Name
Abstract | ||
|---|---|---|
Most research efforts on image classification so far have been focused on medium-scale datasets, which are often defined as datasets that can fit into the memory of a desktop (typically 4G~48G). There are two main reasons for the limited effort on large-scale image classification. First, until the emergence of ImageNet dataset, there was almost no publicly available large-scale benchmark data for image classification. This is mostly because class labels are expensive to obtain. Second, large-scale classification is hard because it poses more challenges than its medium-scale counterparts. A key challenge is how to achieve efficiency in both feature extraction and classifier training without compromising performance. This paper is to show how we address this challenge using ImageNet dataset as an example. For feature extraction, we develop a Hadoop scheme that performs feature extraction in parallel using hundreds of mappers. This allows us to extract fairly sophisticated features (with dimensions being hundreds of thousands) on 1.2 million images within one day. For SVM training, we develop a parallel averaging stochastic gradient descent (ASGD) algorithm for training one-against-all 1000-class SVM classifiers. The ASGD algorithm is capable of dealing with terabytes of training data and converges very fast-typically 5 epochs are sufficient. As a result, we achieve state-of-the-art performance on the ImageNet 1000-class classification, i.e., 52.9% in classification accuracy and 71.8% in top 5 hit rate. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/CVPR.2011.5995477 | CVPR |
Keywords | Field | DocType |
svm training,stochastic processes,hadoop scheme,learning (artificial intelligence),large scale image classification,visual databases,imagenet 1000-class classification,parallel averaging stochastic gradient descent algorithm,imagenet dataset,large-scale image classification,classifier training,feature extraction,image classification,gradient methods,classification accuracy,fast feature extraction,support vector machines,large-scale classification,medium scale datasets,training data,kernel,learning artificial intelligence,encoding | Kernel (linear algebra),Hit rate,Stochastic gradient descent,Pattern recognition,Computer science,Support vector machine,Feature extraction,Artificial intelligence,Contextual image classification,Classifier (linguistics),Machine learning,Encoding (memory) | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
978-1-4577-0394-2 | 157 | 7.30 |
References | Authors | |
20 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lin, Yuanqing | 1 | 1143 | 59.04 |
| Fengjun Lv | 2 | 2490 | 87.05 |
| Zhu, Shenghuo | 3 | 2996 | 167.68 |
| Ming Yang | 4 | 3471 | 162.50 |
| Timothee Cour | 5 | 821 | 34.72 |
| Yu, Kai | 6 | 4799 | 255.21 |
| liangliang cao | 7 | 1816 | 90.71 |
| T. Huang | 8 | 157 | 7.30 |