Is synthetic data from generative models ready for image recognition? R He, S Sun, X Yu, C Xue, W Zhang, P Torr, S Bai, X Qi ICLR, 2022 | 282 | 2022 |
Learning by analogy: Reliable supervision from transformations for unsupervised optical flow estimation L Liu, J Zhang, R He, Y Liu, Y Wang, Y Tai, D Luo, C Wang, J Li, F Huang CVPR, 6489-6498, 2020 | 199 | 2020 |
Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation R He, J Yang, X Qi ICCV, 6930-6940, 2021 | 153 | 2021 |
Knowledge distillation as efficient pre-training: Faster convergence, higher data-efficiency, and better transferability R He, S Sun, J Yang, S Bai, X Qi CVPR, 9161-9171, 2022 | 46 | 2022 |
LUMix: Improving mixup by better modelling label uncertainty S Sun, JN Chen, R He, A Yuille, P Torr, S Bai ICASSP, 2022 | 7 | 2022 |
Debiasing text-to-image diffusion models R He, C Xue, H Tan, W Zhang, Y Yu, S Bai, X Qi Proceedings of the 1st ACM Multimedia Workshop on Multi-modal Misinformation …, 2024 | 4 | 2024 |
Mc-moe: Mixture compressor for mixture-of-experts llms gains more W Huang, Y Liao, J Liu, R He, H Tan, S Zhang, H Li, S Liu, X Qi arXiv preprint arXiv:2410.06270, 2024 | 2 | 2024 |
Vertical layering of quantized neural networks for heterogeneous inference H Wu, R He, H Tan, X Qi, K Huang IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (12 …, 2023 | 2 | 2023 |