Augmenting Strong Supervision Using Web Data for Fine-Grained Categorization

@article{Xu2015AugmentingSS,
  title={Augmenting Strong Supervision Using Web Data for Fine-Grained Categorization},
  author={Zhe Xu and Shaoli Huang and Ya Zhang and Dacheng Tao},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={2524-2532}
}
We propose a new method for fine-grained object recognition that employs part-level annotations and deep convolutional neural networks (CNNs) in a unified framework. Although both schemes have been widely used to boost recognition performance, due to the difficulty in acquiring detailed part annotations, strongly supervised fine-grained datasets are usually too small to keep pace with the rapid evolution of CNN architectures. In this paper, we solve this problem by exploiting inexhaustible web… CONTINUE READING
Highly Cited
This paper has 43 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 27 citations