Timezone: »

The Edge of Orthogonality: A Simple View of What Makes BYOL Tick
Pierre Richemond · Allison Tam · Yunhao Tang · Florian Strub · Bilal Piot · Feilx Hill

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #221

Self-predictive unsupervised learning methods such as BYOL or SimSIAM have shown impressive results, and counter-intuitively, do not collapse to trivial representations. In this work, we aim at exploring the simplest possible mathematical arguments towards explaining the underlying mechanisms behind self-predictive unsupervised learning. We start with the observation that those methods crucially rely on the presence of a predictor network (and stop-gradient). With simple linear algebra, we show that when using a linear predictor, the optimal predictor is close to an orthogonal projection, and propose a general framework based on orthonormalization that enables to interpret and give intuition on why BYOL works. In addition, this framework demonstrates the crucial role of the exponential moving average and stop-gradient operator in BYOL as an efficient orthonormalization mechanism. We use these insights to propose four new closed-form predictor variants of BYOL to support our analysis. Our closed-form predictors outperform standard linear trainable predictor BYOL at 100 and 300 epochs (top-1 linear accuracy on ImageNet).

Author Information

Pierre Richemond (Google DeepMind)
Allison Tam (DeepMind)
Yunhao Tang (Google DeepMind)
Florian Strub (DeepMind)
Bilal Piot (Google DeepMind)
Feilx Hill (Deepmind)

More from the Same Authors