@article{18224,
  abstract     = {Learning from one or few visual examples is one of the key capabilities of humans since early infancy, but is still a significant challenge for modern AI systems. While considerable progress has been achieved in few-shot learning from a few image examples, much less attention has been given to the verbal descriptions that are usually provided to infants when they are presented with a new object. In this paper, we focus on the role of additional semantics that can significantly facilitate few-shot visual learning. Building upon recent advances in few-shot learning with additional semantic information, we demonstrate that further improvements are possible by combining multiple and richer semantics (category labels, attributes, and natural language descriptions). Using these ideas, we offer the community new results on the popular miniImageNet and CUB few-shot benchmarks, comparing favorably to the previous state-of-the-art results for both visual only and visual plus semantics-based approaches. We also performed an ablation study investigating the components and design choices of our approach. Code available on github.com/EliSchwartz/mutiple-semantics.},
  author       = {Schwartz, Eli and Karlinsky, Leonid and Feris, Rogerio and Giryes, Raja and Bronstein, Alexander},
  issn         = {0167-8655},
  journal      = {Pattern Recognition Letters},
  pages        = {142--147},
  publisher    = {Elsevier},
  title        = {{Baby steps towards few-shot learning with multiple semantics}},
  doi          = {10.1016/j.patrec.2022.06.012},
  volume       = {160},
  year         = {2022},
}

@article{18235,
  abstract     = {Recently, great progress has been made in the field of Few-Shot Learning (FSL). While many different methods have been proposed, one of the key factors leading to higher FSL performance is surprisingly simple. It is the backbone network architecture used to embed the images of the few-shot tasks. While first works on FSL resorted to small architectures with just a few convolution layers, recent works show that large architectures pre-trained on the training portion of FSL datasets produce strong features that are more easily transferable to novel few-shot tasks, thus attaining significant gains to methods using them. Despite these observations, little to no work has been done towards finding the right backbone for FSL. In this paper we propose MetAdapt that not only meta-searches for an optimized architecture for FSL using Network Architecture Search (NAS), but also results in a model that can adaptively ‘re-wire’ itself predicting the better architecture for a given novel few-shot task. Using the proposed approach we observe strong results on two popular few-shot benchmarks: miniImageNet and FC100.},
  author       = {Doveh, Sivan and Schwartz, Eli and Xue, Chao and Feris, Rogerio and Bronstein, Alexander and Giryes, Raja and Karlinsky, Leonid},
  issn         = {0167-8655},
  journal      = {Pattern Recognition Letters},
  pages        = {130--136},
  publisher    = {Elsevier},
  title        = {{MetAdapt: Meta-learned task-adaptive architecture for few-shot classification}},
  doi          = {10.1016/j.patrec.2021.05.010},
  volume       = {149},
  year         = {2021},
}