Traditional image classifiers tend to identify whole-image labels. This paper uses Adversarial Erasing, a novel technique to iteratively remove regions from an image, forcing the classifier to learn from more of the image. This technique achieved state-of-the-art for segemntation from whole-image labels on the PASCAL VOC 2012 test set with a mIoU of 55.7%.
Pixelwise Segmentation using Image Classifiers
Post · Mar 27, 2017 16:53 · Share on Twitter
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.