Baby steps towards few-shot learning with multiple semantics

By Eli Schwartz, Leonid Karlinsky, Rogério Schmidt Feris, Raja Giryes, A. Bronstein. 2019

116 citations recorded by the source corpus.

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 using richer semantics and multiple semantic sources. Using these ideas, we offer the community a new result on the one-shot test of the popular miniImageNet benchmark, 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

Shaping Visual Representations with Language for Few-Shot Classification (2019, neutral): “Language has been shown to assist visual classiﬁcation in various settings, including traditional visual classiﬁcation with no transfer [16] and with language available at test time in the form of class labels or descriptions for zero-[10, 11, 27] or few-shot [24, 33] learning.”
Subspace Regularizers for Few-Shot Class Incremental Learning (2021, background): “Specialized approaches exist for integrating side information in few-shot learning settings (Schwartz et al., 2019; Cheraghian et al., 2021).”
Compositional Few-Shot Class-Incremental Learning (2024, background): “In contrast to machines, humans can easily learn from lim-1 ited data without forgetting learned knowledge (Schwartz et al., 2019).”
Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (2020, background): “Recent efforts (Lu et al., 2018; Schwartz et al., 2019) propose to leverage the semantics of class name to enhance class representation.”
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, background): “Zhu et al. [159] and Xian et al. [21] explored generative images and feature vectors, respectively, making promising progress in the ﬁeld of ZSL.”