26 citations · 52 across the 6 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CV2022★ 26 cited
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
Yanpeng Sun, Qiang Chen, Xiangyu He +7
Freezing the pre-trained backbone has become a standard paradigm to avoid overfitting in few-shot segmentation. In this paper, we rethink the paradigm and explore a new regime: {\e…
cs.CV2022★ 10 cited
Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond
Xiangyu He, Jian Cheng
Super-resolution as an ill-posed problem has many high-resolution candidates for a low-resolution input. However, the popular loss used to best fit the given HR image fail…