Matches in SemOpenAlex for { <https://semopenalex.org/work/W2983485270> ?p ?o ?g. }
- W2983485270 abstract "We present a label-based, semantic distance induced regularization learning method for Fine-grained image recognition (FGIR). In contrast to previous label-based methods that involve a nontrivial optimization in multi-task metric learning, our approach can be integrated into an end-to-end network without introducing any extra parameters, thus easy to be optimized. To this end, a category-level hierarchical distance matrix (HDM) that encodes semantic distance between subcategories through a tree-like label hierarchy is constructed. HDM is then incorporated into a DCNN to aggregate misclassified prediction probabilities for model learning, thus providing additional discriminative information for fine-grained feature learning. Experiments on three fine-grained benchmark datasets (Stanford Cars, FGVC-Aircraft, CUB-Birds) validate the effectiveness of our approach and demonstrate its improvements over previous methods." @default.
- W2983485270 created "2019-11-22" @default.
- W2983485270 creator A5004748206 @default.
- W2983485270 creator A5017353282 @default.
- W2983485270 creator A5019450611 @default.
- W2983485270 creator A5023583572 @default.
- W2983485270 creator A5070235642 @default.
- W2983485270 creator A5085342186 @default.
- W2983485270 date "2019-01-01" @default.
- W2983485270 modified "2023-09-22" @default.
- W2983485270 title "Exploiting Category-Level Semantic Relationships for Fine-Grained Image Recognition" @default.
- W2983485270 cites W1496650988 @default.
- W2983485270 cites W1849277567 @default.
- W2983485270 cites W1915485278 @default.
- W2983485270 cites W1929903369 @default.
- W2983485270 cites W2079789819 @default.
- W2983485270 cites W2097117768 @default.
- W2983485270 cites W2112796928 @default.
- W2983485270 cites W2138011018 @default.
- W2983485270 cites W2194011657 @default.
- W2983485270 cites W2194775991 @default.
- W2983485270 cites W2207849498 @default.
- W2983485270 cites W2462457117 @default.
- W2983485270 cites W2479109623 @default.
- W2983485270 cites W2604195031 @default.
- W2983485270 cites W2752782242 @default.
- W2983485270 cites W2765268259 @default.
- W2983485270 cites W2798542376 @default.
- W2983485270 cites W2885613075 @default.
- W2983485270 cites W2891951760 @default.
- W2983485270 cites W2940925558 @default.
- W2983485270 cites W2962794560 @default.
- W2983485270 cites W2963500702 @default.
- W2983485270 cites W2963610729 @default.
- W2983485270 cites W2964189431 @default.
- W2983485270 cites W3099903704 @default.
- W2983485270 cites W3100093508 @default.
- W2983485270 cites W56385144 @default.
- W2983485270 doi "https://doi.org/10.1007/978-3-030-31654-9_5" @default.
- W2983485270 hasPublicationYear "2019" @default.
- W2983485270 type Work @default.
- W2983485270 sameAs 2983485270 @default.
- W2983485270 citedByCount "1" @default.
- W2983485270 countsByYear W29834852702020 @default.
- W2983485270 crossrefType "book-chapter" @default.
- W2983485270 hasAuthorship W2983485270A5004748206 @default.
- W2983485270 hasAuthorship W2983485270A5017353282 @default.
- W2983485270 hasAuthorship W2983485270A5019450611 @default.
- W2983485270 hasAuthorship W2983485270A5023583572 @default.
- W2983485270 hasAuthorship W2983485270A5070235642 @default.
- W2983485270 hasAuthorship W2983485270A5085342186 @default.
- W2983485270 hasConcept C113174947 @default.
- W2983485270 hasConcept C119857082 @default.
- W2983485270 hasConcept C13280743 @default.
- W2983485270 hasConcept C134306372 @default.
- W2983485270 hasConcept C138885662 @default.
- W2983485270 hasConcept C153180895 @default.
- W2983485270 hasConcept C154945302 @default.
- W2983485270 hasConcept C159985019 @default.
- W2983485270 hasConcept C162324750 @default.
- W2983485270 hasConcept C176217482 @default.
- W2983485270 hasConcept C185798385 @default.
- W2983485270 hasConcept C192562407 @default.
- W2983485270 hasConcept C205649164 @default.
- W2983485270 hasConcept C21547014 @default.
- W2983485270 hasConcept C2776135515 @default.
- W2983485270 hasConcept C2776401178 @default.
- W2983485270 hasConcept C2776502983 @default.
- W2983485270 hasConcept C31170391 @default.
- W2983485270 hasConcept C33923547 @default.
- W2983485270 hasConcept C34447519 @default.
- W2983485270 hasConcept C41008148 @default.
- W2983485270 hasConcept C41895202 @default.
- W2983485270 hasConcept C4679612 @default.
- W2983485270 hasConcept C97931131 @default.
- W2983485270 hasConceptScore W2983485270C113174947 @default.
- W2983485270 hasConceptScore W2983485270C119857082 @default.
- W2983485270 hasConceptScore W2983485270C13280743 @default.
- W2983485270 hasConceptScore W2983485270C134306372 @default.
- W2983485270 hasConceptScore W2983485270C138885662 @default.
- W2983485270 hasConceptScore W2983485270C153180895 @default.
- W2983485270 hasConceptScore W2983485270C154945302 @default.
- W2983485270 hasConceptScore W2983485270C159985019 @default.
- W2983485270 hasConceptScore W2983485270C162324750 @default.
- W2983485270 hasConceptScore W2983485270C176217482 @default.
- W2983485270 hasConceptScore W2983485270C185798385 @default.
- W2983485270 hasConceptScore W2983485270C192562407 @default.
- W2983485270 hasConceptScore W2983485270C205649164 @default.
- W2983485270 hasConceptScore W2983485270C21547014 @default.
- W2983485270 hasConceptScore W2983485270C2776135515 @default.
- W2983485270 hasConceptScore W2983485270C2776401178 @default.
- W2983485270 hasConceptScore W2983485270C2776502983 @default.
- W2983485270 hasConceptScore W2983485270C31170391 @default.
- W2983485270 hasConceptScore W2983485270C33923547 @default.
- W2983485270 hasConceptScore W2983485270C34447519 @default.
- W2983485270 hasConceptScore W2983485270C41008148 @default.
- W2983485270 hasConceptScore W2983485270C41895202 @default.
- W2983485270 hasConceptScore W2983485270C4679612 @default.
- W2983485270 hasConceptScore W2983485270C97931131 @default.
- W2983485270 hasLocation W29834852701 @default.