Fine-tuning deep CNN models on specific MS COCO categories

2017/09/05 by Daniel Sonntag, Michael Barz, Sonntag, Daniel +11 · 1 citation
Computer Science · Medicine · #Advanced Neural Network Applications #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1709.01476

openalex publication_date 2017/09/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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_M1024 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.

Citations

• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• ImageNet Large Scale Visual Recognition Challenge

Cited by

• Unsupervised Hard Example Mining from Videos for Improved Object Detection

Related

• Deep CNN Ensemble with Data Augmentation for Object Detection
• DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
• OD-GCN: Object Detection Boosted by Knowledge GCN
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer Vision