{"type":"ScholarlyArticle","title":"Semi-Supervised Multimodal Deep Learning for RGB-D Object Recognition","authors":[{"name":"Yanhua Cheng","slug":"yanhua-cheng","given":"Yanhua","family":"Cheng","affiliation":""},{"name":"Xin Zhao","slug":"xin-zhao","given":"Xin","family":"Zhao","affiliation":""},{"name":"Rui Cai","slug":"rui-cai","given":"Rui","family":"Cai","affiliation":""},{"name":"Zhiwei Li","slug":"zhiwei-li","given":"Zhiwei","family":"Li","affiliation":""},{"name":"Kaiqi Huang","slug":"kaiqi-huang","given":"Kaiqi","family":"Huang","affiliation":""},{"name":"Yong Rui","slug":"yong-rui","given":"Yong","family":"Rui","affiliation":""}],"abstract":"This paper studies the problem of RGB-D object recognition. Inspired by the great success of deep convolutional neural networks (DCNN) in AI, researchers have tried to apply it to improve the performance of RGB-D object recognition. However, DCNN always requires a large-scale annotated dataset to supervise its training. Manually labeling such a large RGB-D dataset is expensive and time consuming, which prevents DCNN from quickly promoting this research area. To address this problem, we propose a semi-supervised multimodal deep learning framework to train DCNN effectively based on very limited labeled data and massive unlabeled data. The core of our framework is a novel diversity preserving co-training algorithm, which can successfully guide DCNN to learn from the unlabeled RGB-D data by making full use of the complementary cues of the RGB and depth data in object representation. Experiments on the benchmark RGB-D dataset demonstrate that, with only 5% labeled training data, our approach achieves competitive performance for object recognition compared with those state-of-the-art results reported by fully-supervised methods.","doi":null,"url":"https://ijcai.org/proceedings/2016/473","pdf":"https://ijcai.org/proceedings/2016/0473.pdf","markdown":"https://ijcai.org/proceedings/2016/473.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/473","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":473,"pages":{"first":3345,"last":3350},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}