality when increasing primitive numbers with our method. We also demonstrate the first attempt at training a 3DGS model with more than one billion primitives on the full MatrixCity dataset that attains a promising visual quality.
Authors: Haodong Li, Haicheng Qu
Abstract: The detection of small objects in aerial images is a fundamental task in the field of computer vision. Moving objects in aerial photography have problems such as different shapes and sizes, dense overlap, occlusion by the background, and object blur, however, the original YOLO algorithm has low overall detection accuracy due to its weak ability to perceive targets of different scales. In order to improve the detection accuracy of densely overlapping small targets and fuzzy targets, this paper proposes a dynamic-attention scale-sequence fusion algorithm (DASSF) for small target detection in aerial images. First, we propose a dynamic scale sequence feature fusion (DSSFF) module that improves the up-sampling mechanism and reduces computational load. Secondly, a x-small object detection head is specially added to enhance the detection capability of small targets. Finally, in order to improve the expressive ability of targets of different types and sizes, we use the dynamic head (DyHead). The model we proposed solves the problem of small target detection in aerial images and can be applied to multiple different versions of the YOLO algorithm, which is universal. Experimental results show that when the DASSF method is applied to YOLOv8, compared to YOLOv8n, on the VisDrone-2019 and DIOR datasets, the model shows an increase of 9.2% and 2.4% in the mean average precision (mAP), respectively, and outperforms the current mainstream methods.
Authors: Ci-Siang Lin, I-Jieh Liu, Min-Hung Chen, Chien-Yi Wang, Sifei Liu, Yu-Chiang Frank Wang
Abstract: Referring Video Object Segmentation (RVOS) aims to segment the object referred to by the query sentence throughout the entire video. Most existing methods require end-to-end training with dense mask annotations, which could be computation-consuming and less scalable. In this work, we aim to efficiently adapt foundation segmentation models for addressing RVOS from weak supervision with the proposed Grounded Prompting (GroPrompt) framework. More specifically, we propose Text-Aware Prompt Contrastive Learning (TAP-CL) to enhance the association between the position prompts and the referring sentences with only box supervisions, including Text-Contrastive Prompt Learning (TextCon) and Modality-Contrastive Prompt Learning (ModalCon) at frame level and video level, respectively. With the proposed TAP-CL, our GroPrompt framework can generate temporal-consistent yet text-aware position prompts describing locations and movements for the referred object from the video. The experimental results in the standard RVOS benchmarks (Ref-YouTube-VOS, Ref-DAVIS17, A2D-Sentences, and JHMDB-Sentences) demonstrate the competitive performance of our proposed GroPrompt framework given only bounding box weak supervisions.
Authors: Daochang Liu, Axel Hu, Mubarak Shah, Chang Xu
Abstract: Surgical triplet recognition is an essential building block to enable next-generation context-aware operating rooms. The goal is to identify the combinations of instruments, verbs, and targets presented in surgical video frames. In this paper, we propose DiffTriplet, a new generative framework for surgical triplet recognition employing the diffusion model, which predicts surgical triplets via iterative denoising. To handle the challenge of triplet association, two unique designs are proposed in our diffusion framework, i.e., association learning and association guidance. During training, we optimize the model in the joint space of triplets and individual components to capture the dependencies among them. At inference, we integrate association constraints into each update of the iterative denoising process, which refines the triplet prediction using the information of individual components. Experiments on the CholecT45 and CholecT50 datasets show the superiority of the proposed method in achieving a new state-of-the-art performance for surgical triplet recognition. Our codes will be released.
