# Improving Weakly-supervised Object Localization via Causal Intervention

arXiv: https://arxiv.org/abs/2104.10351 · HTML: https://mlsanity.com/paper/2104.10351/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 54 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [A Survey on Causal Inference](https://mlsanity.com/paper/2002.02770/) (2020)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [Counterfactual Samples Synthesizing for Robust Visual Question Answering](https://mlsanity.com/paper/2003.06576/) (2020)
- [Attention-based Dropout Layer for Weakly Supervised Object Localization](https://mlsanity.com/paper/1908.10028/) (2019)
- [Interventional Few-Shot Learning](https://mlsanity.com/paper/2009.13000/) (2020)
- [Visual Commonsense R-CNN](https://mlsanity.com/paper/2002.12204/) (2020)
- [Learning Independent Causal Mechanisms](https://mlsanity.com/paper/1712.00961/) (2017)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [Deconfounded Image Captioning: A Causal Retrospect](https://mlsanity.com/paper/2003.03923/) (2020)
- [Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2004.06042/) (2020)
- [Counterfactuals uncover the modular structure of deep generative models](https://mlsanity.com/paper/1812.03253/) (2018)
- [Weakly Supervised Cascaded Convolutional Networks](https://mlsanity.com/paper/1611.08258/) (2016)
- [Deformable Part Models are Convolutional Neural Networks](https://mlsanity.com/paper/1409.5403/) (2014)
- [Macro-Micro Adversarial Network for Human Parsing](https://mlsanity.com/paper/1807.08260/) (2018)
- [Combinational Class Activation Maps for Weakly Supervised Object Localization](https://mlsanity.com/paper/1910.05518/) (2019)
- [TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.04897/) (2018)

## Built on by (most cited first, 14 of 14)

- [NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation](https://mlsanity.com/paper/2207.13316/) (2022)
- [Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning](https://mlsanity.com/paper/2202.12588/) (2022)
- [Weakly-Supervised Video Object Grounding via Causal Intervention](https://mlsanity.com/paper/2112.00475/) (2021)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation](https://mlsanity.com/paper/2602.07011/) (2026)
- [Knowledge-guided Causal Intervention for Weakly-supervised Object Localization](https://mlsanity.com/paper/2301.01060/) (2023)
- [Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization](https://mlsanity.com/paper/2305.15354/) (2023)
- [FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization](https://mlsanity.com/paper/2309.09122/) (2023)
- [Improving Weakly Supervised Sound Event Detection with Causal Intervention](https://mlsanity.com/paper/2303.05678/) (2023)
- [Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2309.01331/) (2023)
- [Hypergraph-State Collaborative Reasoning for Multi-Object Tracking](https://mlsanity.com/paper/2604.12665/) (2026)
- [Reducing Spurious Correlation for Federated Domain Generalization](https://mlsanity.com/paper/2407.19174/) (2024)
- [Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization](https://mlsanity.com/paper/2604.26820/) (2026)
- [Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations](https://mlsanity.com/paper/2608.12299/) (2026)

## Abstract (arXiv)

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.