118 citations · 140 across the 4 of their papers we have counts for
4 papers
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
Ibrahim Alabdulmohsin, Xiao Wang, Andreas Steiner +3
We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffir…
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
Mostafa Dehghani, Basil Mustafa, Josip Djolonga +12
The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challeng…
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision
Lucas Beyer, Bo Wan, Gagan Madan +9
There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a T…
Scaling Vision Transformers to 22 Billion Parameters
Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…