Abstract
We propose a detection and segmentation algorithm for the purposes of ?ne-grained recognition. The algorithm ?rst detects low-level regions that could potentially belong to the object and then performs a full-object segmentation through propagation. Apart from segmenting the object, we can also ‘zoom in’ on the object, i.e. center it, normalize for scale, and thus discount the effects of the background. We then show that combining this with a state-of-the-art classi?cation algorithm leads to signi?cant improvements in performance especially for datasets which are considered particularly hard for recognition, e.g. birds species. The proposed algorithm is much more ef?cient than other known methods in similar scenarios [4, 21]. Our method is also simpler and we apply it here to different classes of objects, e.g. birds, ?owers, cats and dogs. We tested the algorithm on a number of benchmark datasets for ?ne-grained categorization. It outperforms all the known state-of-the-art methods on these datasets, sometimes by as much as 11%. It improves the performance of our baseline algorithm by 3-4%, consistently on all datasets. We also observed more than a 4% improvement in the recognition performance on a challenging largescale ?ower dataset, containing 578 species of ?owers and 250,000 images.