# Target Driven Instance Detection

## TL;DR

The paper introduces TDID, a system that adapts general object detectors for specific instance recognition, excelling in speed, accuracy, and generalization to unseen instances, suitable for applications like household robotics.

## Contribution

The paper presents TDID, a novel method that enhances existing detectors for targeted instance detection with improved speed, accuracy, and generalization capabilities.

## Key findings

- TDID outperforms baseline detectors on known instances.
- TDID generalizes well to unseen instances.
- TDID operates with real-time speed.

## Abstract

While state-of-the-art general object detectors are getting better and better, there are not many systems specifically designed to take advantage of the instance detection problem. For many applications, such as household robotics, a system may need to recognize a few very specific instances at a time. Speed can be critical in these applications, as can the need to recognize previously unseen instances. We introduce a Target Driven Instance Detector(TDID), which modifies existing general object detectors for the instance recognition setting. TDID not only improves performance on instances seen during training, with a fast runtime, but is also able to generalize to detect novel instances.