Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification

By Zhen Zuo, G. Wang, Bing Shuai, Lifan Zhao, Qingxiong Yang. 2015

69 citations recorded by the source corpus.

In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL aims to hierarchically learn feature transformation filter banks to transform raw pixel image patches to features. The learned filter banks are expected to (1) encode common visual patterns of a flexible number of categories; (2) encode discriminative information; and (3) hierarchically extract patterns at different visual levels. Particularly, in each single layer of DDSFL, shareable filters are jointly learned for classes which share the similar patterns. Discriminative power of the filters is achieved by enforcing the features from the same category to be close, while features from different categories to be far away from each other. Furthermore, we also propose two exemplar selection methods to iteratively select training data for more efficient and effective learning. Based on the experimental results, DDSFL can achieve very promising performance, and it also shows great complementary effect to the state-of-the-art Caffe features. HighlightsWe propose to encode shareable and discriminative information in feature learning.Two exemplar selection methods are proposed to select effective training data.We build a hierarchical learning scheme to capture multiple visual level information.Our DDSFL outperforms most of the existing features.DDSFL features show great complementary effect to Caffe features.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhen Zuo
2. G. Wang
3. Bing Shuai
4. Lifan Zhao
5. Bing Wang
6. Jun Liu
7. Alex ChiChung Kot
8. Amir Shahroudy

In Computer Vision and Pattern Recognition

1. G. Wang
2. Bing Shuai
3. Bing Wang
4. Zhen Zuo
5. Lifan Zhao
6. Haibin Ling
7. Jun Liu
8. Yi Yang

In Media Technology

1. G. Wang
2. Zhen Zuo
3. Bing Shuai
4. Bing Wang

Citations in the corpus

• Integrating parametric and non-parametric models for scene labeling (2015, background): “This module is usually ignored by most researchers until recently when machine learning techniques are commonly used to learn discriminative features for various computer vision tasks [1, 4, 21, 31, 32, 39, 38].”