Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313171213> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4313171213 abstract "In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by finetuning. The problem assumes a realistic scenario for face identification, where only a small number of face images is given for enrollment and any unknown identity must be rejected during identification. We observe that face recognition models pretrained on a large dataset and naively fine-tuned models perform poorly for this task. Motivated by this issue, we propose an effective fine-tuning scheme with classifier weight imprinting and exclusive BatchNorm layer tuning. For further improvement of rejection accuracy on unknown identities, we propose a novel matcher called Neighborhood Aware Cosine (NAC) that computes similarity based on neighborhood information. We validate the effectiveness of the proposed schemes thoroughly on large-scale face benchmarks across different convolutional neural network architectures. The source code for this project is available at: https://github.com/1ho0jin1/OSFI-by-FineTuning" @default.
- W4313171213 created "2023-01-06" @default.
- W4313171213 creator A5005138081 @default.
- W4313171213 creator A5026534904 @default.
- W4313171213 creator A5031433040 @default.
- W4313171213 date "2022-08-21" @default.
- W4313171213 modified "2023-09-29" @default.
- W4313171213 title "Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning" @default.
- W4313171213 cites W1990537115 @default.
- W4313171213 cites W2029538739 @default.
- W4313171213 cites W2051224630 @default.
- W4313171213 cites W2074259494 @default.
- W4313171213 cites W2105087447 @default.
- W4313171213 cites W2194775991 @default.
- W4313171213 cites W2515770085 @default.
- W4313171213 cites W2785496677 @default.
- W4313171213 cites W2796346823 @default.
- W4313171213 cites W2871667416 @default.
- W4313171213 cites W2910603373 @default.
- W4313171213 cites W2962945654 @default.
- W4313171213 cites W2963149653 @default.
- W4313171213 cites W2963839617 @default.
- W4313171213 cites W2963968551 @default.
- W4313171213 cites W2969985801 @default.
- W4313171213 cites W2998469040 @default.
- W4313171213 cites W3099206234 @default.
- W4313171213 cites W3101227480 @default.
- W4313171213 cites W3101998545 @default.
- W4313171213 cites W3169129566 @default.
- W4313171213 cites W3177034761 @default.
- W4313171213 cites W3214849901 @default.
- W4313171213 cites W572355794 @default.
- W4313171213 doi "https://doi.org/10.1109/icpr56361.2022.9956714" @default.
- W4313171213 hasPublicationYear "2022" @default.
- W4313171213 type Work @default.
- W4313171213 citedByCount "0" @default.
- W4313171213 crossrefType "proceedings-article" @default.
- W4313171213 hasAuthorship W4313171213A5005138081 @default.
- W4313171213 hasAuthorship W4313171213A5026534904 @default.
- W4313171213 hasAuthorship W4313171213A5031433040 @default.
- W4313171213 hasBestOaLocation W43131712132 @default.
- W4313171213 hasConcept C111919701 @default.
- W4313171213 hasConcept C116834253 @default.
- W4313171213 hasConcept C119857082 @default.
- W4313171213 hasConcept C144024400 @default.
- W4313171213 hasConcept C153180895 @default.
- W4313171213 hasConcept C154945302 @default.
- W4313171213 hasConcept C177264268 @default.
- W4313171213 hasConcept C199360897 @default.
- W4313171213 hasConcept C2776760102 @default.
- W4313171213 hasConcept C2779304628 @default.
- W4313171213 hasConcept C31510193 @default.
- W4313171213 hasConcept C36289849 @default.
- W4313171213 hasConcept C41008148 @default.
- W4313171213 hasConcept C43126263 @default.
- W4313171213 hasConcept C59822182 @default.
- W4313171213 hasConcept C81363708 @default.
- W4313171213 hasConcept C86803240 @default.
- W4313171213 hasConcept C95623464 @default.
- W4313171213 hasConceptScore W4313171213C111919701 @default.
- W4313171213 hasConceptScore W4313171213C116834253 @default.
- W4313171213 hasConceptScore W4313171213C119857082 @default.
- W4313171213 hasConceptScore W4313171213C144024400 @default.
- W4313171213 hasConceptScore W4313171213C153180895 @default.
- W4313171213 hasConceptScore W4313171213C154945302 @default.
- W4313171213 hasConceptScore W4313171213C177264268 @default.
- W4313171213 hasConceptScore W4313171213C199360897 @default.
- W4313171213 hasConceptScore W4313171213C2776760102 @default.
- W4313171213 hasConceptScore W4313171213C2779304628 @default.
- W4313171213 hasConceptScore W4313171213C31510193 @default.
- W4313171213 hasConceptScore W4313171213C36289849 @default.
- W4313171213 hasConceptScore W4313171213C41008148 @default.
- W4313171213 hasConceptScore W4313171213C43126263 @default.
- W4313171213 hasConceptScore W4313171213C59822182 @default.
- W4313171213 hasConceptScore W4313171213C81363708 @default.
- W4313171213 hasConceptScore W4313171213C86803240 @default.
- W4313171213 hasConceptScore W4313171213C95623464 @default.
- W4313171213 hasLocation W43131712131 @default.
- W4313171213 hasLocation W43131712132 @default.
- W4313171213 hasOpenAccess W4313171213 @default.
- W4313171213 hasPrimaryLocation W43131712131 @default.
- W4313171213 hasRelatedWork W2060029454 @default.
- W4313171213 hasRelatedWork W2136485282 @default.
- W4313171213 hasRelatedWork W2347601237 @default.
- W4313171213 hasRelatedWork W2368987896 @default.
- W4313171213 hasRelatedWork W2521062615 @default.
- W4313171213 hasRelatedWork W2976316911 @default.
- W4313171213 hasRelatedWork W2995914718 @default.
- W4313171213 hasRelatedWork W3124066309 @default.
- W4313171213 hasRelatedWork W564581980 @default.
- W4313171213 hasRelatedWork W3158004940 @default.
- W4313171213 isParatext "false" @default.
- W4313171213 isRetracted "false" @default.
- W4313171213 workType "article" @default.