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

arXiv: https://arxiv.org/abs/1709.01476 · HTML: https://mlsanity.com/paper/1709.01476/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2017.

## Built on by (most cited first, 1 of 1)

- [Algorithm Research of ELMo Word Embedding and Deep Learning Multimodal Transformer in Image Description](https://mlsanity.com/paper/2408.06357/) (2024)

## Abstract (arXiv)

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.