# Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation

## TL;DR

This paper introduces a decoupled spatial neural attention network that improves pseudo-annotation quality for weakly supervised semantic segmentation, achieving state-of-the-art results with image labels.

## Contribution

The proposed decoupled attention structure effectively identifies object regions and discriminative parts simultaneously, enhancing pseudo-annotation quality.

## Key findings

- Achieved state-of-the-art performance in weakly supervised segmentation.
- Generated high-quality pseudo-annotations from image labels.
- Improved object localization accuracy.

## Abstract

Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other forms of weak supervision, image labels are quite efficient to obtain. In our work, we focus on the weakly supervised semantic segmentation with image label annotations. Recent progress for this task has been largely dependent on the quality of generated pseudo-annotations. In this work, inspired by spatial neural-attention for image captioning, we propose a decoupled spatial neural attention network for generating pseudo-annotations. Our decoupled attention structure could simultaneously identify the object regions and localize the discriminative parts which generates high-quality pseudo-annotations in one forward path. The generated pseudo-annotations lead to the segmentation results which achieve the state-of-the-art in weakly-supervised semantic segmentation.