Authors: Haruo Fujiwara, Yusuke Mukuta, Tatsuya Harada
Abstract: We propose a simple yet effective pipeline for stylizing a 3D scene, harnessing the power of 2D image diffusion models. Given a NeRF model reconstructed from a set of multi-view images, we perform 3D style transfer by refining the source NeRF model using stylized images generated by a style-aligned image-to-image diffusion model. Given a target style prompt, we first generate perceptually similar multi-view images by leveraging a depth-conditioned diffusion model with an attention-sharing mechanism. Next, based on the stylized multi-view images, we propose to guide the style transfer process with the sliced Wasserstein loss based on the feature maps extracted from a pre-trained CNN model. Our pipeline consists of decoupled steps, allowing users to test various prompt ideas and preview the stylized 3D result before proceeding to the NeRF fine-tuning stage. We demonstrate that our method can transfer diverse artistic styles to real-world 3D scenes with competitive quality. Result videos are also available on our project page: https://haruolabs.github.io/style-n2n/
Authors: Liyan Wang, Cong Wang, Jinshan Pan, Weixiang Zhou, Xiaoran Sun, Wei Wang, Zhixun Su
Abstract: Ultra-High-Definition (UHD) image restoration has acquired remarkable attention due to its practical demand. In this paper, we construct UHD snow and rain benchmarks, named UHD-Snow and UHD-Rain, to remedy the deficiency in this field. The UHD-Snow/UHD-Rain is established by simulating the physics process of rain/snow into consideration and each benchmark contains 3200 degraded/clear image pairs of 4K resolution. Furthermore, we propose an effective UHD image restoration solution by considering gradient and normal priors in model design thanks to these priors' spatial and detail contributions. Specifically, our method contains two branches: (a) feature fusion and reconstruction branch in high-resolution space and (b) prior feature interaction branch in low-resolution space. The former learns high-resolution features and fuses prior-guided low-resolution features to reconstruct clear images, while the latter utilizes normal and gradient priors to mine useful spatial features and detail features to guide high-resolution recovery better. To better utilize these priors, we introduce single prior feature interaction and dual prior feature interaction, where the former respectively fuses normal and gradient priors with high-resolution features to enhance prior ones, while the latter calculates the similarity between enhanced prior ones and further exploits dual guided filtering to boost the feature interaction of dual priors. We conduct experiments on both new and existing public datasets and demonstrate the state-of-the-art performance of our method on UHD image low-light enhancement, UHD image desonwing, and UHD image deraining. The source codes and benchmarks are available at \url{https://github.com/wlydlut/UHDDIP}.
Authors: Baiqi Li, Zhiqiu Lin, Deepak Pathak, Jiayao Li, Yixin Fei, Kewen Wu, Tiffany Ling, Xide Xia, Pengchuan Zhang, Graham Neubig, Deva Ramanan
Abstract: While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct an extensive human study on GenAI-Bench to evaluate the performance of leading image and video generation models in various aspects of compositional text-to-visual generation. We also compare automated evaluation metrics against our collected human ratings and find that VQAScore -- a metric measuring the likelihood that a VQA model views an image as accurately depicting the prompt -- significantly outperforms previous metrics such as CLIPScore. In addition, VQAScore can improve generation in a black-box manner (without finetuning) via simply ranking a few (3 to 9) candidate images. Ranking by VQAScore is 2x to 3x more effective than other scoring methods like PickScore, HPSv2, and ImageReward at improving human alignment ratings for DALL-E 3 and Stable Diffusion, especially on compositional prompts that require advanced visio-linguistic reasoning. We will release a new GenAI-Rank benchmark with over 40,000 human ratings to evaluate scoring metrics on ranking images generated from the same prompt. Lastly, we discuss promising areas for improvement in VQAScore, such as addressing fine-grained visual details. We will release all human ratings (over 80,000) to facilitate scientific benchmarking of both generative models and automated metrics.
Authors: Xuan He, Dongfu Jiang, Ge Zhang, Max Ku, Achint Soni, Sherman Siu, Haonan Chen, Abhranil Chandra, Ziyan Jiang, Aaran Arulraj, Kai Wang, Quy Duc Do, Yuansheng Ni, Bohan Lyu, Yaswanth Narsupalli, Rongqi Fan, Zhiheng Lyu, Yuchen Lin, Wenhu Chen
Abstract: The recent years have witnessed great advances in video generation. However, the development of automatic video metrics is lagging significantly behind. None of the existing metric is able to provide reliable scores over generated videos. The main barrier is the lack of large-scale human-annotated dataset. In this paper, we release VideoFeedback, the first large-scale dataset containing human-provided multi-aspect score over 37.6K synthesized videos from 11 existing video generative models. We train VideoScore (initialized from Mantis) based on VideoFeedback to enable automatic video quality assessment. Experiments show that the Spearman correlation between VideoScore and humans can reach 77.1 on VideoFeedback-test, beating the prior best metrics by about 50 points. Further result on other held-out EvalCrafter, GenAI-Bench, and VBench show that VideoScore has consistently much higher correlation with human judges than other metrics. Due to these results, we believe VideoScore can serve as a great proxy for human raters to (1) rate different video models to track progress (2) simulate fine-grained human feedback in Reinforcement Learning with Human Feedback (RLHF) to improve current video generation models.
