Matches in SemOpenAlex for { <https://semopenalex.org/work/W2743102907> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2743102907 abstract "We present a new learning-to-learn-type approach that enables rapid learning of concepts from small-to-medium sized training sets and is primarily designed for web-initialized image retrieval. At the core of our approach is a deep architecture (a Set2Model network) that maps sets of examples to simple generative probabilistic models such as Gaussians or mixtures of Gaussians in the space of high-dimensional descriptors. The parameters of the embedding into the descriptor space are trained in the end-to-end fashion in the meta-learning stage using a set of training learning problems. The main technical novelty of our approach is the derivation of the backprop process through the mixture model fitting, which makes the likelihood of the resulting models differentiable with respect to the positions of the input descriptors. While the meta-learning process for a Set2Model network is discriminative, a trained Set2Model network performs generative learning of generative models in the descriptor space, which facilitates learning in the cases when no negative examples are available, and whenever the concept being learned is polysemous or represented by noisy training sets. Among other experiments, we demonstrate that these properties allow Set2Model networks to pick visual concepts from the raw outputs of Internet image search engines better than a set of strong baselines." @default.
- W2743102907 created "2017-08-17" @default.
- W2743102907 creator A5021283420 @default.
- W2743102907 creator A5082487287 @default.
- W2743102907 creator A5083458209 @default.
- W2743102907 date "2016-12-22" @default.
- W2743102907 modified "2023-10-08" @default.
- W2743102907 title "Set2Model Networks: Learning Discriminatively To Learn Generative Models" @default.
- W2743102907 cites W1522301498 @default.
- W2743102907 cites W1536943637 @default.
- W2743102907 cites W173906397 @default.
- W2743102907 cites W1825604117 @default.
- W2743102907 cites W1833123814 @default.
- W2743102907 cites W1966418221 @default.
- W2743102907 cites W1969198793 @default.
- W2743102907 cites W2035239430 @default.
- W2743102907 cites W204268067 @default.
- W2743102907 cites W2048318462 @default.
- W2743102907 cites W2073700113 @default.
- W2743102907 cites W2105231718 @default.
- W2743102907 cites W2108598243 @default.
- W2743102907 cites W2112796928 @default.
- W2743102907 cites W2117539524 @default.
- W2743102907 cites W2123713131 @default.
- W2743102907 cites W2129091674 @default.
- W2743102907 cites W2137675680 @default.
- W2743102907 cites W2141362318 @default.
- W2743102907 cites W2147483361 @default.
- W2743102907 cites W2151710526 @default.
- W2743102907 cites W2152175008 @default.
- W2743102907 cites W2153939756 @default.
- W2743102907 cites W2156222070 @default.
- W2743102907 cites W2159805834 @default.
- W2743102907 cites W2172191903 @default.
- W2743102907 cites W2401823607 @default.
- W2743102907 cites W2432717477 @default.
- W2743102907 cites W2472819217 @default.
- W2743102907 cites W2519882289 @default.
- W2743102907 cites W2547446130 @default.
- W2743102907 cites W2950094539 @default.
- W2743102907 cites W2963129433 @default.
- W2743102907 cites W3091905774 @default.
- W2743102907 doi "https://doi.org/10.48550/arxiv.1612.07697" @default.
- W2743102907 hasPublicationYear "2016" @default.
- W2743102907 type Work @default.
- W2743102907 sameAs 2743102907 @default.
- W2743102907 citedByCount "0" @default.
- W2743102907 crossrefType "posted-content" @default.
- W2743102907 hasAuthorship W2743102907A5021283420 @default.
- W2743102907 hasAuthorship W2743102907A5082487287 @default.
- W2743102907 hasAuthorship W2743102907A5083458209 @default.
- W2743102907 hasBestOaLocation W27431029071 @default.
- W2743102907 hasConcept C111919701 @default.
- W2743102907 hasConcept C119857082 @default.
- W2743102907 hasConcept C153180895 @default.
- W2743102907 hasConcept C154945302 @default.
- W2743102907 hasConcept C167966045 @default.
- W2743102907 hasConcept C177264268 @default.
- W2743102907 hasConcept C199360897 @default.
- W2743102907 hasConcept C39890363 @default.
- W2743102907 hasConcept C41008148 @default.
- W2743102907 hasConcept C41608201 @default.
- W2743102907 hasConcept C97931131 @default.
- W2743102907 hasConcept C98045186 @default.
- W2743102907 hasConceptScore W2743102907C111919701 @default.
- W2743102907 hasConceptScore W2743102907C119857082 @default.
- W2743102907 hasConceptScore W2743102907C153180895 @default.
- W2743102907 hasConceptScore W2743102907C154945302 @default.
- W2743102907 hasConceptScore W2743102907C167966045 @default.
- W2743102907 hasConceptScore W2743102907C177264268 @default.
- W2743102907 hasConceptScore W2743102907C199360897 @default.
- W2743102907 hasConceptScore W2743102907C39890363 @default.
- W2743102907 hasConceptScore W2743102907C41008148 @default.
- W2743102907 hasConceptScore W2743102907C41608201 @default.
- W2743102907 hasConceptScore W2743102907C97931131 @default.
- W2743102907 hasConceptScore W2743102907C98045186 @default.
- W2743102907 hasLocation W27431029071 @default.
- W2743102907 hasLocation W27431029072 @default.
- W2743102907 hasOpenAccess W2743102907 @default.
- W2743102907 hasPrimaryLocation W27431029071 @default.
- W2743102907 hasRelatedWork W1576360539 @default.
- W2743102907 hasRelatedWork W2024160000 @default.
- W2743102907 hasRelatedWork W2061273563 @default.
- W2743102907 hasRelatedWork W2093104230 @default.
- W2743102907 hasRelatedWork W2285052147 @default.
- W2743102907 hasRelatedWork W2729514902 @default.
- W2743102907 hasRelatedWork W2770426046 @default.
- W2743102907 hasRelatedWork W2773500201 @default.
- W2743102907 hasRelatedWork W3014948380 @default.
- W2743102907 hasRelatedWork W4287995534 @default.
- W2743102907 isParatext "false" @default.
- W2743102907 isRetracted "false" @default.
- W2743102907 magId "2743102907" @default.
- W2743102907 workType "article" @default.