Classification of Astronomical Bodies by Efficient Layer Fine-Tuning of Deep Neural Networks

EasyChair Preprint 7320

Abstract

The SDSS-IV dataset contains information about various astronomical bodies such as Galaxies, Stars, and Quasars captured by observatories. Inspired by our work on deep multimodal learning, which utilized transfer learning to classify the SDSS-IV dataset, we further extended our research in the fine tuning of these architectures to study the effect in the classification sceanrio. Architectures such as Resnet-50, DenseNet-121 VGG-16, Xception, EfficientNetB2, MobileNetV2 and NasnetMobile have been built using layer wise fine tuning at different levels. Our findings suggest that freezing all layers with Imagenet weights and adding a final trainable layer may not be the optimal solution. Further, baseline models and models that have higher number of trainable layers performed similarly in certain architectures. Model need to be fine tuned at different levels and a specific training ratio is required for a model to be termed ideal. Different architectures had different responses to the change in the number of trainable layers w.r.t accuracies. While models such as DenseNet-121, Xception, EfficientNetB2 achieved peak accuracies that were relatively consistent with near perfect training curves, models such as Resnet-50,VGG-16, MobileNetV2 and NasnetMobile had lower, delayed peak accuracies with poorly fitting training curves. It was also found that though mobile neural networks have lesser parameters and model size, they may not always be ideal for deployment on a low computational device as they had consistently lower validation accuracies. Customized evaluation metrics such as Tuning Parameter Ratio and Tuning Layer Ratio are used for model evaluation.

Keyphrases: CNN, EfficientNetB2, MobileNetV2, NASNetMobile, ResNet50, SDSS, Transfer Learning, Xception, fine-tuning

@booklet{EasyChair:7320,
  author    = {E Sabeesh and Bharath Kumar Bolla},
  title     = {Classification of Astronomical Bodies by Efficient Layer Fine-Tuning of Deep Neural Networks},
  howpublished = {EasyChair Preprint 7320},
  year      = {EasyChair, 2022}}