检索结果-内蒙古大学图书馆

FOCUS: Towards Universal Foreground Segmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： You, Zuyao Kong, Lingyu Meng, Lingchen Wu, Zuxuan Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unification. Moreover, they primarily focus on recognizing foreground objects without effectively distinguishing them from the background. In this paper, we emphasize the importance of the background and its relationship with the foreground. We introduce FOCUS, the Foreground ObjeCts Universal Segmentation framework that can handle multiple foreground tasks. We develop a multi-scale semantic network using the edge information of objects to enhance image features. To achieve boundary-aware segmentation, we propose a novel distillation method, integrating the contrastive learning strategy to refine the prediction mask in multi-modal feature space. We conduct extensive experiments on a total of 13 datasets across 5 tasks, and the results demonstrate that FOCUS consistently outperforms the state-of-the-art task-specific models on most metrics. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

学校读者我要写书评

暂无评论

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

Boosting polyp screening with improved point-teacher weakly semi-supervised

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2025年 191卷 109998-109998页

作者： Du, Xiuquan Zhang, Xuejun Chen, Jiajia Li, Lei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China Department of Neurology Shuyang Affiliated Hospital of Nanjing University of Traditional Chinese Medicine Suqian China School of Computer Science and Technology Anhui University Hefei China

Polyps, like a silent time bomb in the gut, are always lurking and can explode into deadly colorectal cancer at any time. Many methods are attempted to maximize the early detection of colon polyps by screening, however, there are still face some challenges: (i) the scarcity of per-pixel annotation data and clinical features such as the blurred boundary and low contrast of polyps result in poor performance. (ii) existing weakly semi-supervised methods directly using pseudo-labels to supervise student tend to ignore the value brought by intermediate features in the teacher. To adapt the point-prompt teacher model to the challenging scenarios of complex medical images and limited annotation data, we creatively leverage the diverse inductive biases of CNN and Transformer to extract robust and complementary representation of polyp features (boundary and context). At the same time, a novel designed teacher–student intermediate feature distillation method is introduced rather than just using pseudo-labels to guide student learning. Comprehensive experiments demonstrate that our proposed method effectively handles scenarios with limited annotations and exhibits good segmentation performance. All code is available at https://***/dxqllp/WSS-Polyp. © 2025 Elsevier Ltd

关键词： Weakly semi-supervised Medical image segmentation Boundary extraction Feature distillation

BAST: Blockchain-Assisted Secure and Traceable Data Sharing Scheme for Vehicular Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Information Forensics and Security 2025年 20卷 4664-4678页

作者： Liu, Xinzhong Cui, Jie Zhang, Jing Yin, Rongwang Zhong, Hong Wei, Lu Bolodurina, Irina He, Debiao School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei230039 China Anhui University Anhui Engineering Laboratory of IoT Security Technologies Hefei230039 China Hefei University Department of Basic Experiment and Training Hefei230601 China Orenburg State University Faculty of Mathematics and Information Technologies Orenburg460018 Russia Wuhan University School of Cyber Science and Engineering 430072 China MatrixElements Technologies Shanghai Key Laboratory of Privacy Preserving Computation Shanghai201204 China

In vehicular networks, caching service content on edge servers (ESs) is a widely accepted strategy for promptly responding to vehicle requests, reducing communication overhead, and improving service experience. However, implementing such an architecture requires addressing the challenges associated with ES response data reliability and communication security. In this study, to tackle the ES response data reliability issue, a blockchain-assisted threshold signature scheme for cache-based vehicular networks is proposed. The scheme utilizes a threshold mechanism to sign the data broadcast by the ES, incorporates blockchain to trace malicious signers, and avoids the shortcomings and limitations associated with idealized assumptions for the ES in existing data-sharing schemes. Moreover, considering the communication security and high-speed mobility of vehicles, using the non-interactive signatures of knowledge based on the Σ-protocol, a secure and efficient message authentication scheme for vehicles and ESs is provided. Through rigorous security proofs and comprehensive analyses, our scheme satisfies the communication security requirements of vehicular networks. By leveraging the JPBC library for performance analysis, the proposed scheme demonstrates advantages as concerns both computation and communication overheads compared to related schemes. Moreover, we implemented the proposed scheme on an Ethereum test network (i.e., Goerli) to validate its feasibility. © 2005-2012 IEEE.

