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

Source: [Puzzle-CAM: Improved localization via matching partial and full features](<https://www.sota2.com/research/paper/68fa6ada1e209131cea2acbf>)

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

Data updated: 2025-12-22T13:16:34.311Z

Authors: Sanghyun Jo, In-Jae Yu

Published: 2021-01-27T08:19:38.000Z

## Abstract

Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs) to generate pseudo-labels to train the segmentation network. The main limitation of WSSS is that the process of generating pseudo-labels from CAMs that use an image classifier is mainly focused on the most discriminative parts of the objects. To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. Our method consists of a puzzle module and two regularization terms to discover the most integrated region in an object. Puzzle-CAM can activate the overall region of an object using image-level supervision without requiring extra parameters. % In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 test dataset. In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 dataset. Code associated with our experiments is available at https://github.com/OFRIN/PuzzleCAM.

## 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.

- [Weakly Supervised Semantic Segmentation on PASCAL VOC 2012 (val)](<https://www.sota2.com/research/sota/weakly-supervised-semantic-segmentation-on-pascal-voc-2012-val.md>): Weakly supervised semantic segmentation; PASCAL VOC 2012 (val); mIoU: not recorded.

- [Weakly Supervised Semantic Segmentation on PASCAL VOC 2012 (test)](<https://www.sota2.com/research/sota/weakly-supervised-semantic-segmentation-on-pascal-voc-2012-test.md>): Weakly supervised semantic segmentation; PASCAL VOC 2012 (test); mIoU: not recorded.

- [Weakly Supervised Semantic Segmentation on PASCAL VOC 2012 (train)](<https://www.sota2.com/research/sota/weakly-supervised-semantic-segmentation-on-pascal-voc-2012-train.md>): Weakly supervised semantic segmentation; PASCAL VOC 2012 (train); mIoU: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2101.11253>)

[PDF](<https://arxiv.org/pdf/2101.11253.pdf>)