Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks

by   Shun-Yi Pan, et al.

This work addresses weakly-supervised image semantic segmentation based on image-level class labels. One common approach to this task is to propagate the activation scores of Class Activation Maps (CAMs) using a random-walk mechanism in order to arrive at complete pseudo labels for training a semantic segmentation network in a fully-supervised manner. However, the feed-forward nature of the random walk imposes no regularization on the quality of the resulting complete pseudo labels. To overcome this issue, we propose a Graph Convolutional Network (GCN)-based feature propagation framework. We formulate the generation of complete pseudo labels as a semi-supervised learning task and learn a 2-layer GCN separately for every training image by back-propagating a Laplacian and an entropy regularization loss. Experimental results on the PASCAL VOC 2012 dataset confirm the superiority of our scheme to several state-of-the-art baselines. Our code is available at https://github.com/Xavier-Pan/WSGCN.



There are no comments yet.


page 2

page 5


Puzzle-CAM: Improved localization via matching partial and full features

Weakly-supervised semantic segmentation (WSSS) is introduced to narrow t...

Learning random-walk label propagation for weakly-supervised semantic segmentation

Large-scale training for semantic segmentation is challenging due to the...

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation produces pixel-level localizatio...

Scribble-Supervised Semantic Segmentation by Random Walk on Neural Representation and Self-Supervision on Neural Eigenspace

Scribble-supervised semantic segmentation has gained much attention rece...

Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks

Cancer prognostication is a challenging task in computational pathology ...

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation

While self-training has advanced semi-supervised semantic segmentation, ...

Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation

Weakly-supervised semantic segmentation aims to assign each pixel a sema...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.