检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lei Jin Gen Luo Yiyi Zhou Xiaoshuai Sun Guannan Jiang Annan Shu Rongrong Ji Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University P.R. China Institute of Artificial Intelligence Xiamen University P.R. China Intelligent Manufacturing Department Contemporary Amperex Technology Co. Limited (CATL)

Referring Expression Comprehension (REC) is a task of grounding the referent based on an expression, and its development is greatly limited by expensive instance-level annotations. Most existing weakly supervised methods are built based on two-stage detection networks, which are computationally expensive. In this paper, we resort to the efficient one-stage detector and propose a novel weakly supervised model called ***, RefCLIP redefines weakly supervised REC as an anchor-text matching problem, which can avoid the complex post-processing in existing methods. To achieve weakly supervised learning, we introduce anchor-based contrastive loss to optimize Re-fCLlP via numerous anchor-text pairs. Based on RefCLIP, we further propose the first model-agnostic weakly supervised training scheme for existing REC models, where RefCLIP acts as a mature teacher to generate pseudo-labels for teaching common REC models. With our careful designs, this scheme can even help existing REC models achieve better weakly supervised performance than RefCLIP, e.g., TransVg and SimREC. To validate our approaches, we conduct extensive experiments on four REC benchmarks, i.e., RefCOCO, RefCOCO+, RefCOCOg and ReferItGame. Experimental results not only report our significant performance gains over existing weakly supervised models, e.g., +24.87% on RefCOCO, but also show the 5x faster inference speed. Project: https://***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shadow Removal by High-Quality Shadow Synthesis

SSRN

引用

SSRN 2023年

作者： Zhong, Yunshan You, Lizhou Zhang, Yuxin Chao, Fei Ji, Rongrong Institute of Artificial Intelligence Xiamen University Fujian Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Fujian Xiamen China Department of Artificial Intelligence Media Analytics and Computing Laboratory School of Informatics Xiamen University Fujian Xiamen361005 China Peng Cheng Laboratory Guangdong Shenzhen China

Most shadow removal methods rely on paired shadow/non-shadow images to train the shadow removal model, which involves laborious and lavish shadow region annotations. Recently, to avoid the cumbersome collection of paired images, increasing attention has been focused on shadow image synthesis methods that adopt the generator to synthesize pseudo shadow images to construct pseudo pairs for training shadow removal models. However, current methods suffer from poor performance since these synthesized images are shadow-inauthentic and details-impaired. In this paper, we present a novel generation framework, referred to as HQSS, for high-quality pseudo shadow image synthesis. The given image is first decoupled into a shadow region identity and a non-shadow region identity. HQSS employs a shadow feature encoder and a generator to synthesize pseudo images. Specifically, the encoder extracts the shadow feature of a region identity which is then paired with another region identity to serve as the generator input to synthesize a pseudo image. The pseudo image is expected to have the shadow feature as its input shadow feature and as well as a real-like image detail as its input region identity. To fulfill this goal, we design three learning objectives. When the shadow feature and input region identity are from the same region identity, we propose a self-reconstruction loss that guides the generator to reconstruct an identical pseudo image as its input. When the shadow feature and input region identity are from different identities, we introduce an inter-reconstruction loss and a cycle-reconstruction loss to make sure that shadow characteristics and detail information can be well retained in the synthesized images. Our HQSS is observed to outperform the current methods on ISTD dataset, Video Shadow Removal dataset, and SRD dataset. The code is available at \url{https://***/zysxmu/HQSS}. © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Perturbation Synergy Attack for Person Re-identification

arXiv

引用

arXiv 2024年

作者： Gong, Yunpeng Zhong, Zhun Qu, Yansong Luo, Zhiming Ji, Rongrong Jiang, Min School of Informatics Xiamen University China School of Computer Science and Information Engineering Hefei University of Technology China Department of Artificial Intelligence Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Key Laboratory of Digital Protection and Intelligent Processing of Intangible CulturalHeritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University Fujian Xiamen361005 China

In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems. © 2024, CC BY-NC-ND.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Decoupled Augmentation

Graph Contrastive Learning with Decoupled Augmentation

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shihao Gao Caoshuo Li Cunli Mao Xulong Zhang Xiaoyang Qu Taisong Jin Jianzong Wang Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Ping An Technology Co. Ltd. Shenzhen China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph’s semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches.

