# Soft Anchor-Point Object Detection

arXiv: https://arxiv.org/abs/1911.12448 · HTML: https://mlsanity.com/paper/1911.12448/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2019.

## Built on by (most cited first, 30 of 42)

- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [SiamMOT: Siamese Multi-Object Tracking](https://mlsanity.com/paper/2105.11595/) (2021)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation](https://mlsanity.com/paper/2108.07482/) (2021)
- [A Dual Weighting Label Assignment Scheme for Object Detection](https://mlsanity.com/paper/2203.09730/) (2022)
- [IQDet: Instance-wise Quality Distribution Sampling for Object Detection](https://mlsanity.com/paper/2104.06936/) (2021)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Enhanced Training of Query-Based Object Detection via Selective Query Recollection](https://mlsanity.com/paper/2212.07593/) (2022)
- [Open-Set Semi-Supervised Object Detection](https://mlsanity.com/paper/2208.13722/) (2022)
- [Prediction-Guided Distillation for Dense Object Detection](https://mlsanity.com/paper/2203.05469/) (2022)
- [A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance](https://mlsanity.com/paper/2207.12926/) (2022)
- [Mutual Supervision for Dense Object Detection](https://mlsanity.com/paper/2109.05986/) (2021)
- [Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields](https://mlsanity.com/paper/2206.04669/) (2022)
- [CenterNet++ for Object Detection](https://mlsanity.com/paper/2204.08394/) (2022)
- [Location-Sensitive Visual Recognition with Cross-IOU Loss](https://mlsanity.com/paper/2104.04899/) (2021)
- [Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images](https://mlsanity.com/paper/2112.06701/) (2021)
- [Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs](https://mlsanity.com/paper/2201.09396/) (2022)
- [PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling](https://mlsanity.com/paper/2104.13876/) (2021)
- [RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection](https://mlsanity.com/paper/2110.12130/) (2021)
- [Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection](https://mlsanity.com/paper/2104.14082/) (2021)
- [Unitail: Detecting, Reading, and Matching in Retail Scene](https://mlsanity.com/paper/2204.00298/) (2022)
- [Team DETR: Guide Queries as a Professional Team in Detection Transformers](https://mlsanity.com/paper/2302.07116/) (2023)
- [DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation](https://mlsanity.com/paper/2312.13735/) (2023)

## Abstract (arXiv)

Recently, anchor-free detection methods have been through great progress. The major two families, anchor-point detection and key-point detection, are at opposite edges of the speed-accuracy trade-off, with anchor-point detectors having the speed advantage. In this work, we boost the performance of the anchor-point detector over the key-point counterparts while maintaining the speed advantage. To achieve this, we formulate the detection problem from the anchor point's perspective and identify ineffective training as the main problem. Our key insight is that anchor points should be optimized jointly as a group both within and across feature pyramid levels. We propose a simple yet effective training strategy with soft-weighted anchor points and soft-selected pyramid levels to address the false attention issue within each pyramid level and the feature selection issue across all the pyramid levels, respectively. To evaluate the effectiveness, we train a single-stage anchor-free detector called Soft Anchor-Point Detector (SAPD). Experiments show that our concise SAPD pushes the envelope of speed/accuracy trade-off to a new level, outperforming recent state-of-the-art anchor-free and anchor-based detectors. Without bells and whistles, our best model can achieve a single-model single-scale AP of 47.4% on COCO.