FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200237852> ?p ?o ?g. }

• W3200237852 abstract "Generative Adversarial Networks (GANs) can generate near photo realistic images in narrow domains such as human faces. Yet, modeling complex distributions of datasets such as ImageNet and COCO-Stuff remains challenging in unconditional settings. In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. We partition the data manifold into a mixture of overlapping neighborhoods described by a datapoint and its nearest neighbors, and introduce a model, called instance-conditioned GAN (IC-GAN), which learns the distribution around each datapoint. Experimental results on ImageNet and COCO-Stuff show that IC-GAN significantly improves over unconditional models and unsupervised data partitioning baselines. Moreover, we show that IC-GAN can effortlessly transfer to datasets not seen during training by simply changing the conditioning instances, and still generate realistic images. Finally, we extend IC-GAN to the class-conditional case and show semantically controllable generation and competitive quantitative results on ImageNet; while improving over BigGAN on ImageNet-LT. We will opensource our code and trained models to reproduce the reported results." @default.
• W3200237852 created "2021-09-27" @default.
• W3200237852 creator A5024536150 @default.
• W3200237852 creator A5027811140 @default.
• W3200237852 creator A5040312210 @default.
• W3200237852 creator A5045602407 @default.
• W3200237852 creator A5064868620 @default.
• W3200237852 date "2021-09-10" @default.
• W3200237852 modified "2023-09-27" @default.
• W3200237852 title "Instance-Conditioned GAN" @default.
• W3200237852 cites W1663973292 @default.
• W3200237852 cites W1972420097 @default.
• W3200237852 cites W2117539524 @default.
• W3200237852 cites W2125389028 @default.
• W3200237852 cites W2183341477 @default.
• W3200237852 cites W2194775991 @default.
• W3200237852 cites W2554314924 @default.
• W3200237852 cites W2561196672 @default.
• W3200237852 cites W2593864460 @default.
• W3200237852 cites W2758188475 @default.
• W3200237852 cites W2763549966 @default.
• W3200237852 cites W2783879794 @default.
• W3200237852 cites W2787223504 @default.
• W3200237852 cites W2800597160 @default.
• W3200237852 cites W2804078698 @default.
• W3200237852 cites W2920684403 @default.
• W3200237852 cites W2937274663 @default.
• W3200237852 cites W2939117106 @default.
• W3200237852 cites W2953139137 @default.
• W3200237852 cites W2953651675 @default.
• W3200237852 cites W2962770929 @default.
• W3200237852 cites W2962879692 @default.
• W3200237852 cites W2962928367 @default.
• W3200237852 cites W2963184176 @default.
• W3200237852 cites W2963341924 @default.
• W3200237852 cites W2963373786 @default.
• W3200237852 cites W2963522749 @default.
• W3200237852 cites W2963539305 @default.
• W3200237852 cites W2963800363 @default.
• W3200237852 cites W2963809789 @default.
• W3200237852 cites W2963836885 @default.
• W3200237852 cites W2963981733 @default.
• W3200237852 cites W2965833116 @default.
• W3200237852 cites W2965989168 @default.
• W3200237852 cites W2973045729 @default.
• W3200237852 cites W2980459401 @default.
• W3200237852 cites W2983248633 @default.
• W3200237852 cites W2995197345 @default.
• W3200237852 cites W3011483492 @default.
• W3200237852 cites W3034523045 @default.
• W3200237852 cites W3034723908 @default.
• W3200237852 cites W3034954643 @default.
• W3200237852 cites W3035124078 @default.
• W3200237852 cites W3035574324 @default.
• W3200237852 cites W3095121901 @default.
• W3200237852 cites W3102342597 @default.
• W3200237852 cites W3104876213 @default.
• W3200237852 cites W3106453331 @default.
• W3200237852 cites W3106875794 @default.
• W3200237852 cites W3109241881 @default.
• W3200237852 cites W3110991353 @default.
• W3200237852 cites W3148140980 @default.
• W3200237852 cites W3162926177 @default.
• W3200237852 cites W3163884521 @default.
• W3200237852 cites W3200090045 @default.
• W3200237852 hasPublicationYear "2021" @default.
• W3200237852 type Work @default.
• W3200237852 sameAs 3200237852 @default.
• W3200237852 citedByCount "0" @default.
• W3200237852 crossrefType "posted-content" @default.
• W3200237852 hasAuthorship W3200237852A5024536150 @default.
• W3200237852 hasAuthorship W3200237852A5027811140 @default.
• W3200237852 hasAuthorship W3200237852A5040312210 @default.
• W3200237852 hasAuthorship W3200237852A5045602407 @default.
• W3200237852 hasAuthorship W3200237852A5064868620 @default.
• W3200237852 hasConcept C105795698 @default.
• W3200237852 hasConcept C114614502 @default.
• W3200237852 hasConcept C117251300 @default.
• W3200237852 hasConcept C119857082 @default.
• W3200237852 hasConcept C153180895 @default.
• W3200237852 hasConcept C154945302 @default.
• W3200237852 hasConcept C167966045 @default.
• W3200237852 hasConcept C177264268 @default.
• W3200237852 hasConcept C185429906 @default.
• W3200237852 hasConcept C199360897 @default.
• W3200237852 hasConcept C2776760102 @default.
• W3200237852 hasConcept C2777212361 @default.
• W3200237852 hasConcept C33923547 @default.
• W3200237852 hasConcept C39890363 @default.
• W3200237852 hasConcept C41008148 @default.
• W3200237852 hasConcept C42812 @default.
• W3200237852 hasConcept C71134354 @default.
• W3200237852 hasConcept C74193536 @default.
• W3200237852 hasConcept C80444323 @default.
• W3200237852 hasConceptScore W3200237852C105795698 @default.
• W3200237852 hasConceptScore W3200237852C114614502 @default.
• W3200237852 hasConceptScore W3200237852C117251300 @default.
• W3200237852 hasConceptScore W3200237852C119857082 @default.
• W3200237852 hasConceptScore W3200237852C153180895 @default.
• W3200237852 hasConceptScore W3200237852C154945302 @default.

• next