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

Last update: Dec 04, 2022

Overview

ProSelfLC: CVPR 2021

ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks

For any specific discussion or potential future collaboration, please feel free to contact me.

Paper link: https://arxiv.org/abs/2005.03788

Cite our work if you find it useful

@inproceddings{wang2021proselflc,
  title={ {ProSelfLC}: Progressive Self Label Correction
  for Training Robust Deep Neural Networks},
  author={Wang, Xinshao and Hua, Yang and Kodirov, Elyor and Clifton, David A and Robertson, Neil M},
  booktitle={CVPR},
  year={2021}
}

Link to Slide, Poster, Final version

Link to reviewers' comments

List of Content

A GOOD REPRESENTATION DETECTS NOISY LABELS

A GOOD REPRESENTATION DETECTS NOISY LABELS This code is a PyTorch implementation of the paper: Prerequisites Python 3.6.9 PyTorch 1.7.1 Torchvision 0.

64 Jan 4, 2023

A Light CNN for Deep Face Representation with Noisy Labels

A Light CNN for Deep Face Representation with Noisy Labels Citation If you use our models, please cite the following paper: @article{wulight, title=

715 Nov 5, 2022

Large-Scale Pre-training for Person Re-identification with Noisy Labels (LUPerson-NL)

LUPerson-NL Large-Scale Pre-training for Person Re-identification with Noisy Labels (LUPerson-NL) The repository is for our CVPR2022 paper Large-Scale

43 Dec 26, 2022

[CVPR 2022] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Using Unreliable Pseudo Labels Official PyTorch implementation of Semi-Supervised Semantic Segmentation Using Unreliable Pseudo Labels, CVPR 2022. Ple

268 Dec 24, 2022

The repo of the preprinting paper "Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection"

Inferring Spatial Uncertainty in Object Detection A teaser version of the code for the paper Labels Are Not Perfect: Inferring Spatial Uncertainty in

21 Mar 3, 2022

Patch Rotation: A Self-Supervised Auxiliary Task for Robustness and Accuracy of Supervised Models

Patch-Rotation(PatchRot) Patch Rotation: A Self-Supervised Auxiliary Task for Robustness and Accuracy of Supervised Models Submitted to Neurips2021 To

4 Jul 12, 2021

Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

2 Dec 17, 2021

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning This is the official PyTorch implementation for UniMoCo pape

49 Jan 2, 2023

Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness

Orthogonalizing Convolutional Layers with the Cayley Transform This repository contains implementations and source code to reproduce experiments for t

36 Dec 30, 2022

Comments

Full code for reproducing the resutls

Thanks for your excellent work. May I ask whether the full code will be released for reproducing the results and developing new methods based on your work?

Regards

Lei

opened by LeiBAI 4
tabular data/ noisy instances
Hi, thanks for sharing your implementation. I have two questions about it:

Does it also work on tabular data?

Is it possible to identify the noisy instances (return the noisy IDs or the clean set)?

Thanks!
opened by nazaretl 1
Further research: Not All Knowledge Is Created Equal https://arxiv.org/abs/2106.01489

Not All Knowledge Is Created Equal Ziyun Li, Xinshao Wang, Haojin Yang, Di Hu, Neil M. Robertson, David A. Clifton, Christoph Meinel

arXiv: https://arxiv.org/abs/2106.01489

Mutual knowledge distillation (MKD) improves a model by distilling knowledge from another model. However, not all knowledge is certain and correct, especially under adverse conditions. For example, label noise usually leads to less reliable models due to the undesired memorisation [1, 2]. Wrong knowledge misleads the learning rather than helps. This problem can be handled by two aspects: (i) improving the reliability of a model where the knowledge is from (i.e., knowledge source's reliability); (ii) selecting reliable knowledge for distillation. In the literature, making a model more reliable is widely studied while selective MKD receives little attention. Therefore, we focus on studying selective MKD and highlight its importance in this work.

