Data to 14 Oct 2026

Causal Intervention for Weakly-Supervised Semantic Segmentation

arXiv 2009.12547 ↗First posted 26 Sep 2020cs.CVcited by 229

Not on the map. Why?

Abstract (arXiv)

We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of "horse" and "person" may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and class labels. Based on it, we develop a new method: Context Adjustment (CONTA), to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model. On PASCAL VOC 2012 and MS-COCO, we show that CONTA boosts various popular WSSS methods to new state-of-the-arts.

Key facts. Cited by 229 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 43; 2022: 51; 2023: 60; 2024: 48; 2025: 23; 2026: 4.

229 papers.

Sort:

By area:

2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 119
2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
2021Causal Attention for Vision-Language Taskscited by 111
2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87

38 more

2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
2021Deconfounded Video Moment Retrieval with Causal Interventioncited by 84
2021Causal Attention for Unbiased Visual Recognitioncited by 80
2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
2022Class Re-Activation Maps for Weakly-Supervised Semantic Segmentationcited by 75
2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 62
2024ReconBoost: Boosting Can Achieve Modality Reconcilementcited by 60
2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
2022Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answeringcited by 57
2023Class-Incremental Exemplar Compression for Class-Incremental Learningcited by 50
2021Pseudo-mask Matters in Weakly-supervised Semantic Segmentationcited by 48
2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
2022A Causal Lens for Controllable Text Generationcited by 45
2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
2021CTNet: Context-based Tandem Network for Semantic Segmentationcited by 43
2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
2022Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholdscited by 37
2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
2023M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognitioncited by 34
2024Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlookcited by 33
2023GaitGCI: Generative Counterfactual Intervention for Gait Recognitioncited by 31
2023Extracting Class Activation Maps from Non-Discriminative Features as wellcited by 30
2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 29
2021Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentationcited by 29
2024Unbiased Faster R-CNN for Single-source Domain Generalized Object Detectioncited by 29
2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26
2022Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentationcited by 26
2023Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentationcited by 26
2023Shatter and Gather: Learning Referring Image Segmentation with Text Supervisioncited by 25

50 most cited of 229 All 229 (JSON)