Towards Spatial Equilibrium Object Detection

TL;DR

This paper investigates the spatial bias in object detection, introduces a new measurement called Spatial equilibrium Precision (SP), and proposes a spatial equilibrium label assignment (SELA) to improve detection robustness by addressing spatial disequilibrium.

Contribution

The paper presents a novel analysis of spatial bias in object detection, introduces the SP metric, and proposes SELA to mitigate spatial disequilibrium, enhancing detection performance.

Findings

Spatial imbalance significantly impacts detection performance.

The proposed SP metric effectively characterizes spatial detection performance.

SELA improves robustness across multiple datasets.

Abstract

Semantic objects are unevenly distributed over images. In this paper, we study the spatial disequilibrium problem of modern object detectors and propose to quantify this ``spatial bias'' by measuring the detection performance over zones. Our analysis surprisingly shows that the spatial imbalance of objects has a great impact on the detection performance, limiting the robustness of detection applications. This motivates us to design a more generalized measurement, termed Spatial equilibrium Precision (SP), to better characterize the detection performance of object detectors. Furthermore, we also present a spatial equilibrium label assignment (SELA) to alleviate the spatial disequilibrium problem by injecting the prior spatial weight into the optimization process of detectors. Extensive experiments on PASCAL VOC, MS COCO, and 3 application datasets on face mask/fruit/helmet images demonstrate the advantages of our method. Our findings challenge the conventional sense of object detectors and show the indispensability of spatial equilibrium. We hope these discoveries would stimulate the community to rethink how an excellent object detector should be. All the source code, evaluation protocols, and the tutorials are publicly available at https://github.com/Zzh-tju/ZoneEval