关键词： Sensitive data

On four conjectures of Heng-Ding and p-ary linear codes from monomials

学校读者我要写书评

暂无评论

IEEE Transactions on Information Theory 2025年

作者： Qian, Liqin Shi, Minjia Anhui University School of Mathematical Sciences Anhui Hefei230601 China Anhui University Key Laboratory of Intelligent Computing Signal Processing Ministry of Education School of Mathematical Sciences Anhui Hefei230601 China Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China

Subfield codes of linear codes over finite fields have recently attracted great attention due to their wide applications in secret sharing schemes, authentication codes and association schemes. There are two major ingredients in this paper. The first ingredient is to solve four conjectures recently proposed by Heng and Ding (IEEE Trans. Inf. Theory, 68(6): 3643-3656, 2022). Besides, we also determine the weight distributions of subfield codes derived from x3 and oval polynomials over F2m. The second ingredient is to obtain two classes of p-ary linear codes from monomials over Fpm. We study the parameters of the constructed codes and determine their weight distributions. Notably, we show that the codes C(p) (xpi, pm) are optimal and almost optimal in many cases with respect to the online Database of Grassl. Finally, we observe that the derived linear codes also have the minimality property for most cases. © 1963-2012 IEEE.

关键词： Linear code monomial oval polynomial subfield code weight distribution

Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Haoran Wang, Ping Zhou, Zihan Zhang, Xu 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 APUS AI Lab China

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with many approaches building upon the framework that maintains a pool of learnable prompts. Although effective, these methods introduce substantial computational overhead, primarily due to prompt pool querying and increased input sequence lengths from prompt concatenation. In this work, we present a novel prompt-based approach that addresses this limitation. Our method trains a single set of shared prompts across all tasks and, rather than concatenating prompts to the input, directly modifies the CLS token’s attention computation by adding the prompts to it. This simple and lightweight design not only significantly reduces computational complexity—both in terms of inference costs and the number of trainable parameters—but also eliminates the need to optimize prompt lengths for different downstream tasks, offering a more efficient yet powerful solution for rehearsal-free class-incremental learning. Extensive experiments across a diverse range of CIL benchmarks demonstrate the effectiveness of our approach, highlighting its potential to establish a new prompt-based CIL paradigm. Furthermore, experiments on general recognition benchmarks beyond the CIL setting also show strong performance, positioning our method as a promising candidate for a general parameter-efficient fine-tuning approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

Graph-Enhanced Dual-Stream Feature Fusion with Pre-Trained Model for Acoustic Traffic Monitoring

学校读者我要写书评

暂无评论

Graph-Enhanced Dual-Stream Feature Fusion with Pre-Trained M...

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Shitong Fan Feiyang Xiao Wenbo Wang Shuhan Qi Qiaoxi Zhu Wenwu Wang Jian Guan Group of Intelligent Signal Processing Harbin Engineering University Harbin China Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Acoustics Lab University of Technology Sydney Ultimo Australia Centre for Vision Speech and Signal Processing University of Surrey Guildford UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Microphone array techniques are widely used in sound source localization and smart city acoustic-based traffic monitoring, but these applications face significant challenges due to the scarcity of labeled real-world traffic audio data and the complexity and diversity of application scenarios. The DCASE Challenge’s Task 10 focuses on using multi-channel audio signals to count vehicles (cars or commercial vehicles) and identify their directions (left-to-right or vice versa). In this paper, we propose a graph-enhanced dual-stream feature fusion network (GEDF-Net) for acoustic traffic monitoring, which simultaneously considers vehicle type and direction to improve detection. We propose a graph-enhanced dual-stream feature fusion strategy which consists of a vehicle type feature extraction (VTFE) branch, a vehicle direction feature extraction (VDFE) branch, and a frame-level feature fusion module to combine the type and direction feature for enhanced performance. A pre-trained model (PANNs) is used in the VTFE branch to mitigate data scarcity and enhance the type features, followed by a graph attention mechanism to exploit temporal relationships and highlight important audio events within these features. The frame-level fusion of direction and type features enables fine-grained feature representation, resulting in better detection performance. Experiments demonstrate the effectiveness of our proposed method. GEDF-Net is our submission that achieved 1st place in the DCASE 2024 Challenge Task 10.

