CNNComparator: Comparative Analytics of Convolutional Neural Networks

Convolutional neural networks (CNNs) are widely used in many image recognition tasks due to their extraordinary performance. However, training a good CNN model can still be a challenging task. In a training process, a CNN model typically learns a large number of parameters over time, which usually results in different performance. Often, it is difficult to explore the relationships between the learned parameters and the model performance due to a large number of parameters and different random initializations. In this paper, we present a visual analytics approach to compare two different snapshots of a trained CNN model taken after different numbers of epochs, so as to provide some insight into the design or the training of a better CNN model. Our system compares snapshots by exploring the differences in operation parameters and the corresponding blob data at different levels. A case study has been conducted to demonstrate the effectiveness of our system.

[1]  Keith Andrews,et al.  Visual Graph Comparison , 2009, 2009 13th International Conference Information Visualisation.

[2]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[3]  Ben Shneiderman,et al.  The eyes have it: a task by data type taxonomy for information visualizations , 1996, Proceedings 1996 IEEE Symposium on Visual Languages.

[4]  Adam W. Harley.  An Interactive Node-Link Visualization of Convolutional Neural Networks , 2015, ISVC.

[5]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[6]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[7]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

[8]  Jonathan C. Roberts,et al.  Visual comparison for information visualization , 2011, Inf. Vis..

[9]  Grant Potter,et al.  ConvNetJS: Deep Learning in your browser , 2017 .

[10]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Zhen Li,et al.  Towards Better Analysis of Deep Convolutional Neural Networks , 2016, IEEE Transactions on Visualization and Computer Graphics.

[14]  Tobias Isenberg,et al.  Weighted graph comparison techniques for brain connectivity analysis , 2013, CHI.

[15]  Paulo E. Rauber,et al.  Visualizing the Hidden Activity of Artificial Neural Networks , 2017, IEEE Transactions on Visualization and Computer Graphics.

[16]  Jason Yosinski,et al.  Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks , 2016, ArXiv.

[17]  Martin Wattenberg,et al.  Direct-Manipulation Visualization of Deep Networks , 2017, ArXiv.

[18]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[19]  L. Törnqvist,et al.  How Should Relative Changes be Measured , 1985 .

[20]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[22]  Andrew Zisserman,et al.  A Visual Vocabulary for Flower Classification , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[23]  Thomas Brox,et al.  Inverting Visual Representations with Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[25]  Andrea Vedaldi,et al.  Understanding deep image representations by inverting them , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[27]  Luke Yeager,et al.  Effective Visualizations for Training and Evaluating Deep Models , 2016 .

[28]  M. Sheelagh T. Carpendale,et al.  A Descriptive Framework for Temporal Data Visualizations Based on Generalized Space‐Time Cubes , 2017, Comput. Graph. Forum.

[29]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.