FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035200909> ?p ?o ?g. }

• W3035200909 abstract "The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications such as image translation, enhancement and editing. However, compared to the substantial efforts to compressing other deep models, the research on compressing GANs (usually the generators) remains at its infancy stage. Existing GAN compression algorithms are limited to handling specific GAN architectures and losses. Inspired by the recent success of AutoML in deep compression, we introduce AutoML to GAN compression and develop an AutoGAN-Distiller (AGD) framework. Starting with a specifically designed efficient search space, AGD performs an end-to-end discovery for new efficient generators, given the target computational resource constraints. The search is guided by the original GAN model via knowledge distillation, therefore fulfilling the compression. AGD is fully automatic, standalone (i.e., needing no trained discriminators), and generically applicable to various GAN models. We evaluate AGD in two representative GAN tasks: image translation and super resolution. Without bells and whistles, AGD yields remarkably lightweight yet more competitive compressed models, that largely outperform existing alternatives. Our codes and pretrained models are available at this https URL." @default.
• W3035200909 created "2020-06-19" @default.
• W3035200909 creator A5006794114 @default.
• W3035200909 creator A5013562664 @default.
• W3035200909 creator A5019582323 @default.
• W3035200909 creator A5048522863 @default.
• W3035200909 creator A5058253075 @default.
• W3035200909 creator A5061572132 @default.
• W3035200909 date "2020-06-15" @default.
• W3035200909 modified "2023-09-27" @default.
• W3035200909 title "AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks" @default.
• W3035200909 cites W1724438581 @default.
• W3035200909 cites W1791560514 @default.
• W3035200909 cites W1821462560 @default.
• W3035200909 cites W1902934009 @default.
• W3035200909 cites W1930824406 @default.
• W3035200909 cites W2047920195 @default.
• W3035200909 cites W2099471712 @default.
• W3035200909 cites W2121927366 @default.
• W3035200909 cites W2253986341 @default.
• W3035200909 cites W2331128040 @default.
• W3035200909 cites W2476548250 @default.
• W3035200909 cites W2502312327 @default.
• W3035200909 cites W2513419314 @default.
• W3035200909 cites W2515385951 @default.
• W3035200909 cites W2553303224 @default.
• W3035200909 cites W2605287558 @default.
• W3035200909 cites W2737121650 @default.
• W3035200909 cites W2739757502 @default.
• W3035200909 cites W2766527293 @default.
• W3035200909 cites W2785678896 @default.
• W3035200909 cites W2787752464 @default.
• W3035200909 cites W2788836009 @default.
• W3035200909 cites W2798729263 @default.
• W3035200909 cites W2804193803 @default.
• W3035200909 cites W2860338957 @default.
• W3035200909 cites W2885311373 @default.
• W3035200909 cites W2891778567 @default.
• W3035200909 cites W2893749619 @default.
• W3035200909 cites W2901660337 @default.
• W3035200909 cites W2910554758 @default.
• W3035200909 cites W2943305254 @default.
• W3035200909 cites W2944779197 @default.
• W3035200909 cites W2946948417 @default.
• W3035200909 cites W2949939647 @default.
• W3035200909 cites W2951104886 @default.
• W3035200909 cites W2952773607 @default.
• W3035200909 cites W2963067945 @default.
• W3035200909 cites W2963470893 @default.
• W3035200909 cites W2963709416 @default.
• W3035200909 cites W2963918968 @default.
• W3035200909 cites W2963981733 @default.
• W3035200909 cites W2964233199 @default.
• W3035200909 cites W2964259004 @default.
• W3035200909 cites W2964299589 @default.
• W3035200909 cites W2981698279 @default.
• W3035200909 cites W2982802130 @default.
• W3035200909 cites W2994671176 @default.
• W3035200909 cites W3002944878 @default.
• W3035200909 cites W3035204081 @default.
• W3035200909 cites W3035204914 @default.
• W3035200909 cites W3035414587 @default.
• W3035200909 hasPublicationYear "2020" @default.
• W3035200909 type Work @default.
• W3035200909 sameAs 3035200909 @default.
• W3035200909 citedByCount "21" @default.
• W3035200909 countsByYear W30352009092020 @default.
• W3035200909 countsByYear W30352009092021 @default.
• W3035200909 countsByYear W30352009092023 @default.
• W3035200909 crossrefType "posted-content" @default.
• W3035200909 hasAuthorship W3035200909A5006794114 @default.
• W3035200909 hasAuthorship W3035200909A5013562664 @default.
• W3035200909 hasAuthorship W3035200909A5019582323 @default.
• W3035200909 hasAuthorship W3035200909A5048522863 @default.
• W3035200909 hasAuthorship W3035200909A5058253075 @default.
• W3035200909 hasAuthorship W3035200909A5061572132 @default.
• W3035200909 hasConcept C104317684 @default.
• W3035200909 hasConcept C105580179 @default.
• W3035200909 hasConcept C113775141 @default.
• W3035200909 hasConcept C115961682 @default.
• W3035200909 hasConcept C119857082 @default.
• W3035200909 hasConcept C121332964 @default.
• W3035200909 hasConcept C149364088 @default.
• W3035200909 hasConcept C154945302 @default.
• W3035200909 hasConcept C159985019 @default.
• W3035200909 hasConcept C163258240 @default.
• W3035200909 hasConcept C180016635 @default.
• W3035200909 hasConcept C185592680 @default.
• W3035200909 hasConcept C192562407 @default.
• W3035200909 hasConcept C206345919 @default.
• W3035200909 hasConcept C2780992000 @default.
• W3035200909 hasConcept C2988773926 @default.
• W3035200909 hasConcept C31258907 @default.
• W3035200909 hasConcept C37736160 @default.
• W3035200909 hasConcept C39890363 @default.
• W3035200909 hasConcept C41008148 @default.
• W3035200909 hasConcept C55493867 @default.
• W3035200909 hasConcept C62520636 @default.
• W3035200909 hasConcept C80444323 @default.
• W3035200909 hasConceptScore W3035200909C104317684 @default.

• next