The Do’s and Don’ts for CNN-Based Face Verification

@article{Bansal2017TheDA,
  title={The Do’s and Don’ts for CNN-Based Face Verification},
  author={Ankan Bansal and Carlos D. Castillo and Rajeev Ranjan and R. Chellappa},
  journal={2017 IEEE International Conference on Computer Vision Workshops (ICCVW)},
  year={2017},
  pages={2545-2554}
}
  • Ankan Bansal, Carlos D. Castillo, +1 author R. Chellappa
  • Published 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
  • While the research community appears to have developed a consensus on the methods of acquiring annotated data, design and training of CNNs, many questions still remain to be answered. In this paper, we explore the following questions that are critical to face recognition research: (i) Can we train on still images and expect the systems to work on videos? (ii) Are deeper datasets better than wider datasets? (iii) Does adding label noise lead to improvement in performance of deep networks? (iv… CONTINUE READING
    63 Citations

    Figures and Topics from this paper.

    To Frontalize or Not to Frontalize: Do We Really Need Elaborate Pre-processing to Improve Face Recognition?
    • 12
    • PDF
    A Light CNN for Deep Face Representation With Noisy Labels
    • 490
    • PDF
    Exploring the Effects of Frontalization and Data Synthesis on Face Recognition
    A Fast and Accurate System for Face Detection, Identification, and Verification
    • 32
    • PDF
    Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
    • 32
    • PDF
    VGGFace2: A Dataset for Recognising Faces across Pose and Age
    • 748
    • Highly Influenced
    • PDF
    Deep Learning for Understanding Faces
    Investigating Nuisances in DCNN-Based Face Recognition
    • 6
    • Highly Influenced
    Systematic evaluation of deep face recognition methods
    • 3

    References

    SHOWING 1-10 OF 43 REFERENCES
    UMDFaces: An annotated face dataset for training deep networks
    • 112
    • PDF
    Learning Face Representation from Scratch
    • 1,006
    • Highly Influential
    • PDF
    Deep Face Recognition
    • 3,108
    • Highly Influential
    • PDF
    Triplet probabilistic embedding for face verification and clustering
    • 148
    • PDF
    Unconstrained face verification using deep CNN features
    • 225
    • PDF
    Deep Learning Face Attributes in the Wild
    • 2,809
    • PDF
    Face recognition in unconstrained videos with matched background similarity
    • 962
    • Highly Influential
    • PDF
    MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
    • 706
    • Highly Influential
    • PDF
    WIDER FACE: A Face Detection Benchmark
    • 586
    • PDF
    DeepFace: Closing the Gap to Human-Level Performance in Face Verification
    • 4,113
    • PDF