A STUDY OF METHODS FOR TRAINING WITH DIFFERENT DATASETS IN IMAGE CLASSIFICATION

Yuxuan Bao

Northfield Mount Hermon School

ABSTRACT

This research developed a training method of Convolutional Neural Network model with multiple datasets to achieve good performance on both datasets. Two different methods of training with two characteristically different datasets with identical categories, one with very clean images and one with real-world data, were proposed and studied. The model used for the study was a neural network derived from ResNet. Mixed training was shown to produce the best accuracies for each dataset when the dataset is mixed into the training set at the highest proportion, and the best combined performance when the realworld dataset was mixed in at a ratio of around 70%. This ratio produced a top-1 combined performance of 63.8% (no mixing produced 30.8%) and a top-3 combined performance of 83.0% (no mixing produced 55.3%). This research also showed that iterative training has a worse combined performance than mixed training due to the issue of fast forgetting.

KEYWORDS Supervised Learning, Image Classification, Convolutional Neural Network, ResNet, Multiple Datasets

ORIGINAL SOURCE URL: https://airccse.com/adeij/papers/2419adeij01.pdf

VOLUME LINK: https://airccse.com/adeij/current.html