Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367693208> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4367693208 abstract "Deep learning methods are state-of-the-art for spectral image (SI) computational tasks. However, these methods are constrained in their performance since available datasets are limited due to the highly expensive and long acquisition time. Usually, data augmentation techniques are employed to mitigate the lack of data. Surpassing classical augmentation methods, such as geometric transformations, GANs enable diverse augmentation by learning and sampling from the data distribution. Nevertheless, GAN-based SI generation is challenging since the high-dimensionality nature of this kind of data hinders the convergence of the GAN training yielding to suboptimal generation. To surmount this limitation, we propose low-dimensional GAN (LD-GAN), where we train the GAN employing a low-dimensional representation of the {dataset} with the latent space of a pretrained autoencoder network. Thus, we generate new low-dimensional samples which are then mapped to the SI dimension with the pretrained decoder network. Besides, we propose a statistical regularization to control the low-dimensional representation variance for the autoencoder training and to achieve high diversity of samples generated with the GAN. We validate our method LD-GAN as data augmentation strategy for compressive spectral imaging, SI super-resolution, and RBG to spectral tasks with improvements varying from 0.5 to 1 [dB] in each task respectively. We perform comparisons against the non-data augmentation training, traditional DA, and with the same GAN adjusted and trained to generate the full-sized SIs. The code of this paper can be found in https://github.com/romanjacome99/LD_GAN.git" @default.
- W4367693208 created "2023-05-03" @default.
- W4367693208 creator A5028765492 @default.
- W4367693208 creator A5033941982 @default.
- W4367693208 creator A5040298241 @default.
- W4367693208 creator A5081714132 @default.
- W4367693208 date "2023-04-28" @default.
- W4367693208 modified "2023-09-26" @default.
- W4367693208 title "LD-GAN: Low-Dimensional Generative Adversarial Network for Spectral Image Generation with Variance Regularization" @default.
- W4367693208 doi "https://doi.org/10.48550/arxiv.2305.00132" @default.
- W4367693208 hasPublicationYear "2023" @default.
- W4367693208 type Work @default.
- W4367693208 citedByCount "0" @default.
- W4367693208 crossrefType "posted-content" @default.
- W4367693208 hasAuthorship W4367693208A5028765492 @default.
- W4367693208 hasAuthorship W4367693208A5033941982 @default.
- W4367693208 hasAuthorship W4367693208A5040298241 @default.
- W4367693208 hasAuthorship W4367693208A5081714132 @default.
- W4367693208 hasBestOaLocation W43676932081 @default.
- W4367693208 hasConcept C101738243 @default.
- W4367693208 hasConcept C108583219 @default.
- W4367693208 hasConcept C111030470 @default.
- W4367693208 hasConcept C11413529 @default.
- W4367693208 hasConcept C119857082 @default.
- W4367693208 hasConcept C121955636 @default.
- W4367693208 hasConcept C144133560 @default.
- W4367693208 hasConcept C153180895 @default.
- W4367693208 hasConcept C154945302 @default.
- W4367693208 hasConcept C177264268 @default.
- W4367693208 hasConcept C196083921 @default.
- W4367693208 hasConcept C199360897 @default.
- W4367693208 hasConcept C2776135515 @default.
- W4367693208 hasConcept C2776760102 @default.
- W4367693208 hasConcept C41008148 @default.
- W4367693208 hasConcept C59404180 @default.
- W4367693208 hasConceptScore W4367693208C101738243 @default.
- W4367693208 hasConceptScore W4367693208C108583219 @default.
- W4367693208 hasConceptScore W4367693208C111030470 @default.
- W4367693208 hasConceptScore W4367693208C11413529 @default.
- W4367693208 hasConceptScore W4367693208C119857082 @default.
- W4367693208 hasConceptScore W4367693208C121955636 @default.
- W4367693208 hasConceptScore W4367693208C144133560 @default.
- W4367693208 hasConceptScore W4367693208C153180895 @default.
- W4367693208 hasConceptScore W4367693208C154945302 @default.
- W4367693208 hasConceptScore W4367693208C177264268 @default.
- W4367693208 hasConceptScore W4367693208C196083921 @default.
- W4367693208 hasConceptScore W4367693208C199360897 @default.
- W4367693208 hasConceptScore W4367693208C2776135515 @default.
- W4367693208 hasConceptScore W4367693208C2776760102 @default.
- W4367693208 hasConceptScore W4367693208C41008148 @default.
- W4367693208 hasConceptScore W4367693208C59404180 @default.
- W4367693208 hasLocation W43676932081 @default.
- W4367693208 hasOpenAccess W4367693208 @default.
- W4367693208 hasPrimaryLocation W43676932081 @default.
- W4367693208 hasRelatedWork W2538028360 @default.
- W4367693208 hasRelatedWork W2592385986 @default.
- W4367693208 hasRelatedWork W2922457425 @default.
- W4367693208 hasRelatedWork W2998168123 @default.
- W4367693208 hasRelatedWork W3044458868 @default.
- W4367693208 hasRelatedWork W3165463024 @default.
- W4367693208 hasRelatedWork W4213225422 @default.
- W4367693208 hasRelatedWork W4220775285 @default.
- W4367693208 hasRelatedWork W4250304930 @default.
- W4367693208 hasRelatedWork W4287995534 @default.
- W4367693208 isParatext "false" @default.
- W4367693208 isRetracted "false" @default.
- W4367693208 workType "article" @default.