Detect2Rank : Combining Object Detectors Using Learning to Rank

TL;DR

This paper introduces Detect2Rank, a learning-to-rank framework that effectively combines multiple object detectors using contextual features, significantly improving detection accuracy over individual detectors on standard datasets.

Contribution

The paper presents a novel learning-to-rank approach to combine diverse object detectors using high-level contextual features, enhancing detection performance.

Findings

Detect2Rank outperforms individual detectors on VOC datasets.

Significant accuracy improvements: up to 17% on VOC07.

Effective combination of detectors via learning to rank.

Abstract

Object detection is an important research area in the field of computer vision. Many detection algorithms have been proposed. However, each object detector relies on specific assumptions of the object appearance and imaging conditions. As a consequence, no algorithm can be considered as universal. With the large variety of object detectors, the subsequent question is how to select and combine them. In this paper, we propose a framework to learn how to combine object detectors. The proposed method uses (single) detectors like DPM, CN and EES, and exploits their correlation by high level contextual features to yield a combined detection list. Experiments on the PASCAL VOC07 and VOC10 datasets show that the proposed method significantly outperforms single object detectors, DPM (8.4%), CN (6.8%) and EES (17.0%) on VOC07 and DPM (6.5%), CN (5.5%) and EES (16.2%) on VOC10.