FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385347164> ?p ?o ?g. }

• W4385347164 endingPage "3739" @default.
• W4385347164 startingPage "3739" @default.
• W4385347164 abstract "Hyperspectral images can assist change-detection methods in precisely identifying differences in land cover in the same region at different observation times. However, the difficulty of labeling hyperspectral images restricts the number of training samples for supervised change-detection methods, and there are also complex real influences on hyperspectral images, such as noise and observation directions. Furthermore, current deep-learning-based change-detection methods ignore the feature reusage from receptive fields with different scales and cannot effectively suppress unrelated spatial–spectral dependencies globally. To better handle these issues, a contrastive self-supervised two-domain residual attention network (TRAMNet) with a random augmentation pool is proposed for hyperspectral change detection. The contributions of this article are summarized as follows. (1) To improve the feature extraction from hyperspectral images with random Gaussian noise and directional information, a contrastive learning framework with a random data augmentation pool and a soft contrastive loss function (SCLF) is proposed. (2) The multi-scale feature fusion module (MFF) is provided to achieve feature reusage from different receptive fields. (3) A two-domain residual attention (TRA) block is designed to suppress irrelated change information and extract long-range dependencies from both spectral and spatial domains globally. Extensive experiments were carried out on three real datasets. The results show that the proposed TRAMNet can better initialize the model weights for hyperspectral change-detection task and effectively decrease the need for training samples. The proposed method outperforms most existing hyperspectral change-detection methods." @default.
• W4385347164 created "2023-07-29" @default.
• W4385347164 creator A5001246465 @default.
• W4385347164 creator A5003667621 @default.
• W4385347164 creator A5018037147 @default.
• W4385347164 creator A5029239459 @default.
• W4385347164 creator A5067540103 @default.
• W4385347164 date "2023-07-27" @default.
• W4385347164 modified "2023-10-14" @default.
• W4385347164 title "Contrastive Self-Supervised Two-Domain Residual Attention Network with Random Augmentation Pool for Hyperspectral Change Detection" @default.
• W4385347164 cites W1997413270 @default.
• W4385347164 cites W2008265903 @default.
• W4385347164 cites W2104374858 @default.
• W4385347164 cites W2109725152 @default.
• W4385347164 cites W2118116484 @default.
• W4385347164 cites W2127038040 @default.
• W4385347164 cites W2165350297 @default.
• W4385347164 cites W2752509951 @default.
• W4385347164 cites W2756481566 @default.
• W4385347164 cites W2782517596 @default.
• W4385347164 cites W2800240447 @default.
• W4385347164 cites W2811044316 @default.
• W4385347164 cites W2900587135 @default.
• W4385347164 cites W2953308875 @default.
• W4385347164 cites W3099102165 @default.
• W4385347164 cites W3099831940 @default.
• W4385347164 cites W3114632476 @default.
• W4385347164 cites W3176244435 @default.
• W4385347164 cites W3178914557 @default.
• W4385347164 cites W3181727745 @default.
• W4385347164 cites W3187493547 @default.
• W4385347164 cites W3197557720 @default.
• W4385347164 cites W3200020327 @default.
• W4385347164 cites W3205329422 @default.
• W4385347164 cites W4206307542 @default.
• W4385347164 cites W4206550078 @default.
• W4385347164 cites W4285107185 @default.
• W4385347164 cites W4293193074 @default.
• W4385347164 cites W4293370522 @default.
• W4385347164 cites W4294811351 @default.
• W4385347164 cites W4312549298 @default.
• W4385347164 cites W4313472379 @default.
• W4385347164 doi "https://doi.org/10.3390/rs15153739" @default.
• W4385347164 hasPublicationYear "2023" @default.
• W4385347164 type Work @default.
• W4385347164 citedByCount "0" @default.
• W4385347164 crossrefType "journal-article" @default.
• W4385347164 hasAuthorship W4385347164A5001246465 @default.
• W4385347164 hasAuthorship W4385347164A5003667621 @default.
• W4385347164 hasAuthorship W4385347164A5018037147 @default.
• W4385347164 hasAuthorship W4385347164A5029239459 @default.
• W4385347164 hasAuthorship W4385347164A5067540103 @default.
• W4385347164 hasBestOaLocation W43853471641 @default.
• W4385347164 hasConcept C11413529 @default.
• W4385347164 hasConcept C115961682 @default.
• W4385347164 hasConcept C121332964 @default.
• W4385347164 hasConcept C138885662 @default.
• W4385347164 hasConcept C153180895 @default.
• W4385347164 hasConcept C154945302 @default.
• W4385347164 hasConcept C155512373 @default.
• W4385347164 hasConcept C159078339 @default.
• W4385347164 hasConcept C163716315 @default.
• W4385347164 hasConcept C203595873 @default.
• W4385347164 hasConcept C2776401178 @default.
• W4385347164 hasConcept C41008148 @default.
• W4385347164 hasConcept C41895202 @default.
• W4385347164 hasConcept C52622490 @default.
• W4385347164 hasConcept C62520636 @default.
• W4385347164 hasConcept C99498987 @default.
• W4385347164 hasConceptScore W4385347164C11413529 @default.
• W4385347164 hasConceptScore W4385347164C115961682 @default.
• W4385347164 hasConceptScore W4385347164C121332964 @default.
• W4385347164 hasConceptScore W4385347164C138885662 @default.
• W4385347164 hasConceptScore W4385347164C153180895 @default.
• W4385347164 hasConceptScore W4385347164C154945302 @default.
• W4385347164 hasConceptScore W4385347164C155512373 @default.
• W4385347164 hasConceptScore W4385347164C159078339 @default.
• W4385347164 hasConceptScore W4385347164C163716315 @default.
• W4385347164 hasConceptScore W4385347164C203595873 @default.
• W4385347164 hasConceptScore W4385347164C2776401178 @default.
• W4385347164 hasConceptScore W4385347164C41008148 @default.
• W4385347164 hasConceptScore W4385347164C41895202 @default.
• W4385347164 hasConceptScore W4385347164C52622490 @default.
• W4385347164 hasConceptScore W4385347164C62520636 @default.
• W4385347164 hasConceptScore W4385347164C99498987 @default.
• W4385347164 hasFunder F4320321001 @default.
• W4385347164 hasFunder F4320321543 @default.
• W4385347164 hasIssue "15" @default.
• W4385347164 hasLocation W43853471641 @default.
• W4385347164 hasOpenAccess W4385347164 @default.
• W4385347164 hasPrimaryLocation W43853471641 @default.
• W4385347164 hasRelatedWork W1585144779 @default.
• W4385347164 hasRelatedWork W1993337810 @default.
• W4385347164 hasRelatedWork W2002064049 @default.
• W4385347164 hasRelatedWork W2028628118 @default.
• W4385347164 hasRelatedWork W2146076056 @default.
• W4385347164 hasRelatedWork W2546942002 @default.
• W4385347164 hasRelatedWork W2782869875 @default.

• next