Shaohui Lin (林绍辉)

About me

Shaohui Lin is currently a Researcher and a Zijiang Young Scholar in the School of Computer Science and Technology, East China Normal University (ECNU). I received Ph.D. from  Xiamen University under the supervision of Prof. Rongrong Ji. After that, I joint the Department of Computer Science at National University of Singapore as a postdoc researcher, working with Angela Yao.  My research specialty is computer vision, machine learning and deep learning, especially compression and speeding-up of large capacity models.

Chinese version of my homepage: https://faculty.ecnu.edu.cn/_s16/lsh2/main.psp

News

• [2024.4.17] 1 paper accepted by IJCAI 2024. Congratulations to Zikai.

• [2024.2.27] 3 papers accepted by CVPR 2024. Congratulations to Wenxuan & Gangxu.

• [2023.12.9] 4 papers accepted by AAAI 2024. Congratulations to Yunchen & Gangxu.

• [2023.7.26] 1 paper accepted by ACM MM 2023. Congratulations to Jiale.

• [2023.6.20] I accepted the invitation to serve as CVPR 2024 Area Chair.

• [2023.3.20] 1 paper accepted by TMI. Congratulation to Nan Wang.

• [2023.02.28] 1 paper accepted by CVPR 2023. Congratulations to Runqi.

• [2022.11.19] 2 papers accepted by AAAI 2023. Congratulations to Linrui and Yiqing. 

• [2022.07.05] 1 paper accepted by ECCV 2022 (oral).

• [2022.05.15] 1 paper accepted by ICML 2022. Congratulation to Haiyan.

• [2022.03.02] 1 paper accepted by CVPR 2022. Congratulations to Mengtian.

• [2021.04.29] 3 papers accepted by IJCAI 2021. Congratulation to Chengwei, Yanbo, Xuncheng.

• [2021.03.01] 3 papers accepted by CVPR 2021. Congratulations to Yuchao, Xudong and Haiyan.

• [2020.07.03] 2 papers accepted by ECCV 2020. Congratulations to Yuchao, Huixia and Chenqian.

• [2019.03.12] 1 paper accepted by TNNLS.

• [2019.03.02] 2 papers accepted by CVPR 2019.

• [2018.9.15] 1 paper accepted by T-PAMI.

• [2018.4.20] 1 paper accepted by IJCAI 2018.

Publications

Arxiv:

1. Yuchao Li#, Shaohui Lin#, Baochang Zhang, et al. Exploiting kernel sparsity and entropy for interpretable CNN compression. arXiv preprint arXiv:1812.04368, 2018. (# Equal contribution) [Accepted by CVPR 2019][code]

Conference:

1. Runqi Wang, Xiaoyue Duan, Guoliang Kang, Jianzhuang Liu, Shaohui Lin, Songcen Xu, Jinhu Lu, Baochang Zhang. AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning. In CVPR, 2023.

2. Yiqing Cai, Lianggangxu Chen, Haoyue Guan, Shaohui Lin*, Changhong Lu, Changbo Wang, Gaoqi He*. Explicit Invariant Feature Induced Cross-Domain Crowd Counting. In AAAI 2023.

3. Linrui Gong, Shaohui Lin*, Baochang Zhang, Yunhang Shen, Ke Li, Ruizhi Qiao, Bo Ren, Muqing Li, Zhou Yu, Lizhuang Ma. Adaptive Hierarchy-Branch Fusion for Online Knowledge Distillation. In AAAI 2023.

4. Nan Wang, Chengwei Chen, Shaohui Lin*, Lizhuang Ma*. Latent Feature Regularization based Adversarial Network for Brain Tumor Anomaly Detection. In ICME, 2023. (Oral)

5. Yuting Gao, Jia-Xin Zhuang, Shaohui Lin, Hao Cheng, Xing Sun, Ke Li, Chunhua Shen. DisCo: Remedying Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning. In ECCV 2022. (Oral)

6. Haiyan Wu, Yuting Gao, Yinqi Zhang, Shaohui Lin*, Yuan Xie*, Xing Sun, Ke Li. Self-supervised Models are Good Teaching Assistants for Vision Transformers. In ICML, 2022.

7. Mengtian Li, Yuan Xie, Yunhang Shen, Bo Ke, Ruizhi Qiao, Bo Ren, Shaohui Lin*, Lizhuang Ma*. HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization. In CVPR, 2022.

8. Chenwei, Chen, Yuan Xie, Shaohui Lin, et al. Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection. In AAAI, 2022.

9. Yanbo Wang, Shaohui Lin*, Yanyun Qu, et al. Towards Compact Single Image Super-Resolution via Contrastive Self-distillation. In IJCAI, 2021.

10. Chengwei Chen, Yuan Xie, Shaohui Lin*, et al. Novelty Detection via Contrastive Learning with Negative Data Augmentation. In IJCAI, 2021.

11. Xuncheng Liu, Xudong Tian, Shaohui Lin, et al. Learn from Concepts: Towards the Purified Memory for Few-shot Learning. In IJCAI, 2021.

