pith. sign in

arxiv: 2202.10784 · v1 · pith:BECYITBFnew · submitted 2022-02-22 · 💻 cs.CV · cs.AI

RuCLIP -- new models and experiments: a technical report

Alex Shonenkov , Andrey Kuznetsov , Denis Dimitrov , Tatyana Shavrina , Daniil Chesakov , Anastasia Maltseva , Alena Fenogenova , Igor Pavlov
show 5 more authors
Anton Emelyanov Sergey Markov Daria Bakshandaeva Vera Shybaeva Andrey Chertok
This is my paper
classification 💻 cs.CV cs.AI
keywords reportimplementationsclipdatasetsexperimentsmodelopus-mtruclip
0
0 comments X
read the original abstract

In the report we propose six new implementations of ruCLIP model trained on our 240M pairs. The accuracy results are compared with original CLIP model with Ru-En translation (OPUS-MT) on 16 datasets from different domains. Our best implementations outperform CLIP + OPUS-MT solution on most of the datasets in few-show and zero-shot tasks. In the report we briefly describe the implementations and concentrate on the conducted experiments. Inference execution time comparison is also presented in the report.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.