Self-Supervised Class-Cognizant Few-Shot Classification (2022-02-15T00:00:00.000000Z)

TL;DR

This paper focuses on unsupervised learning from an abundance of unlabeled data followed by few-shot fine-tuning on a downstream classification task and extends a recent study on adopting contrastive learning for self-supervised pre-training by incorporating class-level cognizance through iterative clustering and re-ranking and expanding the contrastive optimization loss to account for it.

Abstract

Unsupervised learning is argued to be the dark matter of human intelligence 1. To build in this direction, this paper focuses on unsupervised learning from an abundance of unlabeled data followed by few-shot fine-tuning on a downstream classification task. To this aim, we extend a recent study on adopting contrastive learning for self-supervised pre-training by incorporating class-level cognizance through iterative clustering and re-ranking and by expanding the contrastive optimization loss to account for it. To our knowledge, our experimentation both in standard and cross-domain scenarios demonstrate that we set a new state-of-the-art (SoTA) in (5-way, 1 and 5-shot) settings of standard mini-ImageNet benchmark as well as the (5-way, 5 and 20-shot) settings of cross-domain CDFSL benchmark. Our code and experimentation can be found in our GitHub repository: https://github.com/ojss/c3lr.

Authors

O. Shirekar

1 papers

H. J. Rad

1 papers

TL;DR

Abstract

Authors

References28 items

Self-Supervised Prototypical Transfer Learning for Few-Shot Classification

Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models

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

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

Self-Supervised Learning for Few-Shot Image Classification

Unsupervised Few-shot Learning via Self-supervised Training

A Baseline for Few-Shot Image Classification

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

Meta-Learning for Semi-Supervised Few-Shot Classification

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

hdbscan: Hierarchical density based clustering

Prototypical Networks for Few-shot Learning

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

Re-ranking Person Re-identification with k-Reciprocal Encoding

Matching Networks for One Shot Learning

Using Deep Learning for Image-Based Plant Disease Detection

Human-level concept learning through probabilistic program induction

Adam: A Method for Stochastic Optimization

The Caltech-UCSD Birds-200-2011 Dataset

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

SELF-SUPERVISED CLASS-COGNIZANT FEW-SHOT

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names