Template-based Unseen Instance Detection Article Swipe
YOU?
·
· 2019
· Open Access
·
· OA: W3011837235
Much of the focus in the object detection literature has been on the problem of identifying the bounding box of a particular class of object in an image. Yet, in contexts such as robotics and augmented reality, it is often necessary to find a specific object instance---a unique toy or a custom industrial part for example---rather than a generic object class. Here, applications can require a rapid shift from one object instance to another, thus requiring fast turnaround which affords little-to-no training time. In this context, we propose a generic approach to detect unseen instances based on templates rendered from a textured 3D model. To this effect, we introduce a network architecture which employs tunable filters, and leverage learned feature embeddings to correlate object templates and query images. At test time, our approach is able to successfully detect a previously unknown (not seen in training) object, even under significant occlusion. For instance, our method offers an improvement of almost 30 mAP over the previous template matching methods on the challenging Occluded Linemod (overall mAP of 50.7). With no access to the objects to be detected at training time, our method still yields detection results that are on par with existing ones that are allowed to train on the objects. By reviving this research direction in the context of more powerful, deep feature extractors, our work sets the stage for more development in the area of unseen object instance detection.
