106
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Learning Dense Convolutional Embeddings for Semantic Segmentation

      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

          This paper proposes a new deep convolutional neural network (DCNN) architecture that learns pixel embeddings, such that pairwise distances between the embeddings can be used to infer whether or not the pixels lie on the same region. That is, for any two pixels on the same object, the embeddings are trained to be similar; for any pair that straddles an object boundary, the embeddings are trained to be dissimilar. Experimental results show that when this embedding network is used in conjunction with a DCNN trained on semantic segmentation, there is a systematic improvement in per-pixel classification accuracy. Our contributions are integrated in the popular Caffe deep learning framework, and consist in straightforward modifications to convolution routines. As such, they can be exploited for any task involving convolution layers.

          Related collections

          Author and article information

          Journal
          2015-11-13
          2016-01-07
          Article
          1511.04377
          c35e80e5-58c5-48a4-bc64-59379f01f24f

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

          History
          Custom metadata
          cs.CV

          Computer vision & Pattern recognition
          Computer vision & Pattern recognition

          Comments

          Comment on this article