Pytorch implementation of Cut-Thumbnail in the paper Cut-Thumbnail:A Novel Data Augmentation for Convolutional Neural Network.

Overview

Cut-Thumbnail (Accepted at ACM MULTIMEDIA 2021)

Tianshu Xie, Xuan Cheng, Xiaomin Wang, Minghui Liu, Jiali Deng, Tao Zhou, Ming Liu

This is the official Pytorch implementation of Cut-Thumbnail in the paper Cut-Thumbnail:A Novel Data Augmentation for Convolutional Neural Network.

This implementation is based on these repositories:

Main Requirements

  • torch == 1.0.1
  • torchvision == 0.2.0
  • Python 3

Training Examples

  • Mixed Single Thumbnail
python train.py -d [datasetlocation] --depth 50 --mode mst --size 112 --lam 0.25 --participation_rate 0.8
  • Self Thumbnail
python train.py -d [datasetlocation] --depth 50 --mode st --size 112 --lam 0.25 --participation_rate 0.8

Results

  • ImageNet Results
Model Accuracy (%)
ResNet50 + CutMix 78.60*
ResNet50 + Cut-Thumbnail (ST) 77.74
ResNet50 + Cut-Thumbnail (MST) 79.21

* denotes results reported in the original papers.

  • CIFAR-100 Results
Model Accuracy (%)
WideResNet-28-10 + Cut-Thumbnail (ST) 81.41
WideResNet-28-10 + Cut-Thumbnail (MST) 83.35
  • CUB-200-2011 Results
Model Accuracy (%)
ResNet50 + Cut-Thumbnail (ST) 85.72
ResNet50 + Cut-Thumbnail (MST) 86.56
ResNet50 + Cut-Thumbnail (MDT) 86.72

Citation

If you find our paper and this repo useful, please cite as

@inproceedings{xie20cut-thumbnail,
    author = {Xie, Tianshu and Cheng, Xuan and Wang, Xiaomin and Liu, Minghui and Deng, Jiali and Zhou, Tao and Liu, Ming},
    title = {Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network},
    year = {2021},
    isbn = {9781450386517},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3474085.3475302},
    doi = {10.1145/3474085.3475302},
    booktitle = {Proceedings of the 29th ACM International Conference on Multimedia},
    pages = {1627–1635},
    numpages = {9},
    location = {Virtual Event, China},
    series = {MM '21}
}
Consecutive-Subsequence - Simple software to calculate susequence with highest sum

Simple software to calculate susequence with highest sum This repository contain

Gbadamosi Farouk 1 Jan 31, 2022
Implementation of the Point Transformer layer, in Pytorch

Point Transformer - Pytorch Implementation of the Point Transformer self-attention layer, in Pytorch. The simple circuit above seemed to have allowed

Phil Wang 501 Jan 03, 2023
Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022

LDL Paper | Supplementary Material Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution Jie Liang*, Hu

150 Dec 26, 2022
One line to host them all. Bootstrap your image search case in minutes.

One line to host them all. Bootstrap your image search case in minutes. Survey NOW gives the world access to customized neural image search in just on

Jina AI 403 Dec 30, 2022
Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty

Deep Deterministic Uncertainty This repository contains the code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic

Jishnu Mukhoti 69 Nov 28, 2022
Code for paper Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting

Decoupled Spatial-Temporal Graph Neural Networks Code for our paper: Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting.

S22 43 Jan 04, 2023
Implementation of Online Label Smoothing in PyTorch

Online Label Smoothing Pytorch implementation of Online Label Smoothing (OLS) presented in Delving Deep into Label Smoothing. Introduction As the abst

83 Dec 14, 2022
(CVPR 2021) Lifting 2D StyleGAN for 3D-Aware Face Generation

Lifting 2D StyleGAN for 3D-Aware Face Generation Official implementation of paper "Lifting 2D StyleGAN for 3D-Aware Face Generation". Requirements You

Yichun Shi 66 Nov 29, 2022
Demonstrates iterative FGSM on Apple's NeuralHash model.

apple-neuralhash-attack Demonstrates iterative FGSM on Apple's NeuralHash model. TL;DR: It is possible to apply noise to CSAM images and make them loo

Lim Swee Kiat 11 Jun 23, 2022
Just Randoms Cats with python

Random-Cat Just Randoms Cats with python.

OriCode 2 Dec 21, 2021
Attentional Focus Modulates Automatic Finger‑tapping Movements

"Attentional Focus Modulates Automatic Finger‑tapping Movements", in Scientific Reports

Xingxun Jiang 1 Dec 02, 2021
QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

Introduction QRec is a Python framework for recommender systems (Supported by Python 3.7.4 and Tensorflow 1.14+) in which a number of influential and

Yu 1.4k Dec 30, 2022
U-2-Net: U Square Net - Modified for paired image training of style transfer

U2-Net: U Square Net Modified for paired image training of style transfer This is an unofficial repo making use of the code which was made available b

Doron Adler 43 Oct 03, 2022
TensorFlow implementation of "A Simple Baseline for Bayesian Uncertainty in Deep Learning"

TensorFlow implementation of "A Simple Baseline for Bayesian Uncertainty in Deep Learning"

YeongHyeon Park 7 Aug 28, 2022
Offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation

Shunted Transformer This is the offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation by Sucheng Ren, Daquan Zhou, Shengf

156 Dec 27, 2022
LBK 20 Dec 02, 2022
A Python library for working with arbitrary-dimension hypercomplex numbers following the Cayley-Dickson construction of algebras.

Hypercomplex A Python library for working with quaternions, octonions, sedenions, and beyond following the Cayley-Dickson construction of hypercomplex

7 Nov 04, 2022
This repo is to be freely used by ML devs to check the GAN performances without coding from scratch.

GANs for Fun Created because I can! GOAL The goal of this repo is to be freely used by ML devs to check the GAN performances without coding from scrat

Sagnik Roy 13 Jan 26, 2022
This repository contains the source code of an efficient 1D probabilistic model for music time analysis proposed in ICASSP2022 venue.

Jump Reward Inference for 1D Music Rhythmic State Spaces An implementation of the probablistic jump reward inference model for music rhythmic informat

Mojtaba Heydari 25 Dec 16, 2022
.NET bindings for the Pytorch engine

TorchSharp TorchSharp is a .NET library that provides access to the library that powers PyTorch. It is a work in progress, but already provides a .NET

Matteo Interlandi 17 Aug 30, 2021