Applying curriculum to meta-learning for few shot classification

Overview

Curriculum Meta-Learning for Few-shot Classification

We propose an adaptation of the curriculum training framework, applicable to state-of-the-art meta learning techniques for few-shot classification. Curriculum-based training popularly attempts to mimic human learning by progressively increasing the training complexity to enable incremental concept learning. As the meta-learner's goal is learning how to learn from as few samples as possible, the exact number of those samples (i.e. the size of the support set) arises as a natural proxy of a given task's difficulty. We define a simple yet novel curriculum schedule that begins with a larger support size and progressively reduces it throughout training to eventually match the desired shot-size of the test setup. This proposed method boosts the learning efficiency as well as the generalization capability. Our experiments with the MAML algorithm on two few-shot image classification tasks show significant gains with the curriculum training framework. Ablation studies corroborate the independence of our proposed method from the model architecture as well as the meta-learning hyperparameters.

How to reproduce

Our code is based on the learn2learn library. Specifically we start from their MAML implementation and extend with the ideas presented in our paper. Each of the results presented in the paper (incl. Ablation studies) can be reproduced by invoking the main script with appropriate arguments.

Requirements

Install dependencies:

pip install torch
pip install learn2learn

Examples

5 way - 5 shot MiniImagenet using a Convolutional neural network.

# Vanilla, achieves ~ 58% accuracy
python3 curriculum_meta_learning.py --dataset mini-imagenet --multiplier 1 --shot 5 --ways 5

# Ours, achieves ~ 66% accuracy
python3 curriculum_meta_learning.py --dataset mini-imagenet --multiplier 5 --shot 5 --ways 5

5 way - 1 shot OmniGlot using a Fully Connected neural network.

# Vanilla, achieves ~ 90% accuracy
python3 curriculum_meta_learning.py --dataset omniglot --multiplier 1 --shot 1 --ways 5 --fc

# Ours, achieves ~ 94% accuracy
python3 curriculum_meta_learning.py --dataset omniglot --multiplier 5 --shot 1 --ways 5 --fc

Ablation: disable LR annealing or query size adaptation durinng training.

python3 curriculum_meta_learning.py --multiplier 3 --freeze_lr

python3 curriculum_meta_learning.py --multiplier 3 --freeze_l

Ablation: Use a statically larger support size instead of curriculum.

python3 curriculum_meta_learning.py --dataset mini-imagenet --multiplier 5 --shot 5 --ways 5 --freeze_multiplier

Authors

Owner
Stergiadis Manos
Stergiadis Manos
Collective Multi-type Entity Alignment Between Knowledge Graphs (WWW'20)

CG-MuAlign A reference implementation for "Collective Multi-type Entity Alignment Between Knowledge Graphs", published in WWW 2020. If you find our pa

Bran Zhu 28 Dec 11, 2022
One Million Scenes for Autonomous Driving

ONCE Benchmark This is a reproduced benchmark for 3D object detection on the ONCE (One Million Scenes) dataset. The code is mainly based on OpenPCDet.

148 Dec 28, 2022
Thermal Control of Laser Powder Bed Fusion using Deep Reinforcement Learning

This repository is the implementation of the paper "Thermal Control of Laser Powder Bed Fusion Using Deep Reinforcement Learning", linked here. The project makes use of the Deep Reinforcement Library

BaratiLab 11 Dec 27, 2022
Crab is a flexible, fast recommender engine for Python that integrates classic information filtering recommendation algorithms in the world of scientific Python packages (numpy, scipy, matplotlib).

Crab - A Recommendation Engine library for Python Crab is a flexible, fast recommender engine for Python that integrates classic information filtering r

python-recsys 1.2k Dec 21, 2022
Code for one-stage adaptive set-based HOI detector AS-Net.

AS-Net Code for one-stage adaptive set-based HOI detector AS-Net. Mingfei Chen*, Yue Liao*, Si Liu, Zhiyuan Chen, Fei Wang, Chen Qian. "Reformulating

Mingfei Chen 45 Dec 09, 2022
Code and data for ACL2021 paper Cross-Lingual Abstractive Summarization with Limited Parallel Resources.

Multi-Task Framework for Cross-Lingual Abstractive Summarization (MCLAS) The code for ACL2021 paper Cross-Lingual Abstractive Summarization with Limit

Yu Bai 43 Nov 07, 2022
A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking PoseRBPF Paper Self-supervision Paper Pose Estimation Video Robot Manipulati

NVIDIA Research Projects 107 Dec 25, 2022
Text and code for the forthcoming second edition of Think Bayes, by Allen Downey.

Think Bayes 2 by Allen B. Downey The HTML version of this book is here. Think Bayes is an introduction to Bayesian statistics using computational meth

Allen Downey 1.5k Jan 08, 2023
Tool for live presentations using manim

manim-presentation Tool for live presentations using manim Install pip install manim-presentation opencv-python Usage Use the class Slide as your sce

Federico Galatolo 146 Jan 06, 2023
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
Unified tracking framework with a single appearance model

Paper: Do different tracking tasks require different appearance model? [ArXiv] (comming soon) [Project Page] (comming soon) UniTrack is a simple and U

ZhongdaoWang 300 Dec 24, 2022
VideoGPT: Video Generation using VQ-VAE and Transformers

VideoGPT: Video Generation using VQ-VAE and Transformers [Paper][Website][Colab][Gradio Demo] We present VideoGPT: a conceptually simple architecture

Wilson Yan 470 Dec 30, 2022
Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"

Focal Transformer This is the official implementation of our Focal Transformer -- "Focal Self-attention for Local-Global Interactions in Vision Transf

Microsoft 486 Dec 20, 2022
PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-supervised ViT.

MAE for Self-supervised ViT Introduction This is an unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-sup

36 Oct 30, 2022
Official public repository of paper "Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation"

Intention Adaptive Graph Neural Network (IAGNN) This is the official repository of paper Intention Adaptive Graph Neural Network for Category-Aware Se

9 Nov 22, 2022
This program presents convolutional kernel density estimation, a method used to detect intercritical epilpetic spikes (IEDs)

Description This program presents convolutional kernel density estimation, a method used to detect intercritical epilpetic spikes (IEDs) in [Gardy et

Ludovic Gardy 0 Feb 09, 2022
基于PaddleClas实现垃圾分类,并转换为inference格式用PaddleHub服务端部署

百度网盘链接及提取码: 链接:https://pan.baidu.com/s/1HKpgakNx1hNlOuZJuW6T1w 提取码:wylx 一个垃圾分类项目带你玩转飞桨多个产品(1) 基于PaddleClas实现垃圾分类,导出inference模型并利用PaddleHub Serving进行服务

thomas-yanxin 22 Jul 12, 2022
This application is the basic of automated online-class-joiner(for YıldızEdu) within the right time. Gets the ZOOM link by scheduled date and time.

This application is the basic of automated online-class-joiner(for YıldızEdu) within the right time. Gets the ZOOM link by scheduled date and time.

215355 1 Dec 16, 2021
[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links

LinkBERT: A Knowledgeable Language Model Pretrained with Document Links This repo provides the model, code & data of our paper: LinkBERT: Pretraining

Michihiro Yasunaga 264 Jan 01, 2023
PyTorch reimplementation of REALM and ORQA

PyTorch reimplementation of REALM and ORQA

Li-Huai (Allan) Lin 17 Aug 20, 2022