Code from PropMix, accepted at BMVC'21

Related tags

Deep LearningPropMix
Overview

PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels

This repository is the official implementation of Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels (BMVC 2021).

Authors: Filipe R. Cordeiro; Vasileios Belagiannis, Ian Reid and Gustavo Carneiro

Illustration

Requirements

  • This codebase is written for python3.
  • To install necessary python packages, run pip install -r requirements.txt.

Training and Evaluating

The pipeline for training with PropMix is the following:

  1. Self-supervised pretrain.

In our paper we use SimCLR for most of the datasets. We use moco-v2 to pre-train an InceptionResNetV2 on Webvision. Other self-supervised methods can be used as well.

If you use SimCLR, run:

python simclr.py --config_env configs/env.yml --config_exp configs/pretext/<config_file.yml> --cudaid 0

  1. Clustering

python scan.py --config_env configs/env.yml --config_exp configs/scan/<config_file.yml> --cudaid 0

  1. Train the model (using the pretraining from steps 1 and 2)

For CIFAR-10/CIFAR-100:

python propmix.py --r [0.2/0.5/0.8/0.9] --noise_mode [sym/asym] --config_env configs/env.yml --config_exp configs/propmix/<config_file.yml> --cudaid 0

Add --nopt if you wish to train from scratch, without the self-supervised pretrain, from steps 1 and 2. Add --strong_aug to use strong augmentation. Recommended for high noise rates.

License and Contributing

  • This README is formatted based on paperswithcode.
  • This project is licensed under the terms of the MIT license.
  • Feel free to post issues via Github.

Cite PropMix
If you find the code useful in your research, please consider citing our paper:

@article{cordeiroPropMix2021,
  title={PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels},
  author={Cordeiro, F. R. and Belagiannis, Vasileios and Reid, Ian and Carneiro, Gustavo},
  journal={The 32nd British Machine Vision Conference},
  volume={?},
  year={2021}
}

Contact

Please contact [email protected] if you have any question on the codes.

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds by Mutian Xu*, Runyu Ding*, Hengshuang Zhao, and Xiaojuan Qi. Int

CVMI Lab 228 Dec 25, 2022
Navigating StyleGAN2 w latent space using CLIP

Navigating StyleGAN2 w latent space using CLIP an attempt to build sth with the official SG2-ADA Pytorch impl kinda inspired by Generating Images from

Mike K. 55 Dec 06, 2022
Code for Subgraph Federated Learning with Missing Neighbor Generation (NeurIPS 2021)

To run the code Unzip the package to your local directory; Run 'pip install -r requirements.txt' to download required packages; Open file ~/nips_code/

32 Dec 26, 2022
A framework for multi-step probabilistic time-series/demand forecasting models

JointDemandForecasting.py A framework for multi-step probabilistic time-series/demand forecasting models File stucture JointDemandForecasting contains

Stanford Intelligent Systems Laboratory 3 Sep 28, 2022
[ICLR 2022] Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

AMOS This repository contains the scripts for fine-tuning AMOS pretrained models on GLUE and SQuAD 2.0 benchmarks. Paper: Pretraining Text Encoders wi

Microsoft 22 Sep 15, 2022
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation

Domain Transfer Network (DTN) TensorFlow implementation of Unsupervised Cross-Domain Image Generation. Requirements Python 2.7 TensorFlow 0.12 Pickle

Yunjey Choi 865 Nov 17, 2022
Codes for [NeurIPS'21] You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership.

You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership Codes for [NeurIPS'21] You are caught stealing my winni

VITA 8 Nov 01, 2022
Hard cater examples from Hopper ICLR paper

CATER-h Honglu Zhou*, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf (*Contact: honglu.zhou

NECLA ML Group 6 May 11, 2021
Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch

Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch Reference Paper URL Author: Yi Tay, Dara Bahri, Donald Metzler

Myeongjun Kim 66 Nov 30, 2022
PyTorch implementation of an end-to-end Handwritten Text Recognition (HTR) system based on attention encoder-decoder networks

AttentionHTR PyTorch implementation of an end-to-end Handwritten Text Recognition (HTR) system based on attention encoder-decoder networks. Scene Text

Dmitrijs Kass 31 Dec 22, 2022
UPSNet: A Unified Panoptic Segmentation Network

UPSNet: A Unified Panoptic Segmentation Network Introduction UPSNet is initially described in a CVPR 2019 oral paper. Disclaimer This repository is te

Uber Research 622 Dec 26, 2022
This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization This codebase is the official implementation of Test-Time Classifier A

47 Dec 28, 2022
Tianshou - An elegant PyTorch deep reinforcement learning library.

Tianshou (天授) is a reinforcement learning platform based on pure PyTorch. Unlike existing reinforcement learning libraries, which are mainly based on

Tsinghua Machine Learning Group 5.5k Jan 05, 2023
Fang Zhonghao 13 Nov 19, 2022
QueryFuzz implements a metamorphic testing approach to test Datalog engines.

Datalog is a popular query language with applications in several domains. Like any complex piece of software, Datalog engines may contain bugs. The mo

34 Sep 10, 2022
Randstad Artificial Intelligence Challenge (powered by VGEN). Soluzione proposta da Stefano Fiorucci (anakin87) - primo classificato

Randstad Artificial Intelligence Challenge (powered by VGEN) Soluzione proposta da Stefano Fiorucci (anakin87) - primo classificato Struttura director

Stefano Fiorucci 1 Nov 13, 2021
A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

Rockpool Rockpool is a Python package for developing signal processing applications with spiking neural networks. Rockpool allows you to build network

SynSense 21 Dec 14, 2022
Powerful and efficient Computer Vision Annotation Tool (CVAT)

Computer Vision Annotation Tool (CVAT) CVAT is free, online, interactive video and image annotation tool for computer vision. It is being used by our

OpenVINO Toolkit 8.6k Jan 01, 2023
Caffe models in TensorFlow

Caffe to TensorFlow Convert Caffe models to TensorFlow. Usage Run convert.py to convert an existing Caffe model to TensorFlow. Make sure you're using

Saumitro Dasgupta 2.8k Dec 31, 2022
Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition (AGRA, ACM 2020, Oral)

Cross Domain Facial Expression Recognition Benchmark Implementation of papers: Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchm

89 Dec 09, 2022