Search Results for author:
Found 11 papers, 5 papers with code
Perturbation Robust Representations of Topological Persistence Diagrams
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.
Multiple Subspace Alignment Improves Domain Adaptation
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition.
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
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.
Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches.
Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
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.
MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics.
Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization
In this paper, we focus on the challenging problem of multi-source zero shot DG (MDG), where labeled training data from multiple source domains is available but with no access to data from the target domain.
Ranked #19 on
Domain Generalization
on TerraIncognita
Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation
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.
Domain Alignment Meets Fully Test-Time Adaptation
With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation.
Single-Shot Domain Adaptation via Target-Aware Generative Augmentation
The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks.
Target-Aware Generative Augmentations for Single-Shot Adaptation
We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA, which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data.
