Topic: "binary-variational-autoencoder"
amacaluso/SSB-VAE
Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing: we investigate the robustness of hashing methods based on variational autoencoders to the lack of supervision, focusing on two semi-supervised approaches currently in use. In addition, we propose a novel supervision approach in which the model uses its own predictions of the label distribution to implement the pairwise objective. Compared to the best baseline, this procedure yields similar performance in fully-supervised settings but improves significantly the results when labelled data is scarce.
Language: Python - Size: 35 MB - Last synced at: about 1 year ago - Pushed at: about 4 years ago - Stars: 4 - Forks: 3
fmenat/DiscreteVAE
Public repository for Unsupervised Binary Variational Auto-Encoder (BVAE) used for Hashing
Language: Jupyter Notebook - Size: 600 MB - Last synced at: 28 days ago - Pushed at: 28 days ago - Stars: 2 - Forks: 1
