Unified-IoU: For High-Quality Object Detection
Xiangjie Luo, Zhihao Cai, Bo Shao, Yingxun Wang

TL;DR
Unified-IoU (UIoU) is a novel loss function for object detection that dynamically emphasizes high-quality predictions, improving accuracy especially at high IoU thresholds and balancing training speed.
Contribution
The paper introduces Unified-IoU, a new IoU loss that adaptively shifts focus to high-quality predictions, enhancing detection precision and training efficiency.
Findings
UIoU outperforms existing IoU losses at high IoU thresholds
Improves detection accuracy on multiple datasets
Balances training speed with high-precision detection
Abstract
Object detection is an important part in the field of computer vision, and the effect of object detection is directly determined by the regression accuracy of the prediction box. As the key to model training, IoU (Intersection over Union) greatly shows the difference between the current prediction box and the Ground Truth box. Subsequent researchers have continuously added more considerations to IoU, such as center distance, aspect ratio, and so on. However, there is an upper limit to just refining the geometric differences; And there is a potential connection between the new consideration index and the IoU itself, and the direct addition or subtraction between the two may lead to the problem of "over-consideration". Based on this, we propose a new IoU loss function, called Unified-IoU (UIoU), which is more concerned with the weight assignment between different quality prediction boxes.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsIndustrial Vision Systems and Defect Detection · Robotics and Automated Systems · Brain Tumor Detection and Classification
MethodsSoftmax · Attention Is All You Need
