Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and Ensemble

15 Jul 2020  ·  Byeongjo Kim, Chanran Kim, Jaehoon Lee, Jein Song, Gyoungsoo Park ·

In general, sufficient data is essential for the better performance and generalization of deep-learning models. However, lots of limitations(cost, resources, etc.).. of data collection leads to lack of enough data in most of the areas. In addition, various domains of each data sources and licenses also lead to difficulties in collection of sufficient data. This situation makes us hard to utilize not only the pre-trained model, but also the external knowledge. Therefore, it is important to leverage small dataset effectively for achieving the better performance. We applied some techniques in three aspects: data, loss function, and prediction to enable training from scratch with less data. With these methods, we obtain high accuracy by leveraging ImageNet data which consist of only 50 images per class. Furthermore, our model is ranked 4th in Visual Inductive Printers for Data-Effective Computer Vision Challenge. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Classification ImageNet VIPriors subset EfficientNet (w data augmentation, ensemble) Top-1 67.3 # 2

Methods


No methods listed for this paper. Add relevant methods here