Causal Intervention for Weakly-Supervised Semantic Segmentation

2020-09-26 · NeurIPS 2020 12 · Dong Zhang, Hanwang Zhang, Jinhui Tang, Xian-Sheng Hua, Qianru Sun

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.

📄 PDF Abstract BibTeX arXiv:2009.12547

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeCausal Inference Segmentation Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Causal inference Causal inference is the process of drawing a conclusion about a causal connection based on the conditions of the occurrence of an effect. The main difference between causal…

C2RM-Seg: Causal Counterfactual Reasoning with Structural-Semantic Priors for Weakly Supervised Histopathological Tissue Segmentation

2026-06-24 · Hualong Zhang, Siyang Feng, Zihan Huan, Yi Qian 외 arxiv

Histopathological tissue segmentation is essential for computer-aided diagnosis, yet weakly supervised methods often suffer from noisy pseudo-labels generated by Class Activation Mapping (CAM). Existing CAM approaches te…

Weakly Supervised Semantic Segmentation using Web-Crawled Videos

2017-01-02 · CVPR 2017 7 · Seunghoon Hong, Donghun Yeo, Suha Kwak, Honglak Lee 외

We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative p…

image-classification Image Classification Segmentation Semantic Segmentation+2

C-CAM: Causal CAM for Weakly Supervised Semantic Segmentation on Medical Image

2022-01-01 · CVPR 2022 1 · Zhang Chen, Zhiqiang Tian, Jihua Zhu, Ce Li 외

Recently, many excellent weakly supervised semantic segmentation (WSSS) works are proposed based on class activation mapping (CAM). However, there are few works that consider the characteristics of medical images. In…

Anatomy Organ Segmentation Segmentation Semantic Segmentation+2

Budget-aware Semi-Supervised Semantic and Instance Segmentation

2019-05-14 · Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto

Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker fo…

Image Segmentation Instance Segmentation Segmentation Semantic Segmentation

Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery

2024-03-06 · Jingru Zhu, Ya Guo, Geng Sun, Liang Hong 외

Semantic segmentation of high-resolution remote sensing imagery (HRSI) suffers from the domain shift, resulting in poor performance of the model in another unseen domain. Unsupervised domain adaptive (UDA) semantic segme…

counterfactual Disentanglement Segmentation Semantic Segmentation