Fine-grained Categorization -- Short Summary of our Entry for the ImageNet Challenge 2012
This work addresses fine-grained recognition for dog breeds, but it is incremental as it combines existing techniques without introducing a new method.
The paper tackled the problem of visual categorization of dog breeds, which is challenging due to low interclass distances and high intra-class variances, and achieved a 24.59% mean average precision performance on the Stanford dog dataset.
In this paper, we tackle the problem of visual categorization of dog breeds, which is a surprisingly challenging task due to simultaneously present low interclass distances and high intra-class variances. Our approach combines several techniques well known in our community but often not utilized for fine-grained recognition: (1) automatic segmentation, (2) efficient part detection, and (3) combination of multiple features. In particular, we demonstrate that a simple head detector embedded in an off-the-shelf recognition pipeline can improve recognition accuracy quite significantly, highlighting the importance of part features for fine-grained recognition tasks. Using our approach, we achieved a 24.59% mean average precision performance on the Stanford dog dataset.