Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs

We present a dual-stream CNN that learns both appearance and facial features in tandem from still images and, after feature fusion, infers person identities. We then describe an alternative architecture of a single, lightweight ID-CondenseNet where a face detector-guided DC-GAN is used to generate distractor person images for enhanced training. For evaluation, we test both architectures on FLIMA, a new extension of an existing person re-identification dataset with added frame-by-frame annotations of face presence. Although the dual-stream CNN can outperform the CondenseNet approach on FLIMA, we show that the latter surpasses all state-of-the-art architectures in top-1 ranking performance when applied to the largest existing person re-identification dataset, MSMT17. We conclude that whilst re-identification performance is highly sensitive to the structure of datasets, distractor augmentation and network compression have a role to play for enhancing performance characteristics for larger scale applications.

[1]  Xiaoou Tang,et al.  Surpassing Human-Level Face Verification Performance on LFW with GaussianFace , 2014, AAAI.

[2]  Shiliang Zhang,et al.  Pose-Driven Deep Convolutional Model for Person Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  Athanasios V. Vasilakos,et al.  A Survey on Ambient Intelligence in Healthcare , 2013, Proceedings of the IEEE.

[5]  Deyu Meng,et al.  The Solution Path Algorithm for Identity-Aware Multi-object Tracking , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Longhui Wei,et al.  Person Transfer GAN to Bridge Domain Gap for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Kilian Q. Weinberger,et al.  CondenseNet: An Efficient DenseNet Using Learned Group Convolutions , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  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.

[11]  Fang Zhao,et al.  Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis , 2017, NIPS.

[12]  Barbara Caputo,et al.  Looking beyond appearances: Synthetic training data for deep CNNs in re-identification , 2017, Comput. Vis. Image Underst..

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  R. Vaillant,et al.  An original approach for the localization of objects in images , 1993 .

[15]  Niall Twomey,et al.  The SPHERE Challenge: Activity Recognition with Multimodal Sensor Data , 2016, ArXiv.

[16]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Q. Tian,et al.  GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval , 2017, ACM Multimedia.

[18]  Majid Mirmehdi,et al.  Semantically Selective Augmentation for Deep Compact Person Re-Identification , 2018, ECCV Workshops.

[19]  Luc Van Gool,et al.  Pose Guided Person Image Generation , 2017, NIPS.

[20]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[21]  Qi Tian,et al.  Scalable Person Re-identification: A Benchmark , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Zoran Kalafatic,et al.  Deep metric learning for person Re-identification and De-identification , 2016, 2016 39th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

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

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

[26]  R. Vaillant,et al.  Original approach for the localisation of objects in images , 1994 .

[27]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[28]  John C. Platt,et al.  A Convolutional Neural Network Hand Tracker , 1994, NIPS.

[29]  Yi Yang,et al.  Person Re-identification: Past, Present and Future , 2016, ArXiv.

[30]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[31]  Xiaoming Liu,et al.  Coefficients Pose-Variant Input Recogni 8 on Engine Frontalized Output Generator FF-GAN D Discriminator Extreme Pose Input Frontalized Output , 2017 .

[32]  Edward J. Delp,et al.  A Two Stream Siamese Convolutional Neural Network for Person Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[33]  Mohamed Abdel-Mottaleb,et al.  Lower Resolution Face Recognition in Surveillance Systems Using Discriminant Correlation Analysis , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[34]  Xiaoming Liu,et al.  Disentangled Representation Learning GAN for Pose-Invariant Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Majid Mirmehdi,et al.  A Dataset for Persistent Multi-target Multi-camera Tracking in RGB-D , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[36]  Nathan Halko,et al.  Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions , 2009, SIAM Rev..

[37]  Mahadev Satyanarayanan,et al.  OpenFace: A general-purpose face recognition library with mobile applications , 2016 .