ConViT- Improving Vision Transformers with Soft Convolutional Inductive Biases

International Conference on Machine Learning (ICML)


Convolutional architectures have proven extremely successful for vision tasks. Their hard inductive biases enable sample-efficient learning, but come at the cost of a potentially lower performance ceiling. Vision Transformers (ViTs) rely on more flexible self-attention layers, and have recently outperformed CNNs for image classification. However, they require costly pre-training on large external datasets or distillation from pretrained convolutional networks. In this paper, we ask the following question: is it possible to combine the strengths of these two architectures while avoiding their respective limitations? To this end, we introduce gated positional self-attention (GPSA), a form of positional self-attention which can be equipped with a “soft” convolutional inductive bias. We initialize the GPSA layers to mimic the locality of convolutional layers, then give each attention head the freedom to escape locality by adjusting a gating parameter regulating the attention paid to position versus content information. The resulting convolutional-like ViT architecture, ConViT, outperforms the DeiT on ImageNet, while offering a much improved sample efficiency. We further investigate the role of locality in learning by first quantifying how it is encouraged in vanilla self-attention layers, then analyzing how it is escaped in GPSA layers. We conclude by presenting various ablations to better understand the success of the ConViT. Our code and models are released publicly at:

Related Publications

All Publications

UAI - July 28, 2021

A Nonmyopic Approach to Cost-Constrained Bayesian Optimization

Eric Hans Lee, David Eriksson, Valerio Perrone, Matthias Seeger

ACM MM - October 20, 2021

EVRNet: Efficient Video Restoration on Edge Devices

Sachin Mehta, Amit Kumar, Fitsum Reda, Varun Nasery, Vikram Mulukutla, Rakesh Ranjan, Vikas Chandra

ICCV - October 11, 2021

Egocentric Pose Estimation from Human Vision Span

Hao Jiang, Vamsi Krishna Ithapu

TSE - June 29, 2021

Learning From Mistakes: Machine Learning Enhanced Human Expert Effort Estimates

Federica Sarro, Rebecca Moussa, Alessio Petrozziello, Mark Harman

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy