A Novel Multi-Modal One-Shot Learning Method for Texture Recognition
Most machine learning algorithms require a large set of training samples in order to achieve satisfactory performance. However, this requirement may be difficult to satisfy in practice. Take the one-shot learning (OSL) problem on texture recognition for example; the machine learning algorithm is dif...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8931584/ |
| _version_ | 1831646820416094208 |
|---|---|
| author | Pengwen Xiong Kongfei He Aiguo Song Peter X. Liu |
| author_facet | Pengwen Xiong Kongfei He Aiguo Song Peter X. Liu |
| author_sort | Pengwen Xiong |
| collection | DOAJ |
| description | Most machine learning algorithms require a large set of training samples in order to achieve satisfactory performance. However, this requirement may be difficult to satisfy in practice. Take the one-shot learning (OSL) problem on texture recognition for example; the machine learning algorithm is difficult to achieve satisfactory results. In order to solve this problem, a novel multi-modal one-shot learning method for texture recognition is presented. First, in order to improve the robustness of identification and the anti-interference to noise, we addressed the nontravel texture recognition challenges of learn information about object categories from only one training sample by fusing varied modalities data, including image, sound and acceleration, which provides rich information regarding textures. Second, a novel dictionary learning model is designed, which contains the various modalities information, and can simultaneously learn the latent common sparse code for the different modalities. Third, an original regularization term is developed to enhance the degree of distinction of different classes. Furthermore, the common features of the three modalities are evaluated in the case of one-shot learning and used as the basis for feature selection. In the end, experiments were performed based on a data set which was published openly to validate the effectiveness of the presented method. |
| first_indexed | 2024-12-19T14:01:45Z |
| format | Article |
| id | doaj.art-6393c1bd087140e48364fe86e0d6c997 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T14:01:45Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6393c1bd087140e48364fe86e0d6c9972022-12-21T20:18:26ZengIEEEIEEE Access2169-35362019-01-01718253818254710.1109/ACCESS.2019.29590118931584A Novel Multi-Modal One-Shot Learning Method for Texture RecognitionPengwen Xiong0https://orcid.org/0000-0002-0623-8592Kongfei He1https://orcid.org/0000-0001-7068-5090Aiguo Song2https://orcid.org/0000-0002-1982-6780Peter X. Liu3https://orcid.org/0000-0002-8703-6967School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaSchool of Information Engineering, Nanchang University, Nanchang, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing, ChinaDepartment of Systems and Computer Engineering, Carleton University, Ottawa, CanadaMost machine learning algorithms require a large set of training samples in order to achieve satisfactory performance. However, this requirement may be difficult to satisfy in practice. Take the one-shot learning (OSL) problem on texture recognition for example; the machine learning algorithm is difficult to achieve satisfactory results. In order to solve this problem, a novel multi-modal one-shot learning method for texture recognition is presented. First, in order to improve the robustness of identification and the anti-interference to noise, we addressed the nontravel texture recognition challenges of learn information about object categories from only one training sample by fusing varied modalities data, including image, sound and acceleration, which provides rich information regarding textures. Second, a novel dictionary learning model is designed, which contains the various modalities information, and can simultaneously learn the latent common sparse code for the different modalities. Third, an original regularization term is developed to enhance the degree of distinction of different classes. Furthermore, the common features of the three modalities are evaluated in the case of one-shot learning and used as the basis for feature selection. In the end, experiments were performed based on a data set which was published openly to validate the effectiveness of the presented method.https://ieeexplore.ieee.org/document/8931584/Texture recognitiondictionary learningone-shot learningmulti-modal fusion |
| spellingShingle | Pengwen Xiong Kongfei He Aiguo Song Peter X. Liu A Novel Multi-Modal One-Shot Learning Method for Texture Recognition IEEE Access Texture recognition dictionary learning one-shot learning multi-modal fusion |
| title | A Novel Multi-Modal One-Shot Learning Method for Texture Recognition |
| title_full | A Novel Multi-Modal One-Shot Learning Method for Texture Recognition |
| title_fullStr | A Novel Multi-Modal One-Shot Learning Method for Texture Recognition |
| title_full_unstemmed | A Novel Multi-Modal One-Shot Learning Method for Texture Recognition |
| title_short | A Novel Multi-Modal One-Shot Learning Method for Texture Recognition |
| title_sort | novel multi modal one shot learning method for texture recognition |
| topic | Texture recognition dictionary learning one-shot learning multi-modal fusion |
| url | https://ieeexplore.ieee.org/document/8931584/ |
| work_keys_str_mv | AT pengwenxiong anovelmultimodaloneshotlearningmethodfortexturerecognition AT kongfeihe anovelmultimodaloneshotlearningmethodfortexturerecognition AT aiguosong anovelmultimodaloneshotlearningmethodfortexturerecognition AT peterxliu anovelmultimodaloneshotlearningmethodfortexturerecognition AT pengwenxiong novelmultimodaloneshotlearningmethodfortexturerecognition AT kongfeihe novelmultimodaloneshotlearningmethodfortexturerecognition AT aiguosong novelmultimodaloneshotlearningmethodfortexturerecognition AT peterxliu novelmultimodaloneshotlearningmethodfortexturerecognition |