Towards Open Set Deep Networks

Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans would never classify as a particular object class, yet networks classify such images high confidence as that given class - deep network are easily fooled with images humans do not consider meaningful. The closed set nature of deep networks forces them to choose from one of the known classes leading to such artifacts. Recognition in the real world is open set, i.e. the recognition system should reject unknown/unseen classes at test time. We present a methodology to adapt deep networks for open set recognition, by introducing a new model layer, OpenMax, which estimates the probability of an input being from an unknown class. A key element of estimating the unknown probability is adapting Meta-Recognition concepts to the activation patterns in the penultimate layer of the network. Open-Max allows rejection of "fooling" and unrelated open set images presented to the system, OpenMax greatly reduces the number of obvious errors made by a deep network. We prove that the OpenMax concept provides bounded open space risk, thereby formally providing an open set recognition solution. We evaluate the resulting open set deep networks using pre-trained networks from the Caffe Model-zoo on ImageNet 2012 validation data, and thousands of fooling and open set images. The proposed OpenMax model significantly outperforms open set recognition accuracy of basic deep networks as well as deep networks with thresholding of SoftMax probabilities.

[1]  R. Tibshirani,et al.  Diagnosis of multiple cancer types by shrunken centroids of gene expression , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Christopher D. Manning,et al.  Learning Continuous Phrase Representations and Syntactic Parsing with Recursive Neural Networks , 2010 .

[3]  Anderson Rocha,et al.  Meta-Recognition: The Theory and Practice of Recognition Score Analysis , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Donald H. Rumsfeld.  Known and Unknown: A Memoir , 2011 .

[5]  Gabriela Csurka,et al.  Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost , 2012, ECCV.

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

[7]  C. V. Jawahar,et al.  Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators , 2012, ECCV.

[8]  Gabriela Csurka,et al.  Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Marc'Aurelio Ranzato,et al.  DeViSE: A Deep Visual-Semantic Embedding Model , 2013, NIPS.

[10]  Andrew Y. Ng,et al.  Zero-Shot Learning Through Cross-Modal Transfer , 2013, NIPS.

[11]  Anderson Rocha,et al.  Toward Open Set Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Jonathon Shlens,et al.  Fast, Accurate Detection of 100,000 Object Classes on a Single Machine , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Robinson Piramuthu,et al.  Furniture-geek: Understanding fine-grained furniture attributes from freely associated text and tags , 2014, IEEE Winter Conference on Applications of Computer Vision.

[14]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[15]  Matthieu Guillaumin,et al.  Incremental Learning of NCM Forests for Large-Scale Image Classification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Yang Yu,et al.  Learning with Augmented Class by Exploiting Unlabeled Data , 2014, AAAI.

[17]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[18]  Ali Farhadi,et al.  Predicting Failures of Vision Systems , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Terrance E. Boult,et al.  Probability Models for Open Set Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Andreas Krause,et al.  Advances in Neural Information Processing Systems (NIPS) , 2014 .

[22]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[23]  Geoffrey Zweig,et al.  From captions to visual concepts and back , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[25]  Terrance E. Boult,et al.  Towards Open World Recognition , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Joachim Denzler,et al.  Local Novelty Detection in Multi-class Recognition Problems , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[28]  Vittorio Ferrari,et al.  Object localization in ImageNet by looking out of the window , 2015, BMVC.

[29]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[30]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[32]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[33]  Ivan Laptev,et al.  Is object localization for free? - Weakly-supervised learning with convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).