Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953182626> ?p ?o ?g. }
- W2953182626 abstract "Recent studies show that deep neural networks are vulnerable to adversarial examples which can be generated via certain types of transformations. Being robust to a desired family of adversarial attacks is then equivalent to being invariant to a family of transformations. Learning invariant representations then naturally emerges as an important goal to achieve which we explore in this paper within specific application contexts. Specifically, we propose a cyclically-trained adversarial network to learn a mapping from image space to latent representation space and back such that the latent representation is invariant to a specified factor of variation (e.g., identity). The learned mapping assures that the synthesized image is not only realistic, but has the same values for unspecified factors (e.g., pose and illumination) as the original image and a desired value of the specified factor. Unlike disentangled representation learning, which requires two latent spaces, one for specified and another for unspecified factors, invariant representation learning needs only one such space. We encourage invariance to a specified factor by applying adversarial training using a variational autoencoder in the image space as opposed to the latent space. We strengthen this invariance by introducing a cyclic training process (forward and backward cycle). We also propose a new method to evaluate conditional generative networks. It compares how well different factors of variation can be predicted from the synthesized, as opposed to real, images. In quantitative terms, our approach attains state-of-the-art performance in experiments spanning three datasets with factors such as identity, pose, illumination or style. Our method produces sharp, high-quality synthetic images with little visible artefacts compared to previous approaches." @default.
- W2953182626 created "2019-06-27" @default.
- W2953182626 creator A5028225823 @default.
- W2953182626 creator A5036913803 @default.
- W2953182626 creator A5063199641 @default.
- W2953182626 date "2019-06-21" @default.
- W2953182626 modified "2023-10-16" @default.
- W2953182626 title "A Cyclically-Trained Adversarial Network for Invariant Representation Learning" @default.
- W2953182626 cites W1453222892 @default.
- W2953182626 cites W1731081199 @default.
- W2953182626 cites W1828453565 @default.
- W2953182626 cites W2010625607 @default.
- W2953182626 cites W2097246321 @default.
- W2953182626 cites W2099471712 @default.
- W2953182626 cites W2125874614 @default.
- W2953182626 cites W2161335636 @default.
- W2953182626 cites W2161969291 @default.
- W2953182626 cites W2163922914 @default.
- W2953182626 cites W2170653751 @default.
- W2953182626 cites W2202109488 @default.
- W2953182626 cites W2247194987 @default.
- W2953182626 cites W2279221249 @default.
- W2953182626 cites W2305495461 @default.
- W2953182626 cites W2326925005 @default.
- W2953182626 cites W2344839403 @default.
- W2953182626 cites W2399452755 @default.
- W2953182626 cites W2512351403 @default.
- W2953182626 cites W2537024514 @default.
- W2953182626 cites W2559823555 @default.
- W2953182626 cites W2736899637 @default.
- W2953182626 cites W2737047298 @default.
- W2953182626 cites W2747543643 @default.
- W2953182626 cites W2753738274 @default.
- W2953182626 cites W2768192412 @default.
- W2953182626 cites W2788106150 @default.
- W2953182626 cites W2799121188 @default.
- W2953182626 cites W2949280493 @default.
- W2953182626 cites W2950864148 @default.
- W2953182626 cites W2951004968 @default.
- W2953182626 cites W2952225049 @default.
- W2953182626 cites W2962752582 @default.
- W2953182626 cites W2963129901 @default.
- W2953182626 cites W2963207607 @default.
- W2953182626 cites W2963226019 @default.
- W2953182626 cites W2963278610 @default.
- W2953182626 cites W2963373786 @default.
- W2953182626 cites W2963426391 @default.
- W2953182626 cites W2963446520 @default.
- W2953182626 cites W2963767194 @default.
- W2953182626 cites W2963981733 @default.
- W2953182626 cites W2964124968 @default.
- W2953182626 cites W2971626200 @default.
- W2953182626 cites W3023309920 @default.
- W2953182626 doi "https://doi.org/10.48550/arxiv.1906.09313" @default.
- W2953182626 hasPublicationYear "2019" @default.
- W2953182626 type Work @default.
- W2953182626 sameAs 2953182626 @default.
- W2953182626 citedByCount "1" @default.
- W2953182626 countsByYear W29531826262019 @default.
- W2953182626 crossrefType "posted-content" @default.
- W2953182626 hasAuthorship W2953182626A5028225823 @default.
- W2953182626 hasAuthorship W2953182626A5036913803 @default.
- W2953182626 hasAuthorship W2953182626A5063199641 @default.
- W2953182626 hasBestOaLocation W29531826261 @default.
- W2953182626 hasConcept C101738243 @default.
- W2953182626 hasConcept C119857082 @default.
- W2953182626 hasConcept C121332964 @default.
- W2953182626 hasConcept C153180895 @default.
- W2953182626 hasConcept C154945302 @default.
- W2953182626 hasConcept C17744445 @default.
- W2953182626 hasConcept C190470478 @default.
- W2953182626 hasConcept C199539241 @default.
- W2953182626 hasConcept C24890656 @default.
- W2953182626 hasConcept C2776359362 @default.
- W2953182626 hasConcept C2778355321 @default.
- W2953182626 hasConcept C33923547 @default.
- W2953182626 hasConcept C37736160 @default.
- W2953182626 hasConcept C37914503 @default.
- W2953182626 hasConcept C39890363 @default.
- W2953182626 hasConcept C41008148 @default.
- W2953182626 hasConcept C50644808 @default.
- W2953182626 hasConcept C59404180 @default.
- W2953182626 hasConcept C80444323 @default.
- W2953182626 hasConcept C94625758 @default.
- W2953182626 hasConceptScore W2953182626C101738243 @default.
- W2953182626 hasConceptScore W2953182626C119857082 @default.
- W2953182626 hasConceptScore W2953182626C121332964 @default.
- W2953182626 hasConceptScore W2953182626C153180895 @default.
- W2953182626 hasConceptScore W2953182626C154945302 @default.
- W2953182626 hasConceptScore W2953182626C17744445 @default.
- W2953182626 hasConceptScore W2953182626C190470478 @default.
- W2953182626 hasConceptScore W2953182626C199539241 @default.
- W2953182626 hasConceptScore W2953182626C24890656 @default.
- W2953182626 hasConceptScore W2953182626C2776359362 @default.
- W2953182626 hasConceptScore W2953182626C2778355321 @default.
- W2953182626 hasConceptScore W2953182626C33923547 @default.
- W2953182626 hasConceptScore W2953182626C37736160 @default.
- W2953182626 hasConceptScore W2953182626C37914503 @default.
- W2953182626 hasConceptScore W2953182626C39890363 @default.
- W2953182626 hasConceptScore W2953182626C41008148 @default.