You can also find the update-to-date list of my articles on my Google Scholar profile.
Published in arXiv', 2022
A Light-Weight Convolution-Free Vision Transformers.
Recommended citation: Tao Huang, Lang Huang, Shan You, Fei Wang, Chen Qian, Chang Xu (2022). "LightViT: Towards Light-Weight Convolution-Free Vision Transformers; arXiv/2207.05557. https://arxiv.org/abs/2207.05557
Published in Thirty-sixth Conference on Neural Information Processing Systems, 2022
Efficient masked image modeling with hierarchical vision transformers.
Recommended citation: Lang Huang, Shan You, Mingkai Zheng, Fei Wang, Chen Qian, Toshihiko Yamasaki (2022). "Green Hierarchical Vision Transformer for Masked Image Modeling; Thirty-sixth Conference on Neural Information Processing Systems. https://arxiv.org/abs/2205.13515
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
New algorithm for semi-supervised learning.
Recommended citation: Mingkai Zheng, Shan You, Lang Huang, Fei Wang, Chen Qian, Chang Xu (2022). "SimMatch: Semi-supervised Learning with Similarity Matching; IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://arxiv.org/pdf/2002.10319
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
New self-supervised pre-training algorithm for both image-level predictions and dense predictions.
Recommended citation: Lang Huang, Shan You, Mingkai Zheng, Fei Wang, Chen Qian, Toshihiko Yamasaki (2022). "Learning Where to Learn in Cross-View Self-Supervised Learning; IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://arxiv.org/abs/2203.14898
Published in arXiv/2101.08732, 2021
Unified training algorithm for supervised and self-supervised learning.
Recommended citation: Lang Huang, Chao Zhang, Hongyang Zhang (2022). "Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning; IEEE Transactions on Pattern Analysis and Machine Intelligence. https://arxiv.org/abs/2101.08732
Published in Thirty-fifth Conference on Neural Information Processing Systems, 2021
New algorithm for learning from corruted data.
Recommended citation: Yuhui Yuan, Rao Fu, Lang Huang, Weihong Lin, Chao Zhang, Xilin Chen, Jingdong Wang (2021). "HRFormer: High-Resolution Vision Transformer for Dense Prediction; Thirty-fifth Conference on Neural Information Processing Systems. https://arxiv.org/abs/2110.09408
Published in Thirty-fourth Conference on Neural Information Processing Systems, 2020
New algorithm for learning from corruted data.
Recommended citation: Lang Huang, Chao Zhang, Hongyang Zhang (2020). "Self-Adaptive Training: beyond Empirical Risk Minimization; Thirty-fourth Conference on Neural Information Processing Systems. https://arxiv.org/pdf/2002.10319
Published in International Conference on Computer Vision, 2019
Dual part-aligned representations for person re-Identification.
Recommended citation: Jianyuan Guo, Yuhui Yuan, Lang Huang, Chao Zhang, Jin-Ge Yao and Kai Han (2019). "Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification; International Conference on Computer Vision. https://arxiv.org/pdf/1910.10111
Published in arXiv:1907.12273 | IJCV, 2019
This paper proposed an efficient self-attention.
Recommended citation: Lang Huang, Yuhui Yuan, Jianyuan Guo, Chao Zhang, Xilin Chen, Jingdong Wang (2019). "Interlaced Sparse Self-Attention for Semantic Segmentation; arXiv:1907.12273. https://arxiv.org/abs/1907.12273
Published in International Journal of Computer Vision, 2018
This paper proposed an efficient method to model the object context for semantic segmentation.
Recommended citation: Yuhui Yuan, Lang Huang, Jianyuan Guo, Chao Zhang, Xilin Chen, Jingdong Wang (2021). "OCNet: Object Context for Semantic Segmentation; International Journal of Computer Vision. https://arxiv.org/abs/1809.00916