End-to-End Object Detection with Fully Convolutional Network

2020/12/07 by Wang, Jianfeng, Song, Lin, Li, Zeming +3 · 2 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2012.03544

Abstract

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 .

Cited by

• Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
• A Dataset and Benchmark for Robotic Cloth Unfolding Grasp Selection: The ICRA 2024 Cloth Competition

Related

• Learning non-maximum suppression
• Object Detection Made Simpler by Eliminating Heuristic NMS
• A convnet for non-maximum suppression
• What Makes for End-to-End Object Detection?
• End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression