This repository contains code for the paper "Disentangling Label Distribution for Long-tailed Visual Recognition", published at CVPR' 2021

Related tags

Deep LearningLADE
Overview

Disentangling Label Distribution for Long-tailed Visual Recognition (CVPR 2021)

Install

conda create -n longtail pip python=3.7 -y
source activate longtail
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch
pip install pyyaml tqdm matplotlib sklearn h5py tensorboard

Training

Preliminaries

  • Download pretrained caffe resnet152 model for Places-LT: please refer to link.

  • Prepare dataset: CIFAR-100, Places-LT, ImageNet-LT, iNaturalist 2018

    • Please download those datasets following Decoupling.

CIFAR-100 training

For CIFAR-100 with imbalance ratio 0.01, using LADE:

python main.py --seed 1 --cfg config/CIFAR100_LT/lade.yaml --exp_name lade2021/cifar100_imb0.01_lade --cifar_imb_ratio 0.01 --remine_lambda 0.01 --alpha 0.1 --gpu 0

Places-LT training

For PC Softmax:

python main.py --seed 1 --cfg config/Places_LT/ce.yaml --exp_name lade2021/places_pc_softmax --lr 0.05 --gpu 0,1,2,3

For LADE:

python main.py --seed 1 --cfg config/Places_LT/lade.yaml --exp_name lade2021/places_lade --lr 0.05 --remine_lambda 0.1 --alpha 0.005 --gpu 0,1,2,3

ImageNet-LT training

For LADE:

python main.py --seed 1 --cfg config/ImageNet_LT/lade.yaml  --exp_name lade2021/imagenet_lade --lr 0.05 --remine_lambda 0.5 --alpha 0.05 --gpu 0,1,2,3

iNaturalist18 training

For LADE:

python main.py --seed 1 --cfg ./config/iNaturalist18/lade.yaml --exp_name lade2021/inat_lade --lr 0.1 --alpha 0.05 --gpu 0,1,2,3

Evaluate on shifted test set & Confidence calibration

For Imagenet (Section 4.3, 4.4):

./notebooks/imagenet-shift-calib.ipynb

For CIFAR-100 (Supplementary material):

./notebooks/cifar100-shift-calib.ipynb

License

The use of this software is released under BSD-3.

Citation

If you find our paper or this project helps your research, please kindly consider citing our paper in your publications.

@article{hong2020disentangling,
  title={Disentangling Label Distribution for Long-tailed Visual Recognition},
  author={Hong, Youngkyu and Han, Seungju and Choi, Kwanghee and Seo, Seokjun and Kim, Beomsu and Chang, Buru},
  journal={arXiv preprint arXiv:2012.00321},
  year={2020}
}
Owner
Hyperconnect
Hyperconnect Inc
Hyperconnect
SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]

Learning to Classify Images without Labels This repo contains the Pytorch implementation of our paper: SCAN: Learning to Classify Images without Label

Wouter Van Gansbeke 1.1k Dec 30, 2022
Automated image registration. Registrationimation was too much of a mouthful.

alignimation Automated image registration. Registrationimation was too much of a mouthful. This repo contains the code used for my blog post Alignimat

Ethan Rosenthal 9 Oct 13, 2022
L-Verse: Bidirectional Generation Between Image and Text

Far beyond learning long-range interactions of natural language, transformers are becoming the de-facto standard for many vision tasks with their power and scalabilty

Kim, Taehoon 102 Dec 21, 2022
571 Dec 25, 2022
x-transformers-paddle 2.x version

x-transformers-paddle x-transformers-paddle 2.x version paddle 2.x版本 https://github.com/lucidrains/x-transformers 。 requirements paddlepaddle-gpu==2.2

yujun 7 Dec 08, 2022
[BMVC 2021] Official PyTorch Implementation of Self-supervised learning of Image Scale and Orientation Estimation

Self-Supervised Learning of Image Scale and Orientation Estimation (BMVC 2021) This is the official implementation of the paper "Self-Supervised Learn

Jongmin Lee 17 Nov 10, 2022
DeepHawkeye is a library to detect unusual patterns in images using features from pretrained neural networks

English | 简体中文 Introduction DeepHawkeye is a library to detect unusual patterns in images using features from pretrained neural networks Reference Pat

CV Newbie 28 Dec 13, 2022
A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation

A 3D multi-modal medical image segmentation library in PyTorch We strongly believe in open and reproducible deep learning research. Our goal is to imp

Adaloglou Nikolas 1.2k Dec 27, 2022
PyMove is a Python library to simplify queries and visualization of trajectories and other spatial-temporal data

Use PyMove and go much further Information Package Status License Python Version Platforms Build Status PyPi version PyPi Downloads Conda version Cond

Insight Data Science Lab 64 Nov 15, 2022
YOLOPのPythonでのONNX推論サンプル

YOLOP-ONNX-Video-Inference-Sample YOLOPのPythonでのONNX推論サンプルです。 ONNXモデルは、hustvl/YOLOP/weights を使用しています。 Requirement OpenCV 3.4.2 or later onnxruntime 1.

KazuhitoTakahashi 8 Sep 05, 2022
Robbing the FED: Directly Obtaining Private Data in Federated Learning with Modified Models

Robbing the FED: Directly Obtaining Private Data in Federated Learning with Modified Models This repo contains a barebones implementation for the atta

16 Dec 04, 2022
This is a clean and robust Pytorch implementation of DQN and Double DQN.

DQN/DDQN-Pytorch This is a clean and robust Pytorch implementation of DQN and Double DQN. Here is the training curve: All the experiments are trained

XinJingHao 15 Dec 27, 2022
An Implementation of SiameseRPN with Feature Pyramid Networks

SiameseRPN with FPN This project is mainly based on HelloRicky123/Siamese-RPN. What I've done is just add a Feature Pyramid Network method to the orig

3 Apr 16, 2022
Learning Efficient Online 3D Bin Packing on Packing Configuration Trees

Learning Efficient Online 3D Bin Packing on Packing Configuration Trees This repository is being continuously updated, please stay tuned! Any code con

86 Dec 28, 2022
Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

An official implementation of paper Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

11 Nov 23, 2022
:fire: 2D and 3D Face alignment library build using pytorch

Face Recognition Detect facial landmarks from Python using the world's most accurate face alignment network, capable of detecting points in both 2D an

Adrian Bulat 6k Dec 31, 2022
Python Single Object Tracking Evaluation

pysot-toolkit The purpose of this repo is to provide evaluation API of Current Single Object Tracking Dataset, including VOT2016 VOT2018 VOT2018-LT OT

348 Dec 22, 2022
The code repository for "PyCIL: A Python Toolbox for Class-Incremental Learning" in PyTorch.

PyCIL: A Python Toolbox for Class-Incremental Learning Introduction • Methods Reproduced • Reproduced Results • How To Use • License • Acknowledgement

Fu-Yun Wang 258 Dec 31, 2022
Rotation-Only Bundle Adjustment

ROBA: Rotation-Only Bundle Adjustment Paper, Video, Poster, Presentation, Supplementary Material In this repository, we provide the implementation of

Seong 51 Nov 29, 2022
Kohei's 5th place solution for xview3 challenge

xview3-kohei-solution Usage This repository assumes that the given data set is stored in the following locations: $ ls data/input/xview3/*.csv data/in

Kohei Ozaki 2 Jan 17, 2022