Fine-tuning deep CNN models on specific MS COCO categories

Daniel Sonntag; Michael Barz; Jan Zacharias; Sven Stauden; Vahid Rahmani; Áron Fóthi; András Lőrincz

Fine-tuning deep CNN models on specific MS COCO categories

Computer Vision and Pattern Recognition 2017-09-07 v1 Artificial Intelligence Machine Learning

Authors: Daniel Sonntag , Michael Barz , Jan Zacharias , Sven Stauden , Vahid Rahmani , Áron Fóthi , András Lőrincz

Abstract

Fine-tuning of a deep convolutional neural network (CNN) is often desired. This paper provides an overview of our publicly available py-faster-rcnn-ft software library that can be used to fine-tune the VGG_CNN_M_1024 model on custom subsets of the Microsoft Common Objects in Context (MS COCO) dataset. For example, we improved the procedure so that the user does not have to look for suitable image files in the dataset by hand which can then be used in the demo program. Our implementation randomly selects images that contain at least one object of the categories on which the model is fine-tuned.

Keywords

convolutional neural network fine-grained visual classification deep learning for image classification

Cite

@article{arxiv.1709.01476,
  title  = {Fine-tuning deep CNN models on specific MS COCO categories},
  author = {Daniel Sonntag and Michael Barz and Jan Zacharias and Sven Stauden and Vahid Rahmani and Áron Fóthi and András Lőrincz},
  journal= {arXiv preprint arXiv:1709.01476},
  year   = {2017}
}

Fine-tuning deep CNN models on specific MS COCO categories

Abstract

Keywords

Cite

Related papers