Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PolyViT: Co-training Vision Transformers on Images, Videos and Audio

About

Can we train a single transformer model capable of processing multiple modalities and datasets, whilst sharing almost all of its learnable parameters? We present PolyViT, a model trained on image, audio and video which answers this question. By co-training different tasks on a single modality, we are able to improve the accuracy of each individual task and achieve state-of-the-art results on 5 standard video- and audio-classification datasets. Co-training PolyViT on multiple modalities and tasks leads to a model that is even more parameter-efficient, and learns representations that generalize across multiple domains. Moreover, we show that co-training is simple and practical to implement, as we do not need to tune hyperparameters for each combination of datasets, but can simply adapt those from standard, single-task training.

Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller, Mostafa Dehghani• 2021

Related benchmarks

TaskDatasetResultRank
Action RecognitionKinetics-400
Top-1 Acc82.4
447
Audio ClassificationVGG-Sound
Top-1 Accuracy0.517
83
Action RecognitionMoments in Time
Top-1 Accuracy38.6
53
Audio-Visual ClassificationVGGSound--
33
Showing 4 of 4 rows

Other info

Follow for update