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 Rama Chellappa},
  journal={2017 IEEE International Conference on Computer Vision Workshops (ICCVW)},
  year={2017},
  pages={2545-2554}
}
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

Citations

Publications citing this paper.
SHOWING 1-10 OF 40 CITATIONS

A Fast and Accurate System for Face Detection, Identification, and Verification

VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS

Deep Features for Recognizing Disguised Faces in the Wild

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS

Deep Learning for Understanding Faces: Machines May Be Just as Good, or Better, than Humans

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS

Recurrent Embedding Aggregation Network for Video Face Recognition

VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Investigating Nuisances in DCNN-Based Face Recognition

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification

VIEW 3 EXCERPTS
CITES METHODS

Exploring the Effects of Frontalization and Data Synthesis on Face Recognition

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Deep Face Recognition

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

UMDFaces: An annotated face dataset for training deep networks

VIEW 10 EXCERPTS

Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Learning Face Representation from Scratch

VIEW 17 EXCERPTS
HIGHLY INFLUENTIAL

An All-In-One Convolutional Neural Network for Face Analysis

VIEW 9 EXCERPTS

Triplet probabilistic embedding for face verification and clustering

VIEW 4 EXCERPTS

One millisecond face alignment with an ensemble of regression trees

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL