FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323647500> ?p ?o ?g. }

• W4323647500 endingPage "405" @default.
• W4323647500 startingPage "387" @default.
• W4323647500 abstract "Many applications require robustness, or ideally invariance, of neural networks to certain transformations of input data. Most commonly, this requirement is addressed by training data augmentation, using adversarial training, or defining network architectures that include the desired invariance by design. In this work, we propose a method to make network architectures provably invariant with respect to group actions by choosing one element from a (possibly continuous) orbit based on a fixed criterion. In a nutshell, we intend to ’undo’ any possible transformation before feeding the data into the actual network. Further, we empirically analyze the properties of different approaches which incorporate invariance via training or architecture, and demonstrate the advantages of our method in terms of robustness and computational efficiency. In particular, we investigate the robustness with respect to rotations of images (which can hold up to discretization artifacts) as well as the provable orientation and scaling invariance of 3D point cloud classification." @default.
• W4323647500 created "2023-03-10" @default.
• W4323647500 creator A5048073110 @default.
• W4323647500 creator A5049400969 @default.
• W4323647500 creator A5055911824 @default.
• W4323647500 creator A5077620562 @default.
• W4323647500 creator A5028382876 @default.
• W4323647500 date "2023-01-01" @default.
• W4323647500 modified "2023-10-16" @default.
• W4323647500 title "A Simple Strategy to Provable Invariance via Orbit Mapping" @default.
• W4323647500 cites W1932922755 @default.
• W4323647500 cites W1973975575 @default.
• W4323647500 cites W1974956622 @default.
• W4323647500 cites W2047161559 @default.
• W4323647500 cites W2072072671 @default.
• W4323647500 cites W2108260857 @default.
• W4323647500 cites W2117539524 @default.
• W4323647500 cites W2126833203 @default.
• W4323647500 cites W2136343973 @default.
• W4323647500 cites W2143357187 @default.
• W4323647500 cites W2164278383 @default.
• W4323647500 cites W2167383966 @default.
• W4323647500 cites W2168501771 @default.
• W4323647500 cites W2169013230 @default.
• W4323647500 cites W2194775991 @default.
• W4323647500 cites W2321533354 @default.
• W4323647500 cites W2340427832 @default.
• W4323647500 cites W2558460151 @default.
• W4323647500 cites W2569680626 @default.
• W4323647500 cites W2576915720 @default.
• W4323647500 cites W2796422723 @default.
• W4323647500 cites W2806857275 @default.
• W4323647500 cites W2889300857 @default.
• W4323647500 cites W2890848214 @default.
• W4323647500 cites W2891396148 @default.
• W4323647500 cites W2900611587 @default.
• W4323647500 cites W2924551358 @default.
• W4323647500 cites W2948107928 @default.
• W4323647500 cites W2963242400 @default.
• W4323647500 cites W2963892972 @default.
• W4323647500 cites W2964228567 @default.
• W4323647500 cites W2982376094 @default.
• W4323647500 cites W3005221849 @default.
• W4323647500 cites W3009521361 @default.
• W4323647500 cites W3034707001 @default.
• W4323647500 cites W3035506734 @default.
• W4323647500 cites W3102779874 @default.
• W4323647500 cites W3102785203 @default.
• W4323647500 cites W3104141662 @default.
• W4323647500 cites W3107886455 @default.
• W4323647500 cites W3112541430 @default.
• W4323647500 cites W3126732353 @default.
• W4323647500 cites W3203310607 @default.
• W4323647500 cites W4226392282 @default.
• W4323647500 cites W4312251507 @default.
• W4323647500 cites W4312644556 @default.
• W4323647500 cites W937846259 @default.
• W4323647500 doi "https://doi.org/10.1007/978-3-031-26348-4_23" @default.
• W4323647500 hasPublicationYear "2023" @default.
• W4323647500 type Work @default.
• W4323647500 citedByCount "0" @default.
• W4323647500 crossrefType "book-chapter" @default.
• W4323647500 hasAuthorship W4323647500A5028382876 @default.
• W4323647500 hasAuthorship W4323647500A5048073110 @default.
• W4323647500 hasAuthorship W4323647500A5049400969 @default.
• W4323647500 hasAuthorship W4323647500A5055911824 @default.
• W4323647500 hasAuthorship W4323647500A5077620562 @default.
• W4323647500 hasBestOaLocation W43236475002 @default.
• W4323647500 hasConcept C104317684 @default.
• W4323647500 hasConcept C11413529 @default.
• W4323647500 hasConcept C131979681 @default.
• W4323647500 hasConcept C134306372 @default.
• W4323647500 hasConcept C154945302 @default.
• W4323647500 hasConcept C185592680 @default.
• W4323647500 hasConcept C190470478 @default.
• W4323647500 hasConcept C33923547 @default.
• W4323647500 hasConcept C37914503 @default.
• W4323647500 hasConcept C41008148 @default.
• W4323647500 hasConcept C50644808 @default.
• W4323647500 hasConcept C55493867 @default.
• W4323647500 hasConcept C61445026 @default.
• W4323647500 hasConcept C63479239 @default.
• W4323647500 hasConcept C73000952 @default.
• W4323647500 hasConcept C80444323 @default.
• W4323647500 hasConceptScore W4323647500C104317684 @default.
• W4323647500 hasConceptScore W4323647500C11413529 @default.
• W4323647500 hasConceptScore W4323647500C131979681 @default.
• W4323647500 hasConceptScore W4323647500C134306372 @default.
• W4323647500 hasConceptScore W4323647500C154945302 @default.
• W4323647500 hasConceptScore W4323647500C185592680 @default.
• W4323647500 hasConceptScore W4323647500C190470478 @default.
• W4323647500 hasConceptScore W4323647500C33923547 @default.
• W4323647500 hasConceptScore W4323647500C37914503 @default.
• W4323647500 hasConceptScore W4323647500C41008148 @default.
• W4323647500 hasConceptScore W4323647500C50644808 @default.
• W4323647500 hasConceptScore W4323647500C55493867 @default.
• W4323647500 hasConceptScore W4323647500C61445026 @default.
• W4323647500 hasConceptScore W4323647500C63479239 @default.

• next