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|
Cross-prompt automated essay scoring (AES) requires the system to use non target-prompt essays to award scores to a target-prompt essay.
Features extracted from this source domain are learned using a generative model whose latent space is used as a sampler to retrieve the nearest neighbors for the target data points.
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without model updating.
While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust.
Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own.
The key idea of CuMix is to simulate the test-time domain and semantic shift using images and features from unseen domains and categories generated by mixing up the multiple source domains and categories available during training.
Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indistinguishable features with an ambiguous classification boundary.
To this end, we present a new domain generalization framework that learns how to generalize across domains simultaneously from extrinsic relationship supervision and intrinsic self-supervision for images from multi-source domains.
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift.