Webly-supervised learning for salient object detection

作者：

Highlights：

• We propose a novel webly-supervised learning method for salient object detection, which requires no pixel-wise annotations.

• We introduce a novel quality evaluation method that can help to pick out images with high-quality masks for training.

• We present a self-training approach to boost the performance of our network by selecting more hard web images for training.

• Our method outperforms existing unsupervised methods, weakly supervised methods, and even fully-supervised approaches.

摘要

•We propose a novel webly-supervised learning method for salient object detection, which requires no pixel-wise annotations.•We introduce a novel quality evaluation method that can help to pick out images with high-quality masks for training.•We present a self-training approach to boost the performance of our network by selecting more hard web images for training.•Our method outperforms existing unsupervised methods, weakly supervised methods, and even fully-supervised approaches.

论文关键词：Salient object detection,Webly-supervised learning,Deep learning

论文评审过程：Received 22 May 2019, Revised 14 February 2020, Accepted 24 February 2020, Available online 27 February 2020, Version of Record 13 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107308