CNN-based Repetitive self-revised learning for photos' aesthetics imbalanced classification
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2020
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913597977788416 |
|---|---|
| author | Dai, Ying |
| author_facet | Dai, Ying |
| contents | Aesthetic assessment is subjective, and the distribution of the aesthetic levels is imbalanced. In order to realize the auto-assessment of photo aesthetics, we focus on using repetitive self-revised learning (RSRL) to train the CNN-based aesthetics classification network by imbalanced data set. As RSRL, the network is trained repetitively by dropping out the low likelihood photo samples at the middle levels of aesthetics from the training data set based on the previously trained network. Further, the retained two networks are used in extracting highlight regions of the photos related with the aesthetic assessment. Experimental results show that the CNN-based repetitive self-revised learning is effective for improving the performances of the imbalanced classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2003_03081 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | CNN-based Repetitive self-revised learning for photos' aesthetics imbalanced classification Dai, Ying Computer Vision and Pattern Recognition Aesthetic assessment is subjective, and the distribution of the aesthetic levels is imbalanced. In order to realize the auto-assessment of photo aesthetics, we focus on using repetitive self-revised learning (RSRL) to train the CNN-based aesthetics classification network by imbalanced data set. As RSRL, the network is trained repetitively by dropping out the low likelihood photo samples at the middle levels of aesthetics from the training data set based on the previously trained network. Further, the retained two networks are used in extracting highlight regions of the photos related with the aesthetic assessment. Experimental results show that the CNN-based repetitive self-revised learning is effective for improving the performances of the imbalanced classification. |
| title | CNN-based Repetitive self-revised learning for photos' aesthetics imbalanced classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2003.03081 |