Can the Query-based Object Detector Be Designed with Fewer Stages?

TL;DR

This paper introduces GOLO, a two-stage query-based object detector that reduces decoder stages to lower computational costs while maintaining high accuracy, challenging the traditional multi-stage paradigm.

Contribution

Proposes GOLO, a novel two-stage decoding model for query-based object detection, demonstrating comparable performance with fewer stages and reduced computational burden.

Findings

GOLO achieves competitive accuracy on COCO dataset.

Fewer decoder stages lead to lower computational costs.

Two-stage decoding suffices for high-performance detection.

Abstract

Query-based object detectors have made significant advancements since the publication of DETR. However, most existing methods still rely on multi-stage encoders and decoders, or a combination of both. Despite achieving high accuracy, the multi-stage paradigm (typically consisting of 6 stages) suffers from issues such as heavy computational burden, prompting us to reconsider its necessity. In this paper, we explore multiple techniques to enhance query-based detectors and, based on these findings, propose a novel model called GOLO (Global Once and Local Once), which follows a two-stage decoding paradigm. Compared to other mainstream query-based models with multi-stage decoders, our model employs fewer decoder stages while still achieving considerable performance. Experimental results on the COCO dataset demonstrate the effectiveness of our approach.