中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共52条，第1-10条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 4616-4629
作者:  Ma, Chengcheng;  Liu, Yang;  Deng, Jiankang;  Xie, Lingxi;  Dong, Weiming;  Xu, Changsheng
Adobe PDF(1644Kb)  |  收藏  |  浏览/下载：96/12  |  提交时间：2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
A Closer Look at Self-Supervised Lightweight Vision Transformers 会议论文
, Honolulu, Hawaii, USA, 2023-7
作者:  Wang, Shaoru;  Gao, Jin;  Li, Zeming;  Zhang, Xiaoqin;  Weiming, Hu
Adobe PDF(3478Kb)  |  收藏  |  浏览/下载：188/63  |  提交时间：2023/09/20
Vision Transformer  Self-supervised Learning  Lightweight Networks  Knowledge Distillation  
BViT: Broad Attention-Based Vision Transformer 期刊论文
IEEE Transactions on Neural Networks and Learning Systems, 2023, 页码: 1 - 12
作者:  Nannan Li;  Yaran Chen;  Weifan Li;  Zixiang Ding;  Dongbin Zhao;  Shuai Nie
Adobe PDF(2171Kb)  |  收藏  |  浏览/下载：177/48  |  提交时间：2023/06/27
Broad attention  broad connection  image classification  parameter-free attention  vision transformer  
Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 2, 页码: 1963-1980
作者:  Luo, Chuanchen;  Song, Chunfeng;  Zhang, Zhaoxiang
Adobe PDF(2539Kb)  |  收藏  |  浏览/下载：206/61  |  提交时间：2023/03/20
Person re-identification  domain adaptation  cross-domain mixup  camera-aware learning  self-paced learning  
Towards Automatic Model Compression via A Unified Two-Stage Framework 期刊论文
Pattern Recognition (PR), 2023, 卷号: 140, 页码: 109527
作者:  Weihan Chen;  Peisong Wang;  Jian Cheng
Adobe PDF(765Kb)  |  收藏  |  浏览/下载：92/26  |  提交时间：2023/06/20
Deep Neural Networks  Model Compression  Quantization  Pruning  
Towards Prior Gap and Representation Gap for Long-tailed Recognition, Pattern Recognition 期刊论文
Pattern Recognition, 2023, 卷号: 133, 期号: 109012, 页码: 109012
作者:  Zhang Ming-Liang;  Zhang Xu-Yao;  Wang Chang;  Liu Cheng-Lin
Adobe PDF(2258Kb)  |  收藏  |  浏览/下载：46/10  |  提交时间：2024/04/03
Long-tailed learning  Prior gap  Representation gap  Image recognition  
Learning adversarial point-wise domain alignment for stereo matching 期刊论文
NEUROCOMPUTING, 2022, 卷号: 491, 页码: 564-574
作者:  Zhang, Chenghao;  Meng, Gaofeng;  Xu, Richard Yi Da;  Xiang, Shiming;  Pan, Chunhong
Adobe PDF(3885Kb)  |  收藏  |  浏览/下载：256/49  |  提交时间：2022/09/19
Stereo Matching  Domain adaptation  Point-wise linear transformation  Adversarial learning  
Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots 会议论文
, New Orleans, LA, USA, 18-24 June 2022
作者:  Wang, Zejin;  Liu, Jiazheng;  Li, Guoqing;  Han, Hua
Adobe PDF(7811Kb)  |  收藏  |  浏览/下载：171/90  |  提交时间：2023/05/31
From Individual to Whole: Reducing Intra-class Variance by Feature Aggregation 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 卷号: 130, 期号: 3, 页码: 800-819
作者:  Zhang, Zhaoxiang;  Luo, Chuanchen;  Wu, Haiping;  Chen, Yuntao;  Wang, Naiyan;  Song, Chunfeng
Adobe PDF(1762Kb)  |  收藏  |  浏览/下载：256/33  |  提交时间：2022/06/06
Feature aggregation  Deep learning  Intra-class variance  Person re-identification  Video object detection  
A Semi-supervised End-to-end Framework for Transportation Mode Detection by Using GPS-enabled Sensing Devices 期刊论文
IEEE Internet of Things Journal, 2022, 卷号: 9, 期号: 10, 页码: 7842-7852
作者:  Zhishuai Li;  Gang Xiong;  Zebing Wei;  YIsheng Lv;  Noreen Anwar;  Fei-Yue Wang
Adobe PDF(2754Kb)  |  收藏  |  浏览/下载：209/62  |  提交时间：2022/04/08
Transportation mode detection , Semi-supervised learning, Human mobility , GPS trajectory.