# Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation

Source: [Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation](<https://www.sota2.com/research/paper/68fa63b61e209131cea003d5>)

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

Data updated: 2025-10-25T20:47:17.894Z

Authors: Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez, Stephen Gould

Published: 2017-06-06T03:23:17.000Z

## Abstract

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we propose a novel method to extract accurate masks from networks pre-trained for the task of object recognition, thus forgoing external objectness modules. We first show how foreground/background masks can be obtained from the activations of higher-level convolutional layers of a network. We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network. Our experiments evidence that exploiting these masks in conjunction with a weakly-supervised training loss yields state-of-the-art tag-based weakly-supervised semantic segmentation results.

## 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/1706.02189>)

[PDF](<https://arxiv.org/pdf/1706.02189.pdf>)