Recently, deep dictionary learning (DDL) has aroused attention due to its abilities of learning multiple different dictionaries and extracting multi-level abstract feature representations for samples. It has been applied to many intelligent recognition tasks, such as vehicle detection, traffic sign recognition and driver monitoring. Nevertheless, the off-the-shelf DDL-based methods ignore the essential structural information of data in multi-layer dictionary learning. The learned hierarchical data representations are less discriminative. To address this issue, we develop a new DDL framework, called the hierarchical graph augmented deep collaborative dictionary learning (HGDCDL). Firstly, we propose a new deep collaborative dictionary learning (DCDL) that applies collaborative representation to the deepest-level representation learning. Most importantly, equipped with a simple yet effective hierarchal graph construction mechanism, our HGDCDL uses the structure of data to regularize dictionary learning, and generates more informative dictionaries and discriminative representations at different levels. Extensive experiments show that our HGDCDL performs significantly better than the state-of-the-art shallow and deep representation learning methods for classification.
Hierarchical Graph Augmented Deep Collaborative Dictionary Learning for Classification
IEEE Transactions on Intelligent Transportation Systems ; 23 , 12 ; 25308-25322
2022-12-01
3384288 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Collaborative error reduction for hierarchical classification
British Library Online Contents | 2014
|Unified Dictionary Learning and Region Tagging with Hierarchical Sparse Representation
British Library Online Contents | 2013
|Zero-Shot Image Classification via Coupled Discriminative Dictionary Learning
Springer Verlag | 2017
|