Seminar 'Self-supervised Pre-training with Masked Image Modeling'
On March 31 HSE Centre of Deep Learning and Bayesian Methods will hold a special seminar on 'Self- Pre-training with Masked Image Modeling'. The event will be held online.
Abstract:
Consistent success of BERT-like models in language processing has lead to attempts to adapt masked modeling task to other data domains and create a universal framework for pre-training without manual annotations. In this seminar, we will have an overview of relatively recent (2021-2022) approaches for masked image modeling (MIM). We will start with a brief history of self-supervised methods for images and then discuss different masking strategies, image-processing pipelines and what targets are suitable for masked modeling. We will consider BEiT, SimMIM, MAE, UM-MAE and MaskFeat.
Start time: 18:00