DualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterization

arXiv:2405.16796v1 Announce Type: new
Abstract: Unsupervised disentanglement of content and transformation has recently drawn much research, given their efficacy in solving downstream unsupervised tasks like clustering, alignment, and shape analysis. This problem is particularly important for analyzing shape-focused real-world scientific image datasets, given their significant relevance to downstream tasks. The existing works address the problem by explicitly parameterizing the transformation factors, significantly reducing their expressiveness. Moreover, they are not applicable in cases where transformations can not be readily parametrized. An …

abstract alignment analysis arxiv clustering cs.cv datasets image image datasets problem research scientific shape tasks transformation type unsupervised world