Label-Free Synthetic Pretraining of Object Detectors

Hei Law, Jia Deng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID"approach consists of two main components: (1) generating synthetic images using a collection of unlabelled 3D models with optimized scene arrangement; (2) pretraining an object detector on "instance detection"task - given a query image depicting an object, detecting all instances of the exact same object in a target image. Our approach does not need any semantic labels for pretraining and allows the use of arbitrary, diverse 3D models. Experiments on COCO show that with optimized data generation and a proper pretraining task, synthetic data can be highly effective data for pretraining object detectors. In particular, pretraining on rendered images achieves performance competitive with pretraining on real images while using significantly less computing resources. Code is available at https://github.com/princeton-vl/SOLID.

Original languageEnglish (US)
Title of host publicationProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages935-945
Number of pages11
ISBN (Electronic)9798350318920
DOIs
StatePublished - 2024
Event2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 - Waikoloa, United States
Duration: Jan 4 2024Jan 8 2024

Publication series

NameProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024

Conference

Conference2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
Country/TerritoryUnited States
CityWaikoloa
Period1/4/241/8/24

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Keywords

  • Algorithms
  • Image recognition and understanding

Fingerprint

Dive into the research topics of 'Label-Free Synthetic Pretraining of Object Detectors'. Together they form a unique fingerprint.

Cite this