S-Extension Patch: A simple and efficient way to extend an object detection model

TL;DR

This paper introduces S-Extension Patch, a method to efficiently extend object detection models by adding new classes rapidly, with minimal retraining, maintaining accuracy and inference speed.

Contribution

The paper presents a novel extension technique that significantly reduces training time and data requirements for adding new classes to existing object detection models.

Findings

Extends object detection models in 1/10th of the time of existing methods.

Maintains accuracy and inference speed after extension.

Requires minimal additional data for new classes.

Abstract

While building convolutional network-based systems, the toll it takes to train the network is something that cannot be ignored. In cases where we need to append additional capabilities to the existing model, the attention immediately goes towards retraining techniques. In this paper, I show how to leverage knowledge about the dataset to append the class faster while maintaining the speed of inference as well as the accuracies; while reducing the amount of time and data required. The method can extend a class in the existing object detection model in 1/10th of the time compared to the other existing methods. S-Extension patch not only offers faster training but also speed and ease of adaptation, as it can be appended to any existing system, given it fulfills the similarity threshold condition.