Improving the Efficiency-Accuracy Trade-off of DETR-Style Models in Practice

Yumin Suh,Dongwan Kim,Abhishek Aich,Samuel Schulter,Jong-Chyi Su,Bohyung Han,Manmohan Chandraker; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 8027-8031

Abstract


We aim to provide a comprehensive view of the inference efficiency of DETR-style detection models. We explore the effect of basic efficiency techniques and identify the factors that are easy to implement yet effectively improve the efficiency-accuracy trade-off. Specifically we investigate the effect of input resolution multi-scale feature enhancement and backbone pre-training. Our experiments support that 1) adjusting the input resolution is a simple yet effective way to achieve a better efficiency-accuracy trade-off. 2) Multi-scale feature enhancement can be lightened with a marginal decrease in accuracy and 3) improved backbone pre-training can further improve the trade-off.

Related Material


[pdf]
[bibtex]
@InProceedings{Suh_2024_CVPR, author = {Suh, Yumin and Kim, Dongwan and Aich, Abhishek and Schulter, Samuel and Su, Jong-Chyi and Han, Bohyung and Chandraker, Manmohan}, title = {Improving the Efficiency-Accuracy Trade-off of DETR-Style Models in Practice}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8027-8031} }