Authors: Timm Hess, Eli Verwimp, Gido M. van de Ven, Tinne Tuytelaars
Abstract: Continual learning research has shown that neural networks suffer from catastrophic forgetting "at the output level", but it is debated whether this is also the case at the level of learned representations. Multiple recent studies ascribe representations a certain level of innate robustness against forgetting -- that they only forget minimally in comparison with forgetting at the output level. We revisit and expand upon the experiments that revealed this difference in forgetting and illustrate the coexistence of two phenomena that affect the quality of continually learned representations: knowledge accumulation and feature forgetting. Taking both aspects into account, we show that, even though forgetting in the representation (i.e. feature forgetting) can be small in absolute terms, when measuring relative to how much was learned during a task, forgetting in the representation tends to be just as catastrophic as forgetting at the output level. Next we show that this feature forgetting is problematic as it substantially slows down the incremental learning of good general representations (i.e. knowledge accumulation). Finally, we study how feature forgetting and knowledge accumulation are affected by different types of continual learning methods.
Authors: Hsiu-Hsuan Wang, Tan-Ha Mai, Nai-Xuan Ye, Wei-I Lin, Hsuan-Tien Lin
Abstract: Complementary-label learning (CLL) is a weakly-supervised learning paradigm that aims to train a multi-class classifier using only complementary labels, which indicate classes to which an instance does not belong. Despite numerous algorithmic proposals for CLL, their practical applicability remains unverified for two reasons. Firstly, these algorithms often rely on assumptions about the generation of complementary labels, and it is not clear how far the assumptions are from reality. Secondly, their evaluation has been limited to synthetic datasets. To gain insights into the real-world performance of CLL algorithms, we developed a protocol to collect complementary labels from human annotators. Our efforts resulted in the creation of four datasets: CLCIFAR10, CLCIFAR20, CLMicroImageNet10, and CLMicroImageNet20, derived from well-known classification datasets CIFAR10, CIFAR100, and TinyImageNet200. These datasets represent the very first real-world CLL datasets. Through extensive benchmark experiments, we discovered a notable decrease in performance when transitioning from synthetic datasets to real-world datasets. We investigated the key factors contributing to the decrease with a thorough dataset-level ablation study. Our analyses highlight annotation noise as the most influential factor in the real-world datasets. In addition, we discover that the biased-nature of human-annotated complementary labels and the difficulty to validate with only complementary labels are two outstanding barriers to practical CLL. These findings suggest that the community focus more research efforts on developing CLL algorithms and validation schemes that are robust to noisy and biased complementary-label distributions.
Authors: Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen
Abstract: Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing approaches for LLMs have emerged -- aiming to subtly inject/edit updated knowledge or adjust undesired behavior while minimizing the impact on unrelated inputs. Nevertheless, due to significant differences among various knowledge editing methods and the variations in task setups, there is no standard implementation framework available for the community, which hinders practitioners from applying knowledge editing to applications. To address these issues, we propose EasyEdit, an easy-to-use knowledge editing framework for LLMs. It supports various cutting-edge knowledge editing approaches and can be readily applied to many well-known LLMs such as T5, GPT-J, LlaMA, etc. Empirically, we report the knowledge editing results on LlaMA-2 with EasyEdit, demonstrating that knowledge editing surpasses traditional fine-tuning in terms of reliability and generalization. We have released the source code on GitHub, along with Google Colab tutorials and comprehensive documentation for beginners to get started. Besides, we present an online system for real-time knowledge editing, and a demo video.
Authors: Mariano Rivera
Abstract: Variational Autoencoders (VAEs) have become a cornerstone in generative modeling and representation learning within machine learning. This paper explores a nuanced aspect of VAEs, focusing on interpreting the Kullback-Leibler (KL) Divergence, a critical component within the Evidence Lower Bound (ELBO) that governs the trade-off between reconstruction accuracy and regularization. Meanwhile, the KL Divergence enforces alignment between latent variable distributions and a prior imposing a structure on the overall latent space but leaves individual variable distributions unconstrained. The proposed method redefines the ELBO with a mixture of Gaussians for the posterior probability, introduces a regularization term to prevent variance collapse, and employs a PatchGAN discriminator to enhance texture realism. Implementation details involve ResNetV2 architectures for both the Encoder and Decoder. The experiments demonstrate the ability to generate realistic faces, offering a promising solution for enhancing VAE-based generative models.
