A
Andreas Steiner
Researcher at Google
Publications - 4
Citations - 167
Andreas Steiner is an academic researcher from Google. The author has contributed to research in topics: Contextual image classification & Computer science. The author has an hindex of 2, co-authored 4 publications receiving 148 citations.
Papers
More filters
Posted Content
MLP-Mixer: An all-MLP Architecture for Vision
Ilya Tolstikhin,Neil Houlsby,Alexander Kolesnikov,Lucas Beyer,Xiaohua Zhai,Thomas Unterthiner,Jessica Yung,Andreas Steiner,Daniel Keysers,Jakob Uszkoreit,Mario Lucic,Alexey Dosovitskiy +11 more
TL;DR: MLP-Mixer as discussed by the authors is an architecture based exclusively on multi-layer perceptrons (MLP), which contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with LSTM applied across patches, and it achieves competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-theart models.
Posted Content
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers.
TL;DR: In this paper, the authors conduct a systematic empirical study in order to understand the interplay between the amount of training data, AugReg, model size and compute budget, and find that the combination of increased compute and AugReg can yield models with the same performance as models trained on an order of magnitude more training data.
Posted Content
LiT: Zero-Shot Transfer with Locked-image Text Tuning
Xiaohua Zhai,Xiao Wang,Basil Mustafa,Andreas Steiner,Daniel Keysers,Alexander Kolesnikov,Lucas Beyer +6 more
TL;DR: LiT-tuning as mentioned in this paper aligns image and text models while still taking advantage of their pre-training using contrastive training to achieve zero-shot transfer to new vision tasks.
Proceedings Article
MLP-Mixer: An all-MLP Architecture for Vision
Ilya Tolstikhin,Neil Houlsby,Alexander Kolesnikov,Lucas Beyer,Xiaohua Zhai,Thomas Unterthiner,Jessica Yung,Andreas Steiner,Daniel Keysers,Jakob Uszkoreit,Mario Lucic,Alexey Dosovitskiy +11 more
TL;DR: MLP-Mixer as mentioned in this paper is an architecture based exclusively on multi-layer perceptrons (MLP), which contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with LSTM applied across patches, and it achieves competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-theart models.