Self-Attention Message Passing for Contrastive Few-Shot Learning (2022-10-12T00:00:00.000000Z)

TL;DR

This work proposes a novel self-attention based message passing contrastive learning approach (coined as SAMP-CLR) for U-FSL pre-training and proposes an optimal transport based fine-tuning strategy (OT) to efficiently induce task awareness into the authors' novel end-to-end unsupervised few-shot classification framework (SAMPTransfer).

Abstract

Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision. Deep learning models, however, require an abundance of data and supervision to perform at a satisfactory level. Unsupervised few-shot learning (U-FSL) is the pursuit of bridging this gap between machines and humans. Inspired by the capacity of graph neural networks (GNNs) in discovering complex inter-sample relationships, we propose a novel self-attention based message passing contrastive learning approach (coined as SAMP-CLR) for U-FSL pre-training. We also propose an optimal transport (OT) based fine-tuning strategy (we call OpT-Tune) to efficiently induce task awareness into our novel end-to-end unsupervised few-shot classification framework (SAMPTransfer). Our extensive experimental results corroborate the efficacy of SAMPTransferin a variety of downstream few-shot classification scenarios, setting a new state-of-the-art for U-FSL on both miniImageNet and tieredImageNet benchmarks, offering up to 7%+ and 5%+ improvements, respectively. Our further investigations also confirm that SAMPTransferremains on-par with some supervised baselines on miniImageNet and outperforms all existing U-FSL baselines in a challenging cross-domain scenario. Our code can be found in our GitHub repository: https://github.com/ojss/SAMPTransfer/.

Authors

Ashutosh Kumar Singh

3 papers

Ojas Shirekar

1 papers

H. Jamali-Rad

1 papers

TL;DR

Abstract

Authors

References63 items

Pure Transformers are Powerful Graph Learners

Self-Supervised Class-Cognizant Few-Shot Classification

Multi-Level Second-Order Few-Shot Learning

Hybrid Graph Neural Networks for Few-Shot Learning

How Attentive are Graph Attention Networks?

Cross-Domain Few-Shot Classification via Adversarial Task Augmentation

With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations

Unsupervised meta-learning for few-shot learning

Self-supervised Pretraining of Visual Features in the Wild

Learning Intra-Batch Connections for Deep Metric Learning

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks

Exploring Simple Siamese Representation Learning

Few-Shot Image Classification via Contrastive Self-Supervised Learning

Self-Supervised Prototypical Transfer Learning for Few-Shot Classification

Enhancing Few-Shot Image Classification with Unlabelled Examples

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

DPGN: Distribution Propagation Graph Network for Few-Shot Learning

Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?

A Simple Framework for Contrastive Learning of Visual Representations

Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning

A New Benchmark for Evaluation of Cross-Domain Few-Shot Learning

Momentum Contrast for Unsupervised Visual Representation Learning

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

Unsupervised Few-shot Learning via Self-supervised Training

A Baseline for Few-Shot Image Classification

Boosting Few-Shot Visual Learning With Self-Supervision

Learning Representations by Maximizing Mutual Information Across Views

Edge-Labeling Graph Neural Network for Few-Shot Learning

Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation

Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

Unsupervised Meta-Learning for Few-Shot Image Classification

Unsupervised Learning via Meta-Learning

Learning to Propagate Labels: Transductive Propagation Network for Few-Shot Learning

Computational Optimal Transport

Meta-Learning for Semi-Supervised Few-Shot Classification

Few-Shot Learning with Graph Neural Networks

Graph Attention Networks

EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification

Attention is All you Need

ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases

Prototypical Networks for Few-shot Learning

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Matching Networks for One Shot Learning

Using Deep Learning for Image-Based Plant Disease Detection

Adam: A Method for Stochastic Optimization

Sinkhorn Distances: Lightspeed Computation of Optimal Transport

Metric distances derived from cosine similarity and Pearson and Spearman correlations

The Caltech-UCSD Birds-200-2011 Dataset

ImageNet: A large-scale hierarchical image database

Learning from labeled and unlabeled data with label propagation

Multi-Level 신경망

A Cluster Separation Measure

Concerning nonnegative matrices and doubly stochastic matrices

ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning

Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning

Parameterless Transductive Feature Re-representation for Few-Shot Learning

Attentional Constellation Nets for Few-Shot Learning

on few-shot recognition

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names