Light

townim-faisal / fscil-3d Goto Github PK

View Code? Open in Web Editor NEW

22.0 2.0 6.0 967 KB

[ECCV 2022] Few-shot class incremental learning on 3D point clouid objects

Python 100.00%

3d-object-recognition continual-learning deep-learning few-shot-learning

fscil-3d's Introduction

FSCIL 3D

Few-shot Class-incremental Learning for 3D Point Cloud Objects, ECCV 2022
Townim Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman

This paper addresses the problem of few-shot class incremental learning for the 3D domain alongside the domain gap from synthetic to real objects.

Figure: Overall Architecture

Dependencies

FSCIL 3D is implemented in PyTorch and tested with Ubuntu 20.04.2 LTS, please install PyTorch first in the official instruction. You can also install the anaconda environment using the provided environment.yml file.

Configurations

Here, we only include the configuration for the large cross-dataset experiment: ShapeNet -> CO3D. The configuration files are in configs folder.

You can create similar configuration files for other experimental setups.

Dataset

Please check the readme file in here.

K-Means

You can build your own centroids with this code.

Command

python train_pointnet_incremental_with_knn_with_w2v.py

For this ShapeNet -> CO3D experiment, we provide required centroids and model here.

Citation

@inproceedings{FSCIL3D,
  title={Few-shot Class-incremental Learning for 3D Point Cloud Objects},
  author={Chowdhury, Townim and Cheraghian, Ali and Ramasinghe, Sameera and Ahmadi, Sahar and Saberi, Morteza and Rahman, Shafin},
  booktitle={ECCV},
  year={2022}
}

fscil-3d's People

Contributors

Stargazers

Watchers

Forkers

nahidosen shadmanrohan saharahmadisohraviyeh shengstar ball80012138 instig8r

fscil-3d's Issues

The link of required centroids and model is 404

Thanks for sharing your interesting work, but there is a problem the link to the required centroids and model mentioned in your README.md.

Questions About CO3D dataset

Do you download the entire CO3D dataset v1/v2 and process it by yourself?

How do you get the split of the test set and train set? Could you provide the related code for this?
Could you provide the original 3D point cloud files (i.e., >1024 points) files?
Thank you very much!
@townim-faisal

code problem

The features extracted by your feature extractor are not used in the code, but you still get the same results as the paper. Besides, I counted the accuracy of the new classes, and the result is very low. The model can not learn the knowledge of the new classes at all. Could you tell me what the reason is

data split

Hi. Could you provide the related code for data split? Or provide the dataset for within dataset experiments(modelnet,shapenet,co3d)? Thank you very much.

The link of required centroids and model is invalid

How to download preprocessed CO3D dataset？

The Link appears to contain empty folders.

Recommend Projects

React

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

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

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

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

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

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.