Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

By Han-Jia Ye, Hexiang Hu, De-chuan Zhan, Fei Sha. 2018

830 citations recorded by the source corpus.

Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. We empirically investigated various instantiations of such set-to-set functions and observed the Transformer is most effective --- as it naturally satisfies key properties of our desired model. We denote this model as FEAT (few-shot embedding adaptation w/ Transformer) and validate it on both the standard few-shot classification benchmark and four extended few-shot learning settings with essential use cases, i.e., cross-domain, transductive, generalized few-shot learning, and low-shot learning. It archived consistent improvements over baseline models as well as previous methods, and established the new state-of-the-art results on two benchmarks.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, 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

  1. Han-Jia Ye
  2. De-chuan Zhan
  3. Bernt Schiele
  4. Qianru Sun
  5. Yaoyao Liu
  6. Fei Sha
  7. Wei-Lun Chao
  8. Hexiang Hu

In Computer Vision and Pattern Recognition

  1. Bernt Schiele
  2. Luc Van Gool
  3. Dacheng Tao
  4. Ming-Hsuan Yang
  5. Trevor Darrell
  6. Han-Jia Ye
  7. Chunhua Shen
  8. Xiaogang Wang

In Representation & Self-Supervised Learning

  1. Han-Jia Ye
  2. Bernt Schiele
  3. De-chuan Zhan
  4. Qianru Sun
  5. Yaoyao Liu
  6. Wei-Lun Chao
  7. Fei Sha
  8. Hexiang Hu

In Meta & Continual Learning

  1. Han-Jia Ye
  2. De-chuan Zhan
  3. Bernt Schiele
  4. Yaoyao Liu
  5. Qianru Sun
  6. Wei-Lun Chao
  7. Da-Wei Zhou
  8. Chi Zhang

Citations in the corpus