Image classification using HTM cortical learning algorithms
Recently the improved bag of features (BoF) model with locality-constrained linear coding (LLC) and spatial pyramid matching (SPM) achieved state-of-the-art performance in image classification. However, only adopting SPM to exploit spatial information is not enough for satisfactory performance. In t...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/99526 http://hdl.handle.net/10220/12893 http://ieeexplore.ieee.org.ezlibproxy1.ntu.edu.sg/xpl/login.jsp?tp=&arnumber=6460663&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6460663 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Recently the improved bag of features (BoF) model with locality-constrained linear coding (LLC) and spatial pyramid matching (SPM) achieved state-of-the-art performance in image classification. However, only adopting SPM to exploit spatial information is not enough for satisfactory performance. In this paper, we use hierarchical temporal memory (HTM) cortical learning algorithms to extend this LLC & SPM based model. HTM regions consist of HTM cells are constructed to spatial pool the LLC codes. Each cell receives a subset of LLC codes, and adjacent subsets are overlapped so that more spatial information can be captured. Additionally, HTM cortical learning algorithms have two processes: learning phase which make the HTM cell only receive most frequent LLC codes, and inhibition phase which ensure that the output of HTM regions is sparse. The experimental results on Caltech 101 and UIUC-Sport dataset show the improvement on the original LLC & SPM based model. |
|---|