Authors: Gabriele M. Caddeo, Andrea Maracani, Paolo D. Alfano, Nicola A. Piga, Lorenzo Rosasco, Lorenzo Natale
Abstract: In this paper, we address the Sim2Real gap in the field of vision-based tactile sensors for classifying object surfaces. We train a Diffusion Model to bridge this gap using a relatively small dataset of real-world images randomly collected from unlabeled everyday objects via the DIGIT sensor. Subsequently, we employ a simulator to generate images by uniformly sampling the surface of objects from the YCB Model Set. These simulated images are then translated into the real domain using the Diffusion Model and automatically labeled to train a classifier. During this training, we further align features of the two domains using an adversarial procedure. Our evaluation is conducted on a dataset of tactile images obtained from a set of ten 3D printed YCB objects. The results reveal a total accuracy of 81.9%, a significant improvement compared to the 34.7% achieved by the classifier trained solely on simulated images. This demonstrates the effectiveness of our approach. We further validate our approach using the classifier on a 6D object pose estimation task from tactile data.
Authors: Ian Berlot-Attwell, Kumar Krishna Agrawal, A. Michael Carrell, Yash Sharma, Naomi Saphra
Abstract: The degree to which neural networks can generalize to new combinations of familiar concepts, and the conditions under which they are able to do so, has long been an open question. In this work, we study the systematicity gap in visual question answering: the performance difference between reasoning on previously seen and unseen combinations of object attributes. To test, we introduce a novel diagnostic dataset, CLEVR-HOPE. We find that while increased quantity of training data does not reduce the systematicity gap, increased training data diversity of the attributes in the unseen combination does. In all, our experiments suggest that the more distinct attribute type combinations are seen during training, the more systematic we can expect the resulting model to be.
Authors: Ribana Roscher, Marc Ru{\ss}wurm, Caroline Gevaert, Michael Kampffmeyer, Jefersson A. dos Santos, Maria Vakalopoulou, Ronny H\"ansch, Stine Hansen, Keiller Nogueira, Jonathan Prexl, Devis Tuia
Abstract: Recent developments and research in modern machine learning have led to substantial improvements in the geospatial field. Although numerous deep learning architectures and models have been proposed, the majority of them have been solely developed on benchmark datasets that lack strong real-world relevance. Furthermore, the performance of many methods has already saturated on these datasets. We argue that a shift from a model-centric view to a complementary data-centric perspective is necessary for further improvements in accuracy, generalization ability, and real impact on end-user applications. Furthermore, considering the entire machine learning cycle - from problem definition to model deployment with feedback - is crucial for enhancing machine learning models that can be reliable in unforeseen situations. This work presents a definition as well as a precise categorization and overview of automated data-centric learning approaches for geospatial data. It highlights the complementary role of data-centric learning with respect to model-centric in the larger machine learning deployment cycle. We review papers across the entire geospatial field and categorize them into different groups. A set of representative experiments shows concrete implementation examples. These examples provide concrete steps to act on geospatial data with data-centric machine learning approaches.
Authors: Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu
Abstract: Despite much progress, achieving real-time high-fidelity head avatar animation is still difficult and existing methods have to trade-off between speed and quality. 3DMM based methods often fail to model non-facial structures such as eyeglasses and hairstyles, while neural implicit models suffer from deformation inflexibility and rendering inefficiency. Although 3D Gaussian has been demonstrated to possess promising capability for geometry representation and radiance field reconstruction, applying 3D Gaussian in head avatar creation remains a major challenge since it is difficult for 3D Gaussian to model the head shape variations caused by changing poses and expressions. In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering. The parametric morphable shape model is a Point-based Morphable Shape Model (PMSM) which uses points instead of meshes for 3D representation to achieve enhanced representation flexibility. The PMSM first converts the FLAME mesh to points by sampling on the surfaces as well as off the meshes to enable the reconstruction of not only surface-like structures but also complex geometries such as eyeglasses and hairstyles. By aligning these points with the head shape in an analysis-by-synthesis manner, the PMSM makes it possible to utilize 3D Gaussian for fine detail representation and appearance modeling, thus enabling the creation of high-fidelity avatars. We show that PSAvatar can reconstruct high-fidelity head avatars of a variety of subjects and the avatars can be animated in real-time ($\ge$ 25 fps at a resolution of 512 $\times$ 512 ).
