# Saliency guided deep network for weakly-supervised image segmentation

arXiv: https://arxiv.org/abs/1810.08378 · HTML: https://mlsanity.com/paper/1810.08378/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2018.

## Built on by (most cited first, 4 of 4)

- [A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels](https://mlsanity.com/paper/2209.02957/) (2022)
- [Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation](https://mlsanity.com/paper/2505.10781/) (2025)
- [P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors](https://mlsanity.com/paper/2305.12522/) (2023)
- [Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2308.11052/) (2023)

## Abstract (arXiv)

Weakly-supervised image segmentation is an important task in computer vision. A key problem is how to obtain high quality objects location from image-level category. Classification activation mapping is a common method which can be used to generate high-precise object location cues. However these location cues are generally very sparse and small such that they can not provide effective information for image segmentation. In this paper, we propose a saliency guided image segmentation network to resolve this problem. We employ a self-attention saliency method to generate subtle saliency maps, and render the location cues grow as seeds by seeded region growing method to expand pixel-level labels extent. In the process of seeds growing, we use the saliency values to weight the similarity between pixels to control the growing. Therefore saliency information could help generate discriminative object regions, and the effects of wrong salient pixels can be suppressed efficiently. Experimental results on a common segmentation dataset PASCAL VOC2012 demonstrate the effectiveness of our method.