Cross-view geo-localization holds significant potential for various applications, but drastic differences in viewpoints and visual appearances between cross-view images make this task extremely challenging. Recent works have made notable progress in cross-view geo-localization. However, existing methods either ignore the correspondence between geometric spatial layout in cross-view images or require high costs or strict constraints to achieve such alignment. In response to these challenges, we propose a Feature Recombination Module (FRM) that explicitly establishes the geometric spatial layout correspondences between two views. Unlike existing methods, FRM aligns geometric spatial layout by directly recombining features, avoiding image preprocessing, and introducing no additional computational and parameter costs. This effectively reduces ambiguities caused by geometric misalignments between ground-level and aerial-level images. Furthermore, it is not sensitive to frameworks and applies to both CNN-based and Transformer-based architectures. Additionally, as part of the training procedure, we also introduce a novel weighted (B+1)-tuple loss (WBL) as optimization objective. Compared to the widely used weighted soft margin ranking loss, this innovative loss enhances convergence speed and final performance. Based on the two core components (FRM and WBL), we develop an end-to-end network architecture (FRGeo) to address these limitations from a different perspective. Extensive experiments show that our proposed FRGeo not only achieves state-of-the-art performance on cross-view geo-localization benchmarks, including CVUSA, CVACT, and VIGOR, but also is significantly superior or competitive in terms of computational complexity and trainable parameters. Our project homepage is at https://zqwlearning.github.io/FRGeo.
论文检索
输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view frames and fixed camera views. As a result, these methods may not be practical for detecting people in larger, more complex scenes with severe occlusions and camera calibration errors. This paper focuses on improving multi-view people detection by developing a supervised view-wise contribution weighting approach that better fuses multi-camera information under large scenes. Besides, a large synthetic dataset is adopted to enhance the model's generalization ability and enable more practical evaluation and comparison. The model's performance on new testing scenes is further improved with a simple domain adaptation technique. Experimental results demonstrate the effectiveness of our approach in achieving promising cross-scene multi-view people detection performance.
Document layout analysis is a crucial step for intelligent document understanding. However, many existing methods primarily focus on the visual aspects and overlook the textual features of documents. Although document pre-trained models utilize multi-modal features during the pre-training phase, they tend to operate as a unimodal pipeline when it comes to layout analysis tasks. Furthermore, current multi-modal methods perform worse than unimodal detectors on complex layout analysis datasets. To address these limitations, we propose an effective and pluggable multi-modal fusion approach named M2Doc, which fuses visual and textual features for better layout detection. M2Doc contains two pluggable multi-modal fusion modules, early-fusion and late-fusion, which align and fuse visual and textual features at the pixel level and block level. Benefitting from the concision and effectiveness of M2Doc, it can be easily applied to various detectors for better layout detection, including two-stage and end-to-end object detectors. Our experimental results demonstrate significant performance improvements in detectors equipped with M2Doc on datasets such as DocLayNet (+11.3 mAP) and M6Doc (+1.9 mAP). Furthermore, through the integration of the DINO detector with M2Doc, we achieve state-of-the-art results on DocLayNet (89.0 mAP), M6Doc (69.9 mAP), and PubLayNet (95.5 mAP). The code will be publicly released at https://github.com/johnning2333/M2Doc.
IRPruneDet: Efficient Infrared Small Target Detection via Wavelet Structure-Regularized Soft Channel Pruning
PDF ↗Infrared Small Target Detection (IRSTD) refers to detecting faint targets in infrared images, which has achieved notable progress with the advent of deep learning. However, the drive for improved detection accuracy has led to larger, intricate models with redundant parameters, causing storage and computation inefficiencies. In this pioneering study, we introduce the concept of utilizing network pruning to enhance the efficiency of IRSTD. Due to the challenge posed by low signal-to-noise ratios and the absence of detailed semantic information in infrared images, directly applying existing pruning techniques yields suboptimal performance. To address this, we propose a novel wavelet structure-regularized soft channel pruning method, giving rise to the efficient IRPruneDet model. Our approach involves representing the weight matrix in the wavelet domain and formulating a wavelet channel pruning strategy. We incorporate wavelet regularization to induce structural sparsity without incurring extra memory usage. Moreover, we design a soft channel reconstruction method that preserves important target information against premature pruning, thereby ensuring an optimal sparse structure while maintaining overall sparsity. Through extensive experiments on two widely-used benchmarks, our IRPruneDet method surpasses established techniques in both model complexity and accuracy. Specifically, when employing U-net as the baseline network, IRPruneDet achieves a 64.13% reduction in parameters and a 51.19% decrease in FLOPS, while improving IoU from 73.31% to 75.12% and nIoU from 70.92% to 74.30%. The code is available at https://github.com/hd0013/IRPruneDet.
