Yang Shen

Yang Shen

Auto-generated profile, based on publicly available information

Yang Shen

School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 July 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XWXiu-Shen Wei
Xiu-Shen Wei
YSYang Shen
Yang Shen
XSXuhao Sun
Xuhao Sun
PWPeng Wang
Peng Wang
YPYuxin Peng
Yuxin Peng
Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i.e., the same sub-category labels) highest based on the fine-grained details in the query. It is desirable to alleviate the challenges of both fine-grained nature of small inter-class variations with large intra-class variations and explosive growth of fine-grained data for such a practical task. In this paper, we propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes to not only make the retrieval process efficient, but also establish explicit correspondences between hash codes and visual attributes. Specifically, based on the captured visual representations by attention, we develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors from the appearance-specific visual representations without attribute annotations. Our models are also equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities. Then, driven by preserving original entities' similarity, the required hash codes can be generated from these attribute-specific vectors and thus become attribute-aware. Furthermore, to combat simplicity bias in deep hashing, we consider the model design from the perspective of the self-consistency principle and propose to further enhance models' self-consistency by equipping an additional image reconstruction path. Comprehensive quantitative experiments under diverse empirical settings on six fine-grained retrieval datasets and two generic retrieval datasets show the superiority of our models over competing methods. Moreover, qualitative results demonstrate that not only the obtained hash codes can strongly correspond to certain kinds of crucial properties of fine-grained objects, but also our self-consistency designs can effectively overcome simplicity bias in fine-grained hashing.

23 October 2022
Verified
Book Chapter
Closed access
PDF file
YSYang Shen
Yang Shen
XSXuhao Sun
Xuhao Sun
XWXiu-Shen Wei
Xiu-Shen Wei
QJQing-Yuan Jiang
Qing-Yuan Jiang
JYJian Yang
Jian Yang

27 January 2025 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
JMJunzhu Mao
Junzhu Mao
YSYang Shen
Yang Shen
Jinyang GuoJinyang Guo
Jinyang Guo
YYYazhou Yao
Yazhou Yao
XHXiansheng Hua
Xiansheng Hua
HSHengtao Shen
Hengtao Shen
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token compression method called Prune and Merge. Our approach integrates token pruning and merging operations within transformer models to achieve layer-wise token compression. By introducing trainable merge and reconstruct matrices and utilizing shortcut connections, we efficiently merge tokens while preserving important information and enabling the restoration of pruned tokens. Additionally, we introduce a novel gradient-weighted attention scoring mechanism that computes token importance scores during the training phase, eliminating the need for separate computations during inference and enhancing compression efficiency. We also leverage gradient information to capture the global impact of tokens and automatically identify optimal compression structures. Extensive experiments on the ImageNet-1k and ADE20K datasets validate the effectiveness of our approach, achieving significant speed-ups with minimal accuracy degradation compared to state-of-the-art methods. For instance, on DeiT-Small, we achieve a 1.64× speed-up with only a 0.2% drop in accuracy on ImageNet-1k. Moreover, by compressing segmenter models and comparing with existing methods, we demonstrate the superior performance of our approach in terms of efficiency and effectiveness. Code and models have been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/prune_and_merge.

14 January 2025 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
JJJian Jin
Jian Jin
YSYang Shen
Yang Shen
XZXinyang Zhao
Xinyang Zhao
ZFZhenyong Fu
Zhenyong Fu
JYJian Yang
Jian Yang

1 November 2024
Verified
Book Chapter
Closed access
PDF file
JJJian Jin
Jian Jin
YSYang Shen
Yang Shen
ZFZhenyong Fu
Zhenyong Fu
JYJian Yang
Jian Yang

30 July 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YSYang Shen
Yang Shen
XSXuhao Sun
Xuhao Sun
XWXiu-Shen Wei
Xiu-Shen Wei
AXAnqi Xu
Anqi Xu
LGLingyan Gao
Lingyan Gao