4
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Memory-Based Neighbourhood Embedding for Visual Recognition

      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

          Learning discriminative image feature embeddings is of great importance to visual recognition. To achieve better feature embeddings, most current methods focus on designing different network structures or loss functions, and the estimated feature embeddings are usually only related to the input images. In this paper, we propose Memory-based Neighbourhood Embedding (MNE) to enhance a general CNN feature by considering its neighbourhood. The method aims to solve two critical problems, i.e., how to acquire more relevant neighbours in the network training and how to aggregate the neighbourhood information for a more discriminative embedding. We first augment an episodic memory module into the network, which can provide more relevant neighbours for both training and testing. Then the neighbours are organized in a tree graph with the target instance as the root node. The neighbourhood information is gradually aggregated to the root node in a bottom-up manner, and aggregation weights are supervised by the class relationships between the nodes. We apply MNE on image search and few shot learning tasks. Extensive ablation studies demonstrate the effectiveness of each component, and our method significantly outperforms the state-of-the-art approaches.

          Related collections

          Most cited references19

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

          FaceNet: A unified embedding for face recognition and clustering

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

            Learning to Compare: Relation Network for Few-Shot Learning

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

              DeepReID: Deep Filter Pairing Neural Network for Person Re-identification

                Bookmark

                Author and article information

                Journal
                14 August 2019
                Article
                1908.04992
                d66224db-00c7-40f2-ad82-2a489628e424

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

                History
                Custom metadata
                Accepted by ICCV2019 for oral presentation
                cs.CV cs.LG

                Computer vision & Pattern recognition,Artificial intelligence
                Computer vision & Pattern recognition, Artificial intelligence

                Comments

                Comment on this article