# Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation

arXiv: https://arxiv.org/abs/2005.03572 · HTML: https://mlsanity.com/paper/2005.03572/

## Key facts

- Cited by 98 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 30 of 98)

- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [SIoU Loss: More Powerful Learning for Bounding Box Regression](https://mlsanity.com/paper/2205.12740/) (2022)
- [AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks](https://mlsanity.com/paper/2103.14026/) (2021)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization](https://mlsanity.com/paper/2505.11217/) (2025)
- [Efficient Teacher: Semi-Supervised Object Detection for YOLOv5](https://mlsanity.com/paper/2302.07577/) (2023)
- [CLRerNet: Improving Confidence of Lane Detection with LaneIoU](https://mlsanity.com/paper/2305.08366/) (2023)
- [AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs](https://mlsanity.com/paper/2506.05328/) (2025)
- [Triple-domain Feature Learning with Frequency-aware Memory Enhancement for Moving Infrared Small Target Detection](https://mlsanity.com/paper/2406.06949/) (2024)
- [AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Way](https://mlsanity.com/paper/2409.14577/) (2024)
- [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)
- [Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm](https://mlsanity.com/paper/2304.05071/) (2023)
- [MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression](https://mlsanity.com/paper/2307.07662/) (2023)
- [HIC-YOLOv5: Improved YOLOv5 For Small Object Detection](https://mlsanity.com/paper/2309.16393/) (2023)
- [Lightweight Full-Convolutional Siamese Tracker](https://mlsanity.com/paper/2310.05392/) (2023)
- [Slim-neck by GSConv: A lightweight-design for real-time detector architectures](https://mlsanity.com/paper/2206.02424/) (2022)
- [YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection](https://mlsanity.com/paper/2402.09329/) (2024)
- [NanoMVG: USV-Centric Low-Power Multi-Task Visual Grounding based on Prompt-Guided Camera and 4D mmWave Radar](https://mlsanity.com/paper/2408.17207/) (2024)
- [Table Detection for Visually Rich Document Images](https://mlsanity.com/paper/2305.19181/) (2023)
- [Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation](https://mlsanity.com/paper/2110.09734/) (2021)
- [Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysis](https://mlsanity.com/paper/2210.11939/) (2022)
- [YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detection](https://mlsanity.com/paper/2409.18826/) (2024)
- [Towards Asteroid Detection in Microlensing Surveys with Deep Learning](https://mlsanity.com/paper/2211.02239/) (2022)
- [Illicit item detection in X-ray images for security applications](https://mlsanity.com/paper/2305.01936/) (2023)
- [Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities](https://mlsanity.com/paper/2312.08851/) (2023)
- [Real-time Lane-wise Traffic Monitoring in Optimal ROIs](https://mlsanity.com/paper/2404.15212/) (2024)
- [Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark](https://mlsanity.com/paper/2410.12143/) (2024)
- [Drones4Good: Supporting Disaster Relief Through Remote Sensing and AI](https://mlsanity.com/paper/2308.05074/) (2023)
- [A Flying Bird Object Detection Method for Surveillance Video](https://mlsanity.com/paper/2401.03749/) (2024)

## Abstract (arXiv)

Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, i.e., overlap area, normalized central point distance and aspect ratio, which are crucial for measuring bounding box regression in object detection and instance segmentation. The three geometric factors are then incorporated into CIoU loss for better distinguishing difficult regression cases. The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted ℓn-norm loss and IoU-based loss. Furthermore, we propose Cluster-NMS, where NMS during inference is done by implicitly clustering detected boxes and usually requires less iterations. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR. In the experiments, CIoU loss and Cluster-NMS have been applied to state-of-the-art instance segmentation (e.g., YOLACT and BlendMask-RT), and object detection (e.g., YOLO v3, SSD and Faster R-CNN) models. Taking YOLACT on MS COCO as an example, our method achieves performance gains as +1.7 AP and +6.2 AR100 for object detection, and +0.9 AP and +3.5 AR100 for instance segmentation, with 27.1 FPS on one NVIDIA GTX 1080Ti GPU. All the source code and trained models are available at https://github.com/Zzh-tju/CIoU