A codebook-free and annotation-free approach for fine-grained image categorization

Fine-grained categorization refers to the task of classify-ing objects that belong to the same basic-level class (e.g. different bird species) and share similar shape or visual appearances. Most of the state-of-the-art basic-level ob-ject classification algorithms have difficulties in this chal-lenging problem. One reason for this can be attributed to the popular codebook-based image representation, of-ten resulting in loss of subtle image information that are critical for fine-grained classification. Another way to ad-dress this problem is to introduce human annotations of ob-ject attributes or key points, a tedious process that is al-so difficult to generalize to new tasks. In this work, we propose a codebook-free and annotation-free approach for fine-grained image categorization. Instead of using vector-quantized codewords, we obtain an image representation by running a high throughput template matching process us-ing a large number of randomly generated image templates. We then propose a novel bagging-based algorithm to build a final classifier by aggregating a set of discriminative yet largely uncorrelated classifiers. Experimental results show that our method outperforms state-of-the-art classification approaches on the Caltech-UCSD Birds dataset