Recently, diffusion-based image generation methods are credited for their remarkable text-to-image generation capabilities, while still facing challenges in accurately generating multilingual scene text images. To tackle this problem, we propose Diff-Text, which is a training-free scene text generation framework for any language. Our model outputs a photo-realistic image given a text of any language along with a textual description of a scene. The model leverages rendered sketch images as priors, thus arousing the potential multilingual-generation ability of the pre-trained Stable Diffusion. Based on the observation from the influence of the cross-attention map on object placement in generated images, we propose a localized attention constraint into the cross-attention layer to address the unreasonable positioning problem of scene text. Additionally, we introduce contrastive image-level prompts to further refine the position of the textual region and achieve more accurate scene text generation. Experiments demonstrate that our method outperforms the existing method in both the accuracy of text recognition and the naturalness of foreground-background blending.
Most Graph Convolutional Networks based 3D human pose estimation (HPE) methods were involved in single-view 3D HPE and utilized certain spatial graphs, existing key problems such as depth ambiguity, insufficient feature representation, or limited receptive fields. To address these issues, we propose a multi-view 3D HPE framework based on deep semantic graph transformer, which adaptively learns and fuses multi-view significant semantic features of human nodes to improve 3D HPE performance. First, we propose a deep semantic graph transformer encoder to enrich spatial feature information. It deeply mines the position, spatial structure, and skeletal edge knowledge of joints and dynamically learns their correlations. Then, we build a progressive multi-view spatial-temporal feature fusion framework to mitigate joint depth uncertainty. To enhance the pose spatial representation, deep spatial semantic feature are interacted and fused across different viewpoints during monocular feature extraction. Furthermore, long-time relevant temporal dependencies are modeled and spatial-temporal information from all viewpoints is fused to intermediately supervise the depth. Extensive experiments on three 3D HPE benchmarks show that our method achieves state-of-the-art results. It can effectively enhance pose features, mitigate depth ambiguity in single-view 3D HPE, and improve 3D HPE performance without providing camera parameters. Codes and models are available at https://github.com/z0911k/SGraFormer.
IFL (Image Forgery Location) helps secure digital media forensics. However, many methods suffer from false detections (i.e., FPs) and inaccurate boundaries. In this paper, we proposed the CatmullRom Splines-based Regression Network (CSR-Net), which first rethinks the IFL task from the perspective of regression to deal with this problem. Specifically speaking, we propose an adaptive CutmullRom splines fitting scheme for coarse localization of the tampered regions. Then, for false positive cases, we first develop a novel re-scoring mechanism, which aims to filter out samples that cannot have responses on both the classification branch and the instance branch. Later on, to further restrict the boundaries, we design a learnable texture extraction module, which refines and enhances the contour representation by decoupling the horizontal and vertical forgery features to extract a more robust contour representation, thus suppressing FPs. Compared to segmentation-based methods, our method is simple but effective due to the unnecessity of post-processing. Extensive experiments show the superiority of CSR-Net to existing state-of-the-art methods, not only on standard natural image datasets but also on social media datasets.
Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle each part completely, which means the edited parts will affect the others, resulting in poor diversity and fidelity. In addition, some methods lack constraints between parts, which need manual selections of edited results to ensure quality. Therefore, we propose a four-stage process for point cloud part editing: Segmentation, Generation, Assembly, and Selection. Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint. By independently fitting part-level feature distributions, we realize the feature disentanglement. By explicitly modeling the transformation from object-level distribution to part-level distributions, we realize the feature constraint. Considerable experiments on different datasets demonstrate the efficiency and effectiveness of SGAS on point cloud part editing. In addition, SGAS can be pruned to realize unsupervised part-aware point cloud generation and achieves state-of-the-art results.
