DomainNet

Introduced by Peng et al. in Moment Matching for Multi-Source Domain Adaptation

DomainNet is a dataset of common objects in six different domain. All domains include 345 categories (classes) of objects such as Bracelet, plane, bird and cello. The domains include clipart: collection of clipart images; real: photos and real world images; sketch: sketches of specific objects; infograph: infographic images with specific object; painting artistic depictions of objects in the form of paintings and quickdraw: drawings of the worldwide players of game “Quick Draw!”.

Source: What is being transferred in transfer learning?

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Domain Generalization	DomainNet	PromptStyler
Universal Domain Adaptation	DomainNet	UniAM
Multi-target Domain Adaptation	DomainNet	MCDA
Unsupervised Domain Adaptation	DomainNet	SAMB
Zero-Shot Learning + Domain Generalization	DomainNet	Structured Latent Embed
Multi-Source Unsupervised Domain Adaptation	DomainNet	STEM
Partial Domain Adaptation	DomainNet	AR
Blended-target Domain Adaptation	DomainNet	MCDA
Domain Adaptation	DomainNet	MCDA
Unsupervised Continual Domain Shift Learning	DomainNet	CoDAG