Loading...
Please wait, while we are loading the content...
Similar Documents
Encoding high dimensional local features by sparse coding based fisher vectors
| Content Provider | CiteSeerX |
|---|---|
| Author | Liu, Lingqiao Shen, Chunhua Wang, Lei Hengel, Anton Van Den Wang, Chao |
| Description | Deriving from the gradient vector of a generative model of local features, Fisher vector coding (FVC) has been identified as an effective coding method for im-age classification. Most, if not all, FVC implementations employ the Gaussian mixture model (GMM) to characterize the generation process of local features. This choice has shown to be sufficient for traditional low dimensional local fea-tures, e.g., SIFT; and typically, good performance can be achieved with only a few hundred Gaussian distributions. However, the same number of Gaussians is insuf-ficient to model the feature space spanned by higher dimensional local features, which have become popular recently. In order to improve the modeling capacity for high dimensional features, it turns out to be inefficient and computationally impractical to simply increase the number of Gaussians. In this paper, we propose a model in which each local feature is drawn from a Gaussian distribution whose mean vector is sampled from a subspace. With cer-tain approximation, this model can be converted to a sparse coding procedure and the learning/inference problems can be readily solved by standard sparse coding methods. By calculating the gradient vector of the proposed model, we derive a new fisher vector encoding strategy, termed Sparse Coding based Fisher Vec-tor Coding (SCFVC). Moreover, we adopt the recently developed Deep Convo-lutional Neural Network (CNN) descriptor as a high dimensional local feature and implement image classification with the proposed SCFVC. Our experimen-tal evaluations demonstrate that our method not only significantly outperforms the traditional GMM based Fisher vector encoding but also achieves the state-of-the-art performance in generic object recognition, indoor scene, and fine-grained image classification problems. 1 in Proc. Adv. Neural Inf. Process. Syst., 2014 |
| File Format | |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
