Git Product home page Git Product logo

pdc's Introduction

Proposal Distribution Calibration for Few-Shot Object Detection

Code of Proposal Distribution Calibration for Few-Shot Object Detection.

The code is based on mmdetection and imTED. Thanks a lot to these outstanding work. Please refer to get_started.md and MMDET_README.md to set up the environment and prepare the data.

Data Preparation

For few-shot experiments, please refer to FsDet for data preparation. Remember to modify the path of json in the configuration files, e.g. configs/imted/few_shot_pdc/imted_faster_rcnn_vit_base_2x_base_training_coco.py.

In run_train_pdc_few_shot.sh, you can get the relevant running commands about base training stage and finetune stage for coco dataset.

More detail about experiment for voc dataset and coco dataset will release soon.

Results on VOC Benchmark

Method Split-1 Split-2 Split-3
Shot 1 2 3 5 10 1 2 3 5 10 1 2 3 5 10
YOLO-ft 6.6 10.7 12.5 24.8 38.6 12.5 4.2 11.6 16.1 33.9 13.0 15.9 15.0 32.2 38.4
FRCN-ft 13.8 19.6 32.8 41.5 45.6 7.9 15.3 26.2 31.6 39.1 9.8 11.3 19.1 35.0 45.1
FSRW 14.8 15.5 26.7 33.9 47.2 15.7 15.2 22.7 30.1 40.5 21.3 25.6 28.4 42.8 45.9
TFA 39.8 36.1 44.7 55.7 56.0 23.5 26.9 34.1 35.1 39.1 30.8 34.8 42.8 49.5 49.8
MPSR 41.7 - 51.4 55.2 61.8 24.4 - 39.2 39.9 47.8 35.6 - 42.3 48.0 49.7
CME 41.5 47.5 50.4 58.2 60.9 27.2 30.2 41.4 42.5 46.8 34.3 39.6 45.1 48.3 51.5
FSCE 44.2 43.8 51.4 61.9 63.4 27.3 29.5 43.5 44.2 50.2 37.2 41.9 47.5 54.6 58.5
imTED-S(Our Implement) 43.4 51.0 58.1 67.6 66.6 23.2 26.9 39.4 44.2 52.7 49.9 48.8 56.4 61.4 61.1
imTED-S+PDC 50.1 52.3 60.2 70.7 68.4 23.3 28.5 43.2 48.4 54.6 53.0 50.8 57.7 63.8 62.9
imTED-B(Our Implement) 56.8 64.8 69.4 80.1 76.8 37.4 38.1 59.1 57.6 60.9 60.9 59.3 70.0 73.9 75.7
imTED-B+PDC 61.8 69.1 70.2 78.7 79.6 42.9 41.2 60.0 56.3 65.9 60.3 63.1 70.6 73.3 76.7

Results on COCO Benchmark

Method mAPnovel
Shot 10 30
FRCN-ft 6.5 11.1
FSRW 5.6 9.1
MetaDet 7.1 11.3
MetaR-CNN 8.7 12.4
TFA 10.0 13.7
MPSR 9.8 14.1
imTED-S 15.0 21.0
imTED-S+PDC 15.7 22.1
imTED-B 22.5 30.2
imTED-B+PDC 23.4 30.8

If you have any questions with our code/paper, feel free to contact me through issue or e-mail.

pdc's People

Contributors

bohao-lee avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

pdc's Issues

t-sne

帅哥,你好看到你文章,我发现t-sne是一个很有用的可视化工具,能不能请教一下代码和具体实施细节?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.