Publications (19)
Simple Open-Vocabulary Object Detection with Vision Transformers
Matthias Minderer, Alexey Gritsenko, Austin Stone +11
PaliGemma 2: A Family of Versatile VLMs for Transfer
Andreas Steiner, André Susano Pinto, Michael Tschannen +15
On Robustness and Transferability of Convolutional Neural Networks
Josip Djolonga, Jessica Yung, Michael Tschannen +11
Unsupervised Learning of Object Structure and Dynamics from Videos
Matthias Minderer, Chen Sun, Ruben Villegas +3
Scaling Vision Transformers to 22 Billion Parameters
Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39
FlexiViT: One Model for All Patch Sizes
Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov +7
Video OWL-ViT: Temporally-consistent open-world localization in video
Georg Heigold, Matthias Minderer, Alexey Gritsenko +5
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
Mostafa Dehghani, Basil Mustafa, Josip Djolonga +12
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov +9
PaLI-X: On Scaling up a Multilingual Vision and Language Model
Xi Chen, Josip Djolonga, Piotr Padlewski +40
Decoder Denoising Pretraining for Semantic Segmentation
Emmanuel Brempong Asiedu, Simon Kornblith, Ting Chen +3
SCENIC: A JAX Library for Computer Vision Research and Beyond
Mostafa Dehghani, Alexey Gritsenko, Anurag Arnab +2
Automatic Shortcut Removal for Self-Supervised Representation Learning
Matthias Minderer, Olivier Bachem, Neil Houlsby +1
Scaling Open-Vocabulary Object Detection
Matthias Minderer, Alexey Gritsenko, Neil Houlsby
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
Connor Schenck, Isaac Reid, Mithun George Jacob +19
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
Tim Salzmann, Markus Ryll, Alex Bewley +1
Improving fine-grained understanding in image-text pre-training
Ioana Bica, Anastasija IliÄ, Matthias Bauer +8
Revisiting the Calibration of Modern Neural Networks
Matthias Minderer, Josip Djolonga, Rob Romijnders +5
PaliGemma: A versatile 3B VLM for transfer
Lucas Beyer, Andreas Steiner, André Susano Pinto +32