TY - GEN
T1 - Label-Free Synthetic Pretraining of Object Detectors
AU - Law, Hei
AU - Deng, Jia
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/1/3
Y1 - 2024/1/3
N2 - 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.
AB - 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.
KW - Algorithms
KW - Image recognition and understanding
UR - http://www.scopus.com/inward/record.url?scp=85191944090&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85191944090&partnerID=8YFLogxK
U2 - 10.1109/WACV57701.2024.00099
DO - 10.1109/WACV57701.2024.00099
M3 - Conference contribution
AN - SCOPUS:85191944090
T3 - Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
SP - 935
EP - 945
BT - Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
Y2 - 4 January 2024 through 8 January 2024
ER -