Search Results for author:
Found 12 papers, 4 papers with code
Universal Metric Learning with Parameter-Efficient Transfer Learning
In this regard, we introduce a novel metric learning paradigm, called Universal Metric Learning (UML), which learns a unified distance metric capable of capturing relations across multiple data distributions.
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
In a joint vision-language space, a text feature (e. g., from "a photo of a dog") could effectively represent its relevant image features (e. g., from dog photos).
Ranked #1 on
Domain Generalization
on DomainNet
HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization
Supervision for metric learning has long been given in the form of equivalence between human-labeled classes.
Cross-Domain Ensemble Distillation for Domain Generalization
Domain generalization is the task of learning models that generalize to unseen target domains.
Ranked #31 on
Domain Generalization
on Office-Home
Combating Label Distribution Shift for Active Domain Adaptation
We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint.
Self-Taught Metric Learning without Labels
At the heart of our framework lies an algorithm that investigates contexts of data on the embedding space to predict their class-equivalence relations as pseudo labels.
Learning to Generate Novel Classes for Deep Metric Learning
Motivated by this, we introduce a new data augmentation approach that synthesizes novel classes and their embedding vectors.
Cross Domain Ensemble Distillation for Domain Generalization
For domain generalization, the task of learning a model that generalizes to unseen target domains utilizing multiple source domains, many approaches explicitly align the distribution of the domains.
Ranked #31 on
Domain Generalization
on Office-Home
Embedding Transfer with Label Relaxation for Improved Metric Learning
Our method exploits pairwise similarities between samples in the source embedding space as the knowledge, and transfers them through a loss used for learning target embedding models.
Embedding Transfer via Smooth Contrastive Loss
To this end, we design a new loss called smooth contrastive loss, which pulls together or pushes apart a pair of samples in a target embedding space with strength determined by their semantic similarity in the source embedding space; an analysis of the loss reveals that this property enables more important pairs to contribute more to learning the target embedding space.
Proxy Anchor Loss for Deep Metric Learning
The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity.
Ranked #10 on
Metric Learning
on CUB-200-2011
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Vehicle Classification
+1
Deep Metric Learning Beyond Binary Supervision
Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not.
