Joint Dictionaries for Zero-Shot Learning

By Soheil Kolouri, Mohammad Rostami, Yuri Owechko, Kyungnam Kim. 2017

26 citations recorded by the source corpus.

A classic approach toward zero-shot learning (ZSL) is to map the input domain to a set of semantically meaningful attributes that could be used later on to classify unseen classes of data (e.g. visual data). In this paper, we propose to learn a visual feature dictionary that has semantically meaningful atoms. Such a dictionary is learned via joint dictionary learning for the visual domain and the attribute domain, while enforcing the same sparse coding for both dictionaries. Our novel attribute aware formulation provides an algorithmic solution to the domain shift/hubness problem in ZSL. Upon learning the joint dictionaries, images from unseen classes can be mapped into the attribute space by finding the attribute aware joint sparse representation using solely the visual data. We demonstrate that our approach provides superior or comparable performance to that of the state of the art on benchmark datasets.

Subfields: Artificial Intelligence

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

Citations in the corpus

Detection and Continual Learning of Novel Face Presentation Attacks (2021, background): “The learning setting that we explore is more related to the zero-shot learning (ZSL) formulation [9, 37, 38, 25].”
Learning Transferable Knowledge Through Embedding Spaces (2019, background): “learned knowledge to facilitate transfer [35; 165; 1; 44].”
Small Sample Learning in Big Data Era (2018, background): “Latest work in (Kolouri et al., 2018) modeled the relationship between visual features and semantic attributes via joint sparse dictionaries, demonstrating an entropy regularization scheme can help address the domain shift problem, and a transductive learning scheme can help reduce the hubness pheno”
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer (2017, methodology): “…based on coupled dictionary learning to incorporate task descriptors into knowledge transfer algorithms that use a factorized representation of the learned knowledge to facilitate transfer (Kumar & Daum´e, 2012; Maurer et al., 2013; Ruvolo & Eaton, 2013; Kolouri, Rostami, Owechko, & Kim, 2018).”