Intermediate-depth ResNet backbones in RT-DETR maintain near-perfect accuracy for round objects under lighting or background shifts, with ResNet50 best for illumination changes and ResNet34 best for background changes.
Proceedings of the 32nd International Conference on Machine Learning (ICML) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking ResNet Backbones in RT-DETR: Impact of Depth and Regularization under environmental conditions
Intermediate-depth ResNet backbones in RT-DETR maintain near-perfect accuracy for round objects under lighting or background shifts, with ResNet50 best for illumination changes and ResNet34 best for background changes.