# Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation Source: [Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:23:07.834Z Authors: Erik Stammes, Tom F.H. Runia, Michael Hofmann, Mohsen Ghafoorian Published: 2020-11-09T18:35:35.000Z ## Abstract Semantic segmentation is a task that traditionally requires a large dataset of pixel-level ground truth labels, which is time-consuming and expensive to obtain. Recent advancements in the weakly-supervised setting show that reasonable performance can be obtained by using only image-level labels. Classification is often used as a proxy task to train a deep neural network from which attention maps are extracted. However, the classification task needs only the minimum evidence to make predictions, hence it focuses on the most discriminative object regions. To overcome this problem, we propose a novel formulation of adversarial erasing of the attention maps. In contrast to previous adversarial erasing methods, we optimize two networks with opposing loss functions, which eliminates the requirement of certain suboptimal strategies; for instance, having multiple training steps that complicate the training process or a weight sharing policy between networks operating on different distributions that might be suboptimal for performance. The proposed solution does not require saliency masks, instead it uses a regularization loss to prevent the attention maps from spreading to less discriminative object regions. Our experiments on the Pascal VOC dataset demonstrate that our adversarial approach increases segmentation performance by 2.1 mIoU compared to our baseline and by 1.0 mIoU compared to previous adversarial erasing approaches. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on PASCAL VOC 2012 (test)](): Semantic segmentation; PASCAL VOC 2012 (test); mIoU: 63.8. - [Semantic Segmentation on PASCAL VOC 2012 (val)](): Semantic segmentation; PASCAL VOC 2012 (val); Mean IoU: 62.8. ## Original sources and implementation [Original paper]() [PDF]()