Exploiting attribute correlations: a novel trace lasso-based weakly supervised dictionary learning method

Lin Wu, Yang Wang, Shirui Pan

Research output: Contribution to journalArticleResearchpeer-review

15 Citations (Scopus)

Abstract

It is now well established that sparse representation models are working effectively for many visual recognition tasks, and have pushed forward the success of dictionary learning therein. Recent studies over dictionary learning focus on learning discriminative atoms instead of purely reconstructive ones. However, the existence of intraclass diversities (i.e., data objects within the same category but exhibit large visual dissimilarities), and interclass similarities (i.e., data objects from distinct classes but share much visual similarities), makes it challenging to learn effective recognition models. To this end, a large number of labeled data objects are required to learn models which can effectively characterize these subtle differences. However, labeled data objects are always limited to access, committing it difficult to learn a monolithic dictionary that can be discriminative enough. To address the above limitations, in this paper, we propose a weakly-supervised dictionary learning method to automatically learn a discriminative dictionary by fully exploiting visual attribute correlations rather than label priors. In particular, the intrinsic attribute correlations are deployed as a critical cue to guide the process of object categorization, and then a set of subdictionaries are jointly learned with respect to each category. The resulting dictionary is highly discriminative and leads to intraclass diversity aware sparse representations. Extensive experiments on image classification and object recognition are conducted to show the effectiveness of our approach.

Original languageEnglish
Pages (from-to)4497-4508
Number of pages12
JournalIEEE Transactions on Cybernetics
Volume47
Issue number12
DOIs
Publication statusPublished - Dec 2017
Externally publishedYes

Keywords

  • Sparse representation
  • trace lasso
  • weakly-supervised dictionary learning

Cite this