# Improving Weakly-supervised Object Localization via Causal Intervention

Source: [Improving Weakly-supervised Object Localization via Causal Intervention](<https://www.sota2.com/research/paper/68fa6a7b1e209131cea287e8>)

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

Data updated: 2025-10-25T23:26:28.956Z

Authors: Feifei Shao, Yawei Luo, Li Zhang, Lu Ye, Siliang Tang, Yi Yang, Jun Xiao

Published: 2021-04-21T04:44:33.000Z

## Abstract

The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perceive the interval objects from the small and sparse discriminative attention map, yet ignoring the co-occurrence confounder (e.g., bird and sky), which makes the model inspection (e.g., CAM) hard to distinguish between the object and context. In this paper, we make an early attempt to tackle this challenge via causal intervention (CI). Our proposed method, dubbed CI-CAM, explores the causalities among images, contexts, and categories to eliminate the biased co-occurrence in the class activation maps thus improving the accuracy of object localization. Extensive experiments on several benchmarks demonstrate the effectiveness of CI-CAM in learning the clear object boundaries from confounding contexts. Particularly, in CUB-200-2011 which severely suffers from the co-occurrence confounder, CI-CAM significantly outperforms the traditional CAM-based baseline (58.39% vs 52.4% in top-1 localization accuracy). While in more general scenarios such as ImageNet, CI-CAM can also perform on par with the state of the arts.

## 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/2104.10351>)

[PDF](<https://arxiv.org/pdf/2104.10351.pdf>)
