检索结果-内蒙古大学图书馆

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Quan Wang, Lei Patel, Vishal M. Xie, Xiaohua Lai, Jianhuang School of Computer Science and Engineering Sun Yat-Sen University China Guangdong China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Department of Electrical and Computer Engineering Johns Hopkins University United States

Existing person re-identification methods have achieved remarkable advances in appearance-based identity association across homogeneous cameras, such as ground-ground matching. However, as a more practical scenario, aerial-ground person re-identification (AGPReID) among heterogeneous cameras has received minimal attention. To alleviate the disruption of discriminative identity representation by dramatic view discrepancy as the most significant challenge in AGPReID, the view-decoupled transformer (VDT) is proposed as a simple yet effective framework. Two major components are designed in VDT to decouple view-related and view-unrelated features, namely hierarchical subtractive separation and orthogonal loss, where the former separates these two features inside the VDT, and the latter constrains these two to be independent. In addition, we contribute a large-scale AGPReID dataset called CARGO, consisting of five/eight aerial/ground cameras, 5,000 identities, and 108,563 images. Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5.0%/2.7% on CARGO and 3.7%/5.2% on AG-ReID, keeping the same magnitude of computational complexity. Our project is available at https://***/LinlyAC/VDT-AGPReID. © 2024, CC BY.

关键词： Antennas

CONFIDENCE-GUIDED ADAPTIVE GATE AND DUAL DIFFERENTIAL ENHANCEMENT FOR VIDEO SALIENT OBJECT DETECTION

学校读者我要写书评

暂无评论

CONFIDENCE-GUIDED ADAPTIVE GATE AND DUAL DIFFERENTIAL ENHANC...

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Chen, Peijia Lai, Jianhuang Wang, Guangcong Zhou, Huajun School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781665438643

Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, spatial and temporal cues are often unreliable in real-world scenarios, such as low-contrast foreground, fast motion, and multiple moving objects. To address these problems, we propose a new framework to adaptively capture available information from spatial and temporal cues, which contains Confidence-guided Adaptive Gate (CAG) modules and Dual Differential Enhancement (DDE) modules. For both RGB features and optical flow features, CAG estimates confidence scores supervised by the IoU between predictions and the ground truths to re-calibrate the information with a gate mechanism. DDE captures the differential feature representation to enrich the spatial and temporal information and generate the fused features. Experimental results on four widely used datasets demonstrate the effectiveness of the proposed method against thirteen state-of-the-art methods. © 2021 IEEE

关键词： Object detection

Multimodal Action Quality Assessment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Ling-An Zheng, Wei-Shi School of Artificial Intelligence Sun Yat-sen University Guangdong Zhuhai519082 China School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou510275 China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangdong Guangzhou510275 China Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Ministry of Education Guangdong Guangzhou510275 China

Action quality assessment (AQA) is to assess how well an action is performed. Previous works perform modelling by only the use of visual information, ignoring audio information. We argue that although AQA is highly dependent on visual information, the audio is useful complementary information for improving the score regression accuracy, especially for sports with background music, such as figure skating and rhythmic gymnastics. To leverage multimodal information for AQA, i.e., RGB, optical flow and audio information, we propose a Progressive Adaptive Multimodal Fusion Network (PAMFN) that separately models modality-specific information and mixed-modality information. Our model consists of with three modality-specific branches that independently explore modality-specific information and a mixed-modality branch that progressively aggregates the modality-specific information from the modality-specific branches. To build the bridge between modality-specific branches and the mixed-modality branch, three novel modules are proposed. First, a Modality-specific Feature Decoder module is designed to selectively transfer modality-specific information to the mixed-modality branch. Second, when exploring the interaction between modality-specific information, we argue that using an invariant multimodal fusion policy may lead to suboptimal results, so as to take the potential diversity in different parts of an action into consideration. Therefore, an Adaptive Fusion Module is proposed to learn adaptive multimodal fusion policies in different parts of an action. This module consists of several FusionNets for exploring different multimodal fusion strategies and a PolicyNet for deciding which FusionNets are enabled. Third, a module called Cross-modal Feature Decoder is designed to transfer cross-modal features generated by Adaptive Fusion Module to the mixed-modality branch. Our extensive experiments validate the efficacy of the proposed method, and our method achieves state-of-the-a

关键词： Damage detection

Memory-Guided Contrastive and Triplet Separation for Weakly-Supervised Disease Detection

学校读者我要写书评

暂无评论

Memory-Guided Contrastive and Triplet Separation for Weakly-...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jinwen She Qiong Li Andy J. Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Cancer Center Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Weakly-supervised disease detection has the great potential to alleviate the time-consuming and labor-intensive burden of manual annotations in instance level. While existing methods extract normality prototypes encoding normal patterns to improve the detection performance, they may fail to detect subtle anomalies without considering the diverse abnormal patterns. In this paper, we propose to recognize both normal and abnormal patterns for feature representation learning in disease detection based on a dual memory network. To learn discriminative memory banks and classifiers, dual memory loss is incorporated with a feature magnitude separation loss for model training. With the proposed contrastive feature separation loss and triplet feature separation loss, feature discriminability is further improved to obtain a more separable decision boundary. Additionally, we collect a large-scale CT dataset to evaluate lung tumor detection. Extensive experiments on the publicly available PANDA-MIL dataset and the collected LUNG-MIL dataset demonstrate the superiority of our proposed method compared to the state-of-the-art approaches for weakly-supervised disease detection.

