no code implementations • 28 Mar 2024 • Bo Wan, Michael Tschannen, Yongqin Xian, Filip Pavetic, Ibrahim Alabdulmohsin, Xiao Wang, André Susano Pinto, Andreas Steiner, Lucas Beyer, Xiaohua Zhai
In this paper, we propose a simple visual pretraining method with location-aware captioners (LocCa).
1 code implementation • 30 Mar 2023 • Lucas Beyer, Bo Wan, Gagan Madan, Filip Pavetic, Andreas Steiner, Alexander Kolesnikov, André Susano Pinto, Emanuele Bugliarello, Xiao Wang, Qihang Yu, Liang-Chieh Chen, Xiaohua Zhai
A key finding is that a small decoder learned on top of a frozen pretrained encoder works surprisingly well.
1 code implementation • 16 Feb 2023 • André Susano Pinto, Alexander Kolesnikov, Yuge Shi, Lucas Beyer, Xiaohua Zhai
Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models.
1 code implementation • 20 May 2022 • Alexander Kolesnikov, André Susano Pinto, Lucas Beyer, Xiaohua Zhai, Jeremiah Harmsen, Neil Houlsby
We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks.
1 code implementation • 24 Feb 2022 • Cedric Renggli, André Susano Pinto, Neil Houlsby, Basil Mustafa, Joan Puigcerver, Carlos Riquelme
Transformers are widely applied to solve natural language understanding and computer vision tasks.
1 code implementation • NeurIPS 2021 • Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, André Susano Pinto, Daniel Keysers, Neil Houlsby
We present a Vision MoE (V-MoE), a sparse version of the Vision Transformer, that is scalable and competitive with the largest dense networks.
Ranked #1 on Few-Shot Image Classification on ImageNet - 5-shot
no code implementations • 14 Oct 2020 • Basil Mustafa, Carlos Riquelme, Joan Puigcerver, André Susano Pinto, Daniel Keysers, Neil Houlsby
In the low-data regime, it is difficult to train good supervised models from scratch.
Ranked #6 on Image Classification on VTAB-1k (using extra training data)
no code implementations • CVPR 2022 • Cedric Renggli, André Susano Pinto, Luka Rimanic, Joan Puigcerver, Carlos Riquelme, Ce Zhang, Mario Lucic
Transfer learning has been recently popularized as a data-efficient alternative to training models from scratch, in particular for computer vision tasks where it provides a remarkably solid baseline.
no code implementations • 30 Sep 2020 • Maxim Neumann, André Susano Pinto, Xiaohua Zhai, Neil Houlsby
Automatically finding good and general remote sensing representations allows to perform transfer learning on a wide range of applications - improving the accuracy and reducing the required number of training samples.
no code implementations • ICLR 2021 • Joan Puigcerver, Carlos Riquelme, Basil Mustafa, Cedric Renggli, André Susano Pinto, Sylvain Gelly, Daniel Keysers, Neil Houlsby
We explore the use of expert representations for transfer with a simple, yet effective, strategy.
Ranked #11 on Image Classification on VTAB-1k (using extra training data)