# Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation

Source: [Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation](<https://www.sota2.com/research/paper/68fa6ce51e209131cea369a9>)

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

Data updated: 2025-10-26T00:21:36.840Z

Authors: Weide Liu, Xiangfei Kong, Tzu-Yi Hung, Guosheng Lin

Published: 2021-08-17T02:51:02.000Z

## Abstract

Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the classification objective and lack the ability to generalize. To improve the generality of the objective activation maps, we propose a region prototypical network RPNet to explore the cross-image object diversity of the training set. Similar object parts across images are identified via region feature comparison. Object confidence is propagated between regions to discover new object areas while background regions are suppressed. Experiments show that the proposed method generates more complete and accurate pseudo object masks, while achieving state-of-the-art performance on PASCAL VOC 2012 and MS COCO. In addition, we investigate the robustness of the proposed method on reduced training sets.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.07413>)

[PDF](<https://arxiv.org/pdf/2108.07413.pdf>)