This repository is for Contrastive Embedding Distribution Refinement and Entropy-Aware Attention Network (CEDR)

phoenix

Last update: Feb 27, 2022

Related tags

Deep Learning CEDR

Overview

CEDR

This repository is for Contrastive Embedding Distribution Refinement and Entropy-Aware Attention Network (CEDR) introduced in the following paper:

"Contrastive Embedding Distribution Refinement and Entropy-Aware Attention for 3D Point Cloud Classification"

Updates

03/01/2022 The paper is currently under review, and the codes will be released in the future.
06/01/2022 codes for both model.py and main.py are available now.
10/01/2022 Update a pre-trained model (OA: 82.90%, mAcc: 80.60%) on ScanObjectNN via google drive.
10/01/2022 Pre-trained model (OA: 93.10%, mAcc: 91.10%) on ModelNet40 is available at google drive.

Network Architecture

Implementation Platforms

Python 3.6
Pytorch 0.4.0 with Cuda 9.1
Higher Python/Pytorch/Cuda versions should also be compatible

ModelNet40 Experiment

Test the pre-trained model:

download ModelNet40, unzip and move modelnet40_ply_hdf5_2048 folder to ./data
put the pre-trained model under ./checkpoints/modelnet
then run (more settings can be modified in main.py):

python main.py --exp_name=gbnet_modelnet40_eval --model=gbnet --dataset=modelnet40 --eval=True --model_path=checkpoints/modelnet/gbnet_modelnet40.t7

ScanObjectNN Experiment

Test the pre-trained model:

download ScanObjectNN, and extract both training_objectdataset_augmentedrot_scale75.h5 and test_objectdataset_augmentedrot_scale75.h5 files to ./data
put the pre-trained model under ./checkpoints/gbnet_scanobjectnn
then run (more settings can be modified in main.py):

python main.py --exp_name=gbnet_scanobjectnn_eval --model=gbnet --dataset=ScanObjectNN --eval=True --model_path=checkpoints/gbnet_scanobjectnn/gbnet_scanobjectnn.t7

Pre-trained Models

Python 3.6, Pytorch 0.4.0, Cuda 9.1
8 GeForce RTX 2080Ti GPUs
using default training settings as in main.py

Model	Dataset	#Points	Data Augmentation	Performance on Test Set	Download Link
PointNet++	ModelNet40	1024	random scaling and translation	overall accuracy: 93.10% average class accuracy: 91.10%	google drive
GBNet	ScanObjectNN	1024	random scaling and translation	overall accuracy: 82.90% average class accuracy: 80.60%	google drive

Acknowledgement

The code is built on GBNet. We thank the authors for sharing the codes. We also thank the Big Data Center of Southeast University for providing the facility support on the numerical calculations in this paper.

You might also like...

PyTorch code for SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised DA

PyTorch Code for SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation Viraj Prabhu, Shivam Khare, Deeks

46 Dec 24, 2022

ICLR21 Tent: Fully Test-Time Adaptation by Entropy Minimization

⛺️ Tent: Fully Test-Time Adaptation by Entropy Minimization This is the official project repository for Tent: Fully-Test Time Adaptation by Entropy Mi

204 Dec 25, 2022

RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

State Entropy Maximization with Random Encoders for Efficient Exploration (RE3) (ICML 2021) Code for State Entropy Maximization with Random Encoders f

47 Nov 29, 2022

Implementation of accepted AAAI 2021 paper: Deep Unsupervised Image Hashing by Maximizing Bit Entropy

Deep Unsupervised Image Hashing by Maximizing Bit Entropy This is the PyTorch implementation of accepted AAAI 2021 paper: Deep Unsupervised Image Hash

62 Dec 30, 2022

Semi-supervised Domain Adaptation via Minimax Entropy

Semi-supervised Domain Adaptation via Minimax Entropy (ICCV 2019) Install pip install -r requirements.txt The code is written for Pytorch 0.4.0, but s

243 Jan 9, 2023

PyTorch code accompanying our paper on Maximum Entropy Generators for Energy-Based Models

Maximum Entropy Generators for Energy-Based Models All experiments have tensorboard visualizations for samples / density / train curves etc. To run th

135 Oct 27, 2022

Predicting path with preference based on user demonstration using Maximum Entropy Deep Inverse Reinforcement Learning in a continuous environment

Preference-Planning-Deep-IRL Introduction Check my portfolio post Dependencies Gym stable-baselines3 PyTorch Usage Take Demonstration python3 record.

9 Oct 26, 2022

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

Softlearning Softlearning is a deep reinforcement learning toolbox for training maximum entropy policies in continuous domains. The implementation is

997 Dec 30, 2022

Weakly Supervised Posture Mining with Reverse Cross-entropy for Fine-grained Classification

Fine-grainedImageClassification Weakly Supervised Posture Mining with Reverse Cross-entropy for Fine-grained Classification We trained model here: lin

14 Oct 21, 2022

Comments

T-SNE of features visualization

Nice work! Can you provides your code of T-SNE of features visualization, like the fig.7 in the paper and the fig.1 in the supplementary material. Look forwark to your cde!

opened by xiewende 0
Experiments issues

Dear @YangFengSEU ，

Many thanks for sharing the codes of your work. Could you please kindly let me know where can I find other py files for running the Experiments? There is only train.py available at the moment.

Thanks a lot.

opened by NeilCui6 6

This repository is for Contrastive Embedding Distribution Refinement and Entropy-Aware Attention Network (CEDR)

Related tags

Overview

CEDR

Updates

Network Architecture

Implementation Platforms

ModelNet40 Experiment

ScanObjectNN Experiment

Pre-trained Models

Acknowledgement

You might also like...

PyTorch code for SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised DA

ICLR21 Tent: Fully Test-Time Adaptation by Entropy Minimization

RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

Implementation of accepted AAAI 2021 paper: Deep Unsupervised Image Hashing by Maximizing Bit Entropy

Semi-supervised Domain Adaptation via Minimax Entropy

PyTorch code accompanying our paper on Maximum Entropy Generators for Energy-Based Models

Predicting path with preference based on user demonstration using Maximum Entropy Deep Inverse Reinforcement Learning in a continuous environment

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

Weakly Supervised Posture Mining with Reverse Cross-entropy for Fine-grained Classification

Comments

T-SNE of features visualization

Experiments issues

Owner

phoenix

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification

Official repository for "PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation"

Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional Architects

CVPR2021: Temporal Context Aggregation Network for Temporal Action Proposal Refinement

RefineGNN - Iterative refinement graph neural network for antibody sequence-structure co-design (RefineGNN)

PyTorch code for our paper "Attention in Attention Network for Image Super-Resolution"

AntroPy: entropy and complexity of (EEG) time-series in Python

noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.

Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)