# End-to-End Object Detection with Fully Convolutional Network

arXiv: https://arxiv.org/abs/2012.03544 · HTML: https://mlsanity.com/paper/2012.03544/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 30 of 70)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [DETRs with Hybrid Matching](https://mlsanity.com/paper/2207.13080/) (2022)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)
- [Rethinking Efficient Lane Detection via Curve Modeling](https://mlsanity.com/paper/2203.02431/) (2022)
- [Dense Distinct Query for End-to-End Object Detection](https://mlsanity.com/paper/2303.12776/) (2023)
- [Sparse Instance Activation for Real-Time Instance Segmentation](https://mlsanity.com/paper/2203.12827/) (2022)
- [ISTR: End-to-End Instance Segmentation with Transformers](https://mlsanity.com/paper/2105.00637/) (2021)
- [Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance](https://mlsanity.com/paper/2402.08680/) (2024)
- [Instance-Conditional Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2110.12724/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [Meta-Adapter: An Online Few-shot Learner for Vision-Language Model](https://mlsanity.com/paper/2311.03774/) (2023)
- [Anchor DETR: Query Design for Transformer-Based Object Detection](https://mlsanity.com/paper/2109.07107/) (2021)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)
- [LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.05291/) (2021)
- [Dynamic Grained Encoder for Vision Transformers](https://mlsanity.com/paper/2301.03831/) (2023)
- [ConQueR: Query Contrast Voxel-DETR for 3D Object Detection](https://mlsanity.com/paper/2212.07289/) (2022)
- [IQDet: Instance-wise Quality Distribution Sampling for Object Detection](https://mlsanity.com/paper/2104.06936/) (2021)
- [LGD: Label-guided Self-distillation for Object Detection](https://mlsanity.com/paper/2109.11496/) (2021)
- [Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2212.05505/) (2022)

## Abstract (arXiv)

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 .