Deep Dictionary Learning with An Intra-class Constraint
This work addresses visual classification by improving discriminative representation learning, but it is incremental as it builds on existing deep dictionary learning methods.
The authors tackled the problem of deep dictionary learning lacking category information by introducing an intra-class constraint to make representations more discriminative, achieving superior performance over state-of-the-art methods on four image datasets.
In recent years, deep dictionary learning (DDL)has attracted a great amount of attention due to its effectiveness for representation learning and visual recognition.~However, most existing methods focus on unsupervised deep dictionary learning, failing to further explore the category information.~To make full use of the category information of different samples, we propose a novel deep dictionary learning model with an intra-class constraint (DDLIC) for visual classification. Specifically, we design the intra-class compactness constraint on the intermediate representation at different levels to encourage the intra-class representations to be closer to each other, and eventually the learned representation becomes more discriminative.~Unlike the traditional DDL methods, during the classification stage, our DDLIC performs a layer-wise greedy optimization in a similar way to the training stage. Experimental results on four image datasets show that our method is superior to the state-of-the-art methods.