Recognizing Tiny Faces

Objects are naturally captured over a continuous range of distances, causing dramatic changes in appearance, especially at low resolutions. Recognizing such small objects at range is an open challenge in object recognition. In this paper, we explore solutions to this problem by tackling the fine-grained task of face recognition. State-of-the-art embeddings aim to be scale-invariant by extracting representations in a canonical coordinate frame (by resizing a face window to a resolution of say, 224x224 pixels). However, it is well known in the psychophysics literature that human vision is decidedly scale variant: humans are much less accurate at lower resolutions. Motivated by this, we explore scale-variant multiresolution embeddings that explicitly disentangle factors of variation across resolution and scale. Importantly, multiresolution embeddings can adapt in size and complexity to the resolution of input image on-the-fly (e.g., high resolution input images produce more detailed representations that result in better recognition performance). Compared to state-of-the-art "one-size-fits-all" approaches, our embeddings dramatically reduce error for small faces by at least 70% on standard benchmarks (i.e. IJBC, LFW and MegaFace).

[1]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[2]  Takeo Kanade,et al.  Limits on super-resolution and how to break them , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

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

[4]  Shinichi Tamura,et al.  Male/female identification from 8×6 very low resolution face images by neural network , 1996, Pattern Recognit..

[5]  V. Bruce,et al.  Face Recognition in Poor-Quality Video: Evidence From Security Surveillance , 1999 .

[6]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Patrick J. Flynn,et al.  Multidimensional Scaling for Matching Low-Resolution Face Images , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Yalda Mohsenzadeh,et al.  Low Resolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecture , 2017, Expert Syst. Appl..

[10]  L. D. Harmon.  The recognition of faces. , 1973, Scientific American.

[11]  Yong Man Ro,et al.  Color Face Recognition for Degraded Face Images , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Carlos D. Castillo,et al.  L2-constrained Softmax Loss for Discriminative Face Verification , 2017, ArXiv.

[13]  Gérard G. Medioni,et al.  Pose-Aware Face Recognition in the Wild , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Pong C. Yuen,et al.  Very low resolution face recognition problem , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[15]  Harry Shum,et al.  Face Hallucination: Theory and Practice , 2007, International Journal of Computer Vision.

[16]  Harry Shum,et al.  A two-step approach to hallucinating faces: global parametric model and local nonparametric model , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[17]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[19]  Takeo Kanade,et al.  Hallucinating faces , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

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

[21]  Larry S. Davis,et al.  An Analysis of Scale Invariance in Object Detection - SNIP , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Jing Yang,et al.  To learn image super-resolution, use a GAN to learn how to do image degradation first , 2018, ECCV.

[23]  Edward H. Adelson,et al.  PYRAMID METHODS IN IMAGE PROCESSING. , 1984 .

[24]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[25]  Wei Liu,et al.  Super-Identity Convolutional Neural Network for Face Hallucination , 2018, ECCV.

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

[27]  Pablo H. Hennings-Yeomans,et al.  Simultaneous super-resolution and feature extraction for recognition of low-resolution faces , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Q. M. Jonathan Wu,et al.  Low-resolution face recognition: a review , 2013, The Visual Computer.

[29]  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).

[30]  Kate Saenko,et al.  Fine-to-coarse knowledge transfer for low-res image classification , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[31]  P. Sinha,et al.  The Role of Eyebrows in Face Recognition , 2003, Perception.

[32]  Swami Sankaranarayanan,et al.  Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms , 2018, Proceedings of the National Academy of Sciences.

[33]  Pablo H. Hennings-Yeomans,et al.  Robust low-resolution face identification and verification using high-resolution features , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[34]  Pawan Sinha,et al.  Face Recognition by Humans: Nineteen Results All Computer Vision Researchers Should Know About , 2006, Proceedings of the IEEE.