Labelling LiDAR point clouds for training autonomous driving is extremely expensive and difficult. LiDAR simulation aims at generating realistic LiDAR data with labels for training and verifying self-driving algorithms more efficiently. Recently, Neural Radiance Fields (NeRF) have been proposed for novel view synthesis using implicit reconstruction of 3D scenes. Inspired by this, we present NeRF-LIDAR, a novel LiDAR simulation method that leverages real-world information to generate realistic LIDAR point clouds. Different from existing LiDAR simulators, we use real images and point cloud data collected by self-driving cars to learn the 3D scene representation, point cloud generation and label rendering. We verify the effectiveness of our NeRF-LiDAR by training different 3D segmentation models on the generated LiDAR point clouds. It reveals that the trained models are able to achieve similar accuracy when compared with the same model trained on the real LiDAR data. Besides, the generated data is capable of boosting the accuracy through pre-training which helps reduce the requirements of the real labeled data. Code is available at https://github.com/fudan-zvg/NeRF-LiDAR
Neighborhood-Enhanced 3D Human Pose Estimation with Monocular LiDAR in Long-Range Outdoor Scenes
PDF ↗3D human pose estimation (3HPE) in large-scale outdoor scenes using commercial LiDAR has attracted significant attention due to its potential for real-life applications. However, existing LiDAR-based methods for 3HPE primarily rely on recovering 3D human poses from individual point clouds, and the coherence cues present in the neighborhood are not sufficiently harnessed. In this work, we explore spatial and contexture coherence cues contained in the neighborhood that lead to great performance improvements in 3HPE. Specifically, firstly, we deeply investigate the 3D neighbor in the background (3BN) which serves as a spatial coherence cue for inferring reliable motion since it provides physical laws to limit motion targets. Secondly, we introduce a novel 3D scanning neighbor (3SN) generated during the data collection and 3SN implies structural edge coherence cues. We use 3SN to overcome the degradation of performance and data quality caused by the sparsity-varying properties of LiDAR point clouds. In order to effectively model the complementation between these distinct cues and build consistent temporal relationships across human motions, we propose a new transformer-based module called the CoherenceFuse module. Extensive experiments were conducted on publicly available datasets, namely LidarHuman26M, CIMI4D, SLOPER4D and Waymo Open Dataset v2.0, showcase the superiority and effectiveness of our proposed method. In particular, when compared with LidarCap on the LidarHuman26M dataset, our method demonstrates a reduction of 7.08mm in the average MPJPE metric, along with a decrease of 16.55mm in the MPJPE metric for distances exceeding 25 meters. The code and models are available at https://github.com/jingyi-zhang/Neighborhood-enhanced-LidarCap.
3D single object tracking remains a challenging problem due to the sparsity and incompleteness of the point clouds. Existing algorithms attempt to address the challenges in two strategies. The first strategy is to learn dense geometric features based on the captured sparse point cloud. Nevertheless, it is quite a formidable task since the learned dense geometric features are with high uncertainty for depicting the shape of the target object. The other strategy is to aggregate the sparse geometric features of multiple templates to enrich the shape information, which is a routine solution in 2D tracking. However, aggregating the coarse shape representations can hardly yield a precise shape representation. Different from 2D pixels, 3D points of different frames can be directly fused by coordinate transform, i.e., shape completion. Considering that, we propose to construct a synthetic target representation composed of dense and complete point clouds depicting the target shape precisely by shape completion for robust 3D tracking. Specifically, we design a voxelized 3D tracking framework with shape completion, in which we propose a quality-aware shape completion mechanism to alleviate the adverse effect of noisy historical predictions. It enables us to effectively construct and leverage the synthetic target representation. Besides, we also develop a voxelized relation modeling module and box refinement module to improve tracking performance. Favorable performance against state-of-the-art algorithms on three benchmarks demonstrates the effectiveness and generalization ability of our method.
Few-shot Visual Question Answering (VQA) realizes few-shot cross-modal learning, which is an emerging and challenging task in computer vision. Currently, most of the few-shot VQA methods are confined to simply extending few-shot classification methods to cross-modal tasks while ignoring the spatial distribution properties of multimodal features and cross-modal information interaction. To address this problem, we propose a novel Cross-modal feature Distribution Calibration Inference Network (CDCIN) in this paper, where a new concept named visual information entropy is proposed to realize multimodal features distribution calibration by cross-modal information interaction for more effective few-shot VQA. Visual information entropy is a statistical variable that represents the spatial distribution of visual features guided by the question, which is aligned before and after the reasoning process to mitigate redundant information and improve multi-modal features by our proposed visual information entropy calibration module. To further enhance the inference ability of cross-modal features, we additionally propose a novel pre-training method, where the reasoning sub-network of CDCIN is pretrained on the base class in a VQA classification paradigm and fine-tuned on the few-shot VQA datasets. Extensive experiments demonstrate that our proposed CDCIN achieves excellent performance on few-shot VQA and outperforms state-of-the-art methods on three widely used benchmark datasets.
