CNN-based Repetitive self-revised learning for photos' aesthetics imbalanced classification
This addresses aesthetic assessment for photo classification, but it is incremental as it builds on existing CNN methods with a specific training adjustment.
The paper tackled photo aesthetic classification with imbalanced data by using repetitive self-revised learning (RSRL) to drop low-likelihood samples during CNN training, resulting in improved performance for imbalanced classification.
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.