关键词： Location awareness Smart cities signal processing Feature extraction Acoustics Data models Microphone arrays Speech processing Monitoring Faces

Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhou, Hanyu Wang, Haonan Liu, Haoyue Duan, Yuxing Chang, Yi Yan, Luxin National Key Lab of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China School of Computing National University of Singapore Singapore

High-dynamic scene optical flow is a challenging task, which suffers spatial blur and temporal discontinuous motion due to large displacement in frame imaging, thus deteriorating the spatiotemporal feature of optical flow. Typically, existing methods mainly introduce event camera to directly fuse the spatiotemporal features between the two modalities. However, this direct fusion is ineffective, since there exists a large gap due to the heterogeneous data representation between frame and event modalities. To address this issue, we explore a common-latent space as an intermediate bridge to mitigate the modality gap. In this work, we propose a novel common spatiotemporal fusion between frame and event modalities for high-dynamic scene optical flow, including visual boundary localization and motion correlation fusion. Specifically, in visual boundary localization, we figure out that frame and event share the similar spatiotemporal gradients, whose similarity distribution is consistent with the extracted boundary distribution. This motivates us to design the common spatiotemporal gradient to constrain the reference boundary localization. In motion correlation fusion, we discover that the frame-based motion possesses spatially dense but temporally discontinuous correlation, while the event-based motion has spatially sparse but temporally continuous correlation. This inspires us to use the reference boundary to guide the complementary motion knowledge fusion between the two modalities. Moreover, common spatiotemporal fusion can not only relieve the cross-modal feature discrepancy, but also make the fusion process interpretable for dense and continuous optical flow. Extensive experiments have been performed to verify the superiority of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical flows

A Miniaturized Bandwidth Reconfigurable Bandpass Chip Filter with Semi-lumped Topology and GaAs pHEMT Technology

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2021年第1期30卷 192-198页

作者： LI Linqing ZHU Haoran NING Xingyu LI Zunwen WU Xianliang Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui University

A miniaturized reconfigurable bandpass chip filter with semi-lumped topology and Gallium Arsenide pseudomorphic High electron mobility transistor（GaAs pHEMT） technology is proposed. Semi-lumped topology is employed to instead the traditional lumped inductor with microstrip transmission line, which can reduced the size of the tunable filter significantly. Three-order series and shunt resonated bandpass filter is implemented with shorted stubs and metal-insulator-metal capacitors. Two transmission zeros are introduced with the series resonator and the shunted GaAs FET. By tuning the gate bias circuit of the FET, the capacitance of the series resonator is changed and the bandwidth of the filter is adjusted correspondingly. An equivalent circuit model is developed to interpret the mechanism of the proposed filter circuit. A reconfigurable on chip filter sample operated at 10 GHz is fabricated to validate the design. Two fractional bandwidth of 14.3% and 23.5% are tuned with bias voltage of the FET, while insertion loss of 2.4 d B and 2.2 d B are observed with the filter, respectively. The area of the chip filter is 0.86 × 0.96 mm2and is equivalent to an electrical length of 0.08 × 0.09λg2at center frequency. Measurement results agree well with the simulation ones.

关键词： gallium arsenide tunable filter transmission zeros equivalent circuit model resonator filters shunted FET III-V semiconductors miniaturized bandwidth reconfigurable bandpass chip filter MIM devices microstrip transmission line chip filter sample shunt resonated bandpass filter metal-insulator-metal capacitors semilumped topology loss 2.4 dB Gallium Arsenide pseudomorphic High electron mobility transistor technology insertion loss filter circuit integrated circuit design GaAs integrated circuit manufacture frequency 10.0 GHz pHEMT technology microwave filters loss 2.2 dB HEMT integrated circuits series resonator miniaturized reconfigurable bandpass chip filter band-pass filters