16
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      The Do's and Don'ts for CNN-based Face Verification

      Preprint
      , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Convolutional neural networks (CNN) have become the most sought after tools for addressing object recognition problems. Specifically, they have produced state-of-the art results for unconstrained face recognition and verification tasks. 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) Is alignment needed for face recognition? We address these questions by training CNNs using CASIA-WebFace, UMDFaces, and a new video dataset and testing on YouTubeFaces, IJBA and a disjoint portion of UMDFaces datasets. Our new data set, which will be made publicly available, has 22,075 videos and 3,735,476 human annotated frames extracted from them.

          Related collections

          Most cited references16

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Deep Learning Face Attributes in the Wild

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            DeepFace: Closing the Gap to Human-Level Performance in Face Verification

              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              FaceNet: A Unified Embedding for Face Recognition and Clustering

              , , (2015)
              Despite significant recent advances in the field of face recognition, implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. Once this space has been produced, tasks such as face recognition, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings as feature vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an intermediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-art face recognition performance using only 128-bytes per face. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best published result by 30% on both datasets. We also introduce the concept of harmonic embeddings, and a harmonic triplet loss, which describe different versions of face embeddings (produced by different networks) that are compatible to each other and allow for direct comparison between each other.
                Bookmark

                Author and article information

                Journal
                2017-05-21
                Article
                1705.07426
                26e5dda5-3a27-4e72-90a9-ab7a94e69e22

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                10 pages including references
                cs.CV

                Computer vision & Pattern recognition
                Computer vision & Pattern recognition

                Comments

                Comment on this article