Concretely, a generic MKD framework, Confident knowledge selection followed by Mutual Distillation (CMD), is designed. The key component of CMD is a generic knowledge selection formulation, making the selection threshold either static (CMD-S) or progressive (CMD-P). Additionally, CMD covers two special cases: zero knowledge and all knowledge, leading to a unified MKD framework. We empirically find CMD-P performs better than CMD-S. The main reason is that a model's knowledge upgrades and becomes confident as the training progresses.

Extensive experiments are present to demonstrate the effectiveness of CMD and thoroughly justify the design of CMD. For example, CMD-P obtains new state-of-the-art results in robustness against label noise.

opened by XinshaoAmosWang 0

Releases(v2.0.0)

v2.0.0(Oct 20, 2021)

Source code(tar.gz)
Source code(zip)
v0.1(Mar 18, 2021)

The studied label correction methods are implemented as loss functions, being easy to use and can replace exisiting loss functions.
Source code(tar.gz)
Source code(zip)

Owner

amos_xwang

Deep Metric Learning, Robust Deep Learning, Semisupervised Learning, Label Noise, Sample Imbalance...

GitHub Repository

Code to use Augmented Shapiro Wilks Stopping, as well as code for the paper "Statistically Signifigant Stopping of Neural Network Training"

This codebase is being actively maintained, please create and issue if you have issues using it Basics All data files are included under losses and ea

32 Nov 09, 2021

Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis"

StrengthNet Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis" https://arxiv.org/abs/2110

65 Dec 20, 2022

Bayesian-Torch is a library of neural network layers and utilities extending the core of PyTorch to enable the user to perform stochastic variational inference in Bayesian deep neural networks

Bayesian-Torch is a library of neural network layers and utilities extending the core of PyTorch to enable the user to perform stochastic variational inference in Bayesian deep neural networks. Bayes

210 Jan 04, 2023

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

This repository holds NVIDIA-maintained utilities to streamline mixed precision and distributed training in Pytorch. Some of the code here will be included in upstream Pytorch eventually. The intenti

6.9k Jan 03, 2023

An official PyTorch Implementation of Boundary-aware Self-supervised Learning for Video Scene Segmentation (BaSSL)

72 Dec 28, 2022

SberSwap Video Swap base on deep learning

431 Jan 03, 2023

Streamlit Tutorial (ex: stock price dashboard, cartoon-stylegan, vqgan-clip, stylemixing, styleclip, sefa)

Streamlit Tutorials Install pip install streamlit Run cd [directory] streamlit run app.py --server.address 0.0.0.0 --server.port [your port] # http:/

30 Jan 06, 2023

A simple, unofficial implementation of MAE using pytorch-lightning

Masked Autoencoders in PyTorch A simple, unofficial implementation of MAE (Masked Autoencoders are Scalable Vision Learners) using pytorch-lightning.

20 Dec 03, 2022

[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

FaPN: Feature-aligned Pyramid Network for Dense Image Prediction [arXiv] [Project Page] @inproceedings{ huang2021fapn, title={{FaPN}: Feature-alig

175 Dec 30, 2022

Official Implementation of "Transformers Can Do Bayesian Inference"

Official Code for the Paper "Transformers Can Do Bayesian Inference" We train Transformers to do Bayesian Prediction on novel datasets for a large var

103 Dec 25, 2022

SOLOv2 on onnx & tensorRT

SOLOv2.tensorRT: NOTE: code based on WXinlong/SOLO add support to TensorRT inference onnxruntime tensorRT full_dims and dynamic shape postprocess with

47 Nov 26, 2022

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation (ICCV 2021)

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation (ICCV 2021) This repository contains the official implemen

81 Dec 14, 2022

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

Light Gradient Boosting Machine LightGBM is a gradient boosting framework that uses tree based learning algorithms. It is designed to be distributed a

14.5k Jan 08, 2023