PyTorch Implementation for Our Paper: "Object Detection Made Simpler by Eliminating Heuristic NMS"
- Python 3.7
- PyTorch 1.5.1
- mmdetectoin
The code is being submitted to the company for open source review.
Model | Backbone | lr sched | mAP (COCO2017 val) | link |
---|---|---|---|---|
FCOS | R50 | 3x | 42.0 | model |
ATSS | R50 | 3x | 42.8 | model |
FCOSpss | R50 | 3x | 42.3 | |
ATSSpss | R50 | 3x | 42.6 | |
VFNETpss | R50 | 3x | 44.0 | |
FCOSpss | R101 | 3x | 44.1 | |
ATSSpss | R101 | 3x | 44.2 | |
VFNETpss | R101 | 3x | 45.7 | |
FCOSpss | X-101-DCN | 2x | 47.0 | |
ATSSpss | X-101-DCN | 2x | 47.3 | |
VFNETpss | X-101-DCN | 2x | 49.3 | |
FCOSpss | R2N-101-DCN | 2x | 48.2 | |
ATSSpss | R2N-101-DCN | 2x | 48.6 | |
VFNETpss | R2N-101-DCN | 2x | 50.0 |
NOTE: All models are trained with multi-scale training schedule of ‘[480, 800]
If we have a pretrained model, only finetuning the PSS head can save the training time.
Model | Backbone | MS Training | lr sched | mAP pretrain model (w NMS) |
mAP finetuned PSS (w/o NMS) |
---|---|---|---|---|---|
GFocalV2pss | R50 | Yes | 12 | 43.9 | 43.3 |
GFocalV2pss | X-101-32x4d-DCN | Yes | 12 | 48.8 | 48.2 |
GFocalV2pss | R2N-101-DCN | Yes | 12 | 49.9 | 49.2 |
Model | Backbone | lr sched | bbox mAP | segm mAP | link |
---|---|---|---|---|---|
CondInst | R50 | 3x | 41.9 | 37.5 | |
CondInstpss | R50 | 3x | 41.2 | 36.7 | |
CondInst + sem | R50 | 3x | 42.6 | 38.2 | |
CondInstpss + sem | R50 | 3x | 42.3 | 37.7 | |
CondInst | R101 | 3x | 43.3 | 38.6 | |
CondInstpss | R101 | 3x | 43.1 | 38.2 | |
CondInst + sem | R101 | 3x | 44.6 | 39.8 | |
CondInstpss + sem | R101 | 3x | 44.1 | 39.3 |
NOTE: All models are trained with multi-scale training schedule of ‘[640, 800]
If you use the package in your research, please cite our paper:
@misc{zhou2021object,
title={Object Detection Made Simpler by Eliminating Heuristic NMS},
author={Qiang Zhou and Chaohui Yu and Chunhua Shen and Zhibin Wang and Hao Li},
year={2021},
eprint={2101.11782},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
团队长期招聘中,社招/实习/校招,我们都要 !
欢迎投递简历,邮箱: [email protected]