关键词： Acoustic distortion Semantics Contrastive learning Interference Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

GraCo: Granularity-Controllable Interactive Segmentation

GraCo: Granularity-Controllable Interactive Segmentation

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yian Zhao Kehan Li Zesen Cheng Pengchong Qiao Xiawu Zheng Rongrong Ji Chang Liu Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Peng Cheng Laboratory Shenzhen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Department of Automation and BNRist Tsinghua University Beijing China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Interactive Segmentation (IS) segments specific objects or parts in the image according to user input. Current IS pipelines fall into two categories: single-granularity out-put and multi-granularity output. The latter aims to allevi-ate the spatial ambiguity present in the former. However, the multi-granularity output pipeline suffers from limited interaction flexibility and produces redundant results. In this work, we introduce Granularity-Controllable Interactive Segmentation (GraCo), a novel approach that allows precise control of prediction granularity by introducing ad-ditional parameters to input. This enhances the customization of the interactive system and eliminates redundancy while resolving ambiguity. Nevertheless, the exorbitant cost of annotating multi-granularity masks and the lack of avail-able datasets with granularity annotations make it difficult for models to acquire the necessary guidance to control out-put granularity. To address this problem, we design an any-granularity mask generator that exploits the semantic property of the pre-trained IS model to automatically gen-erate abundant mask-granularity pairs without requiring additional manual annotation. Based on these pairs, we propose a granularity-controllable learning strategy that efficiently imparts the granularity controllability to the IS model. Extensive experiments on intricate scenarios at ob-ject and part levels demonstrate that our GraCo has signifi-cant advantages over previous methods. This highlights the potential of GraCo to be a flexible annotation tool, capable of adapting to diverse segmentation scenarios. The project page: https://***/GraCo.

关键词： Image segmentation Adaptation models Annotations Interactive systems Pipelines Semantics Redundancy

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Intelligent Surface Enhanced Wireless Localization: Phase Optimization for Malicious Interference Mitigation

引用

IEEE Transactions on Communications 2025年

作者： Zhang, Yi Xie, Yajing Wang, Lijia Liwang, Minghui Wang, Xianbin Xiamen University Ministry of Education of China Department of Information and Communication Engineering Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen China Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Department of Control Science and Engineering Shanghai China Western University Department of Electrical and Computer Engineering ON Canada

Recently, unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) have merged as important enabling technologies for localization coverage extension and localization accuracy improvement under signal blockage and malicious interference conditions. However, most existing works assume known locations of jammers, which is generally impractical in real-world networks. To overcome this challenge, we propose a novel RIS-enhanced wireless localization framework against malicious interference with the support of either narrowband or orthogonal frequency division multiplexing (OFDM) pilot signals. A two-stage anti-jamming localization approach is developed to first estimate the unknown channel and signal information of the jammer and then localize the user’s position by eliminating the jamming signal. More importantly, we utilize the full potential of RIS to improve localization accuracy by optimizing the phase shift profile during the iterative process. Extensive simulation results demonstrate the commendable performance of our proposed framework, which can not only mitigate the jamming effect but also achieve better localization accuracy, offering a good reference for future heterogeneous and complex wireless networks. © 1972-2012 IEEE.

关键词： Frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Learning Diffusion High-Quality Priors for Pan-Sharpening: A Two-Stage Approach With Time-Aware Adapter Fine-Tuning

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Wang, Yingying Lin, Yunlong He, Xuanhua Zheng, Hui Yan, keyu Fan, Linyu Huang, Yue Ding, Xinghao Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen361005 China Institute of Artificial Intelligence Xiamen University Xiamen361102 China Xiamen University School of Informatics Xiamen361102 China University of Science and Technology of China Science Island Branch Graduate School Hefei230026 China Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230031 China

Pan-sharpening aims to enhance the spatial resolution of the low-resolution multispectral (LRMS) image by incorporating high-frequency details from the panchromatic (PAN) image, while maintaining the spectral qualities of the LRMS image. Recent advancements in diffusion models have shown remarkable capabilities in image restoration and generation. However, simply applying diffusion models in pan-sharpening yields suboptimal outcomes in terms of fine-grained details and spectral fidelity. To this end, we introduce TA-DiffHQP, a two-stage approach that integrates the diffusion high-quality priors model (DiffHQP) and the time-aware adapter (TA-Adapter). Initially, we perform self-reconstruction pretraining DiffHQP with a fixed sampling strategy on approximately 24K high-resolution remote sensing datasets to explicitly model the high-quality texture details and spectral fidelity, after which we freeze most of DiffHQP's parameters. In stage two, we integrate time-aware fusion adapters with the DiffHQP, enabling rapid adaptation to the pan-sharpening task. The TA-Adapters prioritize low-frequency main scenes during the early phases of the denoising process and refine high-frequency details in the later phases, achieving cross-modal information fusion from coarse to fine. Extensive experiments conducted on three satellite datasets demonstrate that our approach attains state-of-the-art (SOTA) performance over existing methods, revealing superior fusion outcomes in pan-sharpening. © 2025 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization

