# Improving Object Localization with Fitness NMS and Bounded IoU Loss

arXiv: https://arxiv.org/abs/1711.00164 · HTML: https://mlsanity.com/paper/1711.00164/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2017.

## Built on by (most cited first, 30 of 31)

- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [Accelerating DETR Convergence via Semantic-Aligned Matching](https://mlsanity.com/paper/2203.06883/) (2022)
- [Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search](https://mlsanity.com/paper/2102.04700/) (2021)
- [Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection](https://mlsanity.com/paper/2106.06072/) (2021)
- [Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression](https://mlsanity.com/paper/2110.13675/) (2021)
- [ObjectBox: From Centers to Boxes for Anchor-Free Object Detection](https://mlsanity.com/paper/2207.06985/) (2022)
- [Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors](https://mlsanity.com/paper/2208.11356/) (2022)
- [MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression](https://mlsanity.com/paper/2307.07662/) (2023)
- [CenterNet++ for Object Detection](https://mlsanity.com/paper/2204.08394/) (2022)
- [Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion](https://mlsanity.com/paper/2207.14172/) (2022)
- [DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection](https://mlsanity.com/paper/2311.10437/) (2023)
- [SCALoss: Side and Corner Aligned Loss for Bounding Box Regression](https://mlsanity.com/paper/2104.00462/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Decoupled IoU Regression for Object Detection](https://mlsanity.com/paper/2202.00866/) (2022)
- [R(Det)^2: Randomized Decision Routing for Object Detection](https://mlsanity.com/paper/2204.00794/) (2022)
- [Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime](https://mlsanity.com/paper/2307.09562/) (2023)
- [VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching](https://mlsanity.com/paper/2105.05636/) (2021)
- [Learning Interpretable Concept Groups in CNNs](https://mlsanity.com/paper/2109.10078/) (2021)
- [GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data](https://mlsanity.com/paper/2310.20319/) (2023)
- [NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2401.12447/) (2024)
- [From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks](https://mlsanity.com/paper/2405.06038/) (2024)
- [SparseDet: Towards End-to-End 3D Object Detection](https://mlsanity.com/paper/2206.00960/) (2022)
- [Improving Localization for Semi-Supervised Object Detection](https://mlsanity.com/paper/2206.10186/) (2022)
- [Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration](https://mlsanity.com/paper/2309.03110/) (2023)
- [Towards Context-Aware Image Anonymization with Multi-Agent Reasoning](https://mlsanity.com/paper/2603.27817/) (2026)
- [RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection](https://mlsanity.com/paper/2102.04582/) (2021)
- [Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection](https://mlsanity.com/paper/2112.08902/) (2021)
- [Being Aware of Localization Accuracy By Generating Predicted-IoU-Guided Quality Scores](https://mlsanity.com/paper/2309.13269/) (2023)
- [FPDIoU Loss: A Loss Function for Efficient Bounding Box Regression of Rotated Object Detection](https://mlsanity.com/paper/2405.09942/) (2024)

## Abstract (arXiv)

We demonstrate that many detection methods are designed to identify only a sufficently accurate bounding box, rather than the best available one. To address this issue we propose a simple and fast modification to the existing methods called Fitness NMS. This method is tested with the DeNet model and obtains a significantly improved MAP at greater localization accuracies without a loss in evaluation rate, and can be used in conjunction with Soft NMS for additional improvements. Next we derive a novel bounding box regression loss based on a set of IoU upper bounds that better matches the goal of IoU maximization while still providing good convergence properties. Following these novelties we investigate RoI clustering schemes for improving evaluation rates for the DeNet wide model variants and provide an analysis of localization performance at various input image dimensions. We obtain a MAP of 33.6%@79Hz and 41.8%@5Hz for MSCOCO and a Titan X (Maxwell). Source code available from: https://github.com/lachlants/denet