arXiv Analytics

Sign in

arXiv:1706.02493 [cs.CV]AbstractReferencesReviewsResources

Learning Deep Representations for Scene Labeling with Guided Supervision

Zhe Wang, Hongsheng Li, Wanli Ouyang, Xiaogang Wang

Published 2017-06-08Version 1

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the large intra-class variation provides ambiguous training information and hinders the deep models' ability to learn more discriminative deep feature representations. Unlike existing methods that mainly utilize semantic context for regularizing or smoothing the prediction map, we design novel supervisions from semantic context for learning better deep feature representations. Two types of semantic context, scene names of images and label map statistics of image patches, are exploited to create label hierarchies between the original classes and newly created subclasses as the learning supervisions. Such subclasses show lower intra-class variation, and help CNN detect more meaningful visual patterns and learn more effective deep features. Novel training strategies and network structure that take advantages of such label hierarchies are introduced. Our proposed method is evaluated extensively on four popular datasets, Stanford Background (8 classes), SIFTFlow (33 classes), Barcelona (170 classes) and LM+Sun datasets (232 classes) with 3 different networks structures, and show state-of-the-art performance. The experiments show that our proposed method makes deep models learn more discriminative feature representations without increasing model size or complexity.

Related articles: Most relevant | Search more
arXiv:2209.13832 [cs.CV] (Published 2022-09-28)
Learning Deep Representations via Contrastive Learning for Instance Retrieval
arXiv:1712.00250 [cs.CV] (Published 2017-12-01)
Learning Deep Representations for Word Spotting Under Weak Supervision
arXiv:1908.05860 [cs.CV] (Published 2019-08-16)
Learning Deep Representations by Mutual Information for Person Re-identification