Authors: Canyu Zhang, Youbao Tang, Ning Zhang, Ruei-Sung Lin, Mei Han, Jing Xiao, Song Wang
Abstract: Dance serves as a powerful medium for expressing human emotions, but the lifelike generation of dance is still a considerable challenge. Recently, diffusion models have showcased remarkable generative abilities across various domains. They hold promise for human motion generation due to their adaptable many-to-many nature. Nonetheless, current diffusion-based motion generation models often create entire motion sequences directly and unidirectionally, lacking focus on the motion with local and bidirectional enhancement. When choreographing high-quality dance movements, people need to take into account not only the musical context but also the nearby music-aligned dance motions. To authentically capture human behavior, we propose a Bidirectional Autoregressive Diffusion Model (BADM) for music-to-dance generation, where a bidirectional encoder is built to enforce that the generated dance is harmonious in both the forward and backward directions. To make the generated dance motion smoother, a local information decoder is built for local motion enhancement. The proposed framework is able to generate new motions based on the input conditions and nearby motions, which foresees individual motion slices iteratively and consolidates all predictions. To further refine the synchronicity between the generated dance and the beat, the beat information is incorporated as an input to generate better music-aligned dance movements. Experimental results demonstrate that the proposed model achieves state-of-the-art performance compared to existing unidirectional approaches on the prominent benchmark for music-to-dance generation.
Authors: Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, Weihao Chen, Chunhui Li, Jianbing Zhang, Xinyu Dai
Abstract: Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object hallucination. To eliminate hallucinations, existing methods manually annotate paired responses with and without hallucinations, and then employ various alignment algorithms to improve the alignment capability between images and text. However, they not only demand considerable computation resources during the finetuning stage but also require expensive human annotation to construct paired data needed by the alignment algorithms. To address these issues, we borrow the idea of unlearning and propose an efficient fine-grained unlearning framework (EFUF), which can eliminate hallucinations without the need for paired data. Extensive experiments show that our method consistently reduces hallucinations while preserving the generation quality with modest computational overhead. Our code and datasets will be publicly available.
Authors: Yameng Peng, Andy Song, Haytham M. Fayek, Vic Ciesielski, Xiaojun Chang
Abstract: Training-free metrics (a.k.a. zero-cost proxies) are widely used to avoid resource-intensive neural network training, especially in Neural Architecture Search (NAS). Recent studies show that existing training-free metrics have several limitations, such as limited correlation and poor generalisation across different search spaces and tasks. Hence, we propose Sample-Wise Activation Patterns and its derivative, SWAP-Score, a novel high-performance training-free metric. It measures the expressivity of networks over a batch of input samples. The SWAP-Score is strongly correlated with ground-truth performance across various search spaces and tasks, outperforming 15 existing training-free metrics on NAS-Bench-101/201/301 and TransNAS-Bench-101. The SWAP-Score can be further enhanced by regularisation, which leads to even higher correlations in cell-based search space and enables model size control during the search. For example, Spearman's rank correlation coefficient between regularised SWAP-Score and CIFAR-100 validation accuracies on NAS-Bench-201 networks is 0.90, significantly higher than 0.80 from the second-best metric, NWOT. When integrated with an evolutionary algorithm for NAS, our SWAP-NAS achieves competitive performance on CIFAR-10 and ImageNet in approximately 6 minutes and 9 minutes of GPU time respectively.
Authors: Tamir Shor, Chaim Baskin, Alex Bronstein
Abstract: Breast cancer is a prominent health concern worldwide, currently being the secondmost common and second-deadliest type of cancer in women. While current breast cancer diagnosis mainly relies on mammography imaging, in recent years the use of thermography for breast cancer imaging has been garnering growing popularity. Thermographic imaging relies on infrared cameras to capture body-emitted heat distributions. While these heat signatures have proven useful for computer-vision systems for accurate breast cancer segmentation and classification, prior work often relies on handcrafted feature engineering or complex architectures, potentially limiting the comparability and applicability of these methods. In this work, we present a novel algorithm for both breast cancer classification and segmentation. Rather than focusing efforts on manual feature and architecture engineering, our algorithm focuses on leveraging an informative, learned feature space, thus making our solution simpler to use and extend to other frameworks and downstream tasks, as well as more applicable to data-scarce settings. Our classification produces SOTA results, while we are the first work to produce segmentation regions studied in this paper.
Authors: Renzhi Wu, Pramod Chunduri, Dristi J Shah, Ashmitha Julius Aravind, Ali Payani, Xu Chu, Joy Arulraj, Kexin Rong
Abstract: In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface. This novel interface allows users to specify object trajectory events with simple mouse drag-and-drop operations. Users can use trajectories of single objects as building blocks to compose complex events. Using a pre-trained model that encodes trajectory similarity, SketchQL achieves zero-shot video moments retrieval by performing similarity searches over the video to identify clips that are the most similar to the visual query. In this demonstration, we introduce the graphic user interface of SketchQL and detail its functionalities and interaction mechanisms. We also demonstrate the end-to-end usage of SketchQL from query composition to video moments retrieval using real-world scenarios.
Authors: Hongwei Bran Li, Fernando Navarro, Ivan Ezhov, Amirhossein Bayat, Dhritiman Das, Florian Kofler, Suprosanna Shit, Diana Waldmannstetter, Johannes C. Paetzold, Xiaobin Hu, Benedikt Wiestler, Lucas Zimmer, Tamaz Amiranashvili, Chinmay Prabhakar, Christoph Berger, Jonas Weidner, Michelle Alonso-Basant, Arif Rashid, Ujjwal Baid, Wesam Adel, Deniz Ali, Bhakti Baheti, Yingbin Bai, Ishaan Bhatt, Sabri Can Cetindag, Wenting Chen, Li Cheng, Prasad Dutand, Lara Dular, Mustafa A. Elattar, Ming Feng, Shengbo Gao, Henkjan Huisman, Weifeng Hu, Shubham Innani, Wei Jiat, Davood Karimi, Hugo J. Kuijf, Jin Tae Kwak, Hoang Long Le, Xiang Lia, Huiyan Lin, Tongliang Liu, Jun Ma, Kai Ma, Ting Ma, Ilkay Oksuz, Robbie Holland, Arlindo L. Oliveira, Jimut Bahan Pal, Xuan Pei, Maoying Qiao, Anindo Saha, Raghavendra Selvan, Linlin Shen, Joao Lourenco Silva, Ziga Spiclin, Sanjay Talbar, Dadong Wang, Wei Wang, Xiong Wang, Yin Wang, Ruiling Xia, Kele Xu, Yanwu Yan, Mert Yergin, Shuang Yu, Lingxi Zeng, YingLin Zhang, Jiachen Zhao, Yefeng Zheng, Martin Zukovec, Richard Do, Anton Becker, Amber Simpson, Ender Konukoglu, Andras Jakab, Spyridon Bakas, Leo Joskowicz, Bjoern Menze
Abstract: Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consistent and reliable image segmentation. This variability not only reflects the inherent complexity and subjective nature of medical image interpretation but also directly impacts the development and evaluation of automated segmentation algorithms. Accurately modeling and quantifying this variability is essential for enhancing the robustness and clinical applicability of these algorithms. We report the set-up and summarize the benchmark results of the Quantification of Uncertainties in Biomedical Image Quantification Challenge (QUBIQ), which was organized in conjunction with International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020 and 2021. The challenge focuses on the uncertainty quantification of medical image segmentation which considers the omnipresence of inter-rater variability in imaging datasets. The large collection of images with multi-rater annotations features various modalities such as MRI and CT; various organs such as the brain, prostate, kidney, and pancreas; and different image dimensions 2D-vs-3D. A total of 24 teams submitted different solutions to the problem, combining various baseline models, Bayesian neural networks, and ensemble model techniques. The obtained results indicate the importance of the ensemble models, as well as the need for further research to develop efficient 3D methods for uncertainty quantification methods in 3D segmentation tasks.
Authors: Shuhong Liu, Heng Zhou, Liuzhuozheng Li, Yun Liu, Tianchen Deng, Yiming Zhou, Mingrui Li
Abstract: Gaussian SLAM systems have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete reconstructions in complex indoor environments, characterized by substantial holes due to unobserved geometry caused by obstacles or limited view angles. To address this challenge, we present Manhattan Gaussian SLAM (MG-SLAM), an RGB-D system that leverages the Manhattan World hypothesis to enhance geometric accuracy and completeness. By seamlessly integrating fused line segments derived from structured scenes, MG-SLAM ensures robust tracking in textureless indoor areas. Moreover, The extracted lines and planar surface assumption allow strategic interpolation of new Gaussians in regions of missing geometry, enabling efficient scene completion. Extensive experiments conducted on both synthetic and real-world scenes demonstrate that these advancements enable our method to achieve state-of-the-art performance, marking a substantial improvement in the capabilities of Gaussian SLAM systems.
Authors: Baowen Zhang, Chuan Fang, Rakesh Shrestha, Yixun Liang, Xiaoxiao Long, Ping Tan
Abstract: Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods often suffer from limited shape accuracy due to the discrete and unstructured nature of Gaussian splats, which complicates the shape extraction. While recent techniques like 2D GS have attempted to improve shape reconstruction, they often reformulate the Gaussian primitives in ways that reduce both rendering quality and computational efficiency. To address these problems, our work introduces a rasterized approach to render the depth maps and surface normal maps of general 3D Gaussian splats. Our method not only significantly enhances shape reconstruction accuracy but also maintains the computational efficiency intrinsic to Gaussian Splatting. It achieves a Chamfer distance error comparable to NeuraLangelo on the DTU dataset and maintains similar computational efficiency as the original 3D GS methods. Our method is a significant advancement in Gaussian Splatting and can be directly integrated into existing Gaussian Splatting-based methods.
