Catastrophic Interference in Disguised Face Recognition

It is commonly known the natural tendency of artificial neural networks to completely and abruptly forget previously known information when learning new information. We explore this behaviour in the context of Face Verification on the recently proposed Disguised Faces in the Wild dataset (DFW). We empirically evaluate several commonly used DCNN architectures on Face Recognition and distill some insights about the effect of sequential learning on distinct identities from different datasets, showing that the catastrophic forgetness phenomenon is present even in feature embeddings fine-tuned on different tasks from the original domain.

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

[2]  Ethan Stump,et al.  Reduction of catastrophic forgetting with transfer learning and ternary output codes , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[3]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[4]  Bing Liu,et al.  Lifelong machine learning: a paradigm for continuous learning , 2017, Frontiers of Computer Science.

[5]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[6]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[7]  Carlos D. Castillo,et al.  Deep Features for Recognizing Disguised Faces in the Wild , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[8]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[9]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[10]  Omkar M. Parkhi,et al.  VGGFace2: A Dataset for Recognising Faces across Pose and Age , 2017, 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).

[11]  Rama Chellappa,et al.  Disguised Faces in the Wild , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  Anthony V. Robins,et al.  Catastrophic Forgetting, Rehearsal and Pseudorehearsal , 1995, Connect. Sci..

[13]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[14]  Qiang Yang,et al.  Lifelong Machine Learning Systems: Beyond Learning Algorithms , 2013, AAAI Spring Symposium: Lifelong Machine Learning.

[15]  Carlos D. Castillo,et al.  An All-In-One Convolutional Neural Network for Face Analysis , 2016, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[16]  David Filliat,et al.  Generative Models from the perspective of Continual Learning , 2018, 2019 International Joint Conference on Neural Networks (IJCNN).

[17]  Tal Hassner,et al.  Face recognition in unconstrained videos with matched background similarity , 2011, CVPR 2011.

[18]  Ronald Kemker,et al.  Measuring Catastrophic Forgetting in Neural Networks , 2017, AAAI.

[19]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[21]  Evgeny Smirnov,et al.  Hard Example Mining with Auxiliary Embeddings , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[22]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[23]  Abhinav Dhall,et al.  DisguiseNet: A Contrastive Approach for Disguised Face Verification in the Wild , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[24]  Carlos D. Castillo,et al.  UMDFaces: An annotated face dataset for training deep networks , 2016, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[25]  Daksha Yadav,et al.  Face Verification with Disguise Variations via Deep Disguise Recognizer , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[26]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[27]  Yuxiao Hu,et al.  MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition , 2016, ECCV.

[28]  Winston H. Hsu,et al.  Deep Disguised Faces Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).