检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Huang, Xinyu Zhang, Youcai Ma, Jinyu Tian, Weiwei Feng, Rui Zhang, Yuejie Li, Yaqian Guo, Yandong Zhang, Lei Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China OPPO Research Institute China China Academy for Engineering and Technology Fudan University China

This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features. In contrast to prior works which utilize object tags either manually labeled or automatically detected with an off-the-shelf detector with limited performance, our approach explicitly learns an image tagger using tags parsed from image-paired text and thus provides a strong semantic guidance to vision-language models. In this way, Tag2Text can utilize large-scale annotation-free image tags in accordance with image-text pairs, and provides more diverse tag categories beyond objects. As a result, Tag2Text demonstrates the ability of a foundational image tagging model, with superior zero-shot performance even comparable to fully supervised models. Moreover, by leveraging the tagging guidance, Tag2Text effectively enhances the performance of vision-language models on both generation-based and alignment-based tasks. Across a wide range of downstream benchmarks, Tag2Text achieves state-of-the-art results with similar model sizes and data scales, demonstrating the efficacy of the proposed tagging guidance. Codes, demo and pre-trained models are available at https://***/xinyu1205/recognize-anything. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Spk2ImgMamba: Spiking Camera Image Reconstruction with Multi-Scale State Space Models

Spk2ImgMamba: Spiking Camera Image Reconstruction with Multi...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Yin, Jiaoyang Fan, Bin Xu, Chao Huang, Tiejun Shi, Boxin School of Computer Science Peking University State Key Lab of Multimedia Info. Processing China School of Computer Science Peking University Nat'l Eng. Research Ctr. of Visual Technology China School of Intelligence Science and Technology Peking University Nat'l Key Lab of General Ai China

ISBN: (纸本)9798331510831

As a bio-inspired vision sensor, the spiking camera has showcased remarkable capability in high-speed imaging with a sampling rate of 40,000 Hz. Reconstructing clear images from continuous spike streams, which is obtained by each photosensor continuously detecting photons and firing them asynchronously, has garnered significant attention. Despite promising results, existing spike-to-image reconstruction methods face challenges in balancing global receptive fields and efficient computation due to the inherent limitations of their backbones. Recently, due to powerful long-range modeling and linear complexity, the state space model (SSM) has emerged as a competitive alternative to CNNs and Transformers. In this paper, we propose a lightweight spike-to-image reconstruction network that harnesses Mamba as the backbone. Our approach sequentially executes three core modules: temporal information integration, spatial feature enhancement, and progressive image reconstruction. The former accumulates cues across diverse temporal windows to explore both long-term and short-term contexts. Subsequently, to model global dependencies while heightening local detail perception, we develop a multi-scale SSM block characterized by multi-scale multi-direction scanning, which effectively boosts spatial feature representations. Finally, intensity images are decoded progressively from the enhanced light-intensity features. Extensive experiments on both synthetic and real-captured data demonstrate that our approach achieves state-of-the-art performance, with only 10% of the network parameters and nearly two orders of magnitude less computational effort. The code will be available at https://***/interstellarH/Spk2ImgMamba. © 2025 IEEE.

关键词： Bioimaging

来源：评论

学校读者我要写书评

暂无评论

GenRec: Unifying Video Generation and Recognition with Diffusion Models 38

GenRec: Unifying Video Generation and Recognition with Diffu...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Weng, Zejia Yang, Xitong Xing, Zhen 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 Department of Computer Science University of Maryland United States

