Structured Knowledge Distillation for Semantic Segmentation
Structured Knowledge Distillation for Semantic SegmentationYifan Liu1 Ke Chen2Chris Liu2Zengchang Qin3,4Zhenbo Luo5Jingdong Wang2 1The University of Adelaide2Microsoft Research Asia3Beihang University4Keep Labs, Keep Research ChinaAbstractIn this paper, we investigate the Knowledge distillationstrategy for training small Semantic Segmentation networksby making use of large networks. We start from the straight-forward scheme, pixel-wise Distillation , which applies thedistillation scheme adopted for image classi cation andperforms Knowledge Distillation for each further propose to distill thestructuredknowledge fromlarge networks to small networks, which is motivated by thatsemantic Segmentation is a Structured prediction study two Structured Distillation schemes: (i)pair-wisedistillation that distills the pairwise similarities, and (ii)holisticdistillation that uses GAN to distill holistic knowl-edge.
DeepLab [5, 6, 7, 48], PSPNet [56], OCNet [50], Re-fineNet [23] and DenseASPP [46] have achieved significant improvement in segmentation accuracy, often with cumber-some models and expensive computation. Recently, neural networks with small model size, light computation cost and high segmentation accuracy, have at-
Download Structured Knowledge Distillation for Semantic Segmentation
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: