Target Driven Instance Detection
This addresses the need for efficient and generalizable instance detection in applications like household robotics, though it is incremental as it builds on existing detectors.
The paper tackles the instance detection problem by introducing Target Driven Instance Detector (TDID), which modifies general object detectors to improve performance on seen instances with fast runtime and generalize to detect novel instances.
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.