Imperceptibility is one of the crucial requirements for adversarial examples. Previous adversarial attacks on 3D point cloud recognition suffer from noticeable outliers, resulting in low imperceptibility. We think that the drawbacks can be alleviated via taking the local curvature of the point cloud into consideration. Existing approaches introduce the local geometry distance into the attack objective function. However, their definition of the local geometry distance neglects different perceptibility of distortions along different directions. In this paper, we aim to enhance the imperceptibility of adversarial attacks on 3D point cloud recognition by better preserving the local curvature of the original 3D point clouds. To this end, we propose the Curvature-Invariant Method (CIM), which directly regularizes the back-propagated gradient during the generation of adversarial point clouds based on two assumptions. Specifically, we first decompose the back-propagated gradients into the tangent plane and the normal direction. Then we directly reduce the gradient along the large curvature direction on the tangent plane and only keep the gradient along the negative normal direction. Comprehensive experimental comparisons confirm the superiority of our approach. Notably, our strategy can achieve 7.2% and 14.5% improvements in Hausdorff distance and Gaussian curvature measurements of the imperceptibility.
Improving the Adversarial Transferability of Vision Transformers with Virtual Dense Connection
PDF ↗With the great achievement of vision transformers (ViTs), transformer-based approaches have become the new paradigm for solving various computer vision tasks. However, recent research shows that similar to convolutional neural networks (CNNs), ViTs are still vulnerable to adversarial attacks. To explore the shared deficiency of models with different structures, researchers begin to analyze the cross-structure adversarial transferability, which is still under-explored. Therefore, in this work, we focus on the ViT attacks to improve the cross-structure transferability between the transformer-based and convolution-based models. Previous studies fail to thoroughly investigate the influence of the components inside the ViT models on adversarial transferability, leading to inferior performance. To overcome the drawback, we launch a motivating study by linearly down-scaling the gradients of components inside the ViT models to analyze their influence on adversarial transferability. Based on the motivating study, we find that the gradient of the skip connection most influences transferability and believe that back-propagating gradients from deeper blocks can enhance transferability. Therefore, we propose the Virtual Dense Connection method (VDC). Specifically, without changing the forward pass, we first recompose the original network to add virtual dense connections. Then we back-propagate gradients of deeper Attention maps and Multi-layer Perceptron (MLP) blocks via virtual dense connections when generating adversarial samples. Extensive experiments confirm the superiority of our proposed method over the state-of-the-art baselines, with an 8.2% improvement in transferability between ViT models and a 7.2% improvement in cross-structure transferability from ViTs to CNNs.
Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and texturing in 3D that ensure details and various styles (realistic, fictional, etc). We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance. In specific, we introduce a 2D diffusion model conditioned on DensePose signal to establish 3D pose control of avatars through 2D images, which enhances view consistency from partially observed scenarios. It addresses the infamous Janus Problem and significantly stablizes the generation process. Moreover, we propose a progressive high-resolution 3D synthesis strategy, which obtains substantial improvement over the quality of the created 3D avatars. To this end, the proposed AvatarVerse pipeline achieves zero-shot 3D modeling of 3D avatars that are not only more expressive, but also in higher quality and fidelity than previous works. Rigorous qualitative evaluations and user studies showcase AvatarVerse's superiority in synthesizing high-fidelity 3D avatars, leading to a new standard in high-quality and stable 3D avatar creation. Our project page is: https://avatarverse3d.github.io/ .
HR-Pro: Point-Supervised Temporal Action Localization via Hierarchical Reliability Propagation
PDF ↗Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully-supervised methods. Code will be available at https://github.com/pipixin321/HR-Pro.
