In contrast to existing adversarial training-based DA methods, our approach isolates feature learning and distribution alignment steps, and utilizes a primary-auxiliary optimization strategy to effectively balance the objectives of domain invariance and model fidelity.
In this paper, we focus on the challenging problem of multi-source zero-shot DG, where labeled training data from multiple source domains is available but with no access to data from the target domain.
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics.
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generalizable models, has led to crucial insights into network initialization and has enabled efficient inferencing.
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches.
This paper represents a hybrid approach, where we assume simplified data geometry in the form of subspaces, and consider alignment as an auxiliary task to the primary task of maximizing performance on the source.
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition.
However, persistence diagrams are multi-sets of points and hence it is not straightforward to fuse them with features used for contemporary machine learning tools like deep-nets.