Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation

TL;DR

This paper introduces AffinityNet, a neural network that predicts semantic affinities between image regions to improve weakly supervised semantic segmentation using only image-level labels, achieving competitive results.

Contribution

The novel framework propagates local discriminative responses to entire objects by learning semantic affinities with AffinityNet, enabling better segmentation without extra annotations.

Findings

Outperforms previous weakly supervised models on PASCAL VOC 2012

Achieves results comparable to strongly supervised methods

Relies solely on image-level labels for training

Abstract

The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels. In this weakly supervised setting, trained models have been known to segment local discriminative parts rather than the entire object area. Our solution is to propagate such local responses to nearby areas which belong to the same semantic entity. To this end, we propose a Deep Neural Network (DNN) called AffinityNet that predicts semantic affinity between a pair of adjacent image coordinates. The semantic propagation is then realized by random walk with the affinities predicted by AffinityNet. More importantly, the supervision employed to train AffinityNet is given by the initial discriminative part segmentation, which is incomplete as a segmentation annotation but sufficient for learning semantic affinities within small image areas. Thus the entire framework relies only on image-level class labels and does not require any extra data or annotations. On the PASCAL VOC 2012 dataset, a DNN learned with segmentation labels generated by our method outperforms previous models trained with the same level of supervision, and is even as competitive as those relying on stronger supervision.