Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/chenhongyiyang/pgd

[ECCV 2022] Prediction-Guided Distillation for Dense Object Detection

https://github.com/chenhongyiyang/pgd

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.2%) to scientific vocabulary

Keywords

knowledge-distillation object-detection
Last synced: 6 months ago · JSON representation

Repository

[ECCV 2022] Prediction-Guided Distillation for Dense Object Detection

Basic Info
  • Host: GitHub
  • Owner: ChenhongyiYang
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 15.7 MB
Statistics
  • Stars: 60
  • Watchers: 1
  • Forks: 8
  • Open Issues: 2
  • Releases: 0
Topics
knowledge-distillation object-detection
Created almost 4 years ago · Last pushed over 3 years ago
Metadata Files
Readme License

README.md

Prediction-Guided Distillation

PyTorch implementation of our ECCV 2022 paper: Prediction-Guided Distillation for Dense Object Detection

Requirements

  • Our codebase is built on top of MMDetection, which can be installed following the offcial instuctions.
  • We used pytorch pre-trained ResNets for training.
  • Please follow the MMdetection offcial instuction to set up COCO dataset.
  • Please download the CrowdHuman and set up the dataset by running this script.

Usage

Set up datasets and pre-trained models

shell mkdir data ln -s path_to_coco data/coco ln -s path_to_crowdhuman data/crowdhuman ln -s path_to_pretrainedModel data/pretrain_models

COCO Experiments

```shell

------------------------------------

Here we use ATSS as an example

------------------------------------

Training and testing teacher model

zsh tools/disttrain.sh workconfigs/detectors/atssr1013xms.py 8 zsh tools/disttest.sh workconfigs/detectors/atssr1013xms.py workdirs/atssr1013xms/latest.pth 8

Training and testing student model

zsh tools/disttrain.sh workconfigs/detectors/atssr501x.py 8 zsh tools/disttest.sh workconfigs/detectors/atssr501x.py workdirs/atssr50_1x/latest.pth 8

Training and testing PGD model

zsh tools/disttrain.sh workconfigs/pgdatssr101r501x.py 8 zsh tools/disttest.sh workconfigs/pgdatssr101r501x.py workdirs/pgdatssr101r50_1x/latest.pth 8 ```

CrowdHuman Experiments

```shell

Training teacher, conducting KD, and evalauation

zsh tools/run_crowdhuman.sh ```

Model Zoo

COCO

| Detector | Setting | mAP | Config | | :--------: | :-----------------------------: | :---------: | :----------------------------------------------------------: | | FCOS | Teacher (r101, 3x, multi-scale) | 43.1 | config | | - | Student (r50, 1x, single-scale) | 38.2 | config | | - | PGD (r50, 1x, single-scale) | 42.5 (+4.3) | config | | AutoAssign | Teacher (r101, 3x, multi-scale) | 44.8 | config | | - | Student (r50, 1x, single-scale) | 40.6 | config | | - | PGD (r50, 1x, single-scale) | 43.8 (+3.1) | config | | ATSS | Teacher (r101, 3x, multi-scale) | 45.5 | config | | - | Student (r50, 1x, single-scale) | 39.6 | config | | - | PGD (r50, 1x, single-scale) | 44.2 (+4.6) | config | | GFL | Teacher (r101, 3x, multi-scale) | 45.8 | config | | - | Student (r50, 1x, single-scale) | 40.2 | config | | - | PGD (r50, 1x, single-scale) | 43.8 (+3.6) | config | | DDOD | Teacher (r101, 3x, multi-scale) | 46.6 | config | | - | Student (r50, 1x, single-scale) | 42.0 | config | | - | PGD (r50, 1x, single-scale) | 45.4 (+3.4) | config |

CrowdHuman

| Detector | Setting | MR ↓ | AP ↑ | JI ↑ | Config | | :------: | :-----------------------------------: | :---------: | :---------: | :---------: | :----------------------------------------------------------: | | DDOD | Teacher (r101, 36 epoch, multi-scale) | 41.4 | 90.2 | 81.4 | config | | - | Student (r50, 12 epoch, single-scale) | 46.0 | 88.0 | 79.0 | config | | - | PGD (r50, 12 epoch, single-scale) | 42.8 (-3.2) | 90.0 (+2.0) | 80.7 (+1.7) | config |

Ciation

@article{yang2022predictionguided, title={{Prediction-Guided Distillation for Dense Object Detection}}, author={Yang, Chenhongyi and Ochal, Mateusz and Storkey, Amos and Crowley, Elliot J}, journal={ECCV 2022}, year={2022} }

Acknowledgement

We thank FGD and DDOD for their code base.

Owner

  • Name: Chenhongyi Yang
  • Login: ChenhongyiYang
  • Kind: user
  • Location: Zurich, Switzerland
  • Company: Meta

Research Scientist at Meta Reality Labs

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Dependencies

requirements/build.txt pypi
  • cython *
  • numpy *
requirements/docs.txt pypi
  • recommonmark *
  • sphinx *
  • sphinx_markdown_tables *
  • sphinx_rtd_theme *
requirements/mminstall.txt pypi
  • mmcv-full >=1.3.3
requirements/optional.txt pypi
  • albumentations >=0.3.2
  • cityscapesscripts *
  • imagecorruptions *
  • scipy *
  • sklearn *
requirements/readthedocs.txt pypi
  • mmcv *
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • matplotlib *
  • numpy *
  • pycocotools *
  • pycocotools-windows *
  • six *
  • terminaltables *
requirements/tests.txt pypi
  • asynctest * test
  • codecov * test
  • flake8 * test
  • interrogate * test
  • isort ==4.3.21 test
  • kwarray * test
  • onnx ==1.7.0 test
  • onnxruntime ==1.5.1 test
  • pytest * test
  • ubelt * test
  • xdoctest >=0.10.0 test
  • yapf * test