1 citations · 2 across the 2 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023★ 1 cited
Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning
Yihong Cao, Hui Zhang, Xiao Lu +3
Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses…
cs.CV2022★ 1 cited
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
Xiao Lu, Yihong Cao, Sheng Liu +5
It is challenging to annotate large-scale datasets for supervised video shadow detection methods. Using a model trained on labeled images to the video frames directly may lead to h…