# Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation

Source: [Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation](<https://www.sota2.com/research/paper/68fa66541e209131cea0f7ca>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:47:30.843Z

Authors: Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen

Published: 2019-09-09T09:23:11.000Z

## Abstract

Weakly supervised semantic segmentation has attracted much research interest in recent years considering its advantage of low labeling cost. Most of the advanced algorithms follow the design principle that expands and constrains the seed regions from class activation maps (CAM). As well-known, conventional CAM tends to be incomplete or over-activated due to weak supervision. Fortunately, we find that semantic segmentation has a characteristic of spatial transformation equivariance, which can form a few self-supervisions to help weakly supervised learning. This work mainly explores the advantages of scale equivariant constrains for CAM generation, formulated as a self-supervised scale equivariant network (SSENet). Specifically, a novel scale equivariant regularization is elaborately designed to ensure consistency of CAMs from the same input image with different resolutions. This novel scale equivariant regularization can guide the whole network to learn more accurate class activation. This regularized CAM can be embedded in most recent advanced weakly supervised semantic segmentation framework. Extensive experiments on PASCAL VOC 2012 datasets demonstrate that our method achieves the state-of-the-art performance both quantitatively and qualitatively for weakly supervised semantic segmentation. Code has been made available.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Segmentation on PASCAL VOC 2012 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-test.md>): Semantic segmentation; PASCAL VOC 2012 (test); mIoU: 64.9.

- [Semantic Segmentation on PASCAL VOC 2012 (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-val.md>): Semantic segmentation; PASCAL VOC 2012 (val); Mean IoU: 63.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1909.03714>)

[PDF](<https://arxiv.org/pdf/1909.03714.pdf>)