Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210551401> ?p ?o ?g. }
- W4210551401 endingPage "5330" @default.
- W4210551401 startingPage "5319" @default.
- W4210551401 abstract "Existing fine-grained image recognition methods are difficult to learn complete discriminative features from low-resolution (LR) data, because the original subtle inter-class distinctions become slimmer with the reduction of the image resolution. Besides, existing methods of LR fine-grained image recognition and general LR image recognition only consider the restoration and extraction of global discriminative features, ignoring unreliable local fine-grained details can be detrimental to final recognition. To address the above problems, we propose a multi-tasking framework, discriminative feature mining and enhancement network (DME-Net), for the LR fine-grained image recognition task, which aims to capture the reliable object descriptions from macro and micro perspectives, respectively. Macroscopically, we train the framework’s ability to recover and extract global discriminative features based on the whole images. Microscopically, we purposefully reinforce the framework’s ability to repair and capture the local discriminative details on the mined informative parts. To precisely excavate the most potential parts, we design an informative part mining (IPM) module, in which we firstly employ a part generation layer to predict several part masks that focus on different discriminative parts under the guidance of discrepancy loss and discriminant loss. Then we introduce a part selection (PS) submodule to further screen out a group of most informative parts from the predicted part masks according to their corresponding scores, which measure the semantic correlation degree of each part to the others. Experimental results on three benchmark datasets and one retail product dataset consistently show that our proposed framework can significantly boost the performance of the baseline model. Besides, extensive ablation studies are conducted, which further prove the effectiveness of each component of our designs." @default.
- W4210551401 created "2022-02-08" @default.
- W4210551401 creator A5008321836 @default.
- W4210551401 creator A5020149992 @default.
- W4210551401 creator A5045140275 @default.
- W4210551401 creator A5072859971 @default.
- W4210551401 creator A5088142815 @default.
- W4210551401 date "2022-08-01" @default.
- W4210551401 modified "2023-10-16" @default.
- W4210551401 title "Discriminative Feature Mining and Enhancement Network for Low-Resolution Fine-Grained Image Recognition" @default.
- W4210551401 cites W2108598243 @default.
- W4210551401 cites W2138011018 @default.
- W4210551401 cites W2194775991 @default.
- W4210551401 cites W2602572945 @default.
- W4210551401 cites W2761785940 @default.
- W4210551401 cites W2773003563 @default.
- W4210551401 cites W2780544323 @default.
- W4210551401 cites W2798365843 @default.
- W4210551401 cites W2891951760 @default.
- W4210551401 cites W2898124204 @default.
- W4210551401 cites W2939565811 @default.
- W4210551401 cites W2940110727 @default.
- W4210551401 cites W2951464224 @default.
- W4210551401 cites W2961018736 @default.
- W4210551401 cites W2963150697 @default.
- W4210551401 cites W2963393555 @default.
- W4210551401 cites W2963407932 @default.
- W4210551401 cites W2963470893 @default.
- W4210551401 cites W2964274719 @default.
- W4210551401 cites W2982243647 @default.
- W4210551401 cites W2990495699 @default.
- W4210551401 cites W2996411315 @default.
- W4210551401 cites W2998345525 @default.
- W4210551401 cites W3008809756 @default.
- W4210551401 cites W3010121230 @default.
- W4210551401 cites W3018586778 @default.
- W4210551401 cites W3035367622 @default.
- W4210551401 cites W3035996440 @default.
- W4210551401 cites W3038079672 @default.
- W4210551401 cites W3089400682 @default.
- W4210551401 cites W3108870912 @default.
- W4210551401 cites W3181108287 @default.
- W4210551401 cites W639708223 @default.
- W4210551401 doi "https://doi.org/10.1109/tcsvt.2022.3144186" @default.
- W4210551401 hasPublicationYear "2022" @default.
- W4210551401 type Work @default.
- W4210551401 citedByCount "6" @default.
- W4210551401 countsByYear W42105514012023 @default.
- W4210551401 crossrefType "journal-article" @default.
- W4210551401 hasAuthorship W4210551401A5008321836 @default.
- W4210551401 hasAuthorship W4210551401A5020149992 @default.
- W4210551401 hasAuthorship W4210551401A5045140275 @default.
- W4210551401 hasAuthorship W4210551401A5072859971 @default.
- W4210551401 hasAuthorship W4210551401A5088142815 @default.
- W4210551401 hasConcept C115961682 @default.
- W4210551401 hasConcept C119857082 @default.
- W4210551401 hasConcept C124101348 @default.
- W4210551401 hasConcept C13280743 @default.
- W4210551401 hasConcept C138885662 @default.
- W4210551401 hasConcept C153180895 @default.
- W4210551401 hasConcept C154945302 @default.
- W4210551401 hasConcept C185798385 @default.
- W4210551401 hasConcept C205649164 @default.
- W4210551401 hasConcept C2776401178 @default.
- W4210551401 hasConcept C41008148 @default.
- W4210551401 hasConcept C41895202 @default.
- W4210551401 hasConcept C52622490 @default.
- W4210551401 hasConcept C97931131 @default.
- W4210551401 hasConceptScore W4210551401C115961682 @default.
- W4210551401 hasConceptScore W4210551401C119857082 @default.
- W4210551401 hasConceptScore W4210551401C124101348 @default.
- W4210551401 hasConceptScore W4210551401C13280743 @default.
- W4210551401 hasConceptScore W4210551401C138885662 @default.
- W4210551401 hasConceptScore W4210551401C153180895 @default.
- W4210551401 hasConceptScore W4210551401C154945302 @default.
- W4210551401 hasConceptScore W4210551401C185798385 @default.
- W4210551401 hasConceptScore W4210551401C205649164 @default.
- W4210551401 hasConceptScore W4210551401C2776401178 @default.
- W4210551401 hasConceptScore W4210551401C41008148 @default.
- W4210551401 hasConceptScore W4210551401C41895202 @default.
- W4210551401 hasConceptScore W4210551401C52622490 @default.
- W4210551401 hasConceptScore W4210551401C97931131 @default.
- W4210551401 hasFunder F4320321001 @default.
- W4210551401 hasIssue "8" @default.
- W4210551401 hasLocation W42105514011 @default.
- W4210551401 hasOpenAccess W4210551401 @default.
- W4210551401 hasPrimaryLocation W42105514011 @default.
- W4210551401 hasRelatedWork W2024160000 @default.
- W4210551401 hasRelatedWork W2061273563 @default.
- W4210551401 hasRelatedWork W2285052147 @default.
- W4210551401 hasRelatedWork W2546942002 @default.
- W4210551401 hasRelatedWork W2729514902 @default.
- W4210551401 hasRelatedWork W2743258233 @default.
- W4210551401 hasRelatedWork W2773500201 @default.
- W4210551401 hasRelatedWork W2806866760 @default.
- W4210551401 hasRelatedWork W2970216048 @default.
- W4210551401 hasRelatedWork W4287995534 @default.
- W4210551401 hasVolume "32" @default.