Amortised Invariance Learning for Contrastive Self-Supervision

Ruchika Chavhan*, Jan Stuehmer, Calum Heggan, Mehrdad Yaghoobi, Timothy M Hospedales

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong inductive biases. However these may or may not be helpful, depending on if they match the invariance requirements of downstream tasks or not. This has led to several attempts to learn task-specific invariances during pre-training, however, these methods are highly compute intensive and tedious to train. We introduce the notion of amortized invariance learning for contrastive self supervision. In the pre-training stage, we parameterize the feature extractor by differentiable invariance hyper-parameters that control the invariances encoded by the representation. Then, for any downstream task, both linear readout and task-specific invariance requirements can be efficiently and effectively learned by gradient-descent. We evaluate the notion of amortized invariances for contrastive learning over two different modalities: vision and audio, on two widely-used contrastive learning methods in vision: SimCLR and MoCo-v2 with popular architectures like ResNets and Vision Transformers, and SimCLR with ResNet-18 for audio. We show that our amortized features provide a reliable way to learn diverse downstream tasks with different invariance requirements, while using a single feature and avoiding task-specific pre-training. This provides an exciting perspective that opens up new horizons in the field of general purpose representation learning.
Original languageEnglish
Title of host publicationThe Eleventh International Conference on Learning Representations
Subtitle of host publicationICLR 2023
Number of pages23
Publication statusPublished - 1 May 2023
EventThe Eleventh International Conference on Learning Representations - Kigali, Rwanda
Duration: 1 May 20235 May 2023
https://iclr.cc/Conferences/2023

Conference

ConferenceThe Eleventh International Conference on Learning Representations
Abbreviated titleICLR 2023
Country/TerritoryRwanda
CityKigali
Period1/05/235/05/23
Internet address

Fingerprint

Dive into the research topics of 'Amortised Invariance Learning for Contrastive Self-Supervision'. Together they form a unique fingerprint.

Cite this