Conference proceeding
Hyper-class augmented and regularized deep learning for fine-grained image classification
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vol.7-12-, pp.2645-2654
06/2015
DOI: 10.1109/CVPR.2015.7298880
Abstract
Deep convolutional neural networks (CNN) have seen tremendous success in large-scale generic object recognition. In comparison with generic object recognition, fine-grained image classification (FGIC) is much more challenging because (i) fine-grained labeled data is much more expensive to acquire (usually requiring domain expertise); (ii) there exists large intra-class and small inter-class variance. Most recent work exploiting deep CNN for image recognition with small training data adopts a simple strategy: pre-train a deep CNN on a large-scale external dataset (e.g., ImageNet) and fine-tune on the small-scale target data to fit the specific classification task. In this paper, beyond the fine-tuning strategy, we propose a systematic framework of learning a deep CNN that addresses the challenges from two new perspectives: (i) identifying easily annotated hyper-classes inherent in the fine-grained data and acquiring a large number of hyper-class-labeled images from readily available external sources (e.g., image search engines), and formulating the problem into multitask learning; (ii) a novel learning model by exploiting a regularization between the fine-grained recognition model and the hyper-class recognition model. We demonstrate the success of the proposed framework on two small-scale fine-grained datasets (Stanford Dogs and Stanford Cars) and on a large-scale car dataset that we collected.
Details
- Title: Subtitle
- Hyper-class augmented and regularized deep learning for fine-grained image classification
- Creators
- Saining Xie - University of California, San DiegoTianbao Yang - University of IowaXiaoyu Wang - Snapchat Research, USAYuanqing Lin - NEC Laboratories America, Inc., USA
- Resource Type
- Conference proceeding
- Publication Details
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vol.7-12-, pp.2645-2654
- Publisher
- IEEE
- DOI
- 10.1109/CVPR.2015.7298880
- ISSN
- 1063-6919
- eISSN
- 1063-6919
- Language
- English
- Date published
- 06/2015
- Academic Unit
- Computer Science
- Record Identifier
- 9984259473802771
Metrics
7 Record Views