CAUSE uses frontdoor adjustment with a discretized concept clusterbook mediator to perform unsupervised semantic segmentation and reports state-of-the-art results.
More recently, the discovery of semantic consistency in pre-trained self-supervised frameworks at the feature attention map (Caron et al.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Causal Unsupervised Semantic Segmentation
CAUSE uses frontdoor adjustment with a discretized concept clusterbook mediator to perform unsupervised semantic segmentation and reports state-of-the-art results.