Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315777717> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4315777717 abstract "For the few-shot classification problem of low-resolution(LR) images, we propose a meta-learning method based on prototypical networks called LR-ProtoNet. The metric-based meta-learning algorithm mainly extracts the features of the support and query samples through the feature encoder and obtains the prediction categories from a metric module. Our core idea is to add feature-affine layers in the feature encoder to increase the feature distribution of LR images, and use Brownian Distance Covariance(BDC) in the metric module to capture the joint distribution and nonlinear relationship between different affine transformations. We down-sample standard few-shot image datasets to simulate LR images and conduct extensive ablation experiments and comparative studies of other meta methods in general image recognition and fine-grained classification. Experimental results demonstrate that our proposed model can effectively utilize low-resolution image information, achieving state-of-the-art performance compared to baseline works." @default.
- W4315777717 created "2023-01-13" @default.
- W4315777717 creator A5013688291 @default.
- W4315777717 creator A5024899663 @default.
- W4315777717 creator A5084134658 @default.
- W4315777717 creator A5086529957 @default.
- W4315777717 date "2022-12-15" @default.
- W4315777717 modified "2023-10-17" @default.
- W4315777717 title "LR-ProtoNet: Meta-Learning for Low-Resolution Few-Shot Recognition and Classification" @default.
- W4315777717 cites W1885185971 @default.
- W4315777717 cites W2023205960 @default.
- W4315777717 cites W2067042811 @default.
- W4315777717 cites W2194775991 @default.
- W4315777717 cites W2765811365 @default.
- W4315777717 cites W2887695188 @default.
- W4315777717 cites W2913318911 @default.
- W4315777717 cites W2962987395 @default.
- W4315777717 cites W2963101867 @default.
- W4315777717 cites W2963470893 @default.
- W4315777717 cites W2964105864 @default.
- W4315777717 cites W3012255272 @default.
- W4315777717 cites W3034187513 @default.
- W4315777717 cites W3094724482 @default.
- W4315777717 cites W3176341011 @default.
- W4315777717 cites W4312935555 @default.
- W4315777717 cites W7682646 @default.
- W4315777717 doi "https://doi.org/10.1109/icnsc55942.2022.10004182" @default.
- W4315777717 hasPublicationYear "2022" @default.
- W4315777717 type Work @default.
- W4315777717 citedByCount "0" @default.
- W4315777717 crossrefType "proceedings-article" @default.
- W4315777717 hasAuthorship W4315777717A5013688291 @default.
- W4315777717 hasAuthorship W4315777717A5024899663 @default.
- W4315777717 hasAuthorship W4315777717A5084134658 @default.
- W4315777717 hasAuthorship W4315777717A5086529957 @default.
- W4315777717 hasConcept C111919701 @default.
- W4315777717 hasConcept C115961682 @default.
- W4315777717 hasConcept C118505674 @default.
- W4315777717 hasConcept C138885662 @default.
- W4315777717 hasConcept C153180895 @default.
- W4315777717 hasConcept C154945302 @default.
- W4315777717 hasConcept C162324750 @default.
- W4315777717 hasConcept C176217482 @default.
- W4315777717 hasConcept C202444582 @default.
- W4315777717 hasConcept C21547014 @default.
- W4315777717 hasConcept C2776401178 @default.
- W4315777717 hasConcept C31972630 @default.
- W4315777717 hasConcept C33923547 @default.
- W4315777717 hasConcept C41008148 @default.
- W4315777717 hasConcept C41895202 @default.
- W4315777717 hasConcept C52622490 @default.
- W4315777717 hasConcept C75294576 @default.
- W4315777717 hasConcept C92757383 @default.
- W4315777717 hasConceptScore W4315777717C111919701 @default.
- W4315777717 hasConceptScore W4315777717C115961682 @default.
- W4315777717 hasConceptScore W4315777717C118505674 @default.
- W4315777717 hasConceptScore W4315777717C138885662 @default.
- W4315777717 hasConceptScore W4315777717C153180895 @default.
- W4315777717 hasConceptScore W4315777717C154945302 @default.
- W4315777717 hasConceptScore W4315777717C162324750 @default.
- W4315777717 hasConceptScore W4315777717C176217482 @default.
- W4315777717 hasConceptScore W4315777717C202444582 @default.
- W4315777717 hasConceptScore W4315777717C21547014 @default.
- W4315777717 hasConceptScore W4315777717C2776401178 @default.
- W4315777717 hasConceptScore W4315777717C31972630 @default.
- W4315777717 hasConceptScore W4315777717C33923547 @default.
- W4315777717 hasConceptScore W4315777717C41008148 @default.
- W4315777717 hasConceptScore W4315777717C41895202 @default.
- W4315777717 hasConceptScore W4315777717C52622490 @default.
- W4315777717 hasConceptScore W4315777717C75294576 @default.
- W4315777717 hasConceptScore W4315777717C92757383 @default.
- W4315777717 hasLocation W43157777171 @default.
- W4315777717 hasOpenAccess W4315777717 @default.
- W4315777717 hasPrimaryLocation W43157777171 @default.
- W4315777717 hasRelatedWork W2016461833 @default.
- W4315777717 hasRelatedWork W2041525275 @default.
- W4315777717 hasRelatedWork W2382607599 @default.
- W4315777717 hasRelatedWork W2534909612 @default.
- W4315777717 hasRelatedWork W2546942002 @default.
- W4315777717 hasRelatedWork W2781977330 @default.
- W4315777717 hasRelatedWork W2782906384 @default.
- W4315777717 hasRelatedWork W2940977206 @default.
- W4315777717 hasRelatedWork W2972973180 @default.
- W4315777717 hasRelatedWork W3197541072 @default.
- W4315777717 isParatext "false" @default.
- W4315777717 isRetracted "false" @default.
- W4315777717 workType "article" @default.