Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

End-to-End Object Detection with Fully Convolutional Network

About

Mainstream object detectors based on the fully convolutional network has achieved impressive performance. While most of them still need a hand-designed non-maximum suppression (NMS) post-processing, which impedes fully end-to-end training. In this paper, we give the analysis of discarding NMS, where the results reveal that a proper label assignment plays a crucial role. To this end, for fully convolutional detectors, we introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection, which obtains comparable performance with NMS. Besides, a simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region. With these techniques, our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets. The code is available at https://github.com/Megvii-BaseDetection/DeFCN .

Jianfeng Wang, Lin Song, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng• 2020

Related benchmarks

TaskDatasetResultRank
Object DetectionCOCO 2017 (val)
AP41.4
2454
Object DetectionCOCO (val)--
613
Instance SegmentationCOCO (val)
APmk36.1
472
Object DetectionCrowdHuman (val)
AP89.2
52
Lesion DetectionCVA-BUS high-quality labels re-annotated version
Pr@8081.5
16
Showing 5 of 5 rows

Other info

Follow for update