FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200316912> ?p ?o ?g. }

• W4200316912 endingPage "391" @default.
• W4200316912 startingPage "379" @default.
• W4200316912 abstract "Existing person re-identification (Re-ID) methods usually rely heavily on large-scale thoroughly annotated training data. However, label noise is unavoidable due to inaccurate person detection results or annotation errors in real scenes. It is extremely challenging to learn a robust Re-ID model with label noise since each identity has very limited annotated training samples. To avoid fitting to the noisy labels, we propose to learn a prefatory model using a large learning rate at the early stage with a self-label refining strategy, in which the labels and network are jointly optimized. To further enhance the robustness, we introduce an online co-refining (CORE) framework with dynamic mutual learning, where networks and label predictions are online optimized collaboratively by distilling the knowledge from other peer networks. Moreover, it also reduces the negative impact of noisy labels using a favorable selective consistency strategy. CORE has two primary advantages: it is robust to different noise types and unknown noise ratios; it can be easily trained without much additional effort on the architecture design. Extensive experiments on Re-ID and image classification demonstrate that CORE outperforms its counterparts by a large margin under both practical and simulated noise settings. Notably, it also improves the state-of-the-art unsupervised Re-ID performance under standard settings. Code is available at https://github.com/mangye16/ReID-Label-Noise." @default.
• W4200316912 created "2021-12-31" @default.
• W4200316912 creator A5001189204 @default.
• W4200316912 creator A5008999954 @default.
• W4200316912 creator A5058678906 @default.
• W4200316912 creator A5060042752 @default.
• W4200316912 creator A5074834854 @default.
• W4200316912 creator A5082634513 @default.
• W4200316912 date "2022-01-01" @default.
• W4200316912 modified "2023-10-18" @default.
• W4200316912 title "Collaborative Refining for Person Re-Identification With Label Noise" @default.
• W4200316912 cites W1949591461 @default.
• W4200316912 cites W1982925187 @default.
• W4200316912 cites W2046835352 @default.
• W4200316912 cites W2112796928 @default.
• W4200316912 cites W2168356304 @default.
• W4200316912 cites W2183341477 @default.
• W4200316912 cites W2194775991 @default.
• W4200316912 cites W2204750386 @default.
• W4200316912 cites W2219504084 @default.
• W4200316912 cites W2220271458 @default.
• W4200316912 cites W2433217581 @default.
• W4200316912 cites W2577784528 @default.
• W4200316912 cites W2584637367 @default.
• W4200316912 cites W2585635281 @default.
• W4200316912 cites W2592335154 @default.
• W4200316912 cites W2620998106 @default.
• W4200316912 cites W2736410039 @default.
• W4200316912 cites W2750183885 @default.
• W4200316912 cites W2777534232 @default.
• W4200316912 cites W2798329462 @default.
• W4200316912 cites W2798550112 @default.
• W4200316912 cites W2798590501 @default.
• W4200316912 cites W2798775284 @default.
• W4200316912 cites W2808260522 @default.
• W4200316912 cites W2891071241 @default.
• W4200316912 cites W2895589658 @default.
• W4200316912 cites W2896016251 @default.
• W4200316912 cites W2904427185 @default.
• W4200316912 cites W2904949947 @default.
• W4200316912 cites W2904973725 @default.
• W4200316912 cites W2909398625 @default.
• W4200316912 cites W2909593838 @default.
• W4200316912 cites W2948383821 @default.
• W4200316912 cites W2948606739 @default.
• W4200316912 cites W2954773727 @default.
• W4200316912 cites W2962756219 @default.
• W4200316912 cites W2962762068 @default.
• W4200316912 cites W2962926870 @default.
• W4200316912 cites W2963322158 @default.
• W4200316912 cites W2963351448 @default.
• W4200316912 cites W2963362748 @default.
• W4200316912 cites W2963557071 @default.
• W4200316912 cites W2963597983 @default.
• W4200316912 cites W2963901085 @default.
• W4200316912 cites W2963960612 @default.
• W4200316912 cites W2964155802 @default.
• W4200316912 cites W2964274690 @default.
• W4200316912 cites W2967052791 @default.
• W4200316912 cites W2967637014 @default.
• W4200316912 cites W2970390221 @default.
• W4200316912 cites W2978625989 @default.
• W4200316912 cites W2978968642 @default.
• W4200316912 cites W2979302305 @default.
• W4200316912 cites W2979931389 @default.
• W4200316912 cites W2981393440 @default.
• W4200316912 cites W2981873476 @default.
• W4200316912 cites W2985033611 @default.
• W4200316912 cites W2985817549 @default.
• W4200316912 cites W2988852559 @default.
• W4200316912 cites W2994675267 @default.
• W4200316912 cites W3003755145 @default.
• W4200316912 cites W3033235266 @default.
• W4200316912 cites W3034185248 @default.
• W4200316912 cites W3034494316 @default.
• W4200316912 cites W3036967712 @default.
• W4200316912 cites W3092676209 @default.
• W4200316912 cites W3107848599 @default.
• W4200316912 cites W3109976102 @default.
• W4200316912 cites W3161644958 @default.
• W4200316912 doi "https://doi.org/10.1109/tip.2021.3131937" @default.
• W4200316912 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34874857" @default.
• W4200316912 hasPublicationYear "2022" @default.
• W4200316912 type Work @default.
• W4200316912 citedByCount "33" @default.
• W4200316912 countsByYear W42003169122022 @default.
• W4200316912 countsByYear W42003169122023 @default.
• W4200316912 crossrefType "journal-article" @default.
• W4200316912 hasAuthorship W4200316912A5001189204 @default.
• W4200316912 hasAuthorship W4200316912A5008999954 @default.
• W4200316912 hasAuthorship W4200316912A5058678906 @default.
• W4200316912 hasAuthorship W4200316912A5060042752 @default.
• W4200316912 hasAuthorship W4200316912A5074834854 @default.
• W4200316912 hasAuthorship W4200316912A5082634513 @default.
• W4200316912 hasConcept C104317684 @default.
• W4200316912 hasConcept C115961682 @default.
• W4200316912 hasConcept C119857082 @default.
• W4200316912 hasConcept C124101348 @default.

• next