Fast and Generalized Adaptation for Few-Shot Learning

11/25/2019
by   Liang Song, et al.
0

The ability of fast generalizing to novel tasks from a few examples is critical in dealing with few-shot learning problems. However, deep learning models severely suffer from overfitting in extreme low data regime. In this paper, we propose Adaptable Cosine Classifier (ACC) and Amphibian to achieve fast and generalized adaptation for few-shot learning. The ACC realizes the flexible retraining of a deep network on small data without overfitting. The Amphibian learns a good weight initialization in the parameter space where optimal solutions for the tasks of the same class cluster tightly. It enables rapid adaptation to novel tasks with few gradient updates. We conduct comprehensive experiments on four few-shot datasets and achieve state-of-the-art performance in all cases. Notably, we achieve the accuracy of 87.75 by 10 the best results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/19/2018

Few-Shot Adaptation for Multimedia Semantic Indexing

We propose a few-shot adaptation framework, which bridges zero-shot lear...
research
03/15/2017

Prototypical Networks for Few-shot Learning

We propose prototypical networks for the problem of few-shot classificat...
research
02/05/2022

Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach

Few-shot learning (FSL) is the process of rapid generalization from abun...
research
03/02/2017

Attentive Recurrent Comparators

Rapid learning requires flexible representations to quickly adopt to new...
research
04/07/2022

Powering Finetuning in Few-shot Learning: Domain-Agnostic Feature Adaptation with Rectified Class Prototypes

In recent works, utilizing a deep network trained on meta-training set s...
research
10/18/2021

Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning

In few-shot classification, the primary goal is to learn representations...
research
05/01/2021

One-shot learning for acoustic identification of bird species in non-stationary environments

This work introduces the one-shot learning paradigm in the computational...

Please sign up or login with your details

Forgot password? Click here to reset