Search Results for author:
Found 2 papers, 1 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.
Ranked #1 on
Image Clustering
on Rendered SST2
Learning Cluster Structured Sparsity by Reweighting
Recently, the paradigm of unfolding iterative algorithms into finite-length feed-forward neural networks has achieved a great success in the area of sparse recovery.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