Image-text matching bridges vision and language, which is a fundamental task in multimodal intelligence. Its key challenge lies in how to capture visual-semantic relevance. Fine-grained semantic interactions come from fragment alignments between image regions and text words. However, not all fragments contribute to image-text relevance, and many existing methods are devoted to mining the vital ones to measure the relevance accurately. How well image and text relate depends on the degree of semantic sharing between them. Treating the degree as an effect and fragments as its possible causes, we define those indispensable causes for the generation of the degree as necessary undertakers, i.e., if any of them did not occur, the relevance would be no longer valid. In this paper, we revisit image-text matching in the causal view and uncover inherent causal properties of relevance generation. Then we propose a novel theoretical prototype for estimating the probability-of-necessity of fragments, PN_f, for the degree of semantic sharing by means of causal inference, and further design a Necessary Undertaker Identification Framework (NUIF) for image-text matching, which explicitly formalizes the fragment's contribution to image-text relevance by modeling PN_f in two ways. Extensive experiments show our method achieves state-of-the-art on benchmarks Flickr30K and MSCOCO.
Class-incremental object detection (CIOD) is a real-world desired capability, requiring an object detector to continuously adapt to new tasks without forgetting learned ones, with the main challenge being catastrophic forgetting. Many methods based on distillation and replay have been proposed to alleviate this problem. However, they typically learn on a pure visual backbone, neglecting the powerful representation capabilities of textual cues, which to some extent limits their performance. In this paper, we propose task-aware language-image representation to mitigate catastrophic forgetting, introducing a new paradigm for language-image-based CIOD. First of all, we demonstrate the significant advantage of language-image detectors in mitigating catastrophic forgetting. Secondly, we propose a learning task-aware language-image representation method that overcomes the existing drawback of directly utilizing the language-image detector for CIOD. More specifically, we learn the language-image representation of different tasks through an insulating approach in the training stage, while using the alignment scores produced by task-specific language-image representation in the inference stage. Through our proposed method, language-image detectors can be more practical for CIOD. We conduct extensive experiments on COCO 2017 and Pascal VOC 2007 and demonstrate that the proposed method achieves state-of-the-art results under the various CIOD settings.
A Robust Mutual-Reinforcing Framework for 3D Multi-Modal Medical Image Fusion Based on Visual-Semantic Consistency
PDF ↗This work proposes a robust 3D medical image fusion framework to establish a mutual-reinforcing mechanism between visual fusion and lesion segmentation, achieving their double improvement. Specifically, we explore the consistency between vision and semantics by sharing feature fusion modules. Through the coupled optimization of the visual fusion loss and the lesion segmentation loss, visual-related and semantic-related features will be pulled into the same domain, effectively promoting accuracy improvement in a mutual-reinforcing manner. Further, we establish the robustness guarantees by constructing a two-level refinement constraint in the process of feature extraction and reconstruction. Benefiting from full consideration for common degradations in medical images, our framework can not only provide clear visual fusion results for doctor's observation, but also enhance the defense ability of lesion segmentation against these negatives. Extensive evaluations of visual fusion and lesion segmentation scenarios demonstrate the advantages of our method in terms of accuracy and robustness. Moreover, our proposed framework is generic, which can be well-compatible with existing lesion segmentation algorithms and improve their performance. The code is publicly available at https://github.com/HaoZhang1018/RMR-Fusion.
Addressing Out-Of-Distribution (OOD) Segmentation and Zero-Shot Semantic Segmentation (ZS3) is challenging, necessitating segmenting unseen classes. Existing strategies adapt the class-agnostic Mask2Former (CA-M2F) tailored to specific tasks. However, these methods cater to singular tasks, demand training from scratch, and we demonstrate certain deficiencies in CA-M2F, which affect performance. We propose the Class-Agnostic Structure-Constrained Learning (CSL), a plug-in framework that can integrate with existing methods, thereby embedding structural constraints and achieving performance gain, including the unseen, specifically OOD, ZS3, and domain adaptation (DA) tasks. There are two schemes for CSL to integrate with existing methods (1) by distilling knowledge from a base teacher network, enforcing constraints across training and inference phrases, or (2) by leveraging established models to obtain per-pixel distributions without retraining, appending constraints during the inference phase. Our soft assignment and mask split methodologies enhance OOD object segmentation. Empirical evaluations demonstrate CSL's prowess in boosting the performance of existing algorithms spanning OOD segmentation, ZS3, and DA segmentation, consistently transcending the state-of-art across all three tasks.