Semi-supervised learning aims to train a model using limited labels.
Sta...
Generating a video given the first several static frames is challenging ...
We propose techniques to incorporate coarse taxonomic labels to train im...
Semi-iNat is a challenging dataset for semi-supervised classification wi...
We evaluate the effectiveness of semi-supervised learning (SSL) on a
rea...
This document describes the details and the motivation behind a new data...
Given a collection of images, humans are able to discover landmarks of t...
We present a technique to improve the generalization of deep representat...
We present a technique to improve the transferability of deep representa...
We propose an active learning approach for transferring representations
...
We investigate the role of representations and architectures for classif...
Model compression and knowledge distillation have been successfully appl...