Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues

04/03/2019
by   Ting Sun, et al.
0

This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known defects of these cues are coarseness and incompleteness. We use super-pixel to refine them, and fuse the cues extracted from both a color image trained classifier and a gray image trained classifier to compensate for their incompleteness. The conditional random field is adapted to regulate the training process and to refine the outputs further. Besides initializing the segmentation network, the previously trained classifier is also used in the testing phase to suppress the non-existing classes. Experimental results on the PASCAL VOC 2012 dataset illustrate the effectiveness of our method.

READ FULL TEXT

page 4

page 5

research
03/08/2022

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

Weakly supervised semantic segmentation (WSSS) methods are often built o...
research
07/18/2017

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

We propose an approach to discover class-specific pixels for the weakly-...
research
11/04/2019

Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation

To minimize the annotation costs associated with the training of semanti...
research
01/23/2018

A Classification Refinement Strategy for Semantic Segmentation

Based on the observation that semantic segmentation errors are partially...
research
09/01/2021

A Weakly-Supervised Surface Crack Segmentation Method using Localisation with a Classifier and Thresholding

Surface cracks are a common sight on public infrastructure nowadays. Rec...
research
08/30/2019

Learning Rich Representations For Structured Visual Prediction Tasks

We describe an approach to learning rich representations for images, tha...
research
08/21/2023

Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation

In recent years, several Weakly Supervised Semantic Segmentation (WS3) m...

Please sign up or login with your details

Forgot password? Click here to reset