Self-training for Few-shot Transfer Across Extreme Task Differences

Related tags

Deep LearningSTARTUP
Overview

Self-training for Few-shot Transfer Across Extreme Task Differences (STARTUP)

Introduction

This repo contains the official implementation of the following ICLR2021 paper:

Title: Self-training for Few-shot Transfer Across Extreme Task Differences
Authors: Cheng Perng Phoo, Bharath Hariharan
Institution: Cornell University
Arxiv: https://arxiv.org/abs/2010.07734
Abstract:
Most few-shot learning techniques are pre-trained on a large, labeled "base dataset". In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training in a different "source" problem domain (e.g., ImageNet), which can be very different from the desired target task. Traditional few-shot and transfer learning techniques fail in the presence of such extreme differences between the source and target tasks. In this paper, we present a simple and effective solution to tackle this extreme domain gap: self-training a source domain representation on unlabeled data from the target domain. We show that this improves one-shot performance on the target domain by 2.9 points on average on the challenging BSCD-FSL benchmark consisting of datasets from multiple domains.

Requirements

This codebase is tested with:

  1. PyTorch 1.7.1
  2. Torchvision 0.8.2
  3. NumPy
  4. Pandas
  5. wandb (used for logging. More here: https://wandb.ai/)

Running Experiments

Step 0: Dataset Preparation

MiniImageNet and CD-FSL: Download the datasets for CD-FSL benchmark following step 1 and step 2 here: https://github.com/IBM/cdfsl-benchmark
tieredImageNet: Prepare the tieredImageNet dataset following https://github.com/mileyan/simple_shot. Note after running the preparation script, you will need to split the saved images into 3 different folders: train, val, test.

Step 1: Teacher Training on the Base Dataset

We provide scripts to produce teachers for different base datasets. Regardless of the base datasets, please follow the following steps to produce the teachers:

  1. Go into the directory teacher_miniImageNet/ (teacher_ImageNet/ for ImageNet)
  2. Take care of the TODO: in run.sh and configs.py (if applicable).
  3. Run bash run.sh to produce the teachers.

Note that for miniImageNet and tieredImageNet, the training script is adapted based on the official script provided by the CD-FSL benchmark. For ImageNet, we simply download the pre-trained models from PyTorch and convert them to relevant format.

Step 2: Student Training

To train the STARTUP's representation, please follow the following steps:

  1. Go into the directory student_STARTUP/ (student_STARTUP_no_self_supervision/ for the version without SimCLR)
  2. Take care of the TODO: in run.sh and configs.py
  3. Run bash run.sh to produce the student/STARTUP representation.

Step 3: Evaluation

To evaluate different representations, go into evaluation/, modify the TODO: in run.sh and configs.py and run bash run.sh.

Notes

  1. When producing the results for the submitted paper, we did not set torch.backends.cudnn.deterministic and torch.backends.cudnn.benchmark properly, thus causing non-deterministic behaviors. We have rerun our experiments and the updated numbers can be found here: https://docs.google.com/spreadsheets/d/1O1e9xdI1SxVvRWK9VVxcO8yefZhePAHGikypWfhRv8c/edit?usp=sharing. Although some of the numbers has changed, the conclusion in the paper remains unchanged. STARTUP is able to outperform all the baselines, bringing forth tremendous improvements to cross-domain few-shot learning.
  2. All the trainings are done on Nvidia Titan RTX GPU. Evaluation of different representations are performed using Nvidia RTX 2080Ti. Regardless of the GPU models, CUDA11 is used.
  3. This repo is built upon the official CD-FSL benchmark repo: https://github.com/IBM/cdfsl-benchmark/tree/9c6a42f4bb3d2638bb85d3e9df3d46e78107bc53. We thank the creators of the CD-FSL benchmark for releasing code to the public.
  4. If you find this codebase or STARTUP useful, please consider citing our paper:
@inproceeding{phoo2021STARTUP,
    title={Self-training for Few-shot Transfer Across Extreme Task Differences},
    author={Phoo, Cheng Perng and Hariharan, Bharath},
    booktitle={Proceedings of the International Conference on Learning Representations},
    year={2021}
}
Owner
Cheng Perng Phoo
PhD Student at Cornell
Cheng Perng Phoo
1st place solution to the Satellite Image Change Detection Challenge hosted by SenseTime

1st place solution to the Satellite Image Change Detection Challenge hosted by SenseTime