关键词： Training Representation learning Lung cancer Prototypes Manuals Feature extraction Encoding Pattern recognition Diseases Tumors

SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liufu, Xing Tan, Chaolei Lin, Xiaotong Qi, Yonggang Li, Jinxuan Hu, Jian-Fang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China

Edge labels are typically at various granularity levels owing to the varying preferences of annotators, thus handling the subjectivity of per-pixel labels has been a focal point for edge detection. Previous methods often employ a simple voting strategy to diminish such label uncertainty or impose a strong assumption of labels with a pre-defined distribution, e.g., Gaussian. In this work, we unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our key insight is that the intermediate SAM features inherently correspond to object edges at various granularities, which reflects different edge options due to uncertainty. Therefore, we attempt to align uncertainty with granularity by regressing intermediate SAM features from different layers to object edges at multi-granularity levels. In doing so, the model can fully and explicitly explore diverse "uncertainties" in a data-driven fashion. Specifically, we inject a lightweight module (∼ 1.5% additional parameters) into the frozen SAM to progressively fuse and adapt its intermediate features to estimate edges from coarse to fine. It is crucial to normalize the granularity level of human edge labels to match their innate uncertainty. For this, we simply perform linear blending to the real edge labels at hand to create pseudo labels with varying granularities. Consequently, our uncertainty-aligned edge detector can flexibly produce edges at any desired granularity (including an optimal one). Thanks to SAM, our model uniquely demonstrates strong generalizability for cross-dataset edge detection. Extensive experimental results on BSDS500, Muticue and NYUDv2 validate our model’s superiority. Copyright © 2024, The Authors. All rights reserved.

关键词： Edge detection

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution

学校读者我要写书评

暂无评论

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medic...

International Conference on Computer Vision (ICCV)

作者： Zixuan Chen Lingxiao Yang Jian-Huang Lai Xiaohua Xie School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Medical image arbitrary-scale super-resolution (MIASSR) has recently gained widespread attention, aiming to supersample medical volumes at arbitrary scales via a single model. However, existing MIASSR methods face two major limitations: (i) reliance on high-resolution (HR) volumes and (ii) limited generalization ability, which restricts their applications in various scenarios. To overcome these limitations, we propose Cube-based Neural Radiance Field (CuNeRF), a zero-shot MIASSR framework that is able to yield medical images at arbitrary scales and free viewpoints in a continuous domain. Unlike existing MISR methods that only fit the mapping between low-resolution (LR) and HR volumes, CuNeRF focuses on building a continuous volumetric representation from each LR volume without the knowledge of the corresponding HR one. This is achieved by the proposed differentiable modules: cube-based sampling, isotropic volume rendering, and cube-based hierarchical rendering. Through extensive experiments on magnetic resource imaging (MRI) and computed tomography (CT) modalities, we demonstrate that CuNeRF can synthesize high-quality SR medical images, which outperforms state-of-the-art MISR methods, achieving better visual verisimilitude and fewer objectionable artifacts. Compared to existing MISR methods, our CuNeRF is more applicable in practice.

关键词：

Discriminative Gradient Adjustment with Coupled Knowledge Distillation for Class Incremental Learning

学校读者我要写书评

暂无评论

Discriminative Gradient Adjustment with Coupled Knowledge Di...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Hao Zhang Yanxu Hu Jiawen Peng Andy J Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China

Class Incremental Learning (CIL) is a promising approach to addressing the catastrophic forgetting problem when learning for new categories. Though recent works based on dynamic architectures achieve convincing performance, data imbalance caused by limited size of memory and compression of the increasingly growing network are challenges to be solved. In this paper, we propose the novel Discriminative Gradient Adjustment (DGA) and Coupled Knowledge Distillation strategy (CKD) for these two challengs. The DGA mitigates the data imbalance problem by designing the loss function with a static global balance factor and a ground-truth-based dynamic factor. The CKD fully utilizes intermediate layers of the dual-branch models by feature-level distillation with moving-average weight updating for network compression. Extensive experiments on CIFAR100 and ImageNet100 datasets demonstrate the superiority of our method for CIL.

关键词：

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Zixuan Yang, Lingxiao Lai, Jian-Huang Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

关键词： Volume rendering

Dual Episodic Sampling and Momentum Consistency Regularization for Unsupervised Few-shot Learning

学校读者我要写书评

暂无评论

Dual Episodic Sampling and Momentum Consistency Regularizati...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jiaxin Chen Yanxu Hu Meng Shen Andy J. Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Unsupervised Few-shot Learning (UFSL) is a practical approach to adapting knowledge learned from unlabeled data of base classes to novel classes with limited labeled data. Nevertheless, most existing UFSL methods may not learn generalizable features in latter training epochs due to the simplicity of meta-learning tasks constructed by data augmentation. To address this issue, we propose two novel components, namely Dual Episodic Sampling (DES) and Momentum Consistency Regularization (MCR) for UFSL. In the DES, two types of sampling strategies are used to construct harder training tasks with multiple augmentations to generate each pseudo-class of increased diversity. The MCR constrains the consistency of the backbone encoder with its momentum counterpart to learn better generalized features for novel classes. Experimental results on four datasets verify the superiority of our method for unsupervised few-shot image classification.

关键词：