Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark.
Vitali PetsiukAlexander E. SiemennSaisamrit SurbeheraZad ChinKeith TyserGregory HunterArvind RaghavanYann HickeBryan A. PlummerOri KerretTonio BuonassisiKate SaenkoArmando Solar-LezamaIddo DroriPublished in: CoRR (2022)
Keyphrases
- multi task
- input image
- multi task learning
- learning tasks
- random fields
- multiscale
- probabilistic model
- image features
- image segmentation
- image classification
- image retrieval
- image representation
- bayesian framework
- text mining
- data sets
- multitask learning
- gaussian processes
- supervised learning
- active learning
- machine learning