The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We consider the structured data record input as a set of RDF entity-relation triples, a format widely used for knowledge representation and semantics description.
We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data.
We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation.
We introduce three new robustness benchmarks consisting of naturally occurring distribution changes in image style, geographic location, camera operation, and more.
Ranked #1 on Domain Generalization on ImageNet-R
To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model.
To solve this problem, we introduce a Gaussian-guided latent alignment approach to align the latent feature distributions of the two domains under the guidance of the prior distribution.
Ranked #1 on Domain Adaptation on MNIST-to-USPS
We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data sources.
Convolutional Neural Networks (CNNs) show impressive performance in the standard classification setting where training and testing data are drawn i. i. d.