Paper Info
Title
Simple Open-Vocabulary Object Detection.
Abstract
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling properties of this setup shows that increasing image-level pre-training and model size yield consistent improvements on the downstream detection task. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection. Code and models are available on GitHub github.com/google-research/scenic/tree/main/scenic/projects/owl_vit.
Year
DOI
Venue
2022
10.1007/978-3-031-20080-9_42
European Conference on Computer Vision
Keywords
DocType
Citations 
Open-vocabulary detection,Transformer,Vision transformer,Zero-shot detection,Image-conditioned detection,One-shot object detection,Contrastive learning,Image-text models,Foundation models,CLIP
Conference
0
PageRank 
References 
Authors
0.34
0
14
Name
Order
Citations
PageRank
Minderer Matthias100.68
Gritsenko Alexey200.34
Stone Austin300.34
Neumann Maxim400.34
Weissenborn Dirk500.34
Alexey Dosovitskiy6179780.48
Mahendran Aravindh700.34
Arnab Anurag800.34
Dehghani Mostafa900.34
Shen Zhuoran1000.34
Wang Xiao1100.34
Xiaohua Zhai1220913.00
Kipf Thomas1300.34
Neil Houlsby1415314.73