SOTAVerified

Photo to Rest Generalization

It is the practical scenario of training on set of easy-to-collect real photographs and evaluate on the rest of diverse-styled domains (art, cartoon, sketch). Photo-to-rest generalization is a special case of the single-source domain generalization (SSDG) task.

Using only real photographs for training is the only way for SSDG to be compatible with ImageNet pre-trained networks. For any other domain as source, access to the photo domain through ImageNet pre-training violates the hypothesis of the task of a single domain seen during training, taking the task closer to the multy-source domain generalization (MSDG). Finaly pre-training on imagenet, training on a non real photograph domain and testing on real photographs violates the SSDG hypothesis that the target domain should not be used during training.

A large part of the generalization community chooses only this task over SSDG for pre-trained networks and for datasets that contain the photo domain.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–7 of 7 papers

TitleStatusHype
Crafting Distribution Shifts for Validation and Training in Single Source Domain GeneralizationCode1
Adversarial Bayesian Augmentation for Single-Source Domain GeneralizationCode0
Meta-causal Learning for Single Domain Generalization—0
Progressive Random Convolutions for Single Domain Generalization—0
Center-aware Adversarial Augmentation for Single Domain Generalization—0
Meta Convolutional Neural Networks for Single Domain Generalization—0
Learning to Diversify for Single Domain GeneralizationCode1
Show:102550

No leaderboard results yet.