A Dictionary Approach to Domain-Invariant Learning in Deep Networks
arXiv:1909.11285
Abstract
In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN). By exploiting the observation that a convolutional filter can be well approximated as a linear combination of a small set of dictionary atoms, we show for the first time, both empirically and theoretically, that domain shifts can be effectively handled by decomposing a convolutional layer into a domain-specific atom layer and a domain-shared coefficient layer, while both remain convolutional. An input channel will now first convolve spatially only with each respective domain-specific dictionary atom to "absorb" domain variations, and then output channels are linearly combined using common decomposition coefficients trained to promote shared semantics across domains. We use toy examples, rigorous analysis, and real-world examples with diverse datasets and architectures, to show the proposed plug-in framework's effectiveness in cross and joint domain performance and domain adaptation. With the proposed architecture, we need only a small set of dictionary atoms to model each additional domain, which brings a negligible amount of additional parameters, typically a few hundred.
References in corpus (12)
- Deep Domain Confusion: Maximizing for Domain Invariance
- Conditional Adversarial Domain Adaptation
- Unsupervised Domain Adaptation with Residual Transfer Networks
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- Domain Separation Networks
- Beyond Sharing Weights for Deep Domain Adaptation
- Asymmetric Tri-training for Unsupervised Domain Adaptation
- LSDA: Large Scale Detection Through Adaptation
- Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
- Co-regularized Alignment for Unsupervised Domain Adaptation
- Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
- DCFNet: Deep Neural Network with Decomposed Convolutional Filters