Attribute Prototype Network for Any-Shot Learning

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

17 Scopus Citations
View graph of relations

Author(s)

  • Wenjia Xu
  • Yongqin Xian
  • Jiuniu Wang
  • Bernt Schiele
  • Zeynep Akata

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)1735–1753
Journal / PublicationInternational Journal of Computer Vision
Volume130
Online published11 May 2022
Publication statusPublished - Jul 2022

Abstract

Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play an important role, while in the few-shot regime, the effect of attributes is under-explored. To better transfer attribute-based knowledge from seen to unseen classes, we argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks. To this end, we propose a novel representation learning framework that jointly learns discriminative global and local features using only class-level attributes. While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate features. Furthermore, we introduce a zoom-in module that localizes and crops the informative regions to encourage the network to learn informative features explicitly. We show that our locality augmented image representations achieve a new state-of-the-art on challenging benchmarks, i.e. CUB, AWA2, and SUN. As an additional benefit, our model points to the visual evidence of the attributes in an image, confirming the improved attribute localization ability of our image representation. The attribute localization is evaluated quantitatively with ground truth part annotations, qualitatively with visualizations, and through well-designed user studies.

Research Area(s)

  • Attribute localization, Attribute prototype, Few-shot learning, Zero-shot learning

Citation Format(s)

Attribute Prototype Network for Any-Shot Learning. / Xu, Wenjia; Xian, Yongqin; Wang, Jiuniu et al.
In: International Journal of Computer Vision, Vol. 130, 07.2022, p. 1735–1753.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review