12. Yuchao Li#, Shaohui Lin#, Jianzhuang Liu, et al. Towards Compact CNNs via Collaborative Compression. CVPR, 2021.

13. Xudong Tian, Zhizhong Zhang, Shaohui Lin, et al. Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification. CVPR, 2021 (oral)

14. Haiyan Wu, Yanyun Qu, Shaohui Lin*, et al. Contrastive Learning for Compact Single Image Dehazing. CVPR, 2021.

15. Huixia Li, Chenqian Yan, Shaohui Lin, Xiawu Zheng, Baochang Zhang, Fan Yang, Rongrong Ji. PAMS: Quantized Super-Resolution via Parameterized Max Scale. ECCV, 2020.

16. Yuchao Li, Rongrong Ji, Shaohui Lin, Baochang Zhang, Chenqian Yan, Yongjian Wu, Feiyue Huang, Ling Shao. Interpretable Neural Networks Decoupling. ECCV, 2020

17. Moritz Wolter, Shaohui Lin, Angela, Yao. Neural network compression via learnable wavelet transforms. ICANN, 2020 

18. Shaohui Lin, Rongrong Ji, Chenqian Yan, Baochang Zhang, Liujuan Cao, Qixiang Ye, Feiyue Huang, David Doermann, Towards Optimal Structured CNN Pruning via Generative Adversarial Learning. CVPR, 2019. [code]

19. Shaohui Lin, Rongrong Ji, Yuchao Li, Yongjian Wu, Feiyue Huang, Baochang Zhang. Accelerating Convolutional Networks via Global & Dynamic Filter Pruning. IJCAI, 2018. [code]

20. Shaohui Lin, Rongrong Ji, Chao Chen, Feiyue Huang. ESPACE: Accelerating Convolutional Neural Networks via Eliminating Spatial & Channel Redundancy. AAAI, 2017.

21. Shaohui Lin, Rongrong Ji, Xiaowei Guo, Xuelong Li. Towards Convolutional Neural Networks Compression via Global Error Reconstruction. IJCAI, 2016. 

Journal:

1. Shaohui Lin, Rongrong Ji, Chao Chen, Dacheng Tao, Jiebo Luo. Holistic CNN Compression via Low-rank Decomposition with Knowledge Transfer. TPAMI, 2019. [code]

2. Shaohui Lin, Rongrong Ji, Yuchao Li, Cheng Deng, Xuelong Li. Toward Compact ConvNet via Structure-sparsity Regularized Filter Pruning. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020. [code]

3. Shaohui Lin, Ling Cai, Xianming Lin, Rongrong Ji. Masked Face Detection via A Modified LeNet. NEUROCOMPUTING, 2016, 218:197-202.

4. Ji Rongrong, Lin Shaohui*, Chao Fei, Wu yongjian, Huang Feiyue. Deep neural network compression and acceleration: a review. Journal of Computer Research and Development, 2018, 55(9): 1871-1888.  (* Corresponding author)

5. Zongyue Wang, Shaohui Lin*, Jiao Xie, Yangbin Lin. Pruning Blocks for CNN Compression and Acceleration via Online Ensemble Distillation. IEEE Access, 2019. (* Corresponding author)

6. Nan Wang, Shaohui Lin*, Xiaoxiao Li, Ke Li, Yunhang Shen, Yue Gao, Lizhuang Ma*. MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet. IEEE Transactions on Medical Imaging, 2023.

7. Jiao Xie, Shaohui Lin*, Yichen Zhang, Linkai Luo*. Compressing convolutional neural networks with cheap convolutions and online distillation. Displays, 2023.

Thesis (Ph.D):

1. Shaohui Lin. Research on Deep Neural Networks Compression and Acceleration. [Paper-Chinese]

Activities

Reviewer (for journal): IEEE Transactions on Pattern analysis and Machine intelligence (TPAMI), International Journal of Computer Vision (IJCV), IEEE Transactions on Neural Networks and Learning System (TNNLS), IEEE Transactions on Multimedia (TMM), Pattern Recognition (PR), Neural Networks, Multimedia Tools and Applications (MTA)

Reviewer (for conference): CVPR 2020, ACCV 2020, NeurIPS 2020, AAAI 2021, ICML 2021, ICCV 2021

Aear Chair & Senior Program Committee members (SPC):  IJCAI 2021, CVPR 2024, PRCV 2023/2024

Guest Editor: Electronics 

Honors and awards

• Best Reviewer for the journal "Scientia Sinica(Technologica)", 2021

• Outstanding Doctoral Dissertation Nomination Award, Chinese Association for Artificial Intelligence (CAAI), 2020 

• Excellent Ph.D Thesis Award, Fujian, 2019 

• Outstanding Ph.D Graduate Student, 2019 

• National Ph.D. Fellowship, 2018

• “Ge Jiashu” Scholarship, Xiamen University, 2017

• Outstanding Graduate Student, 2011