VarifocalNet (VFNet) learns to predict the IoU-aware classification score which mixes the object presence confidence and localization accuracy together as the detection score for a bounding box. The learning is supervised by the proposed Varifocal Loss (VFL), based on a new star-shaped bounding box feature representation (the features at nine yellow sampling points). Given the new representation, the object localization accuracy is further improved by refining the initially regressed bounding box. The full paper is available at: https://arxiv.org/abs/2008.13367.
Learning to Predict the IoU-aware Classification Score.
@article{zhang2020varifocalnet,
title={VarifocalNet: An IoU-aware Dense Object Detector},
author={Zhang, Haoyang and Wang, Ying and Dayoub, Feras and S{\"u}nderhauf, Niko},
journal={arXiv preprint arXiv:2008.13367},
year={2020}
}
Backbone | Style | DCN | MS train | Lr schd | Inf time (fps) | box AP (val) | box AP (test-dev) | Config | Download |
---|---|---|---|---|---|---|---|---|---|
R-50 | pytorch | N | N | 1x | - | 41.6 | 41.6 | config | model | log |
R-50 | pytorch | N | Y | 2x | - | 44.5 | 44.8 | config | model | log |
R-50 | pytorch | Y | Y | 2x | - | 47.8 | 48.0 | config | model | log |
R-101 | pytorch | N | N | 1x | - | 43.0 | 43.6 | config | model | log |
R-101 | pytorch | N | Y | 2x | - | 46.2 | 46.7 | config | model | log |
R-101 | pytorch | Y | Y | 2x | - | 49.0 | 49.2 | config | model | log |
X-101-32x4d | pytorch | Y | Y | 2x | - | 49.7 | 50.0 | config | model | log |
X-101-64x4d | pytorch | Y | Y | 2x | - | 50.4 | 50.8 | config | model | log |
Notes:
range
mode) and the inference scale keeps 1333x800.DCNv2
in both backbone and head.