Kandinsky 3.0 Technical Report

1 code implementation • 6 Dec 2023 • Vladimir Arkhipkin, Andrei Filatov, Viacheslav Vasilev, Anastasia Maltseva, Said Azizov, Igor Pavlov, Julia Agafonova, Andrey Kuznetsov, Denis Dimitrov

We focus on the key components that, as we have identified as a result of a large number of experiments, had the most significant impact on improving the quality of our model compared to the others.

Text-to-Image Generation

Task Discovery: Finding the Tasks that Neural Networks Generalize on

no code implementations • 1 Dec 2022 • Andrei Atanov, Andrei Filatov, Teresa Yeo, Ajay Sohmshetty, Amir Zamir

An intriguing question would be: what if, instead of fixing the task and searching in the model space, we fix the model and search in the task space?

Simple Control Baselines for Evaluating Transfer Learning

no code implementations • 7 Feb 2022 • Andrei Atanov, Shijian Xu, Onur Beker, Andrei Filatov, Amir Zamir

Transfer learning has witnessed remarkable progress in recent years, for example, with the introduction of augmentation-based contrastive self-supervised learning methods.

Image Classification Self-Supervised Learning +1