TY  - CONF
AU  - Xinhang Song
AU  - Shuqiang Jiang
AU  - Luis Herranz
A2  - IJCAI
PY  - 2017//
TI  - Combining Models from Multiple Sources for RGB-D Scene Recognition
BT  - 26th  International Joint Conference on Artificial Intelligence
SP  - 4523
EP  - 4529
KW  - Robotics and Vision
KW  - Vision and Perception
N2  - Depth can complement RGB with useful cues about object volumes and scene layout. However, RGB-D image datasets are still too small for directly training deep convolutional neural networks (CNNs), in contrast to the massive monomodal RGB datasets. Previous works in RGB-D recognition typically combine two separate networks for RGB and depth data, pretrained with a large RGB dataset and then fine tuned to the respective target RGB and depth datasets. These approaches have several limitations: 1) only use low-level filters learned from RGB data, thus not being able to exploit properly depth-specific patterns, and 2) RGB and depth features are only combined at high-levels but rarely at lower-levels. In this paper, we propose a framework that leverages both knowledge acquired from large RGB datasets together with depth-specific cues learned from the limited depth data, obtaining more effective multi-source and multi-modal representations. We propose a multi-modal combination method that selects discriminative combinations of layers from the different source models and target modalities, capturing both high-level properties of the task and intrinsic low-level properties of both modalities.
L1  - http://refbase.cvc.uab.es/files/SJH2017b.pdf
UR  - http://dx.doi.org/10.24963/ijcai.2017/631
N1  - LAMP; 600.120
ID  - Xinhang Song2017
ER  -