Video diffusion models are able to generate high-quality videos by learning strong spatial-temporal priors on large-scale datasets. In this paper, we aim to investigate whether such priors derived from a generative process are suitable for video recognition, and eventually joint optimization of generation and recognition. Building upon Stable Video Diffusion, we introduce GenRec, the first unified framework trained with a random-frame conditioning process so as to learn generalized spatial-temporal representations. The resulting framework can naturally supports generation and recognition, and more importantly is robust even when visual inputs contain limited information. Extensive experiments demonstrate the efficacy of GenRec for both recognition and generation. In particular, GenRec achieves competitive recognition performance, offering 75.8% and 87.2% accuracy on SSV2 and K400, respectively. GenRec also performs the best on class-conditioned image-to-video generation, achieving 46.5 and 49.3 FVD scores on SSV2 and EK-100 datasets. Furthermore, GenRec demonstrates extraordinary robustness in scenarios that only limited frames can be observed. Code will be available at https://***/wengzejia1/GenRec. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Dual-Domain Calibration and Distance-Driven Correlation Filter:A Probabilistic Perspective for UAV Tracking

引用

computers, Materials & Continua 2023年第12期77卷 3741-3764页

作者： Taiyu Yan Yuxin Cao Guoxia Xu Xiaoran Zhao Hu Zhu Lizhen Deng Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjingChina School of Computer Science Qufu Normal UniversityQufuChina National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and TelecommunicationsNanjingChina

Unmanned Aerial Vehicle(UAV)tracking has been possible because of the growth of intelligent information technology in smart cities,making it simple to gather data at any time by dynamically monitoring events,people,the environment,and other aspects in the *** traditional filter creates a model to address the boundary effect and time filter degradation issues in UAV tracking *** these methods ignore the loss of data integrity terms since they are overly dependent on numerous explicit previous regularization *** light of the aforementioned issues,this work suggests a dual-domain Jensen-Shannon divergence correlation filter(DJSCF)model address the probability-based distance measuring issue in the event of filter *** two-domain weighting matrix and JS divergence constraint are combined to lessen the impact of sample imbalance and *** new tracking models that are based on the perspectives of the actual probability filter distribution and observation probability filter distribution are proposed to translate the statistical distance in the online tracking model into response *** model is roughly transformed into a linear equality constraint issue in the iterative solution,which is then solved by the alternate direction multiplier method(ADMM).The usefulness and superiority of the suggested strategy have been shown by a vast number of experimental findings.

关键词： Dual-domain weighting distance measure correlation filter ADMM

来源：评论

学校读者我要写书评

暂无评论

Concrete Structural Crack Damage Classification Using Nonlinear Dimension Reduction and Broad Learning System

Concrete Structural Crack Damage Classification Using Nonlin...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Bingshu Lin, Jia Zhuang, Xiaodong Zhang, Guanghui Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi'an China Shenzhen University Guangdong Key Lab. of Intelligent Info. Processing and Shenzhen Key Laboratory of Media Security Shenzhen China School of Computer Science and Technology Shandong University Qingdao China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9781665410205

Concrete structural crack damage classification is of importance for road safety. This paper proposes a new method based on broad neural network for crack damage classification in concrete structures. It includes three stages. Firstly, a pre-trained deep neural network is used to extract the features from crack images. Secondly, principal component analysis is used to project the retrieved features from high dimensions to low dimensions. Thirdly, broad learning system is employed to predict the classification using the low-dimensional features. Experimental results demonstrate that this method reduces the model's training time and improves classification accuracy. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras 38

Spatio-Temporal Interactive Learning for Efficient Image Rec...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Fan, Bin Yin, Jiaoyang Dai, Yuchao Xu, Chao Huang, Tiejun Shi, Boxin Nat'l Key Lab of General AI School of Intelligence Science and Technology Peking University China State Key Lab of Multimedia Info. Processing School of Computer Science Peking University China Nat'l Eng. Research Ctr. of Visual Technology School of Computer Science Peking University China School of Electronics and Information Northwestern Polytechnical University China

