dSprites

'dSprites' is a dataset that contains 2D shapes varying in factors such as shape, scale, orientation, and position, and it is used to evaluate the effectiveness of models in achieving disentangled representation learning.

Papers using dSprites (2)

IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks2025Disentanglement as Identifiable Pushforward Factorisation2024