Deployment Prior Injection for Run-time Calibratable Object Detection

arXiv:2402.17207v1 Announce Type: new
Abstract: With a strong alignment between the training and test distributions, object relation as a context prior facilitates object detection. Yet, it turns into a harmful but inevitable training set bias upon test distributions that shift differently across space and time. Nevertheless, the existing detectors cannot incorporate deployment context prior during the test phase without parameter update. Such kind of capability requires the model to explicitly learn disentangled representations with respect to context prior. To achieve …

abstract alignment arxiv bias context cs.cv deployment detection prior set shift space space and time test training type