Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285602687> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4285602687 abstract "The task of webly-supervised fine-grained recognition is to boost recognition accuracy of classifying subordinate categories (e.g., different bird species) by utilizing freely available but noisy web data. As the label noises significantly hurt the network training, it is desirable to distinguish and eliminate noisy images. In this paper, we propose two strategies, i.e., open-set noise removal and closed-set noise correction, to both remove such two kinds of web noises w.r.t. fine-grained recognition. Specifically, for open-set noise removal, we utilize a pre-trained deep model to perform deep descriptor transformation to estimate the positive correlation between these web images, and detect the open-set noises based on the correlation values. Regarding closed-set noise correction, we develop a top-k recall optimization loss for firstly assigning a label set towards each web image to reduce the impact of hard label assignment for closed-set noises. Then, we further propose to correct the sample with its label set as the true single label from a partial label learning perspective. Experiments on several webly-supervised fine-grained benchmark datasets show that our method obviously outperforms other existing state-of-the-art methods." @default.
- W4285602687 created "2022-07-16" @default.
- W4285602687 creator A5005295743 @default.
- W4285602687 creator A5033056599 @default.
- W4285602687 creator A5046051690 @default.
- W4285602687 creator A5046498450 @default.
- W4285602687 creator A5049927248 @default.
- W4285602687 creator A5088454689 @default.
- W4285602687 creator A5091397957 @default.
- W4285602687 date "2022-07-01" @default.
- W4285602687 modified "2023-10-02" @default.
- W4285602687 title "Webly-Supervised Fine-Grained Recognition with Partial Label Learning" @default.
- W4285602687 doi "https://doi.org/10.24963/ijcai.2022/209" @default.
- W4285602687 hasPublicationYear "2022" @default.
- W4285602687 type Work @default.
- W4285602687 citedByCount "2" @default.
- W4285602687 countsByYear W42856026872023 @default.
- W4285602687 crossrefType "proceedings-article" @default.
- W4285602687 hasAuthorship W4285602687A5005295743 @default.
- W4285602687 hasAuthorship W4285602687A5033056599 @default.
- W4285602687 hasAuthorship W4285602687A5046051690 @default.
- W4285602687 hasAuthorship W4285602687A5046498450 @default.
- W4285602687 hasAuthorship W4285602687A5049927248 @default.
- W4285602687 hasAuthorship W4285602687A5088454689 @default.
- W4285602687 hasAuthorship W4285602687A5091397957 @default.
- W4285602687 hasBestOaLocation W42856026871 @default.
- W4285602687 hasConcept C104317684 @default.
- W4285602687 hasConcept C115961682 @default.
- W4285602687 hasConcept C119857082 @default.
- W4285602687 hasConcept C13280743 @default.
- W4285602687 hasConcept C153180895 @default.
- W4285602687 hasConcept C154945302 @default.
- W4285602687 hasConcept C162324750 @default.
- W4285602687 hasConcept C177264268 @default.
- W4285602687 hasConcept C185592680 @default.
- W4285602687 hasConcept C185798385 @default.
- W4285602687 hasConcept C187736073 @default.
- W4285602687 hasConcept C199360897 @default.
- W4285602687 hasConcept C204241405 @default.
- W4285602687 hasConcept C205649164 @default.
- W4285602687 hasConcept C2780451532 @default.
- W4285602687 hasConcept C41008148 @default.
- W4285602687 hasConcept C55493867 @default.
- W4285602687 hasConcept C99498987 @default.
- W4285602687 hasConceptScore W4285602687C104317684 @default.
- W4285602687 hasConceptScore W4285602687C115961682 @default.
- W4285602687 hasConceptScore W4285602687C119857082 @default.
- W4285602687 hasConceptScore W4285602687C13280743 @default.
- W4285602687 hasConceptScore W4285602687C153180895 @default.
- W4285602687 hasConceptScore W4285602687C154945302 @default.
- W4285602687 hasConceptScore W4285602687C162324750 @default.
- W4285602687 hasConceptScore W4285602687C177264268 @default.
- W4285602687 hasConceptScore W4285602687C185592680 @default.
- W4285602687 hasConceptScore W4285602687C185798385 @default.
- W4285602687 hasConceptScore W4285602687C187736073 @default.
- W4285602687 hasConceptScore W4285602687C199360897 @default.
- W4285602687 hasConceptScore W4285602687C204241405 @default.
- W4285602687 hasConceptScore W4285602687C205649164 @default.
- W4285602687 hasConceptScore W4285602687C2780451532 @default.
- W4285602687 hasConceptScore W4285602687C41008148 @default.
- W4285602687 hasConceptScore W4285602687C55493867 @default.
- W4285602687 hasConceptScore W4285602687C99498987 @default.
- W4285602687 hasLocation W42856026871 @default.
- W4285602687 hasOpenAccess W4285602687 @default.
- W4285602687 hasPrimaryLocation W42856026871 @default.
- W4285602687 hasRelatedWork W112744582 @default.
- W4285602687 hasRelatedWork W1485630101 @default.
- W4285602687 hasRelatedWork W2498017833 @default.
- W4285602687 hasRelatedWork W2939912336 @default.
- W4285602687 hasRelatedWork W2961085424 @default.
- W4285602687 hasRelatedWork W2983785000 @default.
- W4285602687 hasRelatedWork W3150234497 @default.
- W4285602687 hasRelatedWork W3177008965 @default.
- W4285602687 hasRelatedWork W4288373736 @default.
- W4285602687 hasRelatedWork W4306674287 @default.
- W4285602687 isParatext "false" @default.
- W4285602687 isRetracted "false" @default.
- W4285602687 workType "article" @default.