FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035580920> ?p ?o ?g. }

• W3035580920 abstract "Generative Adversarial Networks (GANs) are formulated as minimax game problems, whereby generators attempt to approach real data distributions by virtue of adversarial learning against discriminators. The intrinsic problem complexity poses the challenge to enhance the performance of generative networks. In this work, we aim to boost model learning from the perspective of network architectures, by incorporating recent progress on automated architecture search into GANs. To this end, we propose a fully differentiable search framework for generative adversarial networks, dubbed alphaGAN. The searching process is formalized as solving a bi-level minimax optimization problem, in which the outer-level objective aims for seeking a suitable network architecture towards pure Nash Equilibrium conditioned on the generator and the discriminator network parameters optimized with a traditional GAN loss in the inner level. The entire optimization performs a first-order method by alternately minimizing the two-level objective in a fully differentiable manner, enabling architecture search to be completed in an enormous search space. Extensive experiments on CIFAR-10 and STL-10 datasets show that our algorithm can obtain high-performing architectures only with 3-GPU hours on a single GPU in the search space comprised of approximate 2 ? 1011 possible configurations. We also provide a comprehensive analysis on the behavior of the searching process and the properties of searched architectures, which would benefit further research on architectures for generative models. Pretrained models and codes are available at https://github.com/yuesongtian/AlphaGAN." @default.
• W3035580920 created "2020-06-19" @default.
• W3035580920 creator A5014689002 @default.
• W3035580920 creator A5017215030 @default.
• W3035580920 creator A5057354933 @default.
• W3035580920 creator A5071037763 @default.
• W3035580920 creator A5073271972 @default.
• W3035580920 date "2020-06-16" @default.
• W3035580920 modified "2023-09-24" @default.
• W3035580920 title "AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks" @default.
• W3035580920 cites W1522301498 @default.
• W3035580920 cites W1834627138 @default.
• W3035580920 cites W2067050450 @default.
• W3035580920 cites W2099471712 @default.
• W3035580920 cites W2109100253 @default.
• W3035580920 cites W2118858186 @default.
• W3035580920 cites W2173520492 @default.
• W3035580920 cites W2194775991 @default.
• W3035580920 cites W2296701362 @default.
• W3035580920 cites W2553303224 @default.
• W3035580920 cites W2593414223 @default.
• W3035580920 cites W2602963933 @default.
• W3035580920 cites W2603777577 @default.
• W3035580920 cites W2748513770 @default.
• W3035580920 cites W2771120189 @default.
• W3035580920 cites W2775288145 @default.
• W3035580920 cites W2785678896 @default.
• W3035580920 cites W2893749619 @default.
• W3035580920 cites W2917028965 @default.
• W3035580920 cites W2925035065 @default.
• W3035580920 cites W2950274562 @default.
• W3035580920 cites W2950893734 @default.
• W3035580920 cites W2951104886 @default.
• W3035580920 cites W2951520714 @default.
• W3035580920 cites W2955096590 @default.
• W3035580920 cites W2962746461 @default.
• W3035580920 cites W2962760235 @default.
• W3035580920 cites W2962770929 @default.
• W3035580920 cites W2962793481 @default.
• W3035580920 cites W2962879692 @default.
• W3035580920 cites W2963073614 @default.
• W3035580920 cites W2963277051 @default.
• W3035580920 cites W2963373786 @default.
• W3035580920 cites W2963778169 @default.
• W3035580920 cites W2963800363 @default.
• W3035580920 cites W2963821229 @default.
• W3035580920 cites W2963981733 @default.
• W3035580920 cites W2964081807 @default.
• W3035580920 cites W2964444661 @default.
• W3035580920 cites W2965658867 @default.
• W3035580920 cites W2970241862 @default.
• W3035580920 cites W2970258466 @default.
• W3035580920 cites W2970867386 @default.
• W3035580920 cites W2971324138 @default.
• W3035580920 cites W2973943791 @default.
• W3035580920 cites W2981721547 @default.
• W3035580920 cites W2982511758 @default.
• W3035580920 cites W2989221291 @default.
• W3035580920 cites W2996690341 @default.
• W3035580920 cites W3005685053 @default.
• W3035580920 cites W3034600949 @default.
• W3035580920 cites W3034862928 @default.
• W3035580920 cites W3035170495 @default.
• W3035580920 cites W3035231706 @default.
• W3035580920 cites W3035574324 @default.
• W3035580920 cites W3035665052 @default.
• W3035580920 cites W3043547428 @default.
• W3035580920 cites W3099088591 @default.
• W3035580920 cites W3104876213 @default.
• W3035580920 cites W3107781032 @default.
• W3035580920 cites W3108316907 @default.
• W3035580920 cites W3108420015 @default.
• W3035580920 cites W3114187793 @default.
• W3035580920 cites W967544008 @default.
• W3035580920 doi "https://doi.org/10.48550/arxiv.2006.09134" @default.
• W3035580920 hasPublicationYear "2020" @default.
• W3035580920 type Work @default.
• W3035580920 sameAs 3035580920 @default.
• W3035580920 citedByCount "4" @default.
• W3035580920 countsByYear W30355809202020 @default.
• W3035580920 countsByYear W30355809202021 @default.
• W3035580920 countsByYear W30355809202023 @default.
• W3035580920 crossrefType "posted-content" @default.
• W3035580920 hasAuthorship W3035580920A5014689002 @default.
• W3035580920 hasAuthorship W3035580920A5017215030 @default.
• W3035580920 hasAuthorship W3035580920A5057354933 @default.
• W3035580920 hasAuthorship W3035580920A5071037763 @default.
• W3035580920 hasAuthorship W3035580920A5073271972 @default.
• W3035580920 hasBestOaLocation W30355809201 @default.
• W3035580920 hasConcept C119857082 @default.
• W3035580920 hasConcept C121332964 @default.
• W3035580920 hasConcept C123657996 @default.
• W3035580920 hasConcept C126255220 @default.
• W3035580920 hasConcept C134306372 @default.
• W3035580920 hasConcept C142362112 @default.
• W3035580920 hasConcept C149728462 @default.
• W3035580920 hasConcept C153349607 @default.
• W3035580920 hasConcept C154945302 @default.
• W3035580920 hasConcept C163258240 @default.
• W3035580920 hasConcept C165696696 @default.

• next