# Enhanced Training of Query-Based Object Detection via Selective Query Recollection

Source: [Enhanced Training of Query-Based Object Detection via Selective Query Recollection](<https://www.sota2.com/research/paper/68fa6ecc1e209131cea4236f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:13:10.363Z

Authors: Fangyi Chen, Han Zhang, Kai Hu, Yu-kai Huang, Chenchen Zhu, Marios Savvides

Published: 2022-12-15T02:45:57.000Z

## Abstract

This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two limitations: lack of training emphasis and cascading errors from decoding sequence. We design and present Selective Query Recollection (SQR), a simple and effective training strategy for query-based object detectors. It cumulatively collects intermediate queries as decoding stages go deeper and selectively forwards the queries to the downstream stages aside from the sequential structure. Such-wise, SQR places training emphasis on later stages and allows later stages to work with intermediate queries from earlier stages directly. SQR can be easily plugged into various query-based object detectors and significantly enhances their performance while leaving the inference pipeline unchanged. As a result, we apply SQR on Adamixer, DAB-DETR, and Deformable-DETR across various settings (backbone, number of queries, schedule) and consistently brings 1.4-2.8 AP improvement.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-2017-val.md>): Object Detection; COCO 2017 (val); AP: 51.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.07593>)

[PDF](<https://arxiv.org/pdf/2212.07593.pdf>)

[Implementation](<https://github.com/Fangyi-Chen/SQR>)
