Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367000286> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4367000286 abstract "Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains. While UDA methods have access to unlabeled target images, domain generalization does not involve any target data and only learns generalized features from a source domain. Image-style randomization or augmentation is a popular approach to improve network generalization without access to the target domain. Complex methods are often proposed that disregard the potential of simple image augmentations for out-of-domain generalization. For this reason, we systematically study the in- and out-of-domain generalization capabilities of simple, rule-based image augmentations like blur, noise, color jitter and many more. Based on a full factorial design of experiment design we provide a systematic statistical evaluation of augmentations and their interactions. Our analysis provides both, expected and unexpected, outcomes. Expected, because our experiments confirm the common scientific standard that combination of multiple different augmentations out-performs single augmentations. Unexpected, because combined augmentations perform competitive to state-of-the-art domain generalization approaches, while being significantly simpler and without training overhead. On the challenging synthetic-to-real domain shift between Synthia and Cityscapes we reach 39.5% mIoU compared to 40.9% mIoU of the best previous work. When additionally employing the recent vision transformer architecture DAFormer we outperform these benchmarks with a performance of 44.2% mIoU" @default.
- W4367000286 created "2023-04-27" @default.
- W4367000286 creator A5001821249 @default.
- W4367000286 creator A5029365974 @default.
- W4367000286 creator A5032998512 @default.
- W4367000286 creator A5062449429 @default.
- W4367000286 date "2023-04-24" @default.
- W4367000286 modified "2023-09-27" @default.
- W4367000286 title "Augmentation-based Domain Generalization for Semantic Segmentation" @default.
- W4367000286 doi "https://doi.org/10.48550/arxiv.2304.12122" @default.
- W4367000286 hasPublicationYear "2023" @default.
- W4367000286 type Work @default.
- W4367000286 citedByCount "0" @default.
- W4367000286 crossrefType "posted-content" @default.
- W4367000286 hasAuthorship W4367000286A5001821249 @default.
- W4367000286 hasAuthorship W4367000286A5029365974 @default.
- W4367000286 hasAuthorship W4367000286A5032998512 @default.
- W4367000286 hasAuthorship W4367000286A5062449429 @default.
- W4367000286 hasBestOaLocation W43670002861 @default.
- W4367000286 hasConcept C115961682 @default.
- W4367000286 hasConcept C119857082 @default.
- W4367000286 hasConcept C134306372 @default.
- W4367000286 hasConcept C153180895 @default.
- W4367000286 hasConcept C154945302 @default.
- W4367000286 hasConcept C177148314 @default.
- W4367000286 hasConcept C33923547 @default.
- W4367000286 hasConcept C36503486 @default.
- W4367000286 hasConcept C41008148 @default.
- W4367000286 hasConcept C89600930 @default.
- W4367000286 hasConceptScore W4367000286C115961682 @default.
- W4367000286 hasConceptScore W4367000286C119857082 @default.
- W4367000286 hasConceptScore W4367000286C134306372 @default.
- W4367000286 hasConceptScore W4367000286C153180895 @default.
- W4367000286 hasConceptScore W4367000286C154945302 @default.
- W4367000286 hasConceptScore W4367000286C177148314 @default.
- W4367000286 hasConceptScore W4367000286C33923547 @default.
- W4367000286 hasConceptScore W4367000286C36503486 @default.
- W4367000286 hasConceptScore W4367000286C41008148 @default.
- W4367000286 hasConceptScore W4367000286C89600930 @default.
- W4367000286 hasLocation W43670002861 @default.
- W4367000286 hasOpenAccess W4367000286 @default.
- W4367000286 hasPrimaryLocation W43670002861 @default.
- W4367000286 hasRelatedWork W1507687735 @default.
- W4367000286 hasRelatedWork W2005476934 @default.
- W4367000286 hasRelatedWork W2061502286 @default.
- W4367000286 hasRelatedWork W2510758617 @default.
- W4367000286 hasRelatedWork W2754350655 @default.
- W4367000286 hasRelatedWork W2897195263 @default.
- W4367000286 hasRelatedWork W2989932438 @default.
- W4367000286 hasRelatedWork W3095523211 @default.
- W4367000286 hasRelatedWork W4206076898 @default.
- W4367000286 hasRelatedWork W4226401448 @default.
- W4367000286 isParatext "false" @default.
- W4367000286 isRetracted "false" @default.
- W4367000286 workType "article" @default.