Incomplete Modality Transfer Learning via Latent Low-Rank Constraint
When insufficient or incomplete multi-modality data are available in training, the corresponding classi-fication learning may lead to poor training performance or even failure. In order to tackle with this problem, the transfer learning algorithm called IMTL (incomplete modality transfer learning vi...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2022-12-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2103085.pdf |
| _version_ | 1811195254593814528 |
|---|---|
| author | XU Guangsheng, WANG Shitong |
| author_facet | XU Guangsheng, WANG Shitong |
| author_sort | XU Guangsheng, WANG Shitong |
| collection | DOAJ |
| description | When insufficient or incomplete multi-modality data are available in training, the corresponding classi-fication learning may lead to poor training performance or even failure. In order to tackle with this problem, the transfer learning algorithm called IMTL (incomplete modality transfer learning via latent low-rank constraint) is proposed in this paper. The proposed algorithm addresses the incomplete modality problem in two ways. Firstly, latent factors are introduced into a low-rank constrained subspace framework so as to mine missing modality infor-mation on the target domain. With the help of an auxiliary yet complete modality dataset, the proposed cross-modality and cross-dataset transfer learning strategy is used to help align data between modalities or datasets. Sec-ondly, a small amount of labeled target data is used to align the supervision information so as to maintain the internal structure of the target data during the transfer learning. Experimental results show that the proposed algorithm outperforms the previous transfer learning algorithms, and significantly improves the classification performance on the adopted incomplete target datasets. |
| first_indexed | 2024-04-12T00:40:17Z |
| format | Article |
| id | doaj.art-198850a7683848f58fb8dff2050b84c5 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-04-12T00:40:17Z |
| publishDate | 2022-12-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-198850a7683848f58fb8dff2050b84c52022-12-22T03:55:01ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182022-12-0116122775278710.3778/j.issn.1673-9418.2103085Incomplete Modality Transfer Learning via Latent Low-Rank ConstraintXU Guangsheng, WANG Shitong01. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, China;2. Key Laboratory of Media Design and Software Technology of Jiangsu Province, Jiangnan University, Wuxi, Jiangsu 214122, ChinaWhen insufficient or incomplete multi-modality data are available in training, the corresponding classi-fication learning may lead to poor training performance or even failure. In order to tackle with this problem, the transfer learning algorithm called IMTL (incomplete modality transfer learning via latent low-rank constraint) is proposed in this paper. The proposed algorithm addresses the incomplete modality problem in two ways. Firstly, latent factors are introduced into a low-rank constrained subspace framework so as to mine missing modality infor-mation on the target domain. With the help of an auxiliary yet complete modality dataset, the proposed cross-modality and cross-dataset transfer learning strategy is used to help align data between modalities or datasets. Sec-ondly, a small amount of labeled target data is used to align the supervision information so as to maintain the internal structure of the target data during the transfer learning. Experimental results show that the proposed algorithm outperforms the previous transfer learning algorithms, and significantly improves the classification performance on the adopted incomplete target datasets.http://fcst.ceaj.org/fileup/1673-9418/PDF/2103085.pdf|transfer learning|incomplete modality|latent low-rank constraint |
| spellingShingle | XU Guangsheng, WANG Shitong Incomplete Modality Transfer Learning via Latent Low-Rank Constraint Jisuanji kexue yu tansuo |transfer learning|incomplete modality|latent low-rank constraint |
| title | Incomplete Modality Transfer Learning via Latent Low-Rank Constraint |
| title_full | Incomplete Modality Transfer Learning via Latent Low-Rank Constraint |
| title_fullStr | Incomplete Modality Transfer Learning via Latent Low-Rank Constraint |
| title_full_unstemmed | Incomplete Modality Transfer Learning via Latent Low-Rank Constraint |
| title_short | Incomplete Modality Transfer Learning via Latent Low-Rank Constraint |
| title_sort | incomplete modality transfer learning via latent low rank constraint |
| topic | |transfer learning|incomplete modality|latent low-rank constraint |
| url | http://fcst.ceaj.org/fileup/1673-9418/PDF/2103085.pdf |
| work_keys_str_mv | AT xuguangshengwangshitong incompletemodalitytransferlearningvialatentlowrankconstraint |