`

Timezone: »

 
Poster
Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning
Jean-Bastien Grill · Florian Strub · Florent Altché · Corentin Tallec · Pierre Richemond · Elena Buchatskaya · Carl Doersch · Bernardo Avila Pires · Zhaohan Guo · Mohammad Gheshlaghi Azar · Bilal Piot · koray kavukcuoglu · Remi Munos · Michal Valko

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1697
in Poster Session 6 »

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods intrinsically rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches 74.3% top-1 classification accuracy on ImageNet using the standard linear evaluation protocol with a standard ResNet-50 architecture and 79.6% with a larger ResNet. We also show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks.

[ Paper ]

Author Information

Jean-Bastien Grill (DeepMind)
Florian Strub (DeepMind)
Florent Altché (DeepMind)
Corentin Tallec (Deepmind)
Pierre Richemond (Imperial College)
Elena Buchatskaya (DeepMind)
Carl Doersch (DeepMind)
Bernardo Avila Pires (DeepMind)
Zhaohan Guo (DeepMind)
Mohammad Gheshlaghi Azar (DeepMind)
Bilal Piot (DeepMind)
koray kavukcuoglu (DeepMind)
Remi Munos (DeepMind)
Michal Valko (DeepMind)

Michal is a machine learning scientist in DeepMind Paris, SequeL team at Inria, and the lecturer of the master course Graphs in Machine Learning at l'ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. This means 1) reducing the “intelligence” that humans need to input into the system and 2) minimizing the data that humans need to spend inspecting, classifying, or “tuning” the algorithms. Another important feature of machine learning algorithms should be the ability to adapt to changing environments. That is why he is working in domains that are able to deal with minimal feedback, such as online learning, bandit algorithms, semi-supervised learning, and anomaly detection. Most recently he has worked on sequential algorithms with structured decisions where exploiting the structure leads to provably faster learning. Structured learning requires more time and space resources and therefore the most recent work of Michal includes efficient approximations such as graph and matrix sketching with learning guarantees. In past, the common thread of Michal's work has been adaptive graph-based learning and its application to real-world applications such as recommender systems, medical error detection, and face recognition. His industrial collaborators include Adobe, Intel, Technicolor, and Microsoft Research. He received his Ph.D. in 2011 from the University of Pittsburgh under the supervision of Miloš Hauskrecht and after was a postdoc of Rémi Munos before taking a permanent position at Inria in 2012.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors