activity
20162023
most citedScaling Vision Transformers to 22 Billion Parameters

118 citations · 267 across the 13 of their papers we have counts for

collaborators

10 papers

cs.CV202339 cited

PaLI-X: On Scaling up a Multilingual Vision and Language Model

Xi Chen, Josip Djolonga, Piotr Padlewski +40

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training t…

cs.CV20233 cited

End-to-End Spatio-Temporal Action Localisation with Video Transformers

Alexey Gritsenko, Xuehan Xiong, Josip Djolonga +5

The most performant spatio-temporal action localisation models use external person proposals and complex external memory banks. We propose a fully end-to-end, purely-transformer ba…

cs.LG20221 cited

Intersection of Parallels as an Early Stopping Criterion

Ali Vardasbi, Maarten de Rijke, Mostafa Dehghani

A common way to avoid overfitting in supervised learning is early stopping, where a held-out set is used for iterative evaluation during training to find a sweet spot in the number…

cs.LG202211 cited

Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?

Yi Tay, Mostafa Dehghani, Samira Abnar +7

There have been a lot of interest in the scaling properties of Transformer models. However, not much has been done on the front of investigating the effect of scaling properties of…

cs.CV20224 cited

Beyond Transfer Learning: Co-finetuning for Action Localisation

Anurag Arnab, Xuehan Xiong, Alexey Gritsenko +6

Transfer learning is the predominant paradigm for training deep networks on small target datasets. Models are typically pretrained on large ``upstream'' datasets for classification…

cs.CL202240 cited

Confident Adaptive Language Modeling

Tal Schuster, Adam Fisch, Jai Gupta +5

Recent advances in Transformer-based large language models (LLMs) have led to significant performance improvements across many tasks. These gains come with a drastic increase in th…