The spiking camera is an emerging neuromorphic vision sensor that records high-speed motion scenes by asynchronously firing continuous binary spike streams. Prevailing image reconstruction methods, generating intermediate frames from these spike streams, often rely on complex step-by-step network architectures that overlook the intrinsic collaboration of spatio-temporal complementary information. In this paper, we propose an efficient spatio-temporal interactive reconstruction network to jointly perform inter-frame feature alignment and intra-frame feature filtering in a coarse-to-fine manner. Specifically, it starts by extracting hierarchical features from a concise hybrid spike representation, then refines the motion fields and target frames scale-by-scale, ultimately obtaining a full-resolution output. Meanwhile, we introduce a symmetric interactive attention block and a multi-motion field estimation block to further enhance the interaction capability of the overall network. Experiments on synthetic and real-captured data show that our approach exhibits excellent performance while maintaining low model complexity. The code is available at https://***/GitCVfb/STIR. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

arXiv

引用

arXiv 2025年

作者： Han, Feng Chen, Kai Gong, Chao Wei, Zhipeng Chen, Jingjing Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model’s ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module’s outputs across different layers and timesteps, automatically balancing the erasure effects and model’s generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure (detecting only 34 nude parts), Cartoon Concept Removal (with an average LPIPSda of 0.428, 0.113 higher than SOTA at 0.315), and Artistic Style Erasure (with an average LPIPSda of 0.387, 0.088 higher than SOTA at 0.299), clearly outperforming alternative methods. Code is available at https://***/Maplebb/DuMo Copyright © 2025, The Author

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure 39

DuMo: Dual Encoder Modulation Network for Precise Concept Er...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

ISBN: (纸本)157735897X

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model’s ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module’s outputs across different layers and timesteps, automatically balancing the erasure effects and model’s generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure (detecting only 34 nude parts), Cartoon Concept Removal (with an average LPIPS_da of 0.428, 0.113 higher than SOTA at 0.315), and Artistic Style Erasure (with an average LPIPS_da of 0.387, 0.088 higher than SOTA at 0.299), clearly outperforming alternative methods. © 2025, Association for the Advancement of Artificial Intel

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Recognition with Incremental Classes 5

Fine-Grained Recognition with Incremental Classes

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Zhou, Yang-Zhun Pca Lab The Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Info. of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing China

ISBN: (纸本)9781450396899

This work focuses on dealing with fine-grained recognition problems when incremental classes emerge. The task is desirable to not only distinguish subordinate visual classes based on discriminative but subtle object parts, but also recognize new coming sub-classes without suffering from catastrophic forgetting. In this paper, we first propose to localize both object- and part-level image regions for capturing powerful fine-grained patterns. Then, these fine-grained regions are fed into a bilateral network consisting of a stable branch and a flexible branch for supporting observed and incremental sub-classes recognition respectively. Moreover, a cumulative adaptation strategy is further equipped to adjust the network training during the incremental sessions. Meanwhile, to better retain the modeling capability of observed classes, we also replay samples from previous classes by a hallucination approach. Experiments are conducted on three popular fine-grained recognition datasets and results of the proposed method can reveal its superiority over state-of-the-arts. © 2022 ACM.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

arXiv

引用

arXiv 2024年

作者： Gong, Chao Chen, Kai Wei, Zhipeng Chen, Jingjing Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing inappropriate concepts from diffusion models, they often exhibit incomplete erasure, consume a lot of computing resources, and inadvertently damage generation ability. In this work, we introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. Specifically, RECE efficiently leverages a closed-form solution to derive new target embeddings, which are capable of regenerating erased concepts within the unlearned model. To mitigate inappropriate content potentially represented by derived embeddings, RECE further aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts. Besides, to preserve the model’s generation ability, RECE introduces an additional regularization term during the derivation process, resulting in minimizing the impact on unrelated concepts during the erasure process. All the processes above are in closed-form, guaranteeing extremely efficient erasure in only 3 seconds. Benchmarking against previous approaches, our method achieves more efficient and thorough erasure with minor damage to original generation ability and demonstrates enhanced robustness against red-teaming tools. Code is available at https://***/CharlesGong12/RECE. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

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：