检索结果-内蒙古大学图书馆

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is availab.e at this url. © 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

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Learning Interaction Detection 24

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Lear...

引用

33rd ACM Web Conference, WWW 2024

作者： Ma, Haiping Yang, Yong Qin, Chuan Yu, Xiaoshan Yang, Shangshang Zhang, Xingyi Zhu, Hengshu Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin PBC School of Finance Tsinghua University Beijing China School of Artificial Intelligence Anhui University Anhui Hefei China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin Beijing China

ISBN: (纸本)9798400701719

Knowledge tracing (KT) is a crucial task in online learning, aimed at tracing and predicting each student's knowledge states throughout their learning process. Over the past decade, it has garnered widespread attention due to it provides the potential for more tailored and adaptive online learning experiences. Although most current KT methodologies emphasize optimizing network structures to enhance predictive accuracy for future student performance, they often neglect anomalous interactions in students' learning processes, which may arise from low data quality (i.e., inferior question quality) and abnormal student behaviors (i.e., guessing and mistakes). To this end, in this paper, we propose a novel framework, termed HD-KT, designed to enhance the robustness of existing KT methodologies with Hybrid learning interactions Denoising approach. Specifically, we introduce two detectors for anomalous learning interactions, namely knowledge state-guided anomaly detector and student profile-guided anomaly detector. In the first detection module, we design a sequential autoencoder to identify anomalous learning interactions by detecting atypical student knowledge states. In the second module, we incorporate an attention mechanism by modeling a student's long-term profile to capture irregular interactions. Extensive experiments on four real-world benchmark datasets have decisively shown our HD-KT markedly boosts the robustness of numerous prevailing KT models, consequently increasing the accuracy of future student performance predictions. Additionally, our case studies highlight the versatility of HD-KT in addressing diverse downstream tasks, such as exercise quality analysis and learning behavior-based student clustering. © 2024 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Yolov9-Spe: A Novel Deep Learning Method For Classroom Student Behavior Detection

SSRN

引用

SSRN 2024年

作者： Liu, Junxiu Wu, Fengxiang Lu, Baoshan Qin, Sheng Fu, Qiang Luo, Yuling Guangxi Key Lab of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin541004 China Guangxi Wireless Broadband Communication and Signal Processing Key Laboratory Guilin University of Electronic Technology Guilin541004 China

Deep learning can significantly enhance student behavior detection in classrooms. However, challenges such as small target recognition, blurry data, occlusion, and multi-scale detection persist. To address these, we propose YOLOv9-SPE, an improved model based on YOLOv9, incorporating Space-to-Depth Convolution (SPD-Conv), Partial Convolution (PConv), and an Efficient Multi-Scale Attention (EMA) Module. SPD-Conv enhances small target recognition and improves feature extraction for blurry data, while PConv, adapted from FasterNet, addresses occlusion issues. EMA is integrated to handle multi-scale targets in classroom student behavior detection. Experimental results on a student behavior dataset show that YOLOv9-SPE achieves a 2.1% improvement in mean average precision over the original YOLOv9. These enhancements provide a more accurate and efficient method for monitoring and analyzing student behavior in educational settings. © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Hierarchical lab.l Distribution Variations in Test Agnostic Long-tail Recognition 41

Harnessing Hierarchical Label Distribution Variations in Tes...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Zhiyong Xu, Qianqian Wang, Zitai Li, Sicong Han, Boyu Bao, Shilong Cao, Xiaochun Huang, Qingming School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test lab.l distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test lab.l distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the lab.l distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is availab.e at https://***/scongl/DirMixE. Copyright 2024 by the author(s)

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning

arXiv

引用

arXiv 2023年

作者： Jiao, Yang Jie, Zequn Chen, Shaoxiang Cheng, Lechao 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 China Zhejiang Lab. China

Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images. However, existing approaches exhaustively predict depths for every pixel without prioritizing objects, which are precisely the entities requiring detection in the 3D space. To this end, we propose IA-BEV, which integrates image-plane instance awareness into the depth estimation process within a BEV-based detector. First, a category-specific structural priors mining approach is proposed for enhancing the efficacy of monocular depth generation. Besides, a self-boosting learning strategy is further proposed to encourage the model to place more emphasis on challenging objects in computation-expensive temporal stereo matching. Together they provide advanced depth estimation results for high-quality BEV features construction, benefiting the ultimate 3D detection. The proposed method achieves state-of-the-art performances on the challenging nuScenes benchmark, and extensive experimental results demonstrate the effectiveness of our designs. © 2023, CC BY-NC-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM

arXiv

引用

arXiv 2024年

作者： Lyu, Xingyu Xu, Qianqian Yang, Zhiyong Lyu, Shaojie Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech University of Chinese Academy of Sciences China Tencent Corporate China BDKM University of Chinese Academy of Sciences China