Authors: Shenghao Li, Luchao Pang, Xianglong Hu
Abstract: This paper presents a novel approach to visual simultaneous localization and mapping (SLAM) using multiple RGB-D cameras. The proposed method, Multicam-SLAM, significantly enhances the robustness and accuracy of SLAM systems by capturing more comprehensive spatial information from various perspectives. This method enables the accurate determination of pose relationships among multiple cameras without the need for overlapping fields of view. The proposed Muticam-SLAM includes a unique multi-camera model, a multi-keyframes structure, and several parallel SLAM threads. The multi-camera model allows for the integration of data from multiple cameras, while the multi-keyframes and parallel SLAM threads ensure efficient and accurate pose estimation and mapping. Extensive experiments in various environments demonstrate the superior accuracy and robustness of the proposed method compared to conventional single-camera SLAM systems. The results highlight the potential of the proposed Multicam-SLAM for more complex and challenging applications. Code is available at \url{https://github.com/AlterPang/Multi_ORB_SLAM}.
Authors: Michel Adamic, Wellington Avelino, Anna Brandenberger, Bryan Chiang, Hunter Davis, Stephen Fay, Andrew Gregory, Aayush Gupta, Raphael Hotter, Grace Jiang, Fiona Leng, Stephen Polcyn, Thomas Ribeiro, Paul Scotti, Michelle Wang, Marley Xiong, Jonathan Xu
Abstract: We demonstrate the possibility of reconstructing images from fNIRS brain activity and start building a prototype to match the required specs. By training an image reconstruction model on downsampled fMRI data, we discovered that cm-scale spatial resolution is sufficient for image generation. We obtained 71% retrieval accuracy with 1-cm resolution, compared to 93% on the full-resolution fMRI, and 20% with 2-cm resolution. With simulations and high-density tomography, we found that time-domain fNIRS can achieve 1-cm resolution, compared to 2-cm resolution for continuous-wave fNIRS. Lastly, we share designs for a prototype time-domain fNIRS device, consisting of a laser driver, a single photon detector, and a time-to-digital converter system.
Authors: Xueyuan Chen, Dongchao Yang, Dingdong Wang, Xixin Wu, Zhiyong Wu, Helen Meng
Abstract: Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. In this paper, we propose a multi-modal DSR model by leveraging neural codec language modeling to improve the reconstruction results, especially for the speaker similarity and prosody naturalness. Our proposed model consists of: (i) a multi-modal content encoder to extract robust phoneme embeddings from dysarthric speech with auxiliary visual inputs; (ii) a speaker codec encoder to extract and normalize the speaker-aware codecs from the dysarthric speech, in order to provide original timbre and normal prosody; (iii) a codec language model based speech decoder to reconstruct the speech based on the extracted phoneme embeddings and normalized codecs. Evaluations on the commonly used UASpeech corpus show that our proposed model can achieve significant improvements in terms of speaker similarity and prosody naturalness.
Authors: Preetum Nakkiran, Arwen Bradley, Hattie Zhou, Madhu Advani
Abstract: We present an accessible first course on diffusion models and flow matching for machine learning, aimed at a technical audience with no diffusion experience. We try to simplify the mathematical details as much as possible (sometimes heuristically), while retaining enough precision to derive correct algorithms.
