20 citations · 32 across the 2 of their papers we have counts for
2 papers
cs.CV2020★ 12 cited
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
Hao Li, Chenxin Tao, Xizhou Zhu +3
Designing proper loss functions is essential in training deep networks. Especially in the field of semantic segmentation, various evaluation metrics have been proposed for diverse…
cs.CV2019★ 20 cited
Improved Techniques for Training Adaptive Deep Networks
Hao Li, Hong Zhang, Xiaojuan Qi +2
Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph f…