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

03/24/2017
by   Yunchao Wei, et al.
0

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 (mIoU) scores on PASCAL VOC 2012 val and test sets, which are the new state-of-the-arts.

READ FULL TEXT

page 1

page 3

page 6

page 8

research
05/11/2018

Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation

Despite the remarkable progress, weakly supervised segmentation approach...
research
03/16/2021

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation

Weakly supervised semantic segmentation produces a pixel-level localizat...
research
06/14/2020

Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation

Object region mining is a critical step for weakly-supervised semantic s...
research
10/23/2018

Self-Erasing Network for Integral Object Attention

Recently, adversarial erasing for weakly-supervised object attention has...
research
04/19/2018

Adversarial Complementary Learning for Weakly Supervised Object Localization

In this work, we propose Adversarial Complementary Learning (ACoL) to au...
research
07/08/2022

Mining Discriminative Food Regions for Accurate Food Recognition

Automatic food recognition is the very first step towards passive dietar...
research
09/24/2019

Object-Contextual Representations for Semantic Segmentation

In this paper, we address the problem of semantic segmentation and focus...

Please sign up or login with your details

Forgot password? Click here to reset