检索结果-内蒙古大学图书馆

Singular Value Decomposition Compressed Ghost Imaging Based on Non-negative Constraints 11

学校读者我要写书评

暂无评论

Singular Value Decomposition Compressed Ghost Imaging Based ...

2019第十一届数字图像处理国际会议

作者： Cheng Zhang Jun Tang Yuanyuan Zhu Meiqin Wang Qianwen Chen Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University

ISBN: (数字)9781510630765

ISBN: (纸本)9781510630758

Compressed ghost imaging can effectively enhance the quality of original image from far fewer measurements,but due to the non-negativity of the measurement matrix,the recover quality is thus *** this paper,singular value decomposition compressed ghost imaging is proposed;First,the singular value decomposition be used to decompose the measurement matrix,and then the optimized measurement matrix and measurements are used to recover the original *** experiments verify the superiority of our proposed singular value decomposition compression ghost imaging method.

关键词： ghost imaging compressed ghost imaging singular value decomposition compressed ghost imaging

DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Cao, Juan Sheng, Qiang Qi, Peng Li, Xirong Li, Jintao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

The daily practice of sharing images on social media raises a severe issue about privacy leakage. To address the issue, privacy-leaking image detection is studied recently, with the goal to automatically identify images that may leak privacy. Recent advance on this task benefits from focusing on crucial objects via pretrained object detectors and modeling their correlation. However, these methods have two limitations: 1) they neglect other important elements like scenes, textures, and objects beyond the capacity of pretrained object detectors;2) the correlation among objects is fixed, but a fixed correlation is not appropriate for all the images. To overcome the limitations, we propose the Dynamic Region-Aware Graph Convolutional Network (DRAG) that dynamically finds out crucial regions including objects and other important elements, and models their correlation adaptively for each input image. To find out crucial regions, we cluster spatially-correlated feature channels into several region-aware feature maps. Further, we dynamically model the correlation with the self-attention mechanism and explore the interaction among the regions with a graph convolutional network. The DRAG achieved an accuracy of 87% on the largest dataset for privacy-leaking image detection, which is 10 percentage points higher than the state of the art. The further case study demonstrates that it found out crucial regions containing not only objects but other important elements like textures. The code and more details are in https://***/guang-yanng/DRAG. © 2022, CC BY.

关键词： Object detection

Instruction Tuning-free Visual Token Complement for Multimodal LLMs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Dongsheng Cui, Jiequan Li, Miaoge Lin, Wang Chen, Bo Zhang, Hanwang College of Computer Science and Software Engineering Shenzhen University China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computing Hong Kong Polytechnic University Hong Kong College of Computer Science and Technology Zhejiang University China National Key Lab of Radar Signal Processing Xidian University China

As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for high-quality instruction pairs and the loss of visual information in image-to-text training objectives. To this end, we propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features and thus improve response accuracy. Specifically, our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens to enrich the original visual input. Moreover, an iterative strategy is further designed to extract more visual information by iteratively using the visual selector without any additional training. Notably, the training pipeline requires no additional image-text pairs, resulting in a desired instruction tuning-free property. Both qualitative and quantitative experiments demonstrate the superiority and efficiency of our VTC. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual BASIC

Balanced Contrastive Learning for Long-Tailed Visual Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Jianggang Wang, Zheng Chen, Jingjing Chen, Yi-Ping Phoebe Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Department of Computer Science and Information Technology La Trobe University Australia

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle to represent and classify the tail classes. Although the problem of learning unbiased classifiers has been well studied, methods for representing imbalanced data are under-explored. In this paper, we focus on representation learning for imbalanced data. Recently, supervised contrastive learning has shown promising performance on balanced data recently. However, through our theoretical analysis, we find that for long-tailed data, it fails to form a regular simplex which is an ideal geometric configuration for representation learning. To correct the optimization behavior of SCL and further improve the performance of long-tailed visual recognition, we propose a novel loss for balanced contrastive learning (BCL). Compared with SCL, we have two improvements in BCL: class-averaging, which balances the gradient contribution of negative classes;class-complement, which allows all classes to appear in every mini-batch. The proposed balanced contrastive learning (BCL) method satisfies the condition of forming a regular simplex and assists the optimization of cross-entropy. Equipped with BCL, the proposed two-branch framework can obtain a stronger feature representation and achieve competitive performance on long-tailed benchmark datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018. Our code is available at this URL. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Yabin Li, Chenglong Wang, Xiao Tang, Jin Huang, Zhixiang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes School of Electronic and Information Engineering Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant appearance gap between modalities limits the feature representation ability of certain modalities during the fusion process. To address this problem, we propose a novel Progressive Fusion Transformer called ProFormer, which progressively integrates single-modality information into the multimodal representation for robust RGBT tracking. In particular, ProFormer first uses a self-attention module to collaboratively extract the multimodal representation, and then uses two cross-attention modules to interact it with the features of the dual modalities respectively. In this way, the modality-specific information can well be activated in the multimodal representation. Finally, a feed-forward network is used to fuse two interacted multimodal representations for the further enhancement of the final multimodal representation. In addition, existing learning methods of RGBT trackers either fuse multimodal features into one for final classification, or exploit the relationship between unimodal branches and fused branch through a competitive learning strategy. However, they either ignore the learning of single-modality branches or result in one branch failing to be well optimized. To solve these problems, we propose a dynamically guided learning algorithm that adaptively uses well-performing branches to guide the learning of other branches, for enhancing the representation ability of each branch. Extensive experiments demonstrate that our proposed ProFormer sets a new state-of-the-art performance on RGBT210, RGBT234, LasHeR, and VTUAV datasets. In particular, the improvements of ProFormer on the LasHeR dataset are up to +6.2%/+ 4.1% in PR/SR compared with existing best RGBT tracker. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiao, Yang Chen, Shaoxiang Jie, Zequn Chen, Jingjing Ma, Lin Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Meituan Inc China

