Official PyTorch implementation of "Adversarial Reciprocal Points Learning for Open Set Recognition"

Overview

Adversarial Reciprocal Points Learning for Open Set Recognition

Official PyTorch implementation of "Adversarial Reciprocal Points Learning for Open Set Recognition".

1. Requirements

Environments

Currently, requires following packages

  • python 3.6+
  • torch 1.4+
  • torchvision 0.5+
  • CUDA 10.1+
  • scikit-learn 0.22+

Datasets

For Tiny-ImageNet, please download the following datasets to ./data/tiny_imagenet.

2. Training & Evaluation

Open Set Recognition

To train open set recognition models in paper, run this command:

python osr.py --dataset <DATASET> --loss <LOSS>

Option --loss can be one of ARPLoss/RPLoss/GCPLoss/Softmax. --dataset is one of mnist/svhn/cifar10/cifar100/tiny_imagenet. To run ARPL+CS, add --cs after this command.

Out-of-Distribution Detection

To train out-of-distribution models in paper, run this command:

python ood.py --dataset <DATASET> --out-dataset <DATASET> --model <NETWORK> --loss <LOSS>

Option --out-dataset denotes the out-of-distribution dataset for evaluation. --loss can be one of ARPLoss/RPLoss/GCPLoss/Softmax. --dataset is one of mnist/cifar10. --out-dataset is one of kmnist/svhn/cifar100. To run ARPL+CS, add --cs after this command.

Evaluation

To evaluate the trained model for Open Set Classification Rate (OSCR) and Out-of-Distribution (OOD) detection setting, add --eval after the training command.

3. Results

We visualize the deep feature of Softmax/GCPL/ARPL/ARPL+CS as below.

Colored triangles represent the learned reciprocal points of different known classes.

4. PKU-AIR300

A new large-scale challenging aircraft dataset for open set recognition: Aircraft 300 (Air-300). It contains 320,000 annotated colour images from 300 different classes in total. Each category contains 100 images at least, and a maximum of 10,000 images, which leads to the long tail distribution.

Citation

  • If you find our work or the code useful, please consider cite our paper using:
@inproceedings{chen2021adversarial,
    title={Adversarial Reciprocal Points Learning for Open Set Recognition},
    author={Chen, Guangyao and Peng, Peixi and Wang, Xiangqian and Tian, Yonghong},
    journal={arXiv preprint arXiv:2103.00953},
    year={2021}
}
  • All publications using Air-300 Dataset should cite the paper below:
@InProceedings{chen_2020_ECCV,
    author = {Chen, Guangyao and Qiao, Limeng and Shi, Yemin and Peng, Peixi and Li, Jia and Huang, Tiejun and Pu, Shiliang and Tian, Yonghong},
    title = {Learning Open Set Network with Discriminative Reciprocal Points},
    booktitle = {The European Conference on Computer Vision (ECCV)},
    month = {August},
    year = {2020}
}
Owner
Guangyao Chen
Ph.D student @ PKU
Guangyao Chen
[NeurIPS 2021 Spotlight] Code for Learning to Compose Visual Relations

Learning to Compose Visual Relations This is the pytorch codebase for the NeurIPS 2021 Spotlight paper Learning to Compose Visual Relations. Demo Imag

Nan Liu 88 Jan 04, 2023
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Apache MXNet (incubating) for Deep Learning Apache MXNet is a deep learning framework designed for both efficiency and flexibility. It allows you to m

The Apache Software Foundation 20.2k Jan 05, 2023
PyTorch Implementation of Realtime Multi-Person Pose Estimation project.

PyTorch Realtime Multi-Person Pose Estimation This is a pytorch version of Realtime_Multi-Person_Pose_Estimation, origin code is here Realtime_Multi-P

Dave Fang 157 Nov 12, 2022
Source code for our paper "Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures"

Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures Code for the Multiplex Molecular Graph Neural Network (M

shzhang 59 Dec 10, 2022
Official code for paper "Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight"

Demysitifing Local Vision Transformer, arxiv This is the official PyTorch implementation of our paper. We simply replace local self attention by (dyna

138 Dec 28, 2022
A toolkit for developing and comparing reinforcement learning algorithms.

Status: Maintenance (expect bug fixes and minor updates) OpenAI Gym OpenAI Gym is a toolkit for developing and comparing reinforcement learning algori

OpenAI 29.6k Jan 08, 2023
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021

End-to-End Object Detection with Learnable Proposal, CVPR2021

Peize Sun 1.2k Dec 27, 2022
Official code for "Stereo Waterdrop Removal with Row-wise Dilated Attention (IROS2021)"

Stereo-Waterdrop-Removal-with-Row-wise-Dilated-Attention This repository includes official codes for "Stereo Waterdrop Removal with Row-wise Dilated A

29 Oct 01, 2022
Analyzing basic network responses to novel classes

novelty-detection Analyzing how AlexNet responds to novel classes with varying degrees of similarity to pretrained classes from ImageNet. If you find

Noam Eshed 34 Oct 02, 2022
Tensor-Based Quantum Machine Learning

TensorLy_Quantum TensorLy-Quantum is a Python library for Tensor-Based Quantum Machine Learning that builds on top of TensorLy and PyTorch. Website: h

TensorLy 85 Dec 03, 2022
Differential fuzzing for the masses!

NEZHA NEZHA is an efficient and domain-independent differential fuzzer developed at Columbia University. NEZHA exploits the behavioral asymmetries bet

147 Dec 05, 2022
A demonstration of using a live Tensorflow session to create an interactive face-GAN explorer.

Streamlit Demo: The Controllable GAN Face Generator This project highlights Streamlit's new hash_func feature with an app that calls on TensorFlow to

Streamlit 257 Dec 31, 2022
Library for 8-bit optimizers and quantization routines.

bitsandbytes Bitsandbytes is a lightweight wrapper around CUDA custom functions, in particular 8-bit optimizers and quantization functions. Paper -- V

Facebook Research 687 Jan 04, 2023
Data Preparation, Processing, and Visualization for MoVi Data

MoVi-Toolbox Data Preparation, Processing, and Visualization for MoVi Data, https://www.biomotionlab.ca/movi/ MoVi is a large multipurpose dataset of

Saeed Ghorbani 51 Nov 27, 2022
This is a Python wrapper for TA-LIB based on Cython instead of SWIG.

TA-Lib This is a Python wrapper for TA-LIB based on Cython instead of SWIG. From the homepage: TA-Lib is widely used by trading software developers re

John Benediktsson 7.3k Jan 03, 2023
Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021.

UniRE Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021. Requirements python: 3.7.6 pytorch: 1.8.1 transformers:

Wang Yijun 109 Nov 29, 2022
Video-based open-world segmentation

UVO_Challenge Team Alpes_runner Solutions This is an official repo for our UVO Challenge solutions for Image/Video-based open-world segmentation. Our

Yuming Du 84 Dec 22, 2022
Mememoji - A facial expression classification system that recognizes 6 basic emotions: happy, sad, surprise, fear, anger and neutral.

a project built with deep convolutional neural network and ❤️ Table of Contents Motivation The Database The Model 3.1 Input Layer 3.2 Convolutional La

Jostine Ho 761 Dec 05, 2022
DSL for matching Python ASTs

py-ast-rule-engine This library provides a DSL (domain-specific language) to match a pattern inside a Python AST (abstract syntax tree). The library i

1 Dec 18, 2021
Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

Instance segmentation by jointly optimizing spatial embeddings and clustering bandwidth This codebase implements the loss function described in: Insta

209 Dec 07, 2022