Home

Awesome

Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection

Introduction

This repository is the official implementation of ICCV2023: Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection.

News and ToDo List

Install

This repo is build on mmdetection 2.28.2

Please refer this link to build the environment (mmcv...).

Then execute the following command to install.

git clone https://github.com/TinyTigerPan/BCKD.git
cd BCKD
pip install -v -e .

Train

For single GPU

python tools/train.py configs/bckd/bckd_r50_gflv1_r101_fpn_coco_1x.py

For multi GPU

bash tools/dist_train.sh configs/bckd/bckd_r50_gflv1_r101_fpn_coco_1x.py 8

Eval

For single GPU

python tools/test.py config_file ckpt_file --eval bbox

For multi GPU

bash tools/dist_test.sh configs_file ckpt_file 8

Result

TeacherStudentSchedulemAPdownload
GFocal-R501x40.1
GFocal-R101GFocal-R501x43.2log | ckpt
GFocal-R341x38.9
GFocal-R101GFocal-R341x42.0log | ckpt
GFocal-R181x35.8
GFocal-R101GFocal-R181x38.6log | ckpt

Cite

@InProceedings{Yang_2023_ICCV,
    author    = {Yang, Longrong and Zhou, Xianpan and Li, Xuewei and Qiao, Liang and Li, Zheyang and Yang, Ziwei and Wang, Gaoang and Li, Xi},
    title     = {Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {17175-17184}
}