4 citations · 8 across the 5 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.CV2020★ 4 cited
Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels
Xiangwei Shi, Seyran Khademi, Yunqiang Li +1
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visual…
cs.CV2020
WeightAlign: Normalizing Activations by Weight Alignment
Xiangwei Shi, Yunqiang Li, Xin Liu +1
Batch normalization (BN) allows training very deep networks by normalizing activations by mini-batch sample statistics which renders BN unstable for small batch sizes. Current smal…