# Localization Distillation for Dense Object Detection

Source: [Localization Distillation for Dense Object Detection](<https://www.sota2.com/research/paper/68fa6c281e209131cea326c1>)

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

Data updated: 2025-10-26T00:04:48.767Z

Authors: Zhaohui Zheng, Rongguang Ye, Ping Wang, Dongwei Ren, Wangmeng Zuo, Qibin Hou, Ming-Ming Cheng

Published: 2021-02-24T12:26:21.000Z

## Abstract

Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking classification logit due to its inefficiency in distilling localization information and trivial improvement. In this paper, by reformulating the knowledge distillation process on localization, we present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. Moreover, we also heuristically introduce the concept of valuable localization region that can aid to selectively distill the semantic and localization knowledge for a certain region. Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and localization knowledge distillation is more important and efficient than semantic knowledge for distilling object detectors. Our distillation scheme is simple as well as effective and can be easily applied to different dense object detectors. Experiments show that our LD can boost the AP score of GFocal-ResNet-50 with a single-scale 1x training schedule from 40.1 to 42.1 on the COCO benchmark without any sacrifice on the inference speed. Our source code and trained models are publicly available at https://github.com/HikariTJU/LD

## 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 (minival)](<https://www.sota2.com/research/sota/object-detection-on-coco-minival.md>): Object Detection; COCO (minival); mAP: 43.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2102.12252>)

[PDF](<https://arxiv.org/pdf/2102.12252.pdf>)