SSDL: Self-Supervised Dictionary Learning
This work addresses a problem in machine learning for researchers and practitioners by enabling dictionary learning in label-scarce scenarios, though it appears incremental as it builds on existing label-embedded methods.
The paper tackles the limitation of label-embedded dictionary learning methods, which rely on labels and are ineffective in semi-supervised or unsupervised settings, by proposing a Self-Supervised Dictionary Learning (SSDL) framework that uses a pretext task to generate pseudo labels for dictionary training, achieving efficient results on human activity recognition datasets.
The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the label-embedded DL methods rely on the labels due that this way merely achieves ideal performances in supervised learning. While in semi-supervised and unsupervised learning, it is no longer sufficient to be effective. Inspired by the concept of self-supervised learning (e.g., setting the pretext task to generate a universal model for the downstream task), we propose a Self-Supervised Dictionary Learning (SSDL) framework to address this challenge. Specifically, we first design a $p$-Laplacian Attention Hypergraph Learning (pAHL) block as the pretext task to generate pseudo soft labels for DL. Then, we adopt the pseudo labels to train a dictionary from a primary label-embedded DL method. We evaluate our SSDL on two human activity recognition datasets. The comparison results with other state-of-the-art methods have demonstrated the efficiency of SSDL.