Agglomerator++: Interpretable part-whole hierarchies and latent space representations in neural networks

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Zeno Sambugaro, Nicola Garau, Niccoló Bisagno, Nicola Conci
{"title":"Agglomerator++: Interpretable part-whole hierarchies and latent space representations in neural networks","authors":"Zeno Sambugaro,&nbsp;Nicola Garau,&nbsp;Niccoló Bisagno,&nbsp;Nicola Conci","doi":"10.1016/j.cviu.2024.104159","DOIUrl":null,"url":null,"abstract":"<div><p>Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility in understanding and interpreting the network’s response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. This lack of transparency, particularly in crucial areas like autonomous driving, security, and healthcare, can trigger skepticism and limit trust, despite the networks’ high performance. In this work, we want to advance the interpretability in neural networks. We present Agglomerator++, a framework capable of providing a representation of part-whole hierarchies from visual cues and organizing the input distribution to match the conceptual-semantic hierarchical structure between classes. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, showing that our solution delivers a more interpretable model compared to other state-of-the-art approaches. Our code is available at <span><span>https://mmlab-cv.github.io/Agglomeratorplusplus/</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"249 ","pages":"Article 104159"},"PeriodicalIF":4.3000,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1077314224002406/pdfft?md5=ad401203069cc93800237abddffe0b0d&pid=1-s2.0-S1077314224002406-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002406","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility in understanding and interpreting the network’s response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. This lack of transparency, particularly in crucial areas like autonomous driving, security, and healthcare, can trigger skepticism and limit trust, despite the networks’ high performance. In this work, we want to advance the interpretability in neural networks. We present Agglomerator++, a framework capable of providing a representation of part-whole hierarchies from visual cues and organizing the input distribution to match the conceptual-semantic hierarchical structure between classes. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, showing that our solution delivers a more interpretable model compared to other state-of-the-art approaches. Our code is available at https://mmlab-cv.github.io/Agglomeratorplusplus/.

Abstract Image

Agglomerator++:神经网络中可解释的部分-整体层次结构和潜在空间表示法
深度神经网络在各种任务中都取得了出色的成绩,其表现往往优于人类专家。然而,当前神经架构的一个已知局限是,在理解和解释网络对给定输入的响应时,可访问性较差。这与神经模型的大量变量和相关非线性因素直接相关,而神经模型通常被当作黑盒子使用。这种缺乏透明度的情况,尤其是在自动驾驶、安全和医疗保健等关键领域,会引发怀疑并限制信任,尽管网络具有很高的性能。在这项工作中,我们希望提高神经网络的可解释性。我们提出的 Agglomerator++ 是一个框架,它能够从视觉线索中提供部分-整体层次结构的表示,并组织输入分布以匹配类之间的概念-语义层次结构。我们在 SmallNORB、MNIST、FashionMNIST、CIFAR-10 和 CIFAR-100 等常见数据集上对我们的方法进行了评估,结果表明,与其他最先进的方法相比,我们的解决方案提供的模型更具可解释性。我们的代码见 https://mmlab-cv.github.io/Agglomeratorplusplus/。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Computer Vision and Image Understanding
Computer Vision and Image Understanding 工程技术-工程:电子与电气
CiteScore
7.80
自引率
4.40%
发文量
112
审稿时长
79 days
期刊介绍: The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views. Research Areas Include: • Theory • Early vision • Data structures and representations • Shape • Range • Motion • Matching and recognition • Architecture and languages • Vision systems
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信