DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning

TL;DR

DABS introduces a comprehensive benchmark to evaluate self-supervised learning algorithms across diverse domains, highlighting the need for more domain-agnostic methods to advance the field.

Contribution

The paper presents DABS, a new benchmark with seven diverse domains for evaluating domain-agnostic self-supervised learning algorithms, along with baseline methods e-Mix and ShED.

Findings

Baseline algorithms perform modestly across domains

Significant progress is needed for domain-agnostic self-supervised learning

The benchmark facilitates evaluation of algorithms in diverse real-world settings

Abstract

Self-supervised learning algorithms, including BERT and SimCLR, have enabled significant strides in fields like natural language processing, computer vision, and speech processing. However, these algorithms are domain-specific, meaning that new self-supervised learning algorithms must be developed for each new setting, including myriad healthcare, scientific, and multimodal domains. To catalyze progress toward domain-agnostic methods, we introduce DABS: a Domain-Agnostic Benchmark for Self-supervised learning. To perform well on DABS, an algorithm is evaluated on seven diverse domains: natural images, multichannel sensor data, English text, speech recordings, multilingual text, chest x-rays, and images with text descriptions. Each domain contains an unlabeled dataset for pretraining; the model is then is scored based on its downstream performance on a set of labeled tasks in the domain. We also present e-Mix and ShED: two baseline domain-agnostic algorithms; their relatively modest performance demonstrates that significant progress is needed before self-supervised learning is an out-of-the-box solution for arbitrary domains. Code for benchmark datasets and baseline algorithms is available at https://github.com/alextamkin/dabs.