Being Aware of Localization Accuracy By Generating Predicted-IoU-Guided Quality Scores

TL;DR

This paper introduces CLQ, a one-stage object detector that uses a predicted IoU-guided localization quality score embedded within the classification branch, achieving state-of-the-art accuracy and demonstrating strong adaptability.

Contribution

The paper proposes a novel LQE branch guided by predicted IoU integrated into the classification branch, and introduces the CLQ detector with superior performance on COCO.

Findings

CLQ achieves 47.8 AP on COCO test-dev.

CLQ runs at 11.5 fps with ResNeXt-101 backbone.

Extending CLQ to ATSS yields a 1.2 AP improvement.

Abstract

Localization Quality Estimation (LQE) helps to improve detection performance as it benefits post processing through jointly considering classification score and localization accuracy. In this perspective, for further leveraging the close relationship between localization accuracy and IoU (Intersection-Over-Union), and for depressing those inconsistent predictions, we designed an elegant LQE branch to acquire localization quality score guided by predicted IoU. Distinctly, for alleviating the inconsistency of classification score and localization quality during training and inference, under which some predictions with low classification scores but high LQE scores will impair the performance, instead of separately and independently setting, we embedded LQE branch into classification branch, producing a joint classification-localization-quality representation. Then a novel one stage detector termed CLQ is proposed. Extensive experiments show that CLQ achieves state-of-the-arts' performance at an accuracy of 47.8 AP and a speed of 11.5 fps with ResNeXt-101 as backbone on COCO test-dev. Finally, we extend CLQ to ATSS, producing a reliable 1.2 AP gain, showing our model's strong adaptability and scalability. Codes are released at https://github.com/PanffeeReal/CLQ.