# Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/1804.04882 · HTML: https://mlsanity.com/paper/1804.04882/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2018.

## Built on by (most cited first, 5 of 5)

- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Gaussian Dynamic Convolution for Efficient Single-Image Segmentation](https://mlsanity.com/paper/2104.08783/) (2021)
- [Automatic segmentation of meniscus based on MAE self-supervision and point-line weak supervision paradigm](https://mlsanity.com/paper/2205.03525/) (2022)
- [Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2408.02039/) (2024)
- [SEMNAV: Enhancing Visual Semantic Navigation in Robotics through Semantic Segmentation](https://mlsanity.com/paper/2506.01418/) (2025)

## Abstract (arXiv)

Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With this paper we introduce a novel weakly-supervised semantic segmentation model able to learn from image labels, and just image labels. Our model uses the prior knowledge of a network trained for image recognition, employing these image annotations as an attention mechanism to identify semantic regions in the images. We then present a methodology that builds accurate class-specific segmentation masks from these regions, where neither external objectness nor saliency algorithms are required. We describe how to incorporate this mask generation strategy into a fully end-to-end trainable process where the network jointly learns to classify and segment images. Our experiments on PASCAL VOC 2012 dataset show that exploiting these generated class-specific masks in conjunction with our novel end-to-end learning process outperforms several recent weakly-supervised semantic segmentation methods that use image tags only, and even some models that leverage additional supervision or training data.