Fine-tuning deep CNN models on specific MS COCO categories

09/05/2017
by   Daniel Sonntag, et al.
0

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.

READ FULL TEXT
research
07/31/2023

Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?

Machine learning practitioners often fine-tune generative pre-trained mo...
research
04/15/2022

Transfer Learning for Instance Segmentation of Waste Bottles using Mask R-CNN Algorithm

This paper proposes a methodological approach with a transfer learning s...
research
07/14/2022

Exploration of an End-to-End Automatic Number-plate Recognition neural network for Indian datasets

Indian vehicle number plates have wide variety in terms of size, font, s...
research
03/17/2022

On the Importance of Data Size in Probing Fine-tuned Models

Several studies have investigated the reasons behind the effectiveness o...
research
07/10/2021

Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentation

Domain Adaptation (DA) methods are widely used in medical image segmenta...
research
12/12/2019

The Benefits of Close-Domain Fine-Tuning for Table Detection in Document Images

A correct localisation of tables in a document is instrumental for deter...
research
04/14/2022

OmniPD: One-Step Person Detection in Top-View Omnidirectional Indoor Scenes

We propose a one-step person detector for topview omnidirectional indoor...

Please sign up or login with your details

Forgot password? Click here to reset