Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization

  • Jian Pu
  • Yu-Gang Jiang
  • Jun Wang
  • Xiangyang Xue
Conference paper

DOI: 10.1007/978-3-319-10578-9_28

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8691)
Cite this paper as:
Pu J., Jiang YG., Wang J., Xue X. (2014) Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8691. Springer, Cham

Abstract

Fine-grained visual categorization aims at classifying visual data at a subordinate level, e.g., identifying different species of birds. It is a highly challenging topic receiving significant research attention recently. Most existing works focused on the design of more discriminative feature representations to capture the subtle visual differences among categories. Very limited efforts were spent on the design of robust model learning algorithms. In this paper, we treat the training of each category classifier as a single learning task, and formulate a generic multiple task learning (MTL) framework to train multiple classifiers simultaneously. Different from the existing MTL methods, the proposed generic MTL algorithm enforces no structure assumptions and thus is more flexible in handling complex inter-class relationships. In particular, it is able to automatically discover both clusters of similar categories and outliers. We show that the objective of our generic MTL formulation can be solved using an iterative reweighted ℓ2 method. Through an extensive experimental validation, we demonstrate that our method outperforms several state-of-the-art approaches.

Keywords

Fine-grained visual categorization inter-class relationship multiple task learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jian Pu
    • 1
  • Yu-Gang Jiang
    • 1
  • Jun Wang
    • 2
  • Xiangyang Xue
    • 1
  1. 1.School of Computer Science, Shanghai Key Laboratory of Intelligent Information ProcessingFudan UniversityShanghaiChina
  2. 2.IBM T. J. Watson Research CenterYorktown HeightsUSA

Personalised recommendations