HyperAIHyperAI

Command Palette

Search for a command to run...

2 months ago

Generalized Adaptation for Few-Shot Learning

Liang Song Jinlu Liu Yongqiang Qin

Abstract

Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model. In this paper, we propose to use closed-form base learner, which constrains the adapting stage with pre-trained base model to get better generalized novel model. Following theoretical analysis proves its rationality as well as indication of how to train a well-generalized base model. We then conduct experiments on four benchmarks and achieve state-of-the-art performance in all cases. Notably, we achieve the accuracy of 87.75% on 5-shot miniImageNet which approximately outperforms existing methods by 10%.

Benchmarks

BenchmarkMethodologyMetrics
few-shot-image-classification-on-cifar-fs-5ACC + Amphibian
Accuracy: 73.1
few-shot-image-classification-on-cifar-fs-5-1ACC + Amphibian
Accuracy: 89.3
few-shot-image-classification-on-fc100-5-wayACC + Amphibian
Accuracy: 41.6
few-shot-image-classification-on-fc100-5-way-1ACC + Amphibian
Accuracy: 66.9
few-shot-image-classification-on-mini-2ACC + Amphibian
Accuracy: 62.21
few-shot-image-classification-on-mini-3ACC + Amphibian
Accuracy: 80.75
few-shot-image-classification-on-tieredACC + Amphibian
Accuracy: 68.77
few-shot-image-classification-on-tiered-1ACC + Amphibian
Accuracy: 86.75

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp
Generalized Adaptation for Few-Shot Learning | Papers | HyperAI