Matches in SemOpenAlex for { <https://semopenalex.org/work/W3168688436> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3168688436 abstract "Few-shot learning aims to recognize the novel categories from a few examples. However, most of the existing approaches usually focus on general image classification and fail to handle subtle differences between images. To alleviate this issue, we propose a trilinear spatial-awareness network for few-shot-grained visual recognition, called S3Net, which is composed of a spatial selection module, structural pyramid descriptor, and subtle difference mining module. Specifically, we first build the global relation to strengthen the features by spatial selection module. The structural pyramid descriptor then constructs a multi-scale representation for enhancing the rich contextual information by exploiting different receptive fields in the same feature layer. Furthermore, a similarity loss based on local descriptors and a global classification loss is design to help the network learn discrimination capability by handling subtle differences in confused or near-duplicated samples. Extensive experiments on 4 few-shot fine-grained benchmarks demonstrate that our proposed approach is effective and outperforms state-of-the-art models by large margins." @default.
- W3168688436 created "2021-06-22" @default.
- W3168688436 creator A5012352452 @default.
- W3168688436 creator A5059344854 @default.
- W3168688436 creator A5063066022 @default.
- W3168688436 date "2021-07-05" @default.
- W3168688436 modified "2023-09-24" @default.
- W3168688436 title "Selective, Structural, Subtle: Trilinear Spatial-Awareness for Few-Shot Fine-Grained Visual Recognition" @default.
- W3168688436 cites W2109255472 @default.
- W3168688436 cites W2138011018 @default.
- W3168688436 cites W2295107390 @default.
- W3168688436 cites W2885052112 @default.
- W3168688436 cites W2904218366 @default.
- W3168688436 cites W2957105406 @default.
- W3168688436 cites W2963091558 @default.
- W3168688436 cites W2963680240 @default.
- W3168688436 cites W2964105864 @default.
- W3168688436 cites W2979689312 @default.
- W3168688436 cites W2982806777 @default.
- W3168688436 cites W2991559096 @default.
- W3168688436 doi "https://doi.org/10.1109/icme51207.2021.9428223" @default.
- W3168688436 hasPublicationYear "2021" @default.
- W3168688436 type Work @default.
- W3168688436 sameAs 3168688436 @default.
- W3168688436 citedByCount "0" @default.
- W3168688436 crossrefType "proceedings-article" @default.
- W3168688436 hasAuthorship W3168688436A5012352452 @default.
- W3168688436 hasAuthorship W3168688436A5059344854 @default.
- W3168688436 hasAuthorship W3168688436A5063066022 @default.
- W3168688436 hasConcept C103278499 @default.
- W3168688436 hasConcept C115961682 @default.
- W3168688436 hasConcept C120665830 @default.
- W3168688436 hasConcept C121332964 @default.
- W3168688436 hasConcept C138885662 @default.
- W3168688436 hasConcept C142575187 @default.
- W3168688436 hasConcept C148483581 @default.
- W3168688436 hasConcept C153180895 @default.
- W3168688436 hasConcept C154945302 @default.
- W3168688436 hasConcept C17744445 @default.
- W3168688436 hasConcept C192209626 @default.
- W3168688436 hasConcept C199539241 @default.
- W3168688436 hasConcept C2524010 @default.
- W3168688436 hasConcept C2776359362 @default.
- W3168688436 hasConcept C2776401178 @default.
- W3168688436 hasConcept C31972630 @default.
- W3168688436 hasConcept C33923547 @default.
- W3168688436 hasConcept C41008148 @default.
- W3168688436 hasConcept C41895202 @default.
- W3168688436 hasConcept C52622490 @default.
- W3168688436 hasConcept C81917197 @default.
- W3168688436 hasConcept C94625758 @default.
- W3168688436 hasConceptScore W3168688436C103278499 @default.
- W3168688436 hasConceptScore W3168688436C115961682 @default.
- W3168688436 hasConceptScore W3168688436C120665830 @default.
- W3168688436 hasConceptScore W3168688436C121332964 @default.
- W3168688436 hasConceptScore W3168688436C138885662 @default.
- W3168688436 hasConceptScore W3168688436C142575187 @default.
- W3168688436 hasConceptScore W3168688436C148483581 @default.
- W3168688436 hasConceptScore W3168688436C153180895 @default.
- W3168688436 hasConceptScore W3168688436C154945302 @default.
- W3168688436 hasConceptScore W3168688436C17744445 @default.
- W3168688436 hasConceptScore W3168688436C192209626 @default.
- W3168688436 hasConceptScore W3168688436C199539241 @default.
- W3168688436 hasConceptScore W3168688436C2524010 @default.
- W3168688436 hasConceptScore W3168688436C2776359362 @default.
- W3168688436 hasConceptScore W3168688436C2776401178 @default.
- W3168688436 hasConceptScore W3168688436C31972630 @default.
- W3168688436 hasConceptScore W3168688436C33923547 @default.
- W3168688436 hasConceptScore W3168688436C41008148 @default.
- W3168688436 hasConceptScore W3168688436C41895202 @default.
- W3168688436 hasConceptScore W3168688436C52622490 @default.
- W3168688436 hasConceptScore W3168688436C81917197 @default.
- W3168688436 hasConceptScore W3168688436C94625758 @default.
- W3168688436 hasFunder F4320321001 @default.
- W3168688436 hasLocation W31686884361 @default.
- W3168688436 hasOpenAccess W3168688436 @default.
- W3168688436 hasPrimaryLocation W31686884361 @default.
- W3168688436 hasRelatedWork W1497652558 @default.
- W3168688436 hasRelatedWork W2022684485 @default.
- W3168688436 hasRelatedWork W2314710578 @default.
- W3168688436 hasRelatedWork W2515280043 @default.
- W3168688436 hasRelatedWork W2534909612 @default.
- W3168688436 hasRelatedWork W2592385986 @default.
- W3168688436 hasRelatedWork W2962729745 @default.
- W3168688436 hasRelatedWork W3185455591 @default.
- W3168688436 hasRelatedWork W2345184372 @default.
- W3168688436 hasRelatedWork W3127217315 @default.
- W3168688436 isParatext "false" @default.
- W3168688436 isRetracted "false" @default.
- W3168688436 magId "3168688436" @default.
- W3168688436 workType "article" @default.