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSAM) is proposed to leverage the generalization benefits of Sharpness-Aware Minimization (SAM) for long-tailed distributions. The main strategy is to merely enhance the smoothness of the loss function for tail classes. However, we argue that improving generalization in long-tail scenarios requires a careful balance between head and tail classes. We show that neither SAM nor ImbSAM alone can fully achieve this balance. For SAM, we prove that although it enhances the model’s generalization ability by escaping saddle point in the overall loss landscape, it does not effectively address this for tail-class losses. Conversely, while ImbSAM is more effective at avoiding saddle points in tail classes, the head classes are trained insufficiently, resulting in significant performance drops. Based on these insights, we propose Stage-wise Saddle Escaping SAM (SSE-SAM), which uses complementary strengths of ImbSAM and SAM in a phased approach. Initially, SSE-SAM follows the majority sample to avoid saddle points of the head-class loss. During the later phase, it focuses on tail-classes to help them escape saddle points. Our experiments confirm that SSE-SAM has better ability in escaping saddles both on head and tail classes, and shows performance improvements. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm’s generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is availab.e at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

High Common-Mode Rejection Differential Filter Based on Coupled Lines

High Common-Mode Rejection Differential Filter Based on Coup...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Zhen Liu Haoran Zhu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

In this paper, a differential bandpass filter (BPF) based on enhanced coupling line structure has been suggested in this study. Two out-of-band transmission zeros are added to the differential mode by loading the coupling line at the output terminal, which raises the rectangular coefficient of the filter. Two common mode transmission zeros in the passband are additionally provided by the open/short stub that is already loaded at the output port. To accommodate the demands of various filter performances, the location of the transmission zeros can be modified by altering the values of the coupling lines' and stubs' impedances. Finally, the passband common mode suppression might be as high as 40 dB.

关键词： Band-pass filters Couplings Radio frequency Conferences Loading Microwave circuits Filtering theory

来源：评论

学校读者我要写书评

暂无评论

ϵ-π: A Nonparametric Model for Neural Power Spectra Decomposition

引用

IEEE Journal of Biomedical and Health Informatics 2024年第5期28卷 2624-2635页

作者： Hu, Shiang Zhang, Zhihao Zhang, Xiaochu Wu, Xiaopei Valdes-Sosa, Pedro A. Anhui University Anhui Provincial Key Lab of Multimodal Cognitive Computation Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230601 China University of Science and Technology of China School of Humanities and Social Science Department of Psychology Hefei230026 China University of Electronic Science and Technology of China MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China

The power spectra estimated from the brain recordings are the mixed representation of aperiodic transient activity and periodic oscillations, i.e., aperiodic component (AC) and periodic component (PC). Quantitative neurophysiology requires precise decomposition preceding parameterizing each component. However, the shape, statistical distribution, scale, and mixing mechanism of AC and PCs are unclear, challenging the effectiveness of current popular parametric models such as FOOOF, IRASA, BOSC, etc. Here, was proposed to decompose the neural spectra by embedding the nonparametric spectra estimation with penalized Whittle likelihood and the shape language modeling into the expectation maximization framework. was validated on the synthesized spectra with loss statistics and on the sleep EEG and the large sample iEEG with evaluation metrics and neurophysiological evidence. Compared to FOOOF, both the simulation presenting shape irregularities and the batch simulation with multiple isolated peaks indicated that improved the fit of AC and PCs with less loss and higher F1-score in recognizing the centering frequencies and the number of peaks;the sleep EEG revealed that produced more distinguishable AC exponents and improved the sleep state classification accuracy;the iEEG showed that approached the clinical findings in peak discovery. Overall, offered good performance in the spectra decomposition, which allows flexible parameterization using descriptive statistics or kernel functions. is a seminal tool for brain signal decoding in fields such as cognitive neuroscience, brain-computer interface, neurofeedback, and brain diseases. © 2013 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Metasurface-Based Wideband High Isolation Circularly Polarized Antenna For 5G MIMO Millimeter-Wave Systems

A Metasurface-Based Wideband High Isolation Circularly Polar...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Hui Zhu Haoran Zhu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

A wideband high isolation circularly polarized antenna for 5G MIMO millimeter-wave systems is presented in this paper. The presented antenna exhibits wideband characteristics due to the resonance of surface waves along the metasurface. The circularly polarized preliminary bandwidth is achieved by truncated corner patches when the truncation can be adjusted to implement the phase and amplitude values of the two quadrature modes. The port isolation is improved by the resonance of double-layer microstrip lines in the frequency. The size of the antenna is 17.8×17.8×1.02 mm 3 , the impedance bandwidth is 30.4% (23.29-31.66 GHz) and the 3-dB axial ratio bandwidth is 20.5% (24.47-30.12 GHz). In addition, the port isolation of the presented antenna is higher than 25 dB, and the peak gain is 8.4 dB. Therefore, the given antenna has the advantages of wideband, circularly polarized and high isolation.

关键词： Microwave antennas Surface impedance 5G mobile communication Surface waves Metasurfaces Broadband antennas Impedance

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：