Structured Consistency Loss for semi-supervised semantic segmentation

Abstract

The consistency loss has played a key role in solving problems in recent studies on semi-supervised learning. Yet extant studies with the consistency loss are limited to its application to classification tasks; extant studies on semi-supervised semantic segmentation rely on pixel-wise classification, which does not reflect the structured nature of characteristics in prediction. We propose a structured consistency loss to address this limitation of extant studies. Structured consistency loss promotes consistency in inter-pixel similarity between teacher and student networks. Specifically, collaboration with CutMix optimizes the efficient performance of semi-supervised semantic segmentation with structured consistency loss by reducing computational burden dramatically. The superiority of proposed method is verified with the Cityscapes; The Cityscapes benchmark results with validation and with test data are 81.9 mIoU and 83.84 mIoU respectively. This ranks the first place on the pixel-level semantic labeling task of Cityscapes benchmark suite. To the best of our knowledge, we are the first to present the superiority of state-of-the-art semi-supervised learning in semantic segmentation.

10 pages, 4 figures

References in corpus (3)

• Temporal Ensembling for Semi-Supervised Learning
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Global Aggregation then Local Distribution in Fully Convolutional Networks

Cited by in corpus (5)

• PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
• Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
• Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
• Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
• Semi-supervised Domain Adaptation for Semantic Segmentation