检索结果-内蒙古大学图书馆

Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint

学校读者我要写书评

暂无评论

Data-Free Knowledge Distillation via Feature Exchange and Ac...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shikang Yu Jiachen Chen Hu Han Shuqiang Jiang Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Despite the tremendous progress on data-free knowledge distillation (DFKD) based on synthetic data generation, there are still limitations in diverse and efficient data synthesis. It is naive to expect that a simple combination of generative network-based data synthesis and data augmentation will solve these issues. Therefore, this paper proposes a novel data-free knowledge distillation method (Spaceship-Net) based on channel-wise feature exchange (CFE) and multi-scale spatial activation region consistency (mSARC) constraint. Specifically, CFE allows our generative network to better sample from the feature space and efficiently synthesize diverse images for learning the student network. However, using CFE alone can severely amplify the unwanted noises in the synthesized images, which may result in failure to improve distillation learning and even have negative effects. Therefore, we propose mSARC to assure the student network can imitate not only the logit output but also the spatial activation region of the teacher network in order to alleviate the influence of unwanted noises in diverse synthetic images on distillation learning. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet, Imagenette, and ImageNet100 show that our method can work well with different backbone networks, and outperform the state-of-the-art DFKD methods. Code will be available at: https://***/skgyu/Spaceship-Net.

关键词：

Joint relay selection and power allocation protocol for two-way relaying system

学校读者我要写书评

暂无评论

International Journal of Wireless and Mobile computing 2019年第4期17卷 349-360页

作者： Zhi, Hui Zhu, Jun Hu, Yanjun Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei Anhui230601 China

The Joint Relay Selection and Power Allocation (JRSPA) for Amplify-and-Forward (AF) relaying (JRSPA-AF) combines Power Allocation (PA) and Relay Selection (RS) very well in Two- Way Relaying (TWR) system. In order to explore the system performance of JRSPA-AF protocol, the outage probability and Diversity-Multiplexing Trade-off (DMT) of JRSPA-AF protocol are analysed. One upper bound, two lower bounds and approximate expressions of outage probability along with the DMT are derived. Based on this, the idea of JRSPA is introduced into Decode-and- Forward (DF) relaying TWR system, and the JRSPA-DF protocol is proposed. Moreover, the exact expressions of outage probability and DMT for JRSPA-DF are derived. Simulations are developed to validate the analytical results, the results show that the approximation outage probability of JRSPA-AF can be used well to evaluate system outage probability over the entire transmission SNR region, and the analysis results of outage probability of JRSPA-DF are consistent with its simulation results. In addition, the simulation results indicate that JRSPA-DF can achieve lower outage probability than JRSPA-AF and other protocols. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Probability

Fine-Grained Spatial-Temporal Framework for Engagement Prediction 2nd

学校读者我要写书评

暂无评论

Fine-Grained Spatial-Temporal Framework for Engagement Pred...

2nd CSIG Conference on Emotional Intelligence, CEI 2024

作者： Wang, Shanshan Zheng, Yong Wang, keyang Zhang, Xingyi The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Beijing China Institutes of Physical Science and Information Technology Anhui University Anhui China Zhejiang Dahua Technology Co. Ltd. Zhejiang China School of Computer Science and Technology Anhui University Anhui China

ISBN: (纸本)9789819650835

The engagement prediction task aims to identify the current level of involvement of individuals based on the information presented in video clips. In recent years, engagement prediction has attracted considerable attention due to its significance in real-life scenarios. We observed that an individual’s engagement status is often primarily manifested in the facial region. This observation prompted us to solve the engagement prediction problem by exploiting facial information to learn features related to engagement. In this paper, we propose a novel model for learning fine-grained features, called Fine-Grained Spatial-Temporal Framework (FGST). Specifically, we consider both spatial and temporal aspects. In the spatial domain, we propose an entropy-weighted method based on Fourier transform. By applying Fourier transform to video frames and introducing the concept of information entropy, we can segregate engagement-related information from engagement-unrelated information and mining difficult samples. This aids in enabling the model to learn features conducive to engagement prediction. In the temporal domain, we calculate the differences between adjacent frames and sum these differences to obtain regions of pixel variation between video frames, thereby generates saliency weight and improving model performance. Experiments on several public datasets demonstrate the proposed model can outperform the state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Fourier transforms

