arrow
返回

Interpretable few-shot learning with online attribute selection

delete2025-01-01
delete1
delete
OA
AI
M
Mohammad Reza Zarei *
M
Majid Komeili
DOI:10.1016/j.neucom.2024.128755delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Few-shot learning (FSL) presents a challenging learning problem in which only a few samples are available for each class. Decision interpretation is more important in few-shot classification due to a greater chance of error compared to traditional classification. However, the majority of the previous FSL methods are black- box models. In this paper, we propose an inherently interpretable model for FSL based on human-friendly attributes. Previously, human-friendly attributes have been utilized to train models with the potential for human interaction and interpretability. However, such approaches are not directly extendible to the few-shot classification scenario. Moreover, we propose an online attribute selection mechanism to effectively filter out irrelevant attributes in each episode. The attribute selection mechanism improves accuracy and helps with interpretability by reducing the number of attributes that participate in each episode. We further propose a mechanism that automatically detects the episodes where the pool of available human-friendly attributes is insufficient, and subsequently augments it by engaging some learned unknown attributes. We demonstrate that the proposed method achieves results on par with black-box few-shot learning models on four widely used datasets. We also empirically evaluate the level of decision alignment between different models and human understanding and show that our model outperforms the comparison methods based on this criterion.
Keyword:
Few-shot learning
Interpretability
Human-friendly attributes
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
6.5W

机构

C
carleton university
学者数:
7.5K
论文数: 8.3K
被引数: 5
引用论文

引用论文

Attribute Prototype Network for Any-Shot Learning
err2022-05-11
err20
errOAAI
errXu, Wenjia; Xian, Yongqin; Wang, Jiuniu; Schiele, Bernt; Akata, Zeynep
err分享
err收藏
Modification of function in head-injured patients with Sinemet
err2009-07-03
err0
PREAI
errSantosh Lal; Charles P. Merbtiz; Jeffrey C. Grip
err分享
err收藏
err分享
err收藏
err分享
err收藏
学者 查看更多内容