CVAILGOct 11, 2023

Causal Unsupervised Semantic Segmentation

arXiv:2310.07379v124 citationsh-index: 11
Originality Highly original
AI Analysis

This work addresses the problem of unsupervised semantic segmentation for computer vision researchers, offering a novel causal approach that improves segmentation quality without human labels.

The paper tackles the challenge of determining appropriate clustering levels in unsupervised semantic segmentation by proposing CAUSE, a framework that uses causal inference to define two-step tasks, achieving state-of-the-art performance on various datasets.

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction heads for unsupervised dense prediction. However, a significant challenge in this unsupervised setup is determining the appropriate level of clustering required for segmenting concepts. To address it, we propose a novel framework, CAusal Unsupervised Semantic sEgmentation (CAUSE), which leverages insights from causal inference. Specifically, we bridge intervention-oriented approach (i.e., frontdoor adjustment) to define suitable two-step tasks for unsupervised prediction. The first step involves constructing a concept clusterbook as a mediator, which represents possible concept prototypes at different levels of granularity in a discretized form. Then, the mediator establishes an explicit link to the subsequent concept-wise self-supervised learning for pixel-level grouping. Through extensive experiments and analyses on various datasets, we corroborate the effectiveness of CAUSE and achieve state-of-the-art performance in unsupervised semantic segmentation.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes