22k citations · 22.5k across the 18 of their papers we have counts for
19 papers
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
Connor Schenck, Isaac Reid, Mithun George Jacob +19
We introduce STRING: Separable Translationally Invariant Position Encodings. STRING extends Rotary Position Encodings, a recently proposed and widely used algorithm in large langua…
PaliGemma 2: A Family of Versatile VLMs for Transfer
Andreas Steiner, André Susano Pinto, Michael Tschannen +15
PaliGemma 2 is an upgrade of the PaliGemma open Vision-Language Model (VLM) based on the Gemma 2 family of language models. We combine the SigLIP-So400m vision encoder that was als…
PaliGemma: A versatile 3B VLM for transfer
Lucas Beyer, Andreas Steiner, André Susano Pinto +32
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly know…
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
Tim Salzmann, Markus Ryll, Alex Bewley +1
Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to ex…
Improving fine-grained understanding in image-text pre-training
Ioana Bica, Anastasija Ilić, Matthias Bauer +8
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs. Given that multi…
Video OWL-ViT: Temporally-consistent open-world localization in video
Georg Heigold, Matthias Minderer, Alexey Gritsenko +5
We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being const…
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…
Scaling Open-Vocabulary Object Detection
Matthias Minderer, Alexey Gritsenko, Neil Houlsby
Open-vocabulary object detection has benefited greatly from pretrained vision-language models, but is still limited by the amount of available detection training data. While detect…
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…
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…
FlexiViT: One Model for All Patch Sizes
Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov +7
Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher a…
Decoder Denoising Pretraining for Semantic Segmentation
Emmanuel Brempong Asiedu, Simon Kornblith, Ting Chen +3
Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the…
Simple Open-Vocabulary Object Detection with Vision Transformers
Matthias Minderer, Alexey Gritsenko, Austin Stone +11
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are…
SCENIC: A JAX Library for Computer Vision Research and Beyond
Mostafa Dehghani, Alexey Gritsenko, Anurag Arnab +2
Scenic is an open-source JAX library with a focus on Transformer-based models for computer vision research and beyond. The goal of this toolkit is to facilitate rapid experimentati…
Revisiting the Calibration of Modern Neural Networks
Matthias Minderer, Josip Djolonga, Rob Romijnders +5
Accurate estimation of predictive uncertainty (model calibration) is essential for the safe application of neural networks. Many instances of miscalibration in modern neural networ…
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov +9
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention…
On Robustness and Transferability of Convolutional Neural Networks
Josip Djolonga, Jessica Yung, Michael Tschannen +11
Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. However, several recent breakthroughs in transfer learning suggest…
Automatic Shortcut Removal for Self-Supervised Representation Learning
Matthias Minderer, Olivier Bachem, Neil Houlsby +1
In self-supervised visual representation learning, a feature extractor is trained on a "pretext task" for which labels can be generated cheaply, without human annotation. A central…
HNCcorr: A Novel Combinatorial Approach for Cell Identification in Calcium-Imaging Movies
Quico Spaen, Dorit S. Hochbaum, Roberto Asín-Achá
Calcium imaging has emerged as a workhorse method in neuroscience to investigate patterns of neuronal activity. Instrumentation to acquire calcium imaging movies has rapidly progre…