Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175048696> ?p ?o ?g. }
- W3175048696 endingPage "2799" @default.
- W3175048696 startingPage "2791" @default.
- W3175048696 abstract "Most weakly supervised fine-grained image recognition (WFGIR) approaches predominantly focus on learning the discriminative details which contain the visual variances and position clues. The position clues can be indirectly learnt by utilizing context information of discriminative visual content. However, this will cause the selected discriminative regions containing some non-discriminative information introduced by the position clues. These analysis motivate us to directly introduce position clues into visual content to only focus on the visual variances, achieving more precise discriminative region localization. Though important, position modelling usually requires significant pixel/region annotations and therefore is labor-intensive. To address this issue, we propose an end-to-end Dynamic Position-aware Network (DP-Net) to directly incorporate the position clues into visual content and dynamically align them without extra annotations, which eliminates the effect of position information for visual variances of subcategories. In particular, the DP-Net consists of: 1) Position Encoding Module, which learns a set of position-aware parts by directly adding the learnable position information into the horizontal/vertical visual content of images; 2) Position-vision Aligning Module, which dynamically aligns both visual content and learnable position information via performing graph convolution on position-aware parts; 3) Position-vision Reorganization Module, which projects the aligned position clues and visual content into the Euclidean space to construct a position-aware feature maps. Finally, the position-aware feature maps are used which is implicitly applied the aligned visual content and position clues for more accurate discriminative regions localization. Extensive experiments verify that DP-Net yields the best performance under the same settings with most competitive approaches, on CUB Bird, Stanford-Cars, and FGVC Aircraft datasets." @default.
- W3175048696 created "2021-07-05" @default.
- W3175048696 creator A5008321836 @default.
- W3175048696 creator A5035195373 @default.
- W3175048696 creator A5074504754 @default.
- W3175048696 creator A5087818121 @default.
- W3175048696 date "2021-05-18" @default.
- W3175048696 modified "2023-10-14" @default.
- W3175048696 title "Dynamic Position-aware Network for Fine-grained Image Recognition" @default.
- W3175048696 cites W1616462885 @default.
- W3175048696 cites W1898560071 @default.
- W3175048696 cites W2138011018 @default.
- W3175048696 cites W2194775991 @default.
- W3175048696 cites W2479109623 @default.
- W3175048696 cites W2565639579 @default.
- W3175048696 cites W2604134068 @default.
- W3175048696 cites W2604195031 @default.
- W3175048696 cites W2737725206 @default.
- W3175048696 cites W2740620254 @default.
- W3175048696 cites W2755775504 @default.
- W3175048696 cites W2780838211 @default.
- W3175048696 cites W2945081094 @default.
- W3175048696 cites W2961018736 @default.
- W3175048696 cites W2963090248 @default.
- W3175048696 cites W2963403868 @default.
- W3175048696 cites W2963407932 @default.
- W3175048696 cites W2970507129 @default.
- W3175048696 cites W2981954115 @default.
- W3175048696 cites W2990495699 @default.
- W3175048696 cites W3015167968 @default.
- W3175048696 cites W3035220232 @default.
- W3175048696 cites W3035367622 @default.
- W3175048696 cites W3103844505 @default.
- W3175048696 doi "https://doi.org/10.1609/aaai.v35i4.16384" @default.
- W3175048696 hasPublicationYear "2021" @default.
- W3175048696 type Work @default.
- W3175048696 sameAs 3175048696 @default.
- W3175048696 citedByCount "10" @default.
- W3175048696 countsByYear W31750486962022 @default.
- W3175048696 countsByYear W31750486962023 @default.
- W3175048696 crossrefType "journal-article" @default.
- W3175048696 hasAuthorship W3175048696A5008321836 @default.
- W3175048696 hasAuthorship W3175048696A5035195373 @default.
- W3175048696 hasAuthorship W3175048696A5074504754 @default.
- W3175048696 hasAuthorship W3175048696A5087818121 @default.
- W3175048696 hasBestOaLocation W31750486961 @default.
- W3175048696 hasConcept C10138342 @default.
- W3175048696 hasConcept C120665830 @default.
- W3175048696 hasConcept C121332964 @default.
- W3175048696 hasConcept C138885662 @default.
- W3175048696 hasConcept C151730666 @default.
- W3175048696 hasConcept C153180895 @default.
- W3175048696 hasConcept C154945302 @default.
- W3175048696 hasConcept C162324750 @default.
- W3175048696 hasConcept C192209626 @default.
- W3175048696 hasConcept C198082294 @default.
- W3175048696 hasConcept C2776401178 @default.
- W3175048696 hasConcept C2779343474 @default.
- W3175048696 hasConcept C31972630 @default.
- W3175048696 hasConcept C41008148 @default.
- W3175048696 hasConcept C41895202 @default.
- W3175048696 hasConcept C86803240 @default.
- W3175048696 hasConcept C97931131 @default.
- W3175048696 hasConceptScore W3175048696C10138342 @default.
- W3175048696 hasConceptScore W3175048696C120665830 @default.
- W3175048696 hasConceptScore W3175048696C121332964 @default.
- W3175048696 hasConceptScore W3175048696C138885662 @default.
- W3175048696 hasConceptScore W3175048696C151730666 @default.
- W3175048696 hasConceptScore W3175048696C153180895 @default.
- W3175048696 hasConceptScore W3175048696C154945302 @default.
- W3175048696 hasConceptScore W3175048696C162324750 @default.
- W3175048696 hasConceptScore W3175048696C192209626 @default.
- W3175048696 hasConceptScore W3175048696C198082294 @default.
- W3175048696 hasConceptScore W3175048696C2776401178 @default.
- W3175048696 hasConceptScore W3175048696C2779343474 @default.
- W3175048696 hasConceptScore W3175048696C31972630 @default.
- W3175048696 hasConceptScore W3175048696C41008148 @default.
- W3175048696 hasConceptScore W3175048696C41895202 @default.
- W3175048696 hasConceptScore W3175048696C86803240 @default.
- W3175048696 hasConceptScore W3175048696C97931131 @default.
- W3175048696 hasIssue "4" @default.
- W3175048696 hasLocation W31750486961 @default.
- W3175048696 hasOpenAccess W3175048696 @default.
- W3175048696 hasPrimaryLocation W31750486961 @default.
- W3175048696 hasRelatedWork W1652783584 @default.
- W3175048696 hasRelatedWork W2082783427 @default.
- W3175048696 hasRelatedWork W2153315159 @default.
- W3175048696 hasRelatedWork W2358868262 @default.
- W3175048696 hasRelatedWork W2404514746 @default.
- W3175048696 hasRelatedWork W2958404818 @default.
- W3175048696 hasRelatedWork W2965546495 @default.
- W3175048696 hasRelatedWork W3103844505 @default.
- W3175048696 hasRelatedWork W4205463238 @default.
- W3175048696 hasRelatedWork W2088733771 @default.
- W3175048696 hasVolume "35" @default.
- W3175048696 isParatext "false" @default.
- W3175048696 isRetracted "false" @default.
- W3175048696 magId "3175048696" @default.