activity
20182024
most citedMLP-Mixer: An all-MLP Architecture for Vision

1.4k citations · 3k across the 32 of their papers we have counts for

collaborators
Showing 2021Show all

9 papers · 1 filter

cs.CV2021★ 12 cited

A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation

Wuyang Chen, Xianzhi Du, Fan Yang +8

This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive pe…

cs.CV2021★ 2 cited

LiT: Zero-Shot Transfer with Locked-image text Tuning

Xiaohua Zhai, Xiao Wang, Basil Mustafa +4

This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre-training. In our emp…

cs.CV2021★ 1.4k cited

MLP-Mixer: An all-MLP Architecture for Vision

Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov +9

Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this…

cs.CV2021★ 54 cited

How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

Andreas Steiner, Alexander Kolesnikov, Xiaohua Zhai +3

Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications, such as image classification, object detection and seman…

cs.LG2021★ 69 cited

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…

cs.CV2021★ 2 cited

Knowledge distillation: A good teacher is patient and consistent

Lucas Beyer, Xiaohua Zhai, Amélie Royer +3

There is a growing discrepancy in computer vision between large-scale models that achieve state-of-the-art performance and models that are affordable in practical applications. In…