2 papers
cs.CV2023
DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentation
Fengyi Shen, Akhil Gurram, Ziyuan Liu +2
Domain adaptive semantic segmentation methods commonly utilize stage-wise training, consisting of a warm-up and a self-training stage. However, this popular approach still faces se…
cs.CV2022
LoopDA: Constructing Self-loops to Adapt Nighttime Semantic Segmentation
Fengyi Shen, Zador Pataki, Akhil Gurram +3
Due to the lack of training labels and the difficulty of annotating, dealing with adverse driving conditions such as nighttime has posed a huge challenge to the perception system o…