Model-based active learning to detect an isometric deformable object in the wild with a deep architecture.

Highlights • An algorithm for achieving CNN based object-instance recognition across imaging conditions. • An active learning algorithm that can generate images of failure conditions in order to actively adapt the trained model on-the-fly. • A characterization of the extent to which CNNs can learn and cope with different imaging conditions. We dub this the learnability of imaging conditions. • Extensive experiments on both synthetic and real datasets showing the effectiveness of our algorithm. Abstract In the recent past, algorithms based on Convolutional Neural Networks (CNNs) have achieved significant milestones in object recognition. With large examples of each object class, standard datasets train well for inter-class variability. However, gathering sufficient data to train for a particular instance of an object within a class is impractical. Furthermore, quantitatively assessing the imaging conditions for each image in a given dataset is not feasible. By generating sufficient images with known imaging conditions, we study to what extent CNNs can cope with hard imaging conditions for instance-level recognition in an active learning regime. Leveraging powerful rendering techniques to achieve instance-level detection, we present results of training three state-of-the-art object detection algorithms namely, Fast R-CNN, Faster R-CNN and YOLO9000, for hard imaging conditions imposed into the scene by rendering. Our extensive experiments produce a mean Average Precision score of 0.92 on synthetic images and 0.83 on real images using the best performing Faster R-CNN. We show for the first time how well detection algorithms based on deep architectures fare for each hard imaging condition studied. [ABSTRACT FROM AUTHOR]