research-article

Explaining with Counter Visual Attributes and Examples

Authors:

Sadaf Gulshad and

Arnold SmeuldersAuthors Info & Claims

ICMR '20: Proceedings of the 2020 International Conference on Multimedia Retrieval

June 2020

Pages 35 - 43

https://doi.org/10.1145/3372278.3390672

Published: 08 June 2020 Publication History

Abstract

In this paper, we aim to explain the decisions of neural networks by utilizing multimodal information. That is counter-intuitive attributes and counter visual examples which appear when perturbed samples are introduced. Different from previous work on interpreting decisions using saliency maps, text, or visual patches we propose to use attributes and counter-attributes, and examples and counter-examples as part of the visual explanations. When humans explain visual decisions they tend to do so by providing attributes and examples. Hence, inspired by the way of human explanations in this paper we provide attribute-based and example-based explanations. Moreover, humans also tend to explain their visual decisions by adding counter-attributes and counter-examples to explain what isnot seen. We introduce directed perturbations in the examples to observe which attribute values change when classifying the examples into the counter classes. This delivers intuitive counter-attributes and counter-examples. Our experiments with both coarse and fine-grained datasets show that attributes provide discriminating and human-understandable intuitive and counter-intuitive explanations.

References

[1]

Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, and Bernt Schiele. 2015. Evaluation of output embeddings for fine-grained image classification. In CVPR.

[2]

Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang. 2018. Bottom-up and top-down attention for image captioning and visual question answering. In CVPR.

[3]

Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, and Zeynep Akata. 2018. Grounding visual explanations. In ECCV.

[4]

Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In SP. IEEE.

[5]

Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, and Alexei A. Efros. [n.d.]. What Makes Paris Look like Paris? ACM Transactions on Graphics (SIGGRAPH), Vol. 31, 4 ( [n.,d.]), 101:1--101:9.

[6]

Yinpeng Dong, Hang Su, Jun Zhu, and Fan Bao. 2017a. Towards interpretable deep neural networks by leveraging adversarial examples. arXiv (2017).

[7]

Yinpeng Dong, Hang Su, Jun Zhu, and Bo Zhang. 2017b. Improving interpretability of deep neural networks with semantic information. In CVPR.

[8]

Mengnan Du, Ninghao Liu, and Xia Hu. 2018. Techniques for Interpretable Machine Learning. arXiv (2018).

[9]

Ruth C Fong and Andrea Vedaldi. 2017. Interpretable explanations of black boxes by meaningful perturbation. arXiv (2017).

[10]

Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In ICLR.

[11]

Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Counterfactual Visual Explanations. (2019).

[12]

Lisa Anne Hendricks, Zeynep Akata, Marcus Rohrbach, Jeff Donahue, Bernt Schiele, and Trevor Darrell. 2016. Generating visual explanations. In ECCV. Springer.

[13]

Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, and Zeynep Akata. 2018. Generating Counterfactual Explanations with Natural Language. In ICML Workshop on Human Interpretability in Machine Learning. 95--98.

[14]

Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep Ravikumar, Seungyeon Kim, Sanjiv Kumar, and Cho-Jui Hsieh. 2020. Evaluations and Methods for Explanation through Robustness Analysis.

[15]

Liu Jiang, Shixia Liu, and Changjian Chen. 2018. Recent research advances on interactive machine learning. Journal of Visualization (2018).

[16]

Atsushi Kanehira and Tatsuya Harada. 2019. Learning to explain with complemental examples. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8603--8611.

[17]

Jinkyu Kim, Anna Rohrbach, Trevor Darrell, John Canny, and Zeynep Akata. 2018. Textual explanations for self-driving vehicles. In ECCV.

[18]

Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A Shamma, et almbox. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. IJCV (2017).

[19]

Alexey Kurakin, Ian Goodfellow, and Samy Bengio. 2017. Adversarial examples in the physical world. ICLR workshop (2017).

[20]

Christoph H Lampert, Hannes Nickisch, and Stefan Harmeling. 2009. Learning to detect unseen object classes by between-class attribute transfer. In CVPR. IEEE.

[21]

Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. ICLR (2018).

[22]

Christoph Molnar. 2019. Interpretable Machine Learning. https://christophm.github.io/interpretable-ml-book/.

[23]

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard. 2016. Deepfool: a simple and accurate method to fool deep neural networks. In CVPR.

[24]

Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z Berkay Celik, and Ananthram Swami. 2016. The limitations of deep learning in adversarial settings. In EuroS&P. IEEE.

[25]

Dong Huk Park, Lisa Anne Hendricks, Zeynep Akata, Bernt Schiele, Trevor Darrell, and Marcus Rohrbach. 2018. Multimodal explanations: Justifying decisions and pointing to the evidence. In CVPR.

[26]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should i trust you?: Explaining the predictions of any classifier. In ACM SIGKDD.

[27]

Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In ICCV.

[28]

Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In ICML.

[29]

Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv (2013).

[30]

Saurabh Singh, Abhinav Gupta, and Alexei A Efros. 2012. Unsupervised discovery of mid-level discriminative patches. In European Conference on Computer Vision. Springer, 73--86.

[31]

Jiawei Su, Danilo Vasconcellos Vargas, and Kouichi Sakurai. 2019. One pixel attack for fooling deep neural networks. TEVC (2019).

[32]

Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In ICML.

[33]

Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. ICLR (2013).

