Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach

TL;DR

This paper introduces an adversarial erasing method that progressively mines object regions for weakly-supervised semantic segmentation, significantly improving localization and segmentation accuracy.

Contribution

It proposes a novel adversarial erasing approach combined with online prohibitive segmentation learning to enhance object region discovery from classification networks.

Findings

Achieves state-of-the-art 55.0% and 55.7% mIoU on PASCAL VOC 2012 val and test sets.

Effectively localizes dense and complete object regions for segmentation.

Demonstrates simple yet effective improvement over existing weakly-supervised methods.

Abstract

We investigate a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems. Classification networks are only responsive to small and sparse discriminative regions from the object of interest, which deviates from the requirement of the segmentation task that needs to localize dense, interior and integral regions for pixel-wise inference. To mitigate this gap, we propose a new adversarial erasing approach for localizing and expanding object regions progressively. Starting with a single small object region, our proposed approach drives the classification network to sequentially discover new and complement object regions by erasing the current mined regions in an adversarial manner. These localized regions eventually constitute a dense and complete object region for learning semantic segmentation. To further enhance the quality of the discovered regions by adversarial erasing, an online prohibitive segmentation learning approach is developed to collaborate with adversarial erasing by providing auxiliary segmentation supervision modulated by the more reliable classification scores. Despite its apparent simplicity, the proposed approach achieves 55.0% and 55.7% mean Intersection-over-Union (mIoU) scores on PASCAL VOC 2012 val and test sets, which are the new state-of-the-arts.