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 re- cently. 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 au- tomatically discover both clusters of similar categories and outliers. We show that the ob jective of our generic MTL formulation can be solved using an iterative reweighted method. Through an extensive experi- mental validation, we demonstrate that our method outperforms several state-of-the-art approaches.