Name
Abstract | ||
|---|---|---|
The feature coding-pooling framework is shown to perform well in image classification tasks, because it can generate discriminative and robust image representations. The unavoidable information loss incurred by feature quantization in the coding process and the undesired dependence of pooling on the image spatial layout, however, may severely limit the classification. In this paper, we propose a linear distance coding (LDC) method to capture the discriminative information lost in traditional coding methods while simultaneously alleviating the dependence of pooling on the image spatial layout. The core of the LDC lies in transforming local features of an image into more discriminative distance vectors, where the robust image-to-class distance is employed. These distance vectors are further encoded into sparse codes to capture the salient features of the image. The LDC is theoretically and experimentally shown to be complementary to the traditional coding methods, and thus their combination can achieve higher classification accuracy. We demonstrate the effectiveness of LDC on six data sets, two of each of three types (specific object, scene, and general object), i.e., Flower 102 and PFID 61, Scene 15 and Indoor 67, Caltech 101 and Caltech 256. The results show that our method generally outperforms the traditional coding methods, and achieves or is comparable to the state-of-the-art performance on these data sets. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TIP.2012.2218826 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
feature quantization,linear distance coding,image coding,image classification tasks,image-to-class distance,linear distance coding (ldc),robust image-to-class distance,image classification,robust image representations,discriminative distance vectors,ldc method,unavoidable information loss,discriminative information lost,feature coding-pooling framework,discriminative image representations,image spatial layout | Computer vision,Caltech 101,Pattern recognition,U-matrix,Feature detection (computer vision),Coding (social sciences),Feature extraction,Distance transform,Artificial intelligence,Contextual image classification,Discriminative model,Mathematics | Journal |
Volume | Issue | ISSN |
22 | 2 | 1941-0042 |
Citations | PageRank | References |
26 | 0.73 | 23 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zilei Wang | 1 | 78 | 8.06 |
| Jiashi Feng | 2 | 2165 | 140.81 |
| Shuicheng Yan | 3 | 767 | 25.71 |
| Hongsheng Xi | 4 | 357 | 38.39 |