Zhang C, Cheng J, Tian Q. Incremental Codebook Adaptation for Visual Representation and Categorization.
IEEE TRANSACTIONS ON CYBERNETICS 2018;
48:2012-2023. [PMID:
28749362 DOI:
10.1109/tcyb.2017.2726079]
[Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
The bag-of-visual-words model is widely used for visual content analysis. For visual data, the codebook plays an important role for efficient representation. However, the codebook has to be relearned with the changes of training images. Once the codebook is changed, the encoding parameters of local features have to be recomputed. To alleviate this problem, in this paper, we propose an incremental codebook adaptation method for efficient visual representation. Instead of learning a new codebook, we gradually adapt a prelearned codebook using new images in an incremental way. To make use of the prelearned codebook, we try to make changes to the prelearned codebook with sparsity constraint and low-rank correlation. Besides, we also encode visually similar local features within a neighborhood to take advantage of locality information and ensure the encoded parameters are consistent. To evaluate the effectiveness of the proposed method, we apply the proposed method for categorization tasks on several public image datasets. Experimental results prove the effectiveness and usefulness of the proposed method over other codebook-based methods.
Collapse