Rethinking Positive Sampling for Contrastive Learning with Kernel

Benoit Dufumier, Carlo Alberto Barbano, Robin Louiset, Edouard Duchesnay, Pietro Gori

Keywords: contrastive learning, kernel theory, representation learning, deep learning

TL;DR: Improving positive sampling in contrastive learning using kernel

Abstract: Data augmentation is a crucial component in unsupervised contrastive learning (CL). It determines how positive samples are defined and, ultimately, the quality of the representation. Even if efforts have been made to find efficient augmentations for ImageNet, CL underperforms compared to supervised methods and it is still an open problem in other applications, such as medical imaging, or in datasets with easy-to-learn but irrelevant imaging features. In this work, we propose a new way to define positive samples using kernel theory along with a novel loss called \textit{decoupled uniformity}. We propose to integrate prior information, learnt from generative models viewed as feature extractor, or given as auxiliary attributes, into contrastive learning, to make it less dependent on data augmentation. We draw a connection between contrastive learning and the conditional mean embedding theory to derive tight bounds on the downstream classification loss. In an unsupervised setting, we empirically demonstrate that CL benefits from generative models, such as VAE and GAN, to less rely on data augmentations. We validate our framework on vision and medical datasets including CIFAR10, CIFAR100, STL10, ImageNet100, CheXpert and a brain MRI dataset. In the weakly supervised setting, we demonstrate that our formulation provides state-of-the-art results.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2206.01646/code)