Dictionary Learning Inspired Deep Network for Scene Recognition.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018
MetadataShow full item record
Liu, Y., Chen, Q., Chen, W., & Wassell, I. J. (2018). Dictionary Learning Inspired Deep Network for Scene Recognition.. AAAI, 7178-7185. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/schedConf/presentations
Scene recognition remains one of the most challenging prob- lems in image understanding. With the help of fully con- nected layers (FCL) and rectified linear units (ReLu), deep networks can extract the moderately sparse and discrimi- native feature representation required for scene recognition. However, few methods consider exploiting a sparsity model for learning the feature representation in order to provide en- hanced discriminative capability. In this paper, we replace the conventional FCL and ReLu with a new dictionary learn- ing layer, that is composed of a finite number of recurrent units to simultaneously enhance the sparse representation and discriminative abilities of features via the determination of optimal dictionaries. In addition, with the help of the struc- ture of the dictionary, we propose a new label discrimina- tive regressor to boost the discrimination ability. We also pro- pose new constraints to prevent overfitting by incorporating the advantage of the Mahalanobis and Euclidean distances to balance the recognition accuracy and generalization per- formance. Our proposed approach is evaluated using various scene datasets and shows superior performance to many state- of-the-art approaches.
This record's URL: https://www.repository.cam.ac.uk/handle/1810/276786