Research

LaSO: Label-Set Operations networks for multi-label few-shot learning

Computer Vision

Authors

  • Amit Alfassy
  • Leonid Karlinsky
  • Amit Aides
  • Joseph Shtok
  • Sivan Harary
  • Rogerio Feris
  • Raja Giryes
  • Alex M. Bronstein

Published on

02/26/2019

Example synthesis is one of the leading methods to tackle the problem of few-shot learning, where only a small number of samples per class are available. However, current synthesis approaches only address the scenario of a single category label per image. In this work, we propose a novel technique for synthesizing samples with multiple labels for the (yet unhandled) multi-label few-shot classification scenario. We propose to combine pairs of given examples in feature space, so that the resulting synthesized feature vectors will correspond to examples whose label sets are obtained through certain set operations on the label sets of the corresponding input pairs. Thus, our method is capable of producing a sample containing the intersection, union or set-difference of labels present in two input samples. As we show, these set operations generalize to labels unseen during training. This enables performing augmentation on examples of novel categories, thus, facilitating multi-label few-shot classifier learning. We conduct numerous experiments showing promising results for the label-set manipulation capabilities of the proposed approach, both directly (using the classification and retrieval metrics), and in the context of performing data augmentation for multi-label few-shot learning. We propose a benchmark for this new and challenging task and show that our method compares favorably to all the common baselines.

Please cite our work using the BibTeX below.

@article{DBLP:journals/corr/abs-1902-09811,
  author    = {Amit Alfassy and
               Leonid Karlinsky and
               Amit Aides and
               Joseph Shtok and
               Sivan Harary and
               Rog{\'{e}}rio Schmidt Feris and
               Raja Giryes and
               Alexander M. Bronstein},
  title     = {LaSO: Label-Set Operations networks for multi-label few-shot learning},
  journal   = {CoRR},
  volume    = {abs/1902.09811},
  year      = {2019},
  url       = {http://arxiv.org/abs/1902.09811},
  archivePrefix = {arXiv},
  eprint    = {1902.09811},
  timestamp = {Tue, 21 May 2019 18:03:40 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1902-09811.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Close Modal