Molecule optimization via multi-objective evolutionary in implicit chemical space

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xia, Xin Su, Yansen Zheng, Chunhou Zeng, Xiangxiang The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei230601 China College of Computer Science and Electronic Engineering Hunan University China

Machine learning methods have been used to accelerate the molecule optimization process. However, efficient search for optimized molecules satisfying several properties with scarce labeled data remains a challenge for machine learning molecule optimization. In this study, we propose MOMO, a multi-objective molecule optimization framework to address the challenge by combining learning of chemical knowledge with Pareto-based multi-objective evolutionary search. To learn chemistry, it employs a self-supervised codec to construct an implicit chemical space and acquire the continues representation of molecules. To explore the established chemical space, MOMO uses multiobjective evolution to comprehensively and efficiently search for similar molecules with multiple desirable properties. We demonstrate the high performance of MOMO on four multi-objective property and similarity optimization tasks, and illustrate the search capability of MOMO through case studies. Remarkably, our approach significantly outperforms previous approaches in optimizing three objectives simultaneously. The results show the optimization capability of MOMO, suggesting to improve the success rate of lead molecule optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Molecules

AGMR-Net: Attention Guided Multiscale Recovery framework for stroke segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Du, Xiuquan Ma, Kunpeng Song, Yuhui Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Anhui Hefei230601 China School of Computer Science and Technology Anhui University Anhui Hefei230601 China

Automatic and accurate lesion segmentation is critical for clinically estimating the lesion statuses of stroke diseases and developing appropriate diagnostic systems. Although existing methods have achieved remarkable results, further adoption of the models is hindered by: (1) inter-class indistinction, the normal brain tissue resembles the lesion in appearance. (2) intra-class inconsistency, large variability exists between different areas of the lesion. To solve these challenges in stroke segmentation, we propose a novel method, namely Attention Guided Multiscale Recovery framework (AGMR-Net) in this paper. Firstly, a coarse-grained patch attention module in the encoding is adopted to get a patch-based coarse-grained attention map in a multi-stage explicitly supervised way, enabling target spatial context saliency representation with a patch-based weighting technique that eliminates the effect of intra-class inconsistency. Secondly, to obtain a more detailed boundary partitioning to solve the challenge of the inter-class indistinction, a newly designed cross-dimensional feature fusion module is used to capture global contextual information to further guide the selective aggregation of 2D and 3D features, which can compensate for the lack of boundary learning capability of 2D convolution. Lastly, in the decoding stage, an innovative designed multi-scale deconvolution upsampling instead of linear interpolation enhances the recovery of target space and boundary information. The AGMR-Net is evaluated on the open dataset Anatomical Tracings of Lesions-After-Stroke (ATLAS), achieving the highest dice similarity coefficient (DSC) score of 0.594, Hausdorff distance of 27.005 mm, and average symmetry surface distance of 7.137 mm, which demonstrate that our proposed method outperforms other state-of-the-art methods and has great potential in the diagnosis of stroke. Copyright © 2022, The Authors. All rights reserved.

关键词： Recovery

Cross-Point Adversarial Attack Based on Feature Neighborhood Disruption Against Segment Anything Model

学校读者我要写书评

暂无评论

Cross-Point Adversarial Attack Based on Feature Neighborhood...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yan Jiang Guisheng Yin Ye Yuan Jingjing Chen Zhipeng Wei College of Computer Science and Technology Harbin Engineering University Harbin China Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Segment anything model (SAM) has received significant attention owing to its outstanding segmentation performance. However, it may still face security threats from adversarial examples. Since SAM interactively realizes the prediction of target areas according to user-specified prompts (e.g., points), adversarial examples generated by existing end-to-end attack methods usually exhibit limited attack performance when faced with different point prompts. To this end, we propose a cross-point adversarial attack method based on feature neighborhood disruption against SAM, called CP-FND attack. CP-FND aims to generate adversarial examples capable of effectively deceiving SAM under different user-specified point prompts. Specifically, CP-FND forces the intermediate feature of adversarial examples to be similar to the designed disruption features without relying on any specified point prompt. Subsequently, the continuity and relevance of contextual features are disrupted, thereby fooling SAM and suppressing its predicted masks. Extensive experiments demonstrate that CP-FND achieves superior cross-point adversarial attack performance against SAM compared to state-of-the-art methods.

