Joint Representation Learning And Novel Category Discovery On Single- And Multi-modal Data | Awesome Learning to Hash Add your paper to Learning2Hash

Awesome Learning to Hash

A Webpage dedicated to the latest research on Hash Function Learning. Maintained by Sean Moran.

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Joint Representation Learning And Novel Category Discovery On Single- And Multi-modal Data

Jia Xuhui, Han Kai, Zhu Yukun, Green Bradley. Arxiv 2021

[Paper]    
ARXIV Cross Modal Supervised

This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign clusters to unlabelled data. To avoid over-fitting the learnt embedding to labelled data, we take inspiration from self-supervised representation learning by noise-contrastive estimation and extend it to jointly handle labelled and unlabelled data. In particular, we propose using category discrimination on labelled data and cross-modal discrimination on multi-modal data to augment instance discrimination used in conventional contrastive learning approaches. We further employ Winner-Take-All (WTA) hashing algorithm on the shared representation space to generate pairwise pseudo labels for unlabelled data to better predict cluster assignments. We thoroughly evaluate our framework on large-scale multi-modal video benchmarks Kinetics-400 and VGG-Sound, and image benchmarks CIFAR10, CIFAR100 and ImageNet, obtaining state-of-the-art results.

Similar Work