Decoupled IoU Regression for Object Detection

by   Yan Gao, et al.

Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem. We argue that the complex definition of IoU and feature misalignment make it difficult to predict IoU accurately. In this paper, we propose a novel Decoupled IoU Regression (DIR) model to handle these problems. The proposed DIR decouples the traditional localization confidence metric IoU into two new metrics, Purity and Integrity. Purity reflects the proportion of the object area in the detected bounding box, and Integrity refers to the completeness of the detected object area. Separately predicting Purity and Integrity can divide the complex mapping between the bounding box and its IoU into two clearer mappings and model them independently. In addition, a simple but effective feature realignment approach is also introduced to make the IoU regressor work in a hindsight manner, which can make the target mapping more stable. The proposed DIR can be conveniently integrated with existing two-stage detectors and significantly improve their performance. Through a simple implementation of DIR with HTC, we obtain 51.3 AP on MS COCO benchmark, which outperforms previous methods and achieves state-of-the-art.


Acquisition of Localization Confidence for Accurate Object Detection

Modern CNN-based object detectors rely on bounding box regression and no...

FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings

Most state of the art object detectors output multiple detections per ob...

Localization Uncertainty-Based Attention for Object Detection

Object detection has been applied in a wide variety of real world scenar...

SEMI-CenterNet: A Machine Learning Facilitated Approach for Semiconductor Defect Inspection

Continual shrinking of pattern dimensions in the semiconductor domain is...

Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection

This paper presents a novel alternative to Greedy Non-Maxima Suppression...

Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism

The loss function for bounding box regression (BBR) is essential to obje...

Location-Aware Feature Selection for Scene Text Detection

Direct regression-based natural scene text detection methods have alread...

Please sign up or login with your details

Forgot password? Click here to reset