I have published some papers (1 best paper).
Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang: DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers. Tech report, arXiv, Sep. 2021. paper code bibtex
Chenhe Dong, Guangrun Wang, Hang Xu, Jiefeng Peng, Xiaozhe Ren, and Xiaodan Liang, "EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation" [C]. in the Findings of Conference on Empirical Methods in Natural Language Processing . (EMNLP 2021), 2021. paper code bibtex
Guangrun Wang, Keze Wang, Guangcong Wang, Philip H.S. Torr, and Liang Lin, "Solving Inefficiency of Self-supervised Representation Learning" [C]. in Proc. of IEEE International Conference on Computer Vision (ICCV 2021), 2021. Oral presentation paper code bibtex Oral-presentation-slices Poster
Jiqi Zhang, Jiefeng Peng, Changlin Li, Guangrun Wang (corresponding author), Xiaodan Liang, and Liang Lin "Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift" [C]. in Proc. of IEEE International Conference on Computer Vision (ICCV 2021), 2021. paper code bibtex Presentation-slices Poster
Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, and Xiaojun Chang, "BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search" [C]. in Proc. of IEEE International Conference on Computer Vision (ICCV 2021). paper code bibtex
Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, and Xiaojun Chan, "Dynamic Slimmable Network" [C]. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June, 2021. Oral presentation paper code bibtex
Guangrun Wang, Liang Lin, Rongcong Chen, Guangcong Wang, and Jiqi Zhang, "Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition" [J]. in IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2021. paper bibtex
Binbin Yang, Xiaodan Liang, Junhao Zhong, Jiefeng Peng, Guangrun Wang, and Liang Lin, "Unifying Dynamic Optimizer Search and Network Architecture Search" [C]. in 2021 IEEE International Conference on Multimedia and Expo (ICME), IEEE, 2021. paper bibtex
Guangrun Wang, Guangcong Wang, Keze Wang, Xiaodan Liang, Liang Lin, "Grammatically Recognizing Images with Tree Convolution" [C]. in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), San Diego, CA, USA, August 4-8, 2020. ACM, 2020. Oral presentation paper code bibtex
Guangrun Wang, Guangcong Wang, Xujie Zhang, Jianhuang Lai, and Liang Lin, "Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark" [J]. in IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2020. paper code bibtex
Bailin Li, Bowen Wu, Jiang Su, and Guangrun Wang, and Liang Lin, “EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning”, Proc. of European Conference on Computer Vision (ECCV), 2020. Oral presentation paper code bibtex
Hongjun Wang, Guangrun Wang (co-first author), Ya Li, Dongyu Zhang, Liang Lin, "Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking" [C]. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, June 16 - 18, 2020. Oral presentation paper code bibtex
Guangcong Wang, Jianhuang Lai, Wenqi Liang, Guangrun Wang, "Smoothing Adversarial Domain Attack and p-Memory Reconsolidation for Cross-Domain Person Re-Identification" [C]. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, June 16 - 18, 2020. paper bibtex
Changlin Li, Liuchun Yuan, Jiefeng Peng, Guangrun Wang (corresponding author), Xiaodan Liang, Liang Lin, Xiaojun Chang, "Block-wisely Supervised Neural Architecture Search with Knowledge Distillation" [C]. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, June 16 - 18, 2020. paper code bibtex
Guangcong Wang, Jianhuang Lai, Guangrun Wang, Wenqi Liang, "Function Feature Learning of Neural Networks". paper code bibtex
Bailin Li, Bowen Wu, Jiang Su, Guangrun Wang, "FNNP: Fast Neural Network Pruning Using Adaptive Batch Normalization". paper code bibtex
Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang (correspoding author), Xiaodan Liang, Liang Lin, Xiaojun Chang. "Blockwisely Supervised Neural Architecture Search with Knowledge Distillation", arXiv preprint arXiv (2019). paper code bibtex
Guangcong Wang, Jianhuang Lai, Wenqi Liang, and Guangrun Wang. "Learnable Parameter Similarity", arXiv preprint arXiv (2019). paper code bibtex
Hongjun Wang, Guangrun Wang (corresponding author), Guanbin Li and Liang Lin. "CamDrop: A New Explanation of Dropout and A Guided Regularization Method for Deep Neural Networks", In the 28th ACM International Conference on Information and Knowledge Management (CIKM 2019). Oral presentation paper bibtex
Guangrun Wang, Guangcong Wang, Xujie Zhang, Jianhuang Lai, and Liang Lin. "Weakly Supervised Person Re-identification: Cost-effective Learning with A New Benchmark" arXiv preprint arXiv (2019). paper code bibtex
Guangrun Wang, Keze Wang, and Liang Lin. "Adaptively Connected Neural Networks." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019. paper code bibtex
Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, and Liang Lin*, “Kalman Normalization: Normalizing Internal Representations Across Network Layers”, Proc. of Advances in Neural Information Processing Systems (NIPS 2018), 2018. paper bibtex
Guangrun Wang, Ping Luo, Liang Lin, and Xiaogang Wang. "Learning object interactions and descriptions for semantic image segmentation." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), pp. 5859-5867. 2017. paper leaderboard related-code bibtex
Guangrun Wang, Ping Luo (equal contribution), Liang Lin, and Xiaogang Wang. "Deep dual learning for semantic image segmentation." Proc. of IEEE International Conference on Computer Vision (ICCV 2017), pp. 21-26. 2017. paper related-code leaderboard bibtex
Liang Lin (my advisor), Guangrun Wang, Rui Zhang, Ruimao Zhang, Xiaodan Liang, and Wangmeng Zuo. "Deep structured scene parsing by learning with image descriptions." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2016), pp. 2276-2284. 2016. Oral presentation paper bibtex
Guangrun Wang, Liang Lin, Shengyong Ding, Ya Li, and Qing Wang. "DARI: Distance Metric and Representation Integration for Person Verification." In (AAAI 2016), pp. 3611-3617. 2016. paper code bibtex
Liang Lin (my advisor), Guangrun Wang, Wangmeng Zuo, Xiangchu Feng, and Lei Zhang. "Cross-domain visual matching via generalized similarity measure and feature learning." IEEE transactions on pattern analysis and machine intelligence (TPAMI) 39, no. 6 (2017): 1089-1102. paper code bibtex
Ruimao Zhang, Liang Lin (my advisor), Guangrun Wang, Meng Wang, and Wangmeng Zuo. "Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions." IEEE Transactions on Pattern Analysis and Machine Intelligence 1 (TPAMI): 1-1, 2018. paper dataset bibtex
Shengyong Ding, Liang Lin(my advisor), Guangrun Wang, and Hongyang Chao. "Deep feature learning with relative distance comparison for person re-identification." Pattern Recognition 48, no. 10 (2015): 2993-3003. Best Paper Award!. paper code bibtex
Ya Li, Guangrun Wang, Lin Nie, Qing Wang, and Wenwei Tan. "Distance metric optimization driven convolutional neural network for age invariant face recognition." Pattern Recognition 75 (2018):51-62. paper bibtex
Ya Li, Guangrun Wang, Liang Lin, and Huiyou Chang. "A deep joint learning approach for age invariant face verification." In CCF Chinese Conference on Computer Vision, pp. 296-305. Springer, Berlin, Heidelberg, 2015. paper bibtex
Ya Li, Guangrun Wang, Qing Wang. A Deep Joint Learning Approach for Age Invariant Face Verification [J]. Journal of Beijing University of Posts and Telecommunications, 2017, 40(1): 84-88, 110. paper bibtex
Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, and Liang Lin. "Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches." arXiv preprint arXiv:1802.03133 (2018). paper code bibtex
Ruimao Zhang, Liang Lin, Guangrun Wang, Meng Wang, and Wangmeng Zuo. "Scene Parsing by Weakly Supervised Learning with Image Descriptions." arXiv preprint arXiv:1709.09490 (2017). paper dataset bibtex
Patents
Jiqi Zhang, Liang Lin, Lin Nie, Guangrun Wang, Guangcong Wang. "A weakly supervised training method of pedestrian re-identification model based on differentiable graph learning" [Patent]. Published number: 112395997A, 2021.02.23. patent
Liang Lin, Rongcong Chen, Guangrun Wang, Guangcong Wang. "A neural network using tree convolution operation and its image processing method" [Patent]. Published number: 112001493A, 2020.11.27. patent
Jiefeng Peng, Changlin Li, Liuchun Yuan, Guangrun Wang, Xiaodan Liang. "Method and system for Neural Architecture Search with Knowledge Distillation" [Patent]. Published number: 111445008A, 2020.07.24. patent
Liang Lin, Hongjun Wang, Guangrun Wang, Dongyu Zhang. "Method and system for generating confrontation samples of person re-identification system" [Patent]. Published number: 111160217A, 2020.05.15. patent
Ping Luo, Guangrun Wang, Jiefeng Peng, Liang Lin, Xinjiang Wang, "A Batch Normalization Method, Deployment, and Computer Device" [Patent]. Published number: 108229664A, 2018.06.29. patent
Xiaoou Tang, Guangrun Wang, Ping Luo, Liang Lin, Xiaogang Wang, "An Image Segmentation Method, Deployment, Memory, and Program" [Patent]. Published number: 108229478A, 2018.06.29. patent
Rongcong Chen, Liang Lin, Guangrun Wang, Keze Wang [Patent], "Image Processing Method and Device Based on Adaptively Connected Neural Networks" [Patent]. Published number: 111079900A, 2020.04.28. patent
Rongcong Chen, Liang Lin, Guangrun Wang, Guangcong Wang, Jiqi Zhang, Image Recognition Model and Method with Network Structure Self-Adjusting [Patent]. Published number: 111062465A, 2020.04.24. patent
Liang Lin, Hongjun Wang, Guangrun Wang, Guanbin Li, Regularization Method and System Based on Class Activation Map Guidance [Patent]. Published number: 111027634A, 2020.04.17, patent