# DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query

Source: [DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query](<https://www.sota2.com/research/paper/68fa71a21e209131cea52374>)

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

Data updated: 2025-10-26T02:09:33.631Z

Authors: Yuhang Zhang, Yuang Deng, Xiaopeng Zhang, Jie Li, Robert C. Qiu, Qi Tian

Published: 2023-12-28T09:58:32.000Z

## Abstract

Active learning has been demonstrated effective to reduce labeling cost, while most progress has been designed for image recognition, there still lacks instance-level active learning for object detection. In this paper, we rethink two key components, i.e., localization and recognition, for object detection, and find that the correctness of them are highly related, therefore, it is not necessary to annotate both boxes and classes if we are given pseudo annotations provided with the trained model. Motivated by this, we propose an efficient query strategy, termed as DeLR, that Decoupling the Localization and Recognition for active query. In this way, we are probably free of class annotations when the localization is correct, and able to assign the labeling budget for more informative samples. There are two main differences in DeLR: 1) Unlike previous methods mostly focus on image-level annotations, where the queried samples are selected and exhausted annotated. In DeLR, the query is based on region-level, and we only annotate the object region that is queried; 2) Instead of directly providing both localization and recognition annotations, we separately query the two components, and thus reduce the recognition budget with the pseudo class labels provided by the model. Experiments on several benchmarks demonstrate its superiority. We hope our proposed query strategy would shed light on researches in active learning in object detection.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.16931>)

[PDF](<https://arxiv.org/pdf/2312.16931.pdf>)
