Segmentation

Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation

DRS

Official pytorch implementation of our paper: Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation [Paper], Beomyoung Kim, Sangeun Han, and Junmo Kim, AAAI 2021

We propose the discriminative region suppression (DRS) module that is a simple yet effective method to expand object activation regions. DRS suppresses the attention on discriminative regions and spreads it to adjacent non-discriminative regions, generating dense localization maps.

[2021.06.10] we support DeepLab-V3 segmentation network!

DRS_CAM

DRS_module

Setup

  1. Dataset Preparing

    # dataset structure
VOC2012/
    --- Annotations/
    --- ImageSets/
    --- JPEGImages/
    --- SegmentationClassAug/
    --- saliency_map/
    --- refined_pseudo_segmentation_labels/

  2. Requirements
    pip install -r requirements.txt

Training & Pseudo Segmentation Labels Generation