FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025346498> ?p ?o ?g. }

• W3025346498 endingPage "8918" @default.
• W3025346498 startingPage "8905" @default.
• W3025346498 abstract "With the development of convolutional neural networks (CNNs), the semantic understanding of remote sensing (RS) scenes has been significantly improved based on their prominent feature encoding capabilities. While many existing deep-learning models focus on designing different architectures, only a few works in the RS field have focused on investigating the performance of the learned feature embeddings and the associated metric space. In particular, two main loss functions have been exploited: the contrastive and the triplet loss. However, the straightforward application of these techniques to RS images may not be optimal in order to capture their neighborhood structures in the metric space due to the insufficient sampling of image pairs or triplets during the training stage and to the inherent semantic complexity of remotely sensed data. To solve these problems, we propose a new deep metric learning approach, which overcomes the limitation on the class discrimination by means of two different components: 1) scalable neighborhood component analysis (SNCA) that aims at discovering the neighborhood structure in the metric space and 2) the cross-entropy loss that aims at preserving the class discrimination capability based on the learned class prototypes. Moreover, in order to preserve feature consistency among all the minibatches during training, a novel optimization mechanism based on momentum update is introduced for minimizing the proposed loss. An extensive experimental comparison (using several state-of-the-art models and two different benchmark data sets) has been conducted to validate the effectiveness of the proposed method from different perspectives, including: 1) classification; 2) clustering; and 3) image retrieval. The related codes of this article will be made publicly available for reproducible research by the community." @default.
• W3025346498 created "2020-05-21" @default.
• W3025346498 creator A5039348214 @default.
• W3025346498 creator A5049420721 @default.
• W3025346498 creator A5054292278 @default.
• W3025346498 creator A5073808631 @default.
• W3025346498 creator A5074919292 @default.
• W3025346498 creator A5086443350 @default.
• W3025346498 date "2020-12-01" @default.
• W3025346498 modified "2023-10-18" @default.
• W3025346498 title "Deep Metric Learning Based on Scalable Neighborhood Components for Remote Sensing Scene Characterization" @default.
• W3025346498 cites W1576332977 @default.
• W3025346498 cites W1912954554 @default.
• W3025346498 cites W1916279783 @default.
• W3025346498 cites W2002576912 @default.
• W3025346498 cites W2006603039 @default.
• W3025346498 cites W2013081398 @default.
• W3025346498 cites W2077689834 @default.
• W3025346498 cites W2091280333 @default.
• W3025346498 cites W2093679105 @default.
• W3025346498 cites W2095483845 @default.
• W3025346498 cites W2097117768 @default.
• W3025346498 cites W2098676252 @default.
• W3025346498 cites W2115799903 @default.
• W3025346498 cites W2122524329 @default.
• W3025346498 cites W2127597507 @default.
• W3025346498 cites W2138621090 @default.
• W3025346498 cites W2194775991 @default.
• W3025346498 cites W2247062920 @default.
• W3025346498 cites W2253590344 @default.
• W3025346498 cites W2291068538 @default.
• W3025346498 cites W2307094448 @default.
• W3025346498 cites W2342880667 @default.
• W3025346498 cites W2412588858 @default.
• W3025346498 cites W2518815253 @default.
• W3025346498 cites W2549293537 @default.
• W3025346498 cites W2560755969 @default.
• W3025346498 cites W2598199894 @default.
• W3025346498 cites W2605102252 @default.
• W3025346498 cites W2605388673 @default.
• W3025346498 cites W2607508964 @default.
• W3025346498 cites W2615981376 @default.
• W3025346498 cites W2617818785 @default.
• W3025346498 cites W2620429297 @default.
• W3025346498 cites W2620858446 @default.
• W3025346498 cites W2727875856 @default.
• W3025346498 cites W2744582969 @default.
• W3025346498 cites W2762186317 @default.
• W3025346498 cites W2762381996 @default.
• W3025346498 cites W2767581044 @default.
• W3025346498 cites W2783165089 @default.
• W3025346498 cites W2806966882 @default.
• W3025346498 cites W2808773462 @default.
• W3025346498 cites W2809635958 @default.
• W3025346498 cites W2885201931 @default.
• W3025346498 cites W2902163209 @default.
• W3025346498 cites W2909431441 @default.
• W3025346498 cites W2914429466 @default.
• W3025346498 cites W2917187459 @default.
• W3025346498 cites W2963026686 @default.
• W3025346498 cites W3099206234 @default.
• W3025346498 cites W3103856189 @default.
• W3025346498 cites W3105577662 @default.
• W3025346498 cites W3122774149 @default.
• W3025346498 cites W4248614128 @default.
• W3025346498 doi "https://doi.org/10.1109/tgrs.2020.2991657" @default.
• W3025346498 hasPublicationYear "2020" @default.
• W3025346498 type Work @default.
• W3025346498 sameAs 3025346498 @default.
• W3025346498 citedByCount "57" @default.
• W3025346498 countsByYear W30253464982020 @default.
• W3025346498 countsByYear W30253464982021 @default.
• W3025346498 countsByYear W30253464982022 @default.
• W3025346498 countsByYear W30253464982023 @default.
• W3025346498 crossrefType "journal-article" @default.
• W3025346498 hasAuthorship W3025346498A5039348214 @default.
• W3025346498 hasAuthorship W3025346498A5049420721 @default.
• W3025346498 hasAuthorship W3025346498A5054292278 @default.
• W3025346498 hasAuthorship W3025346498A5073808631 @default.
• W3025346498 hasAuthorship W3025346498A5074919292 @default.
• W3025346498 hasAuthorship W3025346498A5086443350 @default.
• W3025346498 hasBestOaLocation W30253464982 @default.
• W3025346498 hasConcept C108583219 @default.
• W3025346498 hasConcept C119857082 @default.
• W3025346498 hasConcept C13280743 @default.
• W3025346498 hasConcept C138885662 @default.
• W3025346498 hasConcept C153180895 @default.
• W3025346498 hasConcept C154945302 @default.
• W3025346498 hasConcept C162324750 @default.
• W3025346498 hasConcept C167981619 @default.
• W3025346498 hasConcept C176217482 @default.
• W3025346498 hasConcept C185798385 @default.
• W3025346498 hasConcept C205649164 @default.
• W3025346498 hasConcept C21547014 @default.
• W3025346498 hasConcept C2776401178 @default.
• W3025346498 hasConcept C41008148 @default.
• W3025346498 hasConcept C41895202 @default.
• W3025346498 hasConcept C48044578 @default.

• next