Weakly-supervised semantic segmentation with saliency and incremental supervision updating

Highlights：

• A new way of weakly-supervised learning with the joint guidance of saliency prior and classification information to effectively obtain better initial supervision for semantic segmentation.

• More foreground regions are discovered through an incremental supervision updating procedure, which is performed along with the training of segmentation 80 and guarantees to increase the number of foreground pixels.

• Extensive experiments on two benchmark segmentation datasets verifies the effectiveness of the proposed method for weakly-supervised semantic segmentation. We achieve mIoU of 62.5% and 62.7% on PASCAL VOC val and test set, respectively.

摘要

•A new way of weakly-supervised learning with the joint guidance of saliency prior and classification information to effectively obtain better initial supervision for semantic segmentation.•More foreground regions are discovered through an incremental supervision updating procedure, which is performed along with the training of segmentation 80 and guarantees to increase the number of foreground pixels.•Extensive experiments on two benchmark segmentation datasets verifies the effectiveness of the proposed method for weakly-supervised semantic segmentation. We achieve mIoU of 62.5% and 62.7% on PASCAL VOC val and test set, respectively.

论文评审过程：Received 15 February 2020, Revised 30 September 2020, Accepted 22 January 2021, Available online 5 February 2021, Version of Record 20 February 2021.