—Aiming to improve recognition rate, we propose a novel flower recognition system that automatically expands the training data from large-scale unlabeled image pools without human intervention. Existing flower recognition approaches often learn classifiers based on a small labeled dataset. However, it is difficult to build a generalizable model (e.g., for realworld environment) with only a handful of labeled training examples, and it is labor-intensive for manually annotating largescale images. To resolve these difficulties, we propose a novel framework that automatically expands the training data to include visually diverse examples from large-scale web images with minimal supervision. Inspired by co-training methods, we investigate two conceptually independent modalities (i.e., shape and color) that provide complementary information to learn our discriminative classifiers. Experimental results show that the augmented training set can significantly improve the recognition acc...
Cheng-Yu Huang, Yen-Liang Lin, Winston H. Hsu