Run Away From your Teacher: Understanding BYOL by a Novel Self-Supervised Approach

by   Haizhou Shi, et al.

Recently, a newly proposed self-supervised framework Bootstrap Your Own Latent (BYOL) seriously challenges the necessity of negative samples in contrastive learning frameworks. BYOL works like a charm despite the fact that it discards the negative samples completely and there is no measure to prevent collapse in its training objective. In this paper, we suggest understanding BYOL from the view of our proposed interpretable self-supervised learning framework, Run Away From your Teacher (RAFT). RAFT optimizes two objectives at the same time: (i) aligning two views of the same data to similar representations and (ii) running away from the model's Mean Teacher (MT, the exponential moving average of the history models) instead of BYOL's running towards it. The second term of RAFT explicitly prevents the representation collapse and thus makes RAFT a more conceptually reliable framework. We provide basic benchmarks of RAFT on CIFAR10 to validate the effectiveness of our method. Furthermore, we prove that BYOL is equivalent to RAFT under certain conditions, providing solid reasoning for BYOL's counter-intuitive success.



There are no comments yet.


page 1

page 2

page 3

page 4


Graph Barlow Twins: A self-supervised representation learning framework for graphs

The self-supervised learning (SSL) paradigm is an essential exploration ...

Concept Representation Learning with Contrastive Self-Supervised Learning

Concept-oriented deep learning (CODL) is a general approach to meet the ...

EqCo: Equivalent Rules for Self-supervised Contrastive Learning

In this paper, we propose a method, named EqCo (Equivalent Rules for Con...

Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning

We present a plug-in replacement for batch normalization (BN) called exp...

Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction

State-of-the-art methods for self-supervised learning (SSL) build repres...

Understanding Self-supervised Learning with Dual Deep Networks

We propose a novel theoretical framework to understand self-supervised l...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.