Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386938567> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4386938567 endingPage "532" @default.
- W4386938567 startingPage "520" @default.
- W4386938567 abstract "Abstract Neural fields are neural networks which map coordinates to a desired signal. When a neural field should jointly model multiple signals, and not memorize only one, it needs to be conditioned on a latent code which describes the signal at hand. Despite being an important aspect, there has been little research on conditioning strategies for neural fields. In this work, we explore the use of neural fields as decoders for 2D semantic segmentation. For this task, we compare three conditioning methods, simple concatenation of the latent code, Feature-wise Linear Modulation (FiLM), and Cross-Attention, in conjunction with latent codes which either describe the full image or only a local region of the image. Our results show a considerable difference in performance between the examined conditioning strategies. Furthermore, we show that conditioning via Cross-Attention achieves the best results and is competitive with a CNN-based decoder for semantic segmentation." @default.
- W4386938567 created "2023-09-22" @default.
- W4386938567 creator A5015567592 @default.
- W4386938567 creator A5033486668 @default.
- W4386938567 creator A5066789231 @default.
- W4386938567 date "2023-01-01" @default.
- W4386938567 modified "2023-09-28" @default.
- W4386938567 title "Neural Field Conditioning Strategies for 2D Semantic Segmentation" @default.
- W4386938567 cites W1901129140 @default.
- W4386938567 cites W1903029394 @default.
- W4386938567 cites W2102673432 @default.
- W4386938567 cites W2194775991 @default.
- W4386938567 cites W2535388113 @default.
- W4386938567 cites W2760103357 @default.
- W4386938567 cites W2955058313 @default.
- W4386938567 cites W2963627347 @default.
- W4386938567 cites W2963674086 @default.
- W4386938567 cites W2963926543 @default.
- W4386938567 cites W2964309882 @default.
- W4386938567 cites W3034864980 @default.
- W4386938567 cites W3109585842 @default.
- W4386938567 cites W3173531806 @default.
- W4386938567 cites W3174865552 @default.
- W4386938567 cites W3176368002 @default.
- W4386938567 cites W3203518786 @default.
- W4386938567 cites W3215926197 @default.
- W4386938567 cites W4214893857 @default.
- W4386938567 cites W4312907595 @default.
- W4386938567 doi "https://doi.org/10.1007/978-3-031-44210-0_42" @default.
- W4386938567 hasPublicationYear "2023" @default.
- W4386938567 type Work @default.
- W4386938567 citedByCount "0" @default.
- W4386938567 crossrefType "book-chapter" @default.
- W4386938567 hasAuthorship W4386938567A5015567592 @default.
- W4386938567 hasAuthorship W4386938567A5033486668 @default.
- W4386938567 hasAuthorship W4386938567A5066789231 @default.
- W4386938567 hasBestOaLocation W43869385671 @default.
- W4386938567 hasConcept C138885662 @default.
- W4386938567 hasConcept C153180895 @default.
- W4386938567 hasConcept C154945302 @default.
- W4386938567 hasConcept C177264268 @default.
- W4386938567 hasConcept C199360897 @default.
- W4386938567 hasConcept C2776401178 @default.
- W4386938567 hasConcept C2776760102 @default.
- W4386938567 hasConcept C28490314 @default.
- W4386938567 hasConcept C33923547 @default.
- W4386938567 hasConcept C41008148 @default.
- W4386938567 hasConcept C41895202 @default.
- W4386938567 hasConcept C50644808 @default.
- W4386938567 hasConcept C87619178 @default.
- W4386938567 hasConcept C89600930 @default.
- W4386938567 hasConcept C94375191 @default.
- W4386938567 hasConceptScore W4386938567C138885662 @default.
- W4386938567 hasConceptScore W4386938567C153180895 @default.
- W4386938567 hasConceptScore W4386938567C154945302 @default.
- W4386938567 hasConceptScore W4386938567C177264268 @default.
- W4386938567 hasConceptScore W4386938567C199360897 @default.
- W4386938567 hasConceptScore W4386938567C2776401178 @default.
- W4386938567 hasConceptScore W4386938567C2776760102 @default.
- W4386938567 hasConceptScore W4386938567C28490314 @default.
- W4386938567 hasConceptScore W4386938567C33923547 @default.
- W4386938567 hasConceptScore W4386938567C41008148 @default.
- W4386938567 hasConceptScore W4386938567C41895202 @default.
- W4386938567 hasConceptScore W4386938567C50644808 @default.
- W4386938567 hasConceptScore W4386938567C87619178 @default.
- W4386938567 hasConceptScore W4386938567C89600930 @default.
- W4386938567 hasConceptScore W4386938567C94375191 @default.
- W4386938567 hasLocation W43869385671 @default.
- W4386938567 hasOpenAccess W4386938567 @default.
- W4386938567 hasPrimaryLocation W43869385671 @default.
- W4386938567 hasRelatedWork W1966366482 @default.
- W4386938567 hasRelatedWork W2382607599 @default.
- W4386938567 hasRelatedWork W2532775738 @default.
- W4386938567 hasRelatedWork W2546942002 @default.
- W4386938567 hasRelatedWork W2789928768 @default.
- W4386938567 hasRelatedWork W2938286185 @default.
- W4386938567 hasRelatedWork W2951125461 @default.
- W4386938567 hasRelatedWork W2970216048 @default.
- W4386938567 hasRelatedWork W3183617448 @default.
- W4386938567 hasRelatedWork W3208028783 @default.
- W4386938567 isParatext "false" @default.
- W4386938567 isRetracted "false" @default.
- W4386938567 workType "book-chapter" @default.