Disentangled Feature Swapping Augmentation for Weakly Supervised Semantic Segmentation

Junehyoung Kwon, Eunju Lee, YunSung Cho, YoungBin Kim

Keywords: Weakly Supervised Semantic Segmentation, Data Augmentation, Feature Disentanglement

TL;DR: We propose a novel feature augmentation for weakly supervised semantic segmentation to prevent the classifier from being biased by misleading correlation.

Abstract: Weakly supervised semantic segmentation utilizes a localization map obtained from a classifier to generate a pseudo-mask. However, classifiers utilize background cues to predict class labels because of a biased dataset consisting of images, in which specific objects frequently co-occur with certain backgrounds. Consequently, the classifier confuses the background with the target objects, resulting in inaccurate localization maps. To this end, we propose DisEntangled FeaTure swapping augmentation(DEFT) to prevent the classifier from being biased by a misleading correlation. Our method first disentangles the foreground and background features. Then, we randomly swap the disentangled features within mini-batches via a two-way process. These features contain various contexts that do not appear in the biased dataset, but the class relevant representation is preserved. In addition, we introduce training schemes to obtain further performance gains. Experimental results showed that when our augmentation was used in various weakly supervised semantic segmentation methods trained on the Pascal VOC 2012 dataset, the performance of the localization maps and pseudo-mask as well as the segmentation results improved.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)