# Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation

Source: [Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation](<https://www.sota2.com/research/paper/68fa73da1e209131cea5e838>)

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

Data updated: 2026-01-02T06:39:14.701Z

Authors: Junsung Park, Hyunjung Shim

Published: 2024-06-28T03:58:02.000Z

## Abstract

Weakly Supervised Semantic Segmentation (WSSS) employs weak supervision, such as image-level labels, to train the segmentation model. Despite the impressive achievement in recent WSSS methods, we identify that introducing weak labels with high mean Intersection of Union (mIoU) does not guarantee high segmentation performance. Existing studies have emphasized the importance of prioritizing precision and reducing noise to improve overall performance. In the same vein, we propose ORANDNet, an advanced ensemble approach tailored for WSSS. ORANDNet combines Class Activation Maps (CAMs) from two different classifiers to increase the precision of pseudo-masks (PMs). To further mitigate small noise in the PMs, we incorporate curriculum learning. This involves training the segmentation model initially with pairs of smaller-sized images and corresponding PMs, gradually transitioning to the original-sized pairs. By combining the original CAMs of ResNet-50 and ViT, we significantly improve the segmentation performance over the single-best model and the naive ensemble model, respectively. We further extend our ensemble method to CAMs from AMN (ResNet-like) and MCTformer (ViT-like) models, achieving performance benefits in advanced WSSS models. It highlights the potential of our ORANDNet as a final add-on module for WSSS models.

## 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: 72.9.

- [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: 72.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.19638>)

[PDF](<https://arxiv.org/pdf/2406.19638.pdf>)