"Disentanglement of Latent Representations via Sparse Causal Interventions. (arXiv:2302.00869v1 [cs.LG])" — A new method for disentanglement inspired by causal dynamics that combines causality theory with vector-quantized variational autoencoders where the model considers the quantized vectors as causal variables and links them in a causal graph.

Paper: http://arxiv.org/abs/2302.00869

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Atomic interventions on one fac…