Weakly Supervised Fine-Grained Image Categorization

TL;DR

This paper introduces a method for fine-grained image categorization that does not require object or part annotations, using multi-scale part proposals to build a global representation, achieving competitive accuracy.

Contribution

It presents an annotation-free approach that selects useful parts from multi-scale proposals for fine-grained classification, eliminating the need for expensive annotations.

Findings

Outperforms existing annotation-free methods on two datasets

Achieves comparable or better accuracy than annotation-dependent methods

Enables visualization of key discriminative parts in objects

Abstract

In this paper, we categorize fine-grained images without using any object / part annotation neither in the training nor in the testing stage, a step towards making it suitable for deployments. Fine-grained image categorization aims to classify objects with subtle distinctions. Most existing works heavily rely on object / part detectors to build the correspondence between object parts by using object or object part annotations inside training images. The need for expensive object annotations prevents the wide usage of these methods. Instead, we propose to select useful parts from multi-scale part proposals in objects, and use them to compute a global image representation for categorization. This is specially designed for the annotation-free fine-grained categorization task, because useful parts have shown to play an important role in existing annotation-dependent works but accurate part detectors can be hardly acquired. With the proposed image representation, we can further detect and visualize the key (most discriminative) parts in objects of different classes. In the experiment, the proposed annotation-free method achieves better accuracy than that of state-of-the-art annotation-free and most existing annotation-dependent methods on two challenging datasets, which shows that it is not always necessary to use accurate object / part annotations in fine-grained image categorization.