# FoveaBox: Beyond Anchor-based Object Detector

arXiv: https://arxiv.org/abs/1904.03797 · HTML: https://mlsanity.com/paper/1904.03797/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 30 of 37)

- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond](https://mlsanity.com/paper/2105.02184/) (2021)
- [Learning to Track Instances without Video Annotations](https://mlsanity.com/paper/2104.00287/) (2021)
- [Enhanced Training of Query-Based Object Detection via Selective Query Recollection](https://mlsanity.com/paper/2212.07593/) (2022)
- [RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection](https://mlsanity.com/paper/2109.11906/) (2021)
- [PointInst3D: Segmenting 3D Instances by Points](https://mlsanity.com/paper/2204.11402/) (2022)
- [Lymph Node Detection in T2 MRI with Transformers](https://mlsanity.com/paper/2111.04885/) (2021)
- [A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey](https://mlsanity.com/paper/2208.10895/) (2022)
- [Bringing Generalization to Deep Multi-View Pedestrian Detection](https://mlsanity.com/paper/2109.12227/) (2021)
- [Universal Lesion Detection in CT Scans using Neural Network Ensembles](https://mlsanity.com/paper/2111.04886/) (2021)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries](https://mlsanity.com/paper/2110.12555/) (2021)
- [A Survey and Evaluation of Adversarial Attacks for Object Detection](https://mlsanity.com/paper/2408.01934/) (2024)
- [Object Detection Made Simpler by Eliminating Heuristic NMS](https://mlsanity.com/paper/2101.11782/) (2021)
- [CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement](https://mlsanity.com/paper/2103.07017/) (2021)
- [NAS-FCOS: Efficient Search for Object Detection Architectures](https://mlsanity.com/paper/2110.12423/) (2021)
- [Scale Normalized Image Pyramids with AutoFocus for Object Detection](https://mlsanity.com/paper/2102.05646/) (2021)
- [PAFNet: An Efficient Anchor-Free Object Detector Guidance](https://mlsanity.com/paper/2104.13534/) (2021)
- [DSLA: Dynamic smooth label assignment for efficient anchor-free object detection](https://mlsanity.com/paper/2208.00817/) (2022)
- [Visual Fault Detection of Multi-scale Key Components in Freight Trains](https://mlsanity.com/paper/2211.14522/) (2022)
- [Balanced Classification: A Unified Framework for Long-Tailed Object Detection](https://mlsanity.com/paper/2308.02213/) (2023)
- [DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection](https://mlsanity.com/paper/2109.06148/) (2021)
- [Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning](https://mlsanity.com/paper/2110.00523/) (2021)
- [Unitail: Detecting, Reading, and Matching in Retail Scene](https://mlsanity.com/paper/2204.00298/) (2022)
- [DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation](https://mlsanity.com/paper/2312.13735/) (2023)
- [Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections](https://mlsanity.com/paper/2105.03139/) (2021)
- [Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap](https://mlsanity.com/paper/2202.06565/) (2022)
- [Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?](https://mlsanity.com/paper/2412.05611/) (2024)
- [Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT](https://mlsanity.com/paper/2504.05591/) (2025)

## Abstract (arXiv)

We present FoveaBox, an accurate, flexible, and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors. Instead, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. The scales of target boxes are naturally associated with feature pyramid representations. In FoveaBox, an instance is assigned to adjacent feature levels to make the model more accurate.We demonstrate its effectiveness on standard benchmarks and report extensive experimental analysis. Without bells and whistles, FoveaBox achieves state-of-the-art single model performance on the standard COCO and Pascal VOC object detection benchmark. More importantly, FoveaBox avoids all computation and hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance. We believe the simple and effective approach will serve as a solid baseline and help ease future research for object detection. The code has been made publicly available at https://github.com/taokong/FoveaBox .