关键词： Image segmentation Correlation Security Faces

Circularly polarized annular slit antenna based on metasurface

学校读者我要写书评

暂无评论

Circularly polarized annular slit antenna based on metasurfa...

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Jingyang Wang Bo Wu Liang Zhang Xianliang Wu Yue Ma Ruikang Wang Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Province Key Laboratory of simulation and design for Electronic information system Hefei Normal University He-fei China

ISBN: (纸本)9781665482271

In this paper, a circularly polarized annular slit antenna with a center frequency of 2.15 GHz realized through a metasurface was designed. The metasurface is made up of 5×5 periodic units. The impedance bandwidth of annular slit antenna is 2.08-2.5 GHz and after loading the metasurface the frequency range in which the axis ratio of the antenna is less than 3dB is 2.12-2.18 GHz and the gain reaches 3.5 dBi. The linear polarization antenna can be directly converted into circular polarization antenna by loading the metasurface. Reserch show that antenna loaded with metasurface can be widely used in electronic communication field.

关键词： Microwave antennas Polarization Simulation Loading Millimeter wave technology Bandwidth Metasurfaces

PoseAnimate: Zero-shot high fidelity pose controllable character animation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Bingwen Wang, Fanyi Lu, Tianyi Liu, Peng Su, Jingwen Liu, Jinxiu Zhang, Yanhao Wu, Zuxuan Qi, Guo-Jun 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 OPPO AI Center South China University of Technology China Westlake University China

Image-to-video (I2V) generation aims to create a video sequence from a single image, which requires high temporal coherence and visual fidelity. However, existing approaches suffer from inconsistency of character appearances and poor preservation of fine details. Moreover, they require a large amount of video data for training, which can be computationally demanding. To address these limitations, we propose PoseAnimate, a novel zero-shot I2V framework for character animation. PoseAnimate contains three key components: 1) a Pose-Aware Control Module (PACM) that incorporates diverse pose signals into text embeddings, to preserve character-independent content and maintain precise alignment of actions. 2) a Dual Consistency Attention Module (DCAM) that enhances temporal consistency and retains character identity and intricate background details. 3) a Mask-Guided Decoupling Module (MGDM) that refines distinct feature perception abilities, improving animation fidelity by decoupling the character and background. We also propose a Pose Alignment Transition Algorithm (PATA) to ensure smooth action transition. Extensive experiment results demonstrate that our approach outperforms the state-of-the-art training-based methods in terms of character consistency and detail fidelity. Moreover, it maintains a high level of temporal coherence throughout the generated animations. Copyright © 2024, The Authors. All rights reserved.

关键词： Animation

Zoom Out and Observe: News Environment Perception for Fake News Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sheng, Qiang Cao, Juan Zhang, Xueyao Li, Rundong Wang, Danding Zhu, Yongchun Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China

Fake news detection is crucial for preventing the dissemination of misinformation on social media. To differentiate fake news from real ones, existing methods observe the language patterns of the news post and "zoom in" to verify its content with knowledge sources or check its readers' replies. However, these methods neglect the information in the external news environment where a fake news post is created and disseminated. The news environment represents recent mainstream media opinion and public attention, which is an important inspiration of fake news fabrication because fake news is often designed to ride the wave of popular events and catch public attention with unexpected novel content for greater exposure and spread. To capture the environmental signals of news posts, we "zoom out" to observe the news environment and propose the News Environment Perception Framework (NEP). For each post, we construct its macro and micro news environment from recent mainstream news. Then we design a popularity-oriented and a novelty-oriented module to perceive useful signals and further assist final prediction. Experiments on our newly built datasets show that the NEP can efficiently improve the performance of basic fake news detectors. © 2022, CC BY-NC-SA.

关键词： Fake detection