arXiv

引用

arXiv 2023年

作者： Zhong, Yunshan Zhou, Yuyao Chao, Fei Ji, Rongrong Institute of Artificial Intelligence Xiamen University Fujian Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Fujian Xiamen China Department of Artificial Intelligence School of Informatics Xiamen University Fujian Xiamen China Peng Cheng Laboratory Guangdong Shenzhen China

Arbitrary bit-width network quantization has received significant attention due to its high adaptability to various bit-width requirements during runtime. However, in this paper, we investigate existing methods and observe a significant accumulation of quantization errors caused by switching weight and activations bit-widths, leading to limited performance. To address this issue, we propose MBQuant, a novel method that utilizes a multi-branch topology for arbitrary bit-width quantization. MBQuant duplicates the network body into multiple independent branches, where the weights of each branch are quantized to a fixed 2-bit and the activations remain in the input bit-width. The computation of a desired bit-width is completed by selecting an appropriate number of branches that satisfy the original computational constraint. By fixing the weight bit-width, this approach substantially reduces quantization errors caused by switching weight bit-widths. Additionally, we introduce an amortization branch selection strategy to distribute quantization errors caused by switching activation bit-widths among branches to improve performance. Finally, we adopt an in-place distillation strategy that facilitates guidance between branches to further enhance MBQuant’s performance. Extensive experiments demonstrate that MBQuant achieves significant performance gains compared to existing arbitrary bit-width quantization methods. Code is made publicly available at https://***/zysxmu/MBQuant. Copyright © 2023, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Meta Architecture for Point Cloud Analysis

Meta Architecture for Point Cloud Analysis

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haojia Lin Xiawu Zheng Lijiang Li Fei Chao Shanshan Wang Yan Wang Yonghong Tian Rongrong Ji Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University P.R. China Peng Cheng Laboratory Chinese Academy of Sciences Samsara Inc. National Engineering Research Center for Visual Technology Peking University Shenzhen Research Institute of Xiamen University

Recent advances in 3D point cloud analysis bring a diverse set of network architectures to the field. However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field. In this paper, we take the initiative to explore and propose a unified framework called PointMeta, to which the popular 3D point cloud analysis approaches could fit. This brings three benefits. First, it allows us to compare different approaches in a fair manner, and use quick experiments to verify any empirical observations or assumptions summarized from the comparison. Second, the big picture brought by PointMeta enables us to think across different components, and revisit common beliefs and key design decisions made by the popular approaches. Third, based on the learnings from the previous two analyses, by doing simple tweaks on the existing approaches, we are able to derive a basic building block, termed PointMetaBase. It shows very strong performance in efficiency and effectiveness through extensive experiments on challenging benchmarks, and thus verifies the necessity and benefits of high-level interpretation, contrast, and comparison like PointMeta. In particular, PointMetaBase surpasses the previous state-of-the-art method by 0.7%/1.4/%2.1% mIoU with only 2%/11%/13% of the computation cost on the S3DIS datasets. The code and models are available at https://***/linhaojia13/PointMetaBase.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Label-Noise Learning with Intrinsically Long-Tailed Data

arXiv

引用

arXiv 2022年

作者： Lu, Yang Zhang, Yiliang Han, Bo Cheung, Yiu-Ming Wang, Hanzi Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China Department of Computer Science Hong Kong Baptist University Hong Kong

Label noise is one of the key factors that lead to the poor generalization of deep learning models. Existing label-noise learning methods usually assume that the ground-truth classes of the training data are balanced. However, the real-world data is often imbalanced, leading to the inconsistency between observed and intrinsic class distribution with label noises. In this case, it is hard to distinguish clean samples from noisy samples on the intrinsic tail classes with the unknown intrinsic class distribution. In this paper, we propose a learning framework for label-noise learning with intrinsically long-tailed data. Specifically, we propose two-stage bi-dimensional sample selection (TABASCO) to better separate clean samples from noisy samples, especially for the tail classes. TABASCO consists of two new separation metrics that complement each other to compensate for the limitation of using a single metric in sample separation. Extensive experiments on benchmarks demonstrate the effectiveness of our method. Our code is available at https://***/Wakings/TABASCO. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：