Deep Template-based Object Instance Detection

TL;DR

This paper introduces a fast, training-free 2D object instance detection method that leverages viewpoint templates to locate specific objects in images, outperforming traditional template matching on occluded datasets.

Contribution

The proposed approach enables rapid detection of specific object instances without additional training, using viewpoint-based templates to improve accuracy in challenging scenarios.

Findings

Almost 30 mAP improvement over previous template matching methods

Achieves 50.7 mAP on Occluded Linemod dataset

Single generic model performs on par with object-specific trained models

Abstract

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. What is more, gathering a dataset and training a model for every new object instance to be detected can be an expensive and time-consuming process. In this context, we propose a generic 2D object instance detection approach that uses example viewpoints of the target object at test time to retrieve its 2D location in RGB images, without requiring any additional training (i.e. fine-tuning) step. To this end, we present an end-to-end architecture that extracts global and local information of the object from its viewpoints. The global information is used to tune early filters in the backbone while local viewpoints are correlated with the input image. Our method offers an improvement of almost 30 mAP over the previous template matching methods on the challenging Occluded Linemod dataset (overall mAP of 50.7). Our experiments also show that our single generic model (not trained on any of the test objects) yields detection results that are on par with approaches that are trained specifically on the target objects.