You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

Abstract

Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure? To answer this question, we present You Only Look at One Sequence (YOLOS), a series of object detection models based on the vanilla Vision Transformer with the fewest possible modifications, region priors, as well as inductive biases of the target task. We find that YOLOS pre-trained on the mid-sized ImageNet-1k dataset only can already achieve quite competitive performance on the challenging COCO object detection benchmark, e.g., YOLOS-Base directly adopted from BERT-Base architecture can obtain 42.0 box AP on COCO val. We also discuss the impacts as well as limitations of current pre-train schemes and model scaling strategies for Transformer in vision through YOLOS. Code and pre-trained models are available at https://github.com/hustvl/YOLOS.

NeurIPS 2021 Camera Ready

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Visual Models From Natural Language Supervision
• Language Models are Few-Shot Learners
• GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
• Toward Transformer-Based Object Detection
• Scaled-YOLOv4: Scaling Cross Stage Partial Network
• Learning Deep Transformer Models for Machine Translation

Cited by in corpus (2)

• Tracking Instances as Queries
• Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads