# Fine-tuning deep CNN models on specific MS COCO categories

Source: [Fine-tuning deep CNN models on specific MS COCO categories](<https://www.sota2.com/research/paper/68fa639c1e209131ce9ffa59>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:45:17.380Z

Authors: Daniel Sonntag, Michael Barz, Jan Zacharias, Sven Stauden, Vahid Rahmani, \\'Aron F\\'othi, Andr\\'as L\\H{o}rincz

Published: 2017-09-05T16:22:28.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1709.01476>)

[PDF](<https://arxiv.org/pdf/1709.01476.pdf>)