3D dense captioning is a recently-proposed novel task, where point clouds contain more geometric information than the 2D counterpart. However, it is also more challenging due to the higher complexity and wider variety of inter-object relations contained in point clouds. Existing methods only treat such relations as by-products of object feature learning in graphs without specifically encoding them, which leads to sub-optimal results. In this paper, aiming at improving 3D dense captioning via capturing and utilizing the complex relations in the 3D scene, we propose MORE, a Multi-Order RElation mining model, to support generating more descriptive and comprehensive captions. Technically, our MORE encodes object relations in a progressive manner since complex relations can be deduced from a limited number of basic ones. We first devise a novel Spatial Layout Graph Convolution (SLGC), which semantically encodes several first-order relations as edges of a graph constructed over 3D object proposals. Next, from the resulting graph, we further extract multiple triplets which encapsulate basic first-order relations as the basic unit, and construct several Object-centric Triplet Attention Graphs (OTAG) to infer multi-order relations for every target object. The updated node features from OTAG are aggregated and fed into the caption decoder to provide abundant relational cues, so that captions including diverse relations with context objects can be generated. Extensive experiments on the Scan2Cap dataset prove the effectiveness of our proposed MORE and its components, and we also outperform the current state-of-the-art method. Our code is available at https://***/SxJyJay/MORE. Copyright © 2022, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

Robust DOA Estimation Against Outliers via Joint Sparse Representation

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Li, Yingsong Xiao, Wudang Zhao, Luyu Huang, Zhixiang Li, Qiang Li, Liping de Lamare, Rodrigo C. Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei230601 China PUC-Rio Brazil University of York United Kingdom Gávea 22451-900 Brazil Department of Electronic Engineering University of York YorkYO10 5DD United Kingdom

Standard Direction of Arrival (DOA) estimation methods are typically derived based on the Gaussian noise assumption, making them highly sensitive to outliers. Therefore, in the presence of impulsive noise, the performance of these methods may significantly deteriorate. In this paper, we model impulsive noise as Gaussian noise mixed with sparse outliers. By exploiting their statistical differences, we propose a novel DOA estimation method based on sparse signal recovery (SSR). Furthermore, to address the issue of grid mismatch, we utilize an alternating optimization approach that relies on the estimated outlier matrix and the on-grid DOA estimates to obtain the off-grid DOA estimates. Simulation results demonstrate that the proposed method exhibits robustness against large outliers. © 2023, CC BY.

关键词： Direction of arrival

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Meng, Lingchen Dai, Xiyang Chen, Yinpeng Zhang, Pengchuan Chen, Dongdong Liu, Mengchen Wang, Jianfeng Wu, Zuxuan Yuan, Lu Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Microsoft United States

Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets due to two inconsistencies among detection datasets: taxonomy difference and domain gap. In this paper, we address these challenges by a new design (named Detection Hub) that is dataset-aware and category-aligned. It not only mitigates the dataset inconsistency but also provides coherent guidance for the detector to learn across multiple datasets. In particular, the dataset-aware design is achieved by learning a dataset embedding that is used to adapt object queries as well as convolutional kernels in detection heads. The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding and leveraging the semantic coherence of language embedding. Detection Hub fulfills the benefits of large data on object detection. Experiments demonstrate that joint training on multiple datasets achieves significant performance gains over training on each dataset alone. Detection Hub further achieves SoTA performance on UODB benchmark with wide variety of datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Haoran Han, Xintong Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Huya Inc China

Most existing methods for unsupervised domain adaptation (UDA) rely on a shared network to extract domain-invariant features. However, when facing multiple source domains, optimizing such a network involves updating the parameters of the entire network, making it both computationally expensive and challenging, particularly when coupled with min-max objectives. Inspired by recent advances in prompt learning that adapts high-capacity models for downstream tasks in a computationally economic way, we introduce Multi-Prompt Alignment (MPA), a simple yet efficient framework for multi-source UDA. Given a source and target domain pair, MPA first trains an individual prompt to minimize the domain gap through a contrastive loss. Then, MPA denoises the learned prompts through an auto-encoding process and aligns them by maximizing the agreement of all the reconstructed prompts. Moreover, we show that the resulting subspace acquired from the auto-encoding process can easily generalize to a streamlined set of target domains, making our method more efficient for practical usage. Extensive experiments show that MPA achieves state-of-the-art results on three popular datasets with an impressive average accuracy of 54.1% on DomainNet. Code is available at https://***/HaoranChen/Multi-Prompt-Alignment-for-MSUDA. © 2022, CC BY.

关键词： signal encoding