Search Results for author:
Found 5 papers, 4 papers with code
Let Go of Your Labels with Unsupervised Transfer
In particular, TURTLE matches the average performance of CLIP zero-shot on 26 datasets by employing the same representation space, spanning a wide range of architectures and model sizes.
Let Go of Your Labels with Unsupervised Transfer
In particular, TURTLE matches the average performance of CLIP zero-shot on 26 datasets by employing the same representation space, spanning a wide range of architectures and model sizes.
Ranked #1 on
Image Clustering
on DTD
Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces
Structured latent variables allow incorporating meaningful prior knowledge into deep learning models.
Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution
Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates.
Conditional Generators of Words Definitions
We explore recently introduced definition modeling technique that provided the tool for evaluation of different distributed vector representations of words through modeling dictionary definitions of words.