[34]

Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, and Aleksander Madry. 2018. Robustness may be at odds with accuracy. stat, Vol. 1050 (2018).

[35]

Hristina Uzunova, Jan Ehrhardt, Timo Kepp, and Heinz Handels. 2019. Interpretable explanations of black box classifiers applied on medical images by meaningful perturbations using variational autoencoders. In Medical Imaging 2019: Image Processing.

[36]

Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011).

[37]

Matthew D Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In ECCV. Springer.

[38]

Tianyuan Zhang and Zhanxing Zhu. 2019. Interpreting Adversarially Trained Convolutional Neural Networks. arXiv (2019).

[39]

Bo Zhao, Yanwei Fu, Rui Liang, Jiahong Wu, Yonggang Wang, and Yizhou Wang. 2018. A Large-scale Attribute Dataset for Zero-shot Learning. arXiv (2018).

[40]

Luisa M Zintgraf, Taco S Cohen, Tameem Adel, and Max Welling. 2017. Visualizing deep neural network decisions: Prediction difference analysis. ICLR (2017).

Cited By

Park HLee SHoover BWright AShaikh ODuggal RDas NLi KHoffman JChau DFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and DiscoveriesProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614819(2044-2054)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614819
Chen RLi JZhang HSheng CLiu LCao X(2023)Sim2Word: Explaining Similarity with Representative Attribute Words via Counterfactual ExplanationsACM Transactions on Multimedia Computing, Communications, and Applications10.1145/356303919:6(1-22)Online publication date: 12-Jul-2023
https://dl.acm.org/doi/10.1145/3563039
Liu SLi JZhang HXu LCao X(2023)Prediction With Visual Evidence: Sketch Classification Explanation via Stroke-Level AttributionsIEEE Transactions on Image Processing10.1109/TIP.2023.329740432(4393-4406)Online publication date: 2023
https://doi.org/10.1109/TIP.2023.3297404
Show More Cited By

Index Terms

Explaining with Counter Visual Attributes and Examples
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision

Recommendations

Explaining Deep Learning Models with Constrained Adversarial Examples
PRICAI 2019: Trends in Artificial Intelligence
Abstract
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a ...
Read More
Constructing adversarial examples to investigate the plausibility of explanations in deep audio and image classifiers
Abstract
Given the rise of deep learning and its inherent black-box nature, the desire to interpret these systems and explain their behaviour became increasingly more prominent. The main idea of so-called explainers is to identify which features of ...
Read More
Explaining black-box classifiers: Properties and functions
Abstract
Explaining black-box classification models is a hot topic in AI, with the overall goal of improving trust in decisions made by such models. Several works have been done and diverse functions have been proposed. However, their formal ...
Read More

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ICMR '20: Proceedings of the 2020 International Conference on Multimedia Retrieval

June 2020

605 pages

ISBN:9781450370875

DOI:10.1145/3372278

General Chairs:
Cathal Gurrin
Dublin City University, Ireland
,
Björn Þór Jónsson
IT University of Copenhagen, Denmark
,
Noriko Kando
National Institute of Informatics, Tokyo
,
Program Chairs:
Klaus Schoeffmann
Klagenfurt University, Austria
,
Phoebe Chen
La Trobe University, Australia
,
Noel E. O'Connor
Dublin City University, Ireland

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 June 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

ICMR '20

Sponsor:

SIGMM

ICMR '20: International Conference on Multimedia Retrieval

June 8 - 11, 2020

Dublin, Ireland

Acceptance Rates

Overall Acceptance Rate 254 of 830 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
252
Total Downloads

Downloads (Last 12 months)18
Downloads (Last 6 weeks)0

Other Metrics

View Author Metrics

Citations

Cited By

Park HLee SHoover BWright AShaikh ODuggal RDas NLi KHoffman JChau DFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and DiscoveriesProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614819(2044-2054)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614819
Chen RLi JZhang HSheng CLiu LCao X(2023)Sim2Word: Explaining Similarity with Representative Attribute Words via Counterfactual ExplanationsACM Transactions on Multimedia Computing, Communications, and Applications10.1145/356303919:6(1-22)Online publication date: 12-Jul-2023
https://dl.acm.org/doi/10.1145/3563039
Liu SLi JZhang HXu LCao X(2023)Prediction With Visual Evidence: Sketch Classification Explanation via Stroke-Level AttributionsIEEE Transactions on Image Processing10.1109/TIP.2023.329740432(4393-4406)Online publication date: 2023
https://doi.org/10.1109/TIP.2023.3297404
Gulshad SLong Tvan Noord N(2023)Hierarchical Explanations for Video Action Recognition2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)10.1109/CVPRW59228.2023.00379(3703-3708)Online publication date: Jun-2023
https://doi.org/10.1109/CVPRW59228.2023.00379
Joshi GWalambe RKotecha K(2021)A Review on Explainability in Multimodal Deep Neural NetsIEEE Access10.1109/ACCESS.2021.30702129(59800-59821)Online publication date: 2021
https://doi.org/10.1109/ACCESS.2021.3070212
Gulshad SSmeulders A(2021)Counterfactual attribute-based visual explanations for classificationInternational Journal of Multimedia Information Retrieval10.1007/s13735-021-00208-310:2(127-140)Online publication date: 18-Apr-2021
https://doi.org/10.1007/s13735-021-00208-3

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents