Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035220232> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3035220232 abstract "Existing weakly supervised fine-grained image recognition (WFGIR) methods usually pick out the discriminative regions from the high-level feature maps directly. We discover that due to the operation of stacking local receptive filed, Convolutional Neural Network causes the discriminative region diffusion in high-level feature maps, which leads to inaccurate discriminative region localization. In this paper, we propose an end-to-end Discriminative Feature-oriented Gaussian Mixture Model (DF-GMM), to address the problem of discriminative region diffusion and find better fine-grained details. Specifically, DF-GMM consists of 1) a low-rank representation mechanism (LRM), which learns a set of low-rank discriminative bases by Gaussian Mixture Model (GMM) to accurately select discriminative details and filter more irrelevant information in high-level semantic feature maps, 2) a low-rank representation reorganization mechanism (LR2M) which resumes the space information of low-rank discriminative bases to reconstruct the low-rank feature maps. By recovering the low-rank discriminative bases into the same embedding space of highlevel feature maps, LR2M alleviates the discriminative region diffusion problem in high-level feature map and discriminative regions can be located more precisely on the new low-rank feature maps. Extensive experiments verify that DF-GMM yields the best performance under the same settings with the most competitive approaches, in CUBBird, Stanford-Cars datasets, and FGVC Aircraft." @default.
- W3035220232 created "2020-06-19" @default.
- W3035220232 creator A5008321836 @default.
- W3035220232 creator A5018617993 @default.
- W3035220232 creator A5031938628 @default.
- W3035220232 creator A5035195373 @default.
- W3035220232 creator A5065492056 @default.
- W3035220232 creator A5074504754 @default.
- W3035220232 date "2020-06-01" @default.
- W3035220232 modified "2023-10-09" @default.
- W3035220232 title "Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning" @default.
- W3035220232 cites W1677182931 @default.
- W3035220232 cites W1898560071 @default.
- W3035220232 cites W2104657103 @default.
- W3035220232 cites W2138011018 @default.
- W3035220232 cites W2194775991 @default.
- W3035220232 cites W2250389441 @default.
- W3035220232 cites W2289708887 @default.
- W3035220232 cites W2479109623 @default.
- W3035220232 cites W2604195031 @default.
- W3035220232 cites W2737725206 @default.
- W3035220232 cites W2740620254 @default.
- W3035220232 cites W2752782242 @default.
- W3035220232 cites W2755775504 @default.
- W3035220232 cites W2765268259 @default.
- W3035220232 cites W2773003563 @default.
- W3035220232 cites W2780838211 @default.
- W3035220232 cites W2808269424 @default.
- W3035220232 cites W2951464224 @default.
- W3035220232 cites W2961018736 @default.
- W3035220232 cites W2963066927 @default.
- W3035220232 cites W2963090248 @default.
- W3035220232 cites W2963148524 @default.
- W3035220232 cites W2963336685 @default.
- W3035220232 cites W2963407932 @default.
- W3035220232 cites W2981954115 @default.
- W3035220232 cites W2990495699 @default.
- W3035220232 cites W3103844505 @default.
- W3035220232 doi "https://doi.org/10.1109/cvpr42600.2020.00977" @default.
- W3035220232 hasPublicationYear "2020" @default.
- W3035220232 type Work @default.
- W3035220232 sameAs 3035220232 @default.
- W3035220232 citedByCount "37" @default.
- W3035220232 countsByYear W30352202322020 @default.
- W3035220232 countsByYear W30352202322021 @default.
- W3035220232 countsByYear W30352202322022 @default.
- W3035220232 countsByYear W30352202322023 @default.
- W3035220232 crossrefType "proceedings-article" @default.
- W3035220232 hasAuthorship W3035220232A5008321836 @default.
- W3035220232 hasAuthorship W3035220232A5018617993 @default.
- W3035220232 hasAuthorship W3035220232A5031938628 @default.
- W3035220232 hasAuthorship W3035220232A5035195373 @default.
- W3035220232 hasAuthorship W3035220232A5065492056 @default.
- W3035220232 hasAuthorship W3035220232A5074504754 @default.
- W3035220232 hasConcept C114614502 @default.
- W3035220232 hasConcept C138885662 @default.
- W3035220232 hasConcept C153180895 @default.
- W3035220232 hasConcept C154945302 @default.
- W3035220232 hasConcept C164226766 @default.
- W3035220232 hasConcept C2776401178 @default.
- W3035220232 hasConcept C33923547 @default.
- W3035220232 hasConcept C41008148 @default.
- W3035220232 hasConcept C41895202 @default.
- W3035220232 hasConcept C61224824 @default.
- W3035220232 hasConcept C83665646 @default.
- W3035220232 hasConcept C97931131 @default.
- W3035220232 hasConceptScore W3035220232C114614502 @default.
- W3035220232 hasConceptScore W3035220232C138885662 @default.
- W3035220232 hasConceptScore W3035220232C153180895 @default.
- W3035220232 hasConceptScore W3035220232C154945302 @default.
- W3035220232 hasConceptScore W3035220232C164226766 @default.
- W3035220232 hasConceptScore W3035220232C2776401178 @default.
- W3035220232 hasConceptScore W3035220232C33923547 @default.
- W3035220232 hasConceptScore W3035220232C41008148 @default.
- W3035220232 hasConceptScore W3035220232C41895202 @default.
- W3035220232 hasConceptScore W3035220232C61224824 @default.
- W3035220232 hasConceptScore W3035220232C83665646 @default.
- W3035220232 hasConceptScore W3035220232C97931131 @default.
- W3035220232 hasLocation W30352202321 @default.
- W3035220232 hasOpenAccess W3035220232 @default.
- W3035220232 hasPrimaryLocation W30352202321 @default.
- W3035220232 hasRelatedWork W1461621550 @default.
- W3035220232 hasRelatedWork W2020350089 @default.
- W3035220232 hasRelatedWork W2024160000 @default.
- W3035220232 hasRelatedWork W2061273563 @default.
- W3035220232 hasRelatedWork W2125743092 @default.
- W3035220232 hasRelatedWork W2135346345 @default.
- W3035220232 hasRelatedWork W2729514902 @default.
- W3035220232 hasRelatedWork W2773500201 @default.
- W3035220232 hasRelatedWork W2944661354 @default.
- W3035220232 hasRelatedWork W2970216048 @default.
- W3035220232 isParatext "false" @default.
- W3035220232 isRetracted "false" @default.
- W3035220232 magId "3035220232" @default.
- W3035220232 workType "article" @default.