Self-Supervised Relational Reasoning for Representation Learning

In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly manual annotation. In this work, we propose a novel self-supervised formulation of relational reasoning that allows a learner to bootstrap a signal from information implicit in unlabeled data. Training a relation head to discriminate how entities relate to themselves (intra-reasoning) and other entities (inter-reasoning), results in rich and descriptive representations in the underlying neural network backbone, which can be used in downstream tasks such as classification and image retrieval. We evaluate the proposed method following a rigorous experimental procedure, using standard datasets, protocols, and backbones. Self-supervised relational reasoning outperforms the best competitor in all conditions by an average 14 in accuracy, and the most recent state-of-the-art model by 3 effectiveness of the method to the maximization of a Bernoulli log-likelihood, which can be considered as a proxy for maximizing the mutual information, resulting in a more efficient objective with respect to the commonly used contrastive losses.


page 4

page 17

page 18

page 19

page 21

page 22


Self-Supervised Image Representation Learning: Transcending Masking with Paired Image Overlay

Self-supervised learning has become a popular approach in recent years f...

Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning

Self-supervised learning achieves superior performance in many domains b...

Improving Visual Reasoning by Exploiting The Knowledge in Texts

This paper presents a new framework for training image-based classifiers...

From Patches to Objects: Exploiting Spatial Reasoning for Better Visual Representations

As the field of deep learning steadily transitions from the realm of aca...

Understanding the World Through Action

The recent history of machine learning research has taught us that machi...

Self-supervised Representation Learning with Relative Predictive Coding

This paper introduces Relative Predictive Coding (RPC), a new contrastiv...

Self-Supervised Learning with an Information Maximization Criterion

Self-supervised learning allows AI systems to learn effective representa...

Please sign up or login with your details

Forgot password? Click here to reset