research
∙
05/26/2023
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
We introduce Three Towers (3T), a flexible method to improve the contras...
share
research
∙
05/22/2023
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
Scaling laws have been recently employed to derive compute-optimal model...
research
∙
03/30/2023
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision
There has been a recent explosion of computer vision models which perfor...
research
∙
03/27/2023
Sigmoid Loss for Language Image Pre-Training
We propose a simple pairwise sigmoid loss for image-text pre-training. U...
research
∙
02/16/2023
Tuning computer vision models with task rewards
Misalignment between model predictions and intended usage can be detrime...
research
∙
12/15/2022
FlexiViT: One Model for All Patch Sizes
Vision Transformers convert images to sequences by slicing them into pat...
research
∙
09/14/2022
PaLI: A Jointly-Scaled Multilingual Language-Image Model
Effective scaling and a flexible task interface enable large language mo...
research
∙
09/13/2022
Revisiting Neural Scaling Laws in Language and Vision
The remarkable progress in deep learning in recent years is largely driv...
research
∙
05/20/2022
UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes
We introduce UViM, a unified approach capable of modeling a wide range o...
research
∙
05/03/2022
Better plain ViT baselines for ImageNet-1k
It is commonly accepted that the Vision Transformer model requires sophi...
research
∙
12/17/2021
A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation
This work presents a simple vision transformer design as a strong baseli...
research
∙
11/15/2021
LiT: Zero-Shot Transfer with Locked-image Text Tuning
This paper presents contrastive-tuning, a simple method employing contra...
research
∙
06/18/2021
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Vision Transformers (ViT) have been shown to attain highly competitive p...
research
∙
06/15/2021
Revisiting the Calibration of Modern Neural Networks
Accurate estimation of predictive uncertainty (model calibration) is ess...
research
∙
06/09/2021
Knowledge distillation: A good teacher is patient and consistent
There is a growing discrepancy in computer vision between large-scale mo...
research
∙
06/08/2021
Scaling Vision Transformers
Attention-based neural networks such as the Vision Transformer (ViT) hav...
research
∙
05/04/2021
MLP-Mixer: An all-MLP Architecture for Vision
Convolutional Neural Networks (CNNs) are the go-to model for computer vi...
research
∙
04/09/2021
SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size
Before deploying machine learning models it is critical to assess their ...
research
∙
04/06/2021
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
Meta and transfer learning are two successful families of approaches to ...
research
∙
11/06/2020
Underspecification Presents Challenges for Credibility in Modern Machine Learning
ML models often exhibit unexpectedly poor behavior when they are deploye...
research
∙
10/22/2020
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
While the Transformer architecture has become the de-facto standard for ...
research
∙
09/30/2020
Training general representations for remote sensing using in-domain knowledge
Automatically finding good and general remote sensing representations al...
research
∙
07/16/2020
On Robustness and Transferability of Convolutional Neural Networks
Modern deep convolutional networks (CNNs) are often criticized for not g...
research
∙
06/12/2020
Are we done with ImageNet?
Yes, and no. We ask whether recent progress on the ImageNet classificati...
research
∙
12/24/2019
Large Scale Learning of General Visual Representations for Transfer
Transfer of pre-trained representations improves sample efficiency and s...
research
∙
11/15/2019
In-domain representation learning for remote sensing
Given the importance of remote sensing, surprisingly little attention ha...
research
∙
05/09/2019
S^4L: Self-Supervised Semi-Supervised Learning
This work tackles the problem of semi-supervised learning of image class...
research
∙
03/06/2019
High-Fidelity Image Generation With Fewer Labels
Deep generative models are becoming a cornerstone of modern machine lear...
research
∙
01/25/2019
Revisiting Self-Supervised Visual Representation Learning
Unsupervised visual representation learning remains a largely unsolved p...
research
∙
11/27/2018
Self-Supervised Generative Adversarial Networks
Conditional GANs are at the forefront of natural image synthesis. The ma...
research
∙
10/27/2018
Self-Supervised GAN to Counter Forgetting
GANs involve training two networks in an adversarial game, where each ne...
research
∙
07/12/2018
The GAN Landscape: Losses, Architectures, Regularization, and Normalization
Generative Adversarial Networks (GANs) are a class of deep generative mo...
research
∙
03/29/2018