# Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

arXiv: https://arxiv.org/abs/2011.12885 · HTML: https://mlsanity.com/paper/2011.12885/

## Key facts

- Cited by 104 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2020.

## Built on by (most cited first, 30 of 104)

- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://mlsanity.com/paper/2209.02976/) (2022)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [AdaMixer: A Fast-Converging Query-Based Object Detector](https://mlsanity.com/paper/2203.16507/) (2022)
- [Dense Distinct Query for End-to-End Object Detection](https://mlsanity.com/paper/2303.12776/) (2023)
- [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://mlsanity.com/paper/2410.13842/) (2024)
- [Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation](https://mlsanity.com/paper/2204.02136/) (2022)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation](https://mlsanity.com/paper/2203.10593/) (2022)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [CrossKD: Cross-Head Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2306.11369/) (2023)
- [Equalized Focal Loss for Dense Long-Tailed Object Detection](https://mlsanity.com/paper/2201.02593/) (2022)
- [Rethinking Pseudo Labels for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.00168/) (2021)
- [Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images](https://mlsanity.com/paper/2303.14488/) (2023)
- [Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation](https://mlsanity.com/paper/2112.04840/) (2021)
- [Task-specific Inconsistency Alignment for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15345/) (2022)
- [MS-DETR: Efficient DETR Training with Mixed Supervision](https://mlsanity.com/paper/2401.03989/) (2024)
- [UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery](https://mlsanity.com/paper/2112.10415/) (2021)
- [NMS Strikes Back](https://mlsanity.com/paper/2212.06137/) (2022)
- [YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection](https://mlsanity.com/paper/2308.05480/) (2023)
- [Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation](https://mlsanity.com/paper/2408.04804/) (2024)
- [Action Sensitivity Learning for Temporal Action Localization](https://mlsanity.com/paper/2305.15701/) (2023)
- [A Dual Weighting Label Assignment Scheme for Object Detection](https://mlsanity.com/paper/2203.09730/) (2022)
- [One-Stage Cascade Refinement Networks for Infrared Small Target Detection](https://mlsanity.com/paper/2212.08472/) (2022)

## Abstract (arXiv)

Localization Quality Estimation (LQE) is crucial and popular in the recent advancement of dense object detectors since it can provide accurate ranking scores that benefit the Non-Maximum Suppression processing and improve detection performance. As a common practice, most existing methods predict LQE scores through vanilla convolutional features shared with object classification or bounding box regression. In this paper, we explore a completely novel and different perspective to perform LQE -- based on the learned distributions of the four parameters of the bounding box. The bounding box distributions are inspired and introduced as "General Distribution" in GFLV1, which describes the uncertainty of the predicted bounding boxes well. Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality. Specifically, a bounding box distribution with a sharp peak usually corresponds to high localization quality, and vice versa. By leveraging the close correlation between distribution statistics and the real localization quality, we develop a considerably lightweight Distribution-Guided Quality Predictor (DGQP) for reliable LQE based on GFLV1, thus producing GFLV2. To our best knowledge, it is the first attempt in object detection to use a highly relevant, statistical representation to facilitate LQE. Extensive experiments demonstrate the effectiveness of our method. Notably, GFLV2 (ResNet-101) achieves 46.2 AP at 14.6 FPS, surpassing the previous state-of-the-art ATSS baseline (43.6 AP at 14.6 FPS) by absolute 2.6 AP on COCO tt test-dev, without sacrificing the efficiency both in training and inference. Code will be available at https://github.com/implus/GFocalV2.