Generalized Data Weighting via Class-level Gradient Manipulation

Related tags

Deep Learning deep-learning pytorch meta-learning
Overview

Generalized Data Weighting via Class-level Gradient Manipulation

This repository is the official implementation of Generalized Data Weighting via Class-level Gradient Manipulation (NeurIPS 2021).



If you find this code useful in your research then please cite:

@misc{chen2021generalized,
      title={Generalized Data Weighting via Class-level Gradient Manipulation}, 
      author={Can Chen and Shuhao Zheng and Xi Chen and Erqun Dong and Xue Liu and Hao Liu and Dejing Dou},
      year={2021},
      eprint={2111.00056},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Requirements

  • Linux
  • Python 3.7
  • Pytorch 1.9.0
  • Torchvision 0.9.1

More specifically, run this command:

pip install -r requirements.txt

Run mw-net and gdw on CIFAR10

Download CIFAR10 and place it in ./data.

To compare mw-net and gdw on CIFAR10 under 40% uniform noise, run this command:

python -u  main.py --corruption_prob 0.4 --dataset cifar10 --mode mw-net --outer_lr 100
python -u  main.py --corruption_prob 0.4 --dataset cifar10 --mode gdw --outer_lr 100

We set the outer level learning as 100 on CIFAR10 and 1000 on CIFAR100.

Results

We place training logs of the above command in ./log and list results as below:

Method mw-net gdw
Accuracy 86.62% 87.97%

Acknowledgements

We thank the Pytorch implementation on mw-net(https://github.com/xjtushujun/meta-weight-net).

You might also like...
A generalized framework for prototyping full-stack cooperative driving automation applications under CARLA+SUMO.
A generalized framework for prototyping full-stack cooperative driving automation applications under CARLA+SUMO.

OpenCDA OpenCDA is a SIMULATION tool integrated with a prototype cooperative driving automation (CDA; see SAE J3216) pipeline as well as regular autom

UCLA Mobility Lab 726 Dec 29, 2022
code for ICCV 2021 paper 'Generalized Source-free Domain Adaptation'

G-SFDA Code (based on pytorch 1.3) for our ICCV 2021 paper 'Generalized Source-free Domain Adaptation'. [project] [paper]. Dataset preparing Download

Shiqi Yang 84 Dec 26, 2022
An official implementation of "Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation" (ICCV 2021) in PyTorch.

Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation This is an official implementation of the paper "Exploiting a Joint

CV Lab @ Yonsei University 35 Oct 26, 2022
GeDML is an easy-to-use generalized deep metric learning library
GeDML is an easy-to-use generalized deep metric learning library

GeDML is an easy-to-use generalized deep metric learning library

Borui Zhang 32 Dec 5, 2022
Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation
Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation

Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation The code repository for "Audio-Visual Generalized Few-Shot Learning with

Kaiaicy 3 Jun 27, 2022
Generalized hybrid model for mode-locked laser diodes with an extended passive cavity

GenHybridMLLmodel Generalized hybrid model for mode-locked laser diodes with an extended passive cavity This hybrid simulation strategy combines a tra

Stijn Cuyvers 3 Sep 21, 2022
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

The official code for the NeurIPS 2021 paper Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

null 13 Dec 22, 2022
Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks

OnsagerNet Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks This is the original pyTorch implemenati

Haijun.Yu 3 Aug 24, 2022
Generalized Decision Transformer for Offline Hindsight Information Matching

Generalized Decision Transformer for Offline Hindsight Information Matching [arxiv] If you use this codebase for your research, please cite the paper:

Hiroki Furuta 35 Dec 12, 2022
Comments
  • What's the function of VNET?

    What's the function of VNET?

    I am reading your great work, but I am confused about the vnet in your code. Could you explain the function of vnet in your code？

    I guess v_lambda[index, targets] = (torch.sum(v_lambda * p.data, dim=1) - v_lambda[index, targets] * p.data[index, targets]) / (1 - p.data[index, targets]) is the code for eq.4 in the paper. But why v_lambda is the output of vnet in v_lambda = vnet(cost_v.data) ??

    I'm looking forward to your reply. Thank you so much.

    (If you can speak Chinese, could you reply me in Chinese? My English is not very good.)

    opened by Chauncey-Wang 2
Owner
null
GitHub
ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a large-scale learning-from-demonstrations benchmark for object manipulation.

ManiSkill-Learn ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge, a large-scale learning-from-dem

Hao Su's Lab, UCSD 48 Dec 30, 2022
A PyTorch implementation of Learning to learn by gradient descent by gradient descent

Intro PyTorch implementation of Learning to learn by gradient descent by gradient descent. Run python main.py TODO Initial implementation Toy data LST

Ilya Kostrikov 300 Dec 11, 2022
Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection

LMFD-PAD Note This is the official repository of the paper: LMFD-PAD: Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechani

null 28 Dec 2, 2022
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.

Nonuniform-to-Uniform Quantization This repository contains the training code of N2UQ introduced in our CVPR 2022 paper: "Nonuniform-to-Uniform Quanti

Zechun Liu 60 Dec 28, 2022
Code release for our paper, "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo"

SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo Thomas Kollar, Michael Laskey, Kevin Stone, Brijen Thananjeyan

null 68 Dec 14, 2022
The official implementation of You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient.

You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient (paper) @misc{zhang2021compress,

null 46 Dec 7, 2022
MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks

MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks Introduction This repo contains the pytorch impl

Meta Research 38 Oct 10, 2022
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch

Transformer in Transformer Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image c

Phil Wang 272 Dec 23, 2022
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

Learning Pixel-level Semantic Affinity with Image-level Supervision This code is deprecated. Please see https://github.com/jiwoon-ahn/irn instead. Int

Jiwoon Ahn 337 Dec 15, 2022
This is the source code for our ICLR2021 paper: Adaptive Universal Generalized PageRank Graph Neural Network.

GPRGNN This is the source code for our ICLR2021 paper: Adaptive Universal Generalized PageRank Graph Neural Network. Hidden state feature extraction i

Jianhao 92 Jan 3, 2023