Ishan Misra
Diane Larlus's Personal Page
The past two years have seen major advances in self-supervised learning, with many new methods reaching astounding performances on standard benchmarks. Moreover, many recent works have shown the large potential of coupled data sources such as image-text in producing even stronger models capable of zero-shot tasks, and often inspired by NLP. We have just witnessed a jump from the "default" single-modal pretraining with CNNs to Transformer-based multi-modal training, and these early developments will surely m
A major goal of unsupervised learning in computer vision is to learn general data representations without labels. For this, countless pretext tasks such as image colorization and more recently contrastive learning and teacher-student approaches have been proposed to learn neural networks for feature extraction. While these methods are rapidly improving in performance and have surpassed supervised representations on many downstream tasks, many challenges remain and the ``next big step'' is not apparent.
As the methods are maturing, the field is now at the point where we have to start discussing how we can make optimal use of self-supervised representations in applications, as well as what are the remaining obstacles and possible approaches to tackle them. The workshop aims to give space to ask and discuss fundamental, longer-term questions with researchers that are leading this area. Key questions we aim to tackle include: What are the current bottlenecks in self-supervised learning? What is the future rol
Ishan Misra
Diane Larlus's Personal Page