Authors: Chengqian Ma, Zhanxiang Hua, Alexandra Anderson-Frey, Vikram Iyer, Xin Liu, Lianhui Qin
Abstract: Severe convective weather events, such as hail, tornadoes, and thunderstorms, often occur quickly yet cause significant damage, costing billions of dollars every year. This highlights the importance of forecasting severe weather threats hours in advance to better prepare meteorologists and residents in at-risk areas. Can modern large foundation models perform such forecasting? Existing weather benchmarks typically focus only on predicting time-series changes in certain weather parameters (e.g., temperature, moisture) with text-only features. In this work, we introduce WeatherQA, the first multimodal dataset designed for machines to reason about complex combinations of weather parameters (a.k.a., ingredients) and predict severe weather in real-world scenarios. The dataset includes over 8,000 (multi-images, text) pairs for diverse severe weather events. Each pair contains rich information crucial for forecasting -- the images describe the ingredients capturing environmental instability, surface observations, and radar reflectivity, and the text contains forecast analyses written by human experts. With WeatherQA, we evaluate state-of-the-art vision language models, including GPT4, Claude3.5, Gemini-1.5, and a fine-tuned Llama3-based VLM, by designing two challenging tasks: (1) multi-choice QA for predicting affected area and (2) classification of the development potential of severe convection. These tasks require deep understanding of domain knowledge (e.g., atmospheric dynamics) and complex reasoning over multimodal data (e.g., interactions between weather parameters). We show a substantial gap between the strongest VLM, GPT4o, and human reasoning. Our comprehensive case study with meteorologists further reveals the weaknesses of the models, suggesting that better training and data integration are necessary to bridge this gap. WeatherQA link: https://github.com/chengqianma/WeatherQA.
Authors: Chuyan Xiong, Chengyu Shen, Xiaoqi Li, Kaichen Zhou, Jiaming Liu, Ruiping Wang, Hao Dong
Abstract: The ability to reflect on and correct failures is crucial for robotic systems to interact stably with real-life objects.Observing the generalization and reasoning capabilities of Multimodal Large Language Models (MLLMs), previous approaches have aimed to utilize these models to enhance robotic systems accordingly.However, these methods typically focus on high-level planning corrections using an additional MLLM, with limited utilization of failed samples to correct low-level contact poses. To address this gap, we propose an Autonomous Interactive Correction (AIC) MLLM, which makes use of previous low-level interaction experiences to correct SE(3) pose predictions. Specifically, AIC MLLM is initially fine-tuned to acquire both pose prediction and feedback prompt comprehension abilities.We carefully design two types of prompt instructions through interactions with objects: 1) visual masks to highlight unmovable parts for position correction, and 2)textual descriptions to indicate potential directions for rotation correction.During inference, a Feedback Information Extraction module is introduced to recognize the failure cause, allowing AIC MLLM to adaptively correct the pose prediction using the corresponding prompts. To further enhance manipulation stability, we devise a Test Time Adaptation strategy that enables AIC MLLM to better adapt to the current scene configuration.Finally, extensive experiments are conducted in both simulated and real-world environments to evaluate the proposed method. The results demonstrate that our AIC MLLM can efficiently correct failure samples by leveraging interaction experience prompts.Real-world demonstration can be found at https://sites.google.com/view/aic-mllm
Authors: Mengdan Zhu, Raasikh Kanjiani, Jiahui Lu, Andrew Choi, Qirui Ye, Liang Zhao
Abstract: Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in interpreting machine learning models, understanding latent variables in generative models remains challenging. This paper introduces LatentExplainer, a framework for automatically generating semantically meaningful explanations of latent variables in deep generative models. LatentExplainer tackles three main challenges: inferring the meaning of latent variables, aligning explanations with inductive biases, and handling varying degrees of explainability. By perturbing latent variables and interpreting changes in generated data, the framework provides a systematic approach to understanding and controlling the data generation process, enhancing the transparency and interpretability of deep generative models. We evaluate our proposed method on several real-world and synthetic datasets, and the results demonstrate superior performance in generating high-quality explanations of latent variables.
Authors: Teo Guichoux, Laure Soulier, Nicolas Obin, Catherine Pelachaud
Abstract: Co-speech gestures play a crucial role in the interactions between humans and embodied conversational agents (ECA). Recent deep learning methods enable the generation of realistic, natural co-speech gestures synchronized with speech, but such approaches require large amounts of training data. "In-the-wild" datasets, which compile videos from sources such as YouTube through human pose detection models, offer a solution by providing 2D skeleton sequences that are paired with speech. Concurrently, innovative lifting models have emerged, capable of transforming these 2D pose sequences into their 3D counterparts, leading to large and diverse datasets of 3D gestures. However, the derived 3D pose estimation is essentially a pseudo-ground truth, with the actual ground truth being the 2D motion data. This distinction raises questions about the impact of gesture representation dimensionality on the quality of generated motions, a topic that, to our knowledge, remains largely unexplored. In this work, we evaluate the impact of the dimensionality of the training data, 2D or 3D joint coordinates, on the performance of a multimodal speech-to-gesture deep generative model. We use a lifting model to convert 2D-generated sequences of body pose to 3D. Then, we compare the sequence of gestures generated directly in 3D to the gestures generated in 2D and lifted to 3D as post-processing.