Deep Neural Networks Do Not Recognize Negative Images

Deep Neural Networks (DNNs) have achieved remarkable performance on a variety of pattern-recognition tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. In this paper, we test the state-of-the-art DNNs with negative images and show that the accuracy drops to the level of random classification. This leads us to the conjecture that the DNNs, which are merely trained on raw data, do not recognize the semantics of the objects, but rather memorize the inputs. We suggest that negative images can be thought as “semantic adversarial examples”, which we define as transformed inputs that semantically represent the same objects, but the model does not classify them correctly.

[1]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[3]  Eduardo Valle,et al.  Exploring the space of adversarial images , 2015, 2016 International Joint Conference on Neural Networks (IJCNN).

[4]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[5]  Thomas Brox,et al.  Learning to generate chairs with convolutional neural networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Luca Maria Gambardella,et al.  Deep, Big, Simple Neural Nets for Handwritten Digit Recognition , 2010, Neural Computation.

[8]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[9]  Daan Wierstra,et al.  One-shot Learning with Memory-Augmented Neural Networks , 2016, ArXiv.

[10]  Sinan Kalkan,et al.  Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision? , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[12]  Yann LeCun,et al.  Regularization of Neural Networks using DropConnect , 2013, ICML.

[13]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

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

[15]  Johannes Stallkamp,et al.  Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition , 2012, Neural Networks.

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

[17]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[18]  James J. DiCarlo,et al.  How Does the Brain Solve Visual Object Recognition? , 2012, Neuron.

[19]  Ananthram Swami,et al.  The Limitations of Deep Learning in Adversarial Settings , 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

[20]  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).

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