Lihe Yang 209 Jan 01, 2023
验证码识别 深度学习 tensorflow 神经网络

captcha_tf2 验证码识别 深度学习 tensorflow 神经网络 使用卷积神经网络,对字符,数字类型验证码进行识别,tensorflow使用2.0以上 目前项目还在更新中,诸多bug,欢迎提出issue和PR, 希望和你一起共同完善项目。 实例demo 训练过程 优化器选择: Adam

5 Apr 28, 2022
Simple tutorials on Pytorch DDP training

pytorch-distributed-training Distribute Dataparallel (DDP) Training on Pytorch Features Easy to study DDP training You can directly copy this code for

Ren Tianhe 188 Jan 06, 2023
CryptoFrog - My First Strategy for freqtrade

cryptofrog-strategies CryptoFrog - My First Strategy for freqtrade NB: (2021-04-20) You'll need the latest freqtrade develop branch otherwise you migh

Robert Davey 137 Jan 01, 2023
JAXDL: JAX (Flax) Deep Learning Library

JAXDL: JAX (Flax) Deep Learning Library Simple and clean JAX/Flax deep learning algorithm implementations: Soft-Actor-Critic (arXiv:1812.05905) Transf

Patrick Hart 4 Nov 27, 2022
Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.

Vision Transformer with Progressive Sampling This is the official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.

yuexy 123 Jan 01, 2023
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator

DRL-robot-navigation Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gra

87 Jan 07, 2023
Cross-media Structured Common Space for Multimedia Event Extraction (ACL2020)

Cross-media Structured Common Space for Multimedia Event Extraction Table of Contents Overview Requirements Data Quickstart Citation Overview The code

Manling Li 49 Nov 21, 2022
Faster RCNN with PyTorch

Faster RCNN with PyTorch Note: I re-implemented faster rcnn in this project when I started learning PyTorch. Then I use PyTorch in all of my projects.

Long Chen 1.6k Dec 23, 2022
using STGCN to achieve egg classification task

EEG Classification   The task requires us to classify electroencephalography(EEG) into six categories, including human body, human face, animal body,

4 Jun 13, 2022
CT-Net: Channel Tensorization Network for Video Classification

[ICLR2021] CT-Net: Channel Tensorization Network for Video Classification @inproceedings{ li2021ctnet, title={{\{}CT{\}}-Net: Channel Tensorization Ne

33 Nov 15, 2022
​ This is the Pytorch implementation of Progressive Attentional Manifold Alignment.

PAMA This is the Pytorch implementation of Progressive Attentional Manifold Alignment. Requirements python 3.6 pytorch 1.2.0+ PIL, numpy, matplotlib C

98 Nov 15, 2022
Open source Python implementation of the HDR+ photography pipeline

hdrplus-python Open source Python implementation of the HDR+ photography pipeline, originally developped by Google and presented in a 2016 article. Th

77 Jan 05, 2023
Public repository containing materials used for Feed Forward (FF) Neural Networks article.

Art041_NN_Feed_Forward Public repository containing materials used for Feed Forward (FF) Neural Networks article. -- Illustration of a very simple Fee

SolClover 2 Dec 29, 2021
MiraiML: asynchronous, autonomous and continuous Machine Learning in Python

MiraiML Mirai: future in japanese. MiraiML is an asynchronous engine for continuous & autonomous machine learning, built for real-time usage. Usage In

Arthur Paulino 25 Jul 27, 2022
Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision.

Monk - A computer vision toolkit for everyone Why use Monk Issue: Want to begin learning computer vision Solution: Start with Monk's hands-on study ro

Tessellate Imaging 507 Dec 04, 2022
TrTr: Visual Tracking with Transformer

TrTr: Visual Tracking with Transformer We propose a novel tracker network based on a powerful attention mechanism called Transformer encoder-decoder a

趙 漠居(Zhao, Moju) 66 Dec 27, 2022
Robot Servers and Server Manager software for robo-gym

robo-gym-server-modules Robot Servers and Server Manager software for robo-gym. For info on how to use this package please visit the robo-gym website

JR ROBOTICS 4 Aug 16, 2021
A no-BS, dead-simple training visualizer for tf-keras

A no-BS, dead-simple training visualizer for tf-keras TrainingDashboard Plot inter-epoch and intra-epoch loss and metrics within a jupyter notebook wi

Vibhu Agrawal 3 May 28, 2021
Speech Recognition using DeepSpeech2.

deepspeech.pytorch Implementation of DeepSpeech2 for PyTorch using PyTorch Lightning. The repo supports training/testing and inference using the DeepS

Sean Naren 2k Jan 04, 2023