SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.11787 · ICCV · 2021

Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation

Wanli Ouyang, Lian Xu, Farid Boussaid, Mohammed Bennamoun, Dan Xu, Ferdous Sohel

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pretrained models to produce coarse saliency maps to guide the generation of pseudo segmentation labels. However, the commonly used off-line heuristic generation process cannot fully exploit the benefits of these coarse saliency maps. Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels. Inspired by their similar structured semantics, we also propose to learn a cross-task global pixellevel affinity map from the saliency and segmentation representations. The learned cross-task affinity can be used to refine saliency predictions and propagate CAM maps to provide improved pseudo labels for both tasks. The mutual boost between pseudo label updating and cross-task affinity learning enables iterative improvements on segmentation performance. Extensive experiments demonstrate the effectiveness of the proposed auxiliary learning network structure and the cross-task affinity learning method. The proposed approach achieves state-of-the-art weakly supervised segmentation performance on the challenging PAS-CAL VOC 2012 and MS COCO benchmarks. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2107.11787")
get_code_for_paper("2107.11787")
have("2107.11787")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2107.11787.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2107.11787.svg)](https://syntology.ai/paper/2107.11787)

Connect an agent — have() is free.