Multimodal Deep Learning for Robust RGB-D Object Recognition
This addresses the problem of robust object recognition for robotics applications, but it is incremental as it builds on existing CNN methods.
The paper tackles robust object recognition in robotics by proposing a novel RGB-D architecture using CNNs with late fusion, achieving state-of-the-art results on the RGB-D object dataset and demonstrating effectiveness in noisy real-world settings.
Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object recognition. Our architecture is composed of two separate CNN processing streams - one for each modality - which are consecutively combined with a late fusion network. We focus on learning with imperfect sensor data, a typical problem in real-world robotics tasks. For accurate learning, we introduce a multi-stage training methodology and two crucial ingredients for handling depth data with CNNs. The first, an effective encoding of depth information for CNNs that enables learning without the need for large depth datasets. The second, a data augmentation scheme for robust learning with depth images by corrupting them with realistic noise patterns. We present state-of-the-art results on the RGB-D object dataset and show recognition in challenging RGB-D real-world noisy settings.