Combining randomization and discrimination for fine-grained image categorization

TLDR

The paper investigates fine‑grained image categorization by exploring fine image statistics to identify discriminative patches for recognition. It combines discriminative feature mining with randomization, employing a random forest of discriminative decision trees where each node is trained on its own and upstream information to handle the large feature space and prevent over‑fitting. Experimental results demonstrate that the method identifies semantically meaningful visual information and outperforms state‑of‑the‑art algorithms on multiple datasets.

Abstract

In this paper, we study the problem of fine-grained image categorization. The goal of our method is to explore fine image statistics and identify the discriminative image patches for recognition. We achieve this goal by combining two ideas, discriminative feature mining and randomization. Discriminative feature mining allows us to model the detailed information that distinguishes different classes of images, while randomization allows us to handle the huge feature space and prevents over-fitting. We propose a random forest with discriminative decision trees algorithm, where every tree node is a discriminative classifier that is trained by combining the information in this node as well as all upstream nodes. Our method is tested on both subordinate categorization and activity recognition datasets. Experimental results show that our method identifies semantically meaningful visual information and outperforms state-of-the-art algorithms on various datasets.