Browse > Article
http://dx.doi.org/10.30693/SMJ.2019.8.2.39

Superpixel Exclusion-Inclusion Multiscale Approach for Explanations of Deep Learning  

Seo, Dasom (전북대학교 컴퓨터공학부)
Oh, KangHan (전북대학교 컴퓨터공학부)
Oh, Il-Seok (전북대학교 컴퓨터공학부)
Yoo, Tae-Woong (전북대학교 컴퓨터공학부)
Publication Information
Smart Media Journal / v.8, no.2, 2019 , pp. 39-45 More about this Journal
Abstract
As deep learning has become popular, researches which can help explaining the prediction results also become important. Superpixel based multi-scale combining technique, which provides the advantage of visual pleasing by maintaining the shape of the object, has been recently proposed. Based on the principle of prediction difference, this technique computes the saliency map from the difference between the predicted result excluding the superpixel and the original predicted result. In this paper, we propose a new technique of both excluding and including super pixels. Experimental results show 3.3% improvement in IoU evaluation.
Keywords
deep learning; explanation model; superpixel; visualization;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 A. Shrikumar, P. Greenside, and A. Kundaje, "Learning important features through propagating activation differences," ICML'17 Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3145-3153, Aug 2017.
2 B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, "Learning deep features for discriminative localization," In IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921-2929, June 2016.
3 R.S. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-CAM: Visual explanations from deep networks via gradient-based localization," In International Conference on Computer Vision, pp. 618-626, 2017.
4 S. Barratt, "InterpNET: Neural introspection for interpretable deep learning," In Symposium on Interpretable Machine Learning, 2017.
5 Y. Dong, H. Su, J. Zhu, and B. Zhang, "Improving interpretability of deep neural networks with semantic information," The IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp. 4306-4314, July 2017.
6 L.M. Zintgraf, T.S. Cohen, T. Adel, and M. Welling, "Visualizing deep neural network decisions: Prediction difference analysis," In International Conference on Learning Representation, 2017.
7 M.T. Ribeiro, S. Singh, and C. Guestrin, "Why should I trust you?: Explaining the predictions of any classifier," In The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135-1144, Aug 2016.
8 J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," In IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255, 2009.
9 M.Y. Liu, O. Tuzel, S. Ramalingam, and R. Chellappa, "Entropy rate superpixel segmentation," In IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097-2104, June 2011.
10 C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, and V. Vanhoucke, "Going deeper with convolutions," In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015.
11 Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, 521, pp. 436-444, May 2015.   DOI
12 G. Montavon, W. Samek, and K.R. Muller, "Methods for interpreting and understanding deep neural networks," Digital Signal Processing, vol. 73, pp. 1-15. Feb 2018.   DOI
13 박선, 김종원, "오픈 소스 기반의 딥러닝을 이용한 적조생물 이미지 분류," 스마트미디어저널, 제7권, 제2호, 34-39쪽, 2018년 6월   DOI
14 김서정, 이재수, 김형석, "딥러닝을 이용한 양파 밭의 잡초 검출 연구," 스마트미디어저널, 제7권, 제3호, 16-21쪽, 2018년 9월   DOI
15 오정원, 김행곤, 김일태, "머신러닝 적용 과일 수확시기 예측시스템 설계 및 구현," 스마트미디어저널, 제8권, 제1호, 73-81쪽, 2019년 3월
16 L.H. Gilpin, D. Bau, B.Z. Yuan, A. Bajwa, M. Specter, and L. Kagal, "Explaining Explanations: An Overview of Interpretability of Machine Learning," arXiv preprint arXiv:1806.00069v3, Feb 2019.
17 B. Goodman, and S. Flaxman, "European Union regulations on algorithmic decision-making and a "right to explanation"," AI MAGAZINE, vol. 38, no. 4, pp. 50-57, Fall 2017.   DOI
18 D. Erhan, Y. Bengio, A. Courville, and P. Vincent, "Visualizing higher-layer features of a deep network," Technical Report, University of Montreal, 1341. June 2009.
19 K. Simonyan, A. Vedaldi, and A. Zisserman, "Deep inside convolutional networks: visualising image classification models and saliency maps," In International Conference on Learning Representations Workshop. 2013.
20 W. Samek, A. Binder, G. Montavon, S. Lapuschkin, and K.R. Muller, "Evaluating the visualization of what a deep neural network has learned," IEEE Transactions on Neural Networks and Learning Systems, vol. 28(11), pp. 2660-2673. Aug 2016.   DOI
21 M. Robnik-Šikonja, and I Kononenko, "Explaining classifications for individual instances," IEEE Transactions on Knowledge and Data Engineering, vol. 20(5), pp. 589-600, May 2008.   DOI
22 D.S. Seo, K.H. Oh, and I.S. Oh, "Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks," arXiv preprint arXiv:1807.11720v2, Aug 2018.
23 Z.C. Lipton, "The mythos of model interpretability," Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016). June 2016.
24 D. Doran, S. Schulz, and T.R. Besold, "What does explainable AI really mean? A new conceptualization of perspectives," arXiv preprint arXiv:1710.00794v1, Oct 2017.
25 J. Yosinski, J. Clune, A. Nguyen, T. Fuchs, and H. Lipson, "Understanding neural networks through deep visualization," In International Conference on Machine Learning. 2015.
26 M.D. Zeiler, and R. Fergus, "Visualizing and understanding convolutional networks," In European Conference on Computer Vision, pp. 818-833. Sep 2014.
27 S. Bach, A. Binder, G. Montavon, F. Klauschen, K.R. Müller, and W. Samek, "On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation," PloS One, 10(7), e0130140. July 2015.   DOI