# MetaAnchor: Learning to Detect Objects with Customized Anchors

arXiv: https://arxiv.org/abs/1807.00980 · HTML: https://mlsanity.com/paper/1807.00980/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2018.

## Built on by (most cited first, 21 of 21)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [AdaMixer: A Fast-Converging Query-Based Object Detector](https://mlsanity.com/paper/2203.16507/) (2022)
- [Image Synthesis via Semantic Composition](https://mlsanity.com/paper/2109.07053/) (2021)
- [Towards Data-Efficient Detection Transformers](https://mlsanity.com/paper/2203.09507/) (2022)
- [Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning](https://mlsanity.com/paper/2104.02230/) (2021)
- [Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images](https://mlsanity.com/paper/2112.06701/) (2021)
- [Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection](https://mlsanity.com/paper/2210.02368/) (2022)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)
- [Anchor Pruning for Object Detection](https://mlsanity.com/paper/2104.00432/) (2021)
- [Plot2Spectra: an Automatic Spectra Extraction Tool](https://mlsanity.com/paper/2107.02827/) (2021)
- [Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation](https://mlsanity.com/paper/2110.09734/) (2021)
- [Revisiting the Loss Weight Adjustment in Object Detection](https://mlsanity.com/paper/2103.09488/) (2021)
- [ROIFormer: Semantic-Aware Region of Interest Transformer for Efficient Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.05729/) (2022)
- [ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation](https://mlsanity.com/paper/2302.09765/) (2023)
- [Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections](https://mlsanity.com/paper/2105.03139/) (2021)
- [Density-based Object Detection in Crowded Scenes](https://mlsanity.com/paper/2504.09819/) (2025)
- [RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection](https://mlsanity.com/paper/2102.04582/) (2021)
- [Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection](https://mlsanity.com/paper/2103.10091/) (2021)
- [Metric-aligned Sample Selection and Critical Feature Sampling for Oriented Object Detection](https://mlsanity.com/paper/2306.16718/) (2023)
- [PESFormer: Boosting Macro- and Micro-expression Spotting with Direct Timestamp Encoding](https://mlsanity.com/paper/2410.18695/) (2024)

## Abstract (arXiv)

We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnchor anchor functions could be dynamically generated from the arbitrary customized prior boxes. Taking advantage of weight prediction, MetaAnchor is able to work with most of the anchor-based object detection systems such as RetinaNet. Compared with the predefined anchor scheme, we empirically find that MetaAnchor is more robust to anchor settings and bounding box distributions; in addition, it also shows the potential on transfer tasks. Our experiment on COCO detection task shows that MetaAnchor consistently outperforms the counterparts in various scenarios.