Citation: Du, W.; Hu, X.; Wei, X.; Zuo,
K. Prototype-Based Self-Adaptive
Distribution Calibration for Few-Shot
Image Classification. Electronics 2023,
12, 134. https://doi.org/10.3390/
electronics12010134
Academic Editor: Silvia Liberata Ullo
Received: 30 November 2022
Revised: 23 December 2022
Accepted: 23 December 2022
Published: 28 December 2022
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Prototype-Based Self-Adaptive Distribution Calibration for
Few-Shot Image Classification
Wei Du , Xiaoping Hu, Xin Wei and Ke Zuo *
School of Software, Nanchang University, 235 East Nanjing Road, Nanchang 330047, China
* Correspondence: zuoke@ncu.edu.cn
Abstract:
Deep learning has flourished in large-scale supervised tasks. However, in many practical
conditions, rich and available labeled data are a luxury. Thus, few-shot learning (FSL) has recently
received boosting interest and achieved significant progress, which can learn new classes from
several labeled samples. The advanced distribution calibration approach estimates the ground-truth
distribution of few-shot classes by reusing the statistics of auxiliary data. However, there is still
a significant discrepancy between the estimated distributions and ground-truth distributions, and
artificially set hyperparameters cannot be adapted to different application scenarios (i.e., datasets).
This paper proposes a prototype-based self-adaptive distribution calibration framework for estimating
ground-truth distribution accurately and self-adaptive hyperparameter optimization for different
application scenarios. Specifically, the proposed method is divided into two components. The
prototype-based representative mechanism is for obtaining and utilizing more global information
about few-shot classes and improving classification performance. The self-adaptive hyperparameter
optimization algorithm searches robust hyperparameters for the distribution calibration of different
application scenarios. The ablation studies verify the effectiveness of the various components of the
proposed framework. Enormous experiments are conducted on three standard benchmarks such as
miniImageNet, CUB-200-2011, and CIFAR-FS. The competitive results and compelling visualizations
indicate that the proposed framework achieves state-of-the-art performance.
Keywords:
few-shot learning; image classification; prototype; simulated annealing; distribution
calibration; data augmentation; deep learning
1. Introduction
Humans have a remarkable ability to recognize novelty after only looking at a few
examples. However, the enormous development of deep learning is inseparable from large-
scale datasets and networks. As a bridge between human ability and artificial intelligence,
few-shot learning (FSL) has recently obtained considerable attention [
1
,
2
], particularly for
image classification [
3
]. Under the few-shot challenge, the image classification model learns
to classify images when only a few samples per class are provided to the model for training.
Most methods of few-shot image classification are proposed based on meta-learning [
4
,
5
]
and metric-learning [
6
,
7
], making the model adapt quickly to unseen tasks to improve
model generalization ability. Furthermore, some researchers try to avoid model overfitting
through data augmentation. Bendre et al. [
8
] utilize a multimodal method to reconstruct
features with semantic and image knowledge from the latent space. Li et al. [
9
] utilize a
conditional Wasserstein Generative Adversarial Network to synthesize various discrimina-
tive features to alleviate sample shortage. Current few-shot image classification methods
focus on deep neural network training strategies to directly describe the class-level sample
distributions. Unlike these methods, Yang et al. [
10
] recently estimated the ground-truth
distribution of the samples by distribution calibration (DC) in a simple and hand-crafted
manner but achieving very competitive performance. On the one hand, the classification ac-
curacies of the existing methods are still not satisfactory. On the other hand, the distribution
Electronics 2023, 12, 134. https://doi.org/10.3390/electronics12010134 https://www.mdpi.com/journal/electronics
