Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288732030> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4288732030 abstract "Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like machine learning. State-of-the-art solutions involve learning to find a good metric and representation space to compute the distance between samples. Despite the promising accuracy performance, how to model uncertainty for metric-based FSC methods effectively is still a challenge. To model uncertainty, We place a distribution over class probability based on the theory of evidence. As a result, uncertainty modeling and metric learning can be decoupled. To reduce the uncertainty of classification, we propose a Bayesian evidence fusion theorem. Given observed samples, the network learns to get posterior distribution parameters given the prior parameters produced by the pre-trained network. Detailed gradient analysis shows that our method provides a smooth optimization target and can capture the uncertainty. The proposed method is agnostic to metric learning strategies and can be implemented as a plug-and-play module. We integrate our method into several newest FSC methods and demonstrate the improved accuracy and uncertainty quantification on standard FSC benchmarks." @default.
- W4288732030 created "2022-07-30" @default.
- W4288732030 creator A5024067111 @default.
- W4288732030 creator A5028122995 @default.
- W4288732030 creator A5031215254 @default.
- W4288732030 creator A5063319286 @default.
- W4288732030 creator A5063901345 @default.
- W4288732030 creator A5069232660 @default.
- W4288732030 creator A5075918508 @default.
- W4288732030 date "2022-07-18" @default.
- W4288732030 modified "2023-10-18" @default.
- W4288732030 title "Bayesian Evidential Learning for Few-Shot Classification" @default.
- W4288732030 doi "https://doi.org/10.48550/arxiv.2207.13137" @default.
- W4288732030 hasPublicationYear "2022" @default.
- W4288732030 type Work @default.
- W4288732030 citedByCount "0" @default.
- W4288732030 crossrefType "posted-content" @default.
- W4288732030 hasAuthorship W4288732030A5024067111 @default.
- W4288732030 hasAuthorship W4288732030A5028122995 @default.
- W4288732030 hasAuthorship W4288732030A5031215254 @default.
- W4288732030 hasAuthorship W4288732030A5063319286 @default.
- W4288732030 hasAuthorship W4288732030A5063901345 @default.
- W4288732030 hasAuthorship W4288732030A5069232660 @default.
- W4288732030 hasAuthorship W4288732030A5075918508 @default.
- W4288732030 hasBestOaLocation W42887320301 @default.
- W4288732030 hasConcept C107673813 @default.
- W4288732030 hasConcept C119857082 @default.
- W4288732030 hasConcept C154945302 @default.
- W4288732030 hasConcept C162324750 @default.
- W4288732030 hasConcept C176217482 @default.
- W4288732030 hasConcept C17744445 @default.
- W4288732030 hasConcept C199539241 @default.
- W4288732030 hasConcept C21547014 @default.
- W4288732030 hasConcept C2776359362 @default.
- W4288732030 hasConcept C33724603 @default.
- W4288732030 hasConcept C41008148 @default.
- W4288732030 hasConcept C57830394 @default.
- W4288732030 hasConcept C94625758 @default.
- W4288732030 hasConceptScore W4288732030C107673813 @default.
- W4288732030 hasConceptScore W4288732030C119857082 @default.
- W4288732030 hasConceptScore W4288732030C154945302 @default.
- W4288732030 hasConceptScore W4288732030C162324750 @default.
- W4288732030 hasConceptScore W4288732030C176217482 @default.
- W4288732030 hasConceptScore W4288732030C17744445 @default.
- W4288732030 hasConceptScore W4288732030C199539241 @default.
- W4288732030 hasConceptScore W4288732030C21547014 @default.
- W4288732030 hasConceptScore W4288732030C2776359362 @default.
- W4288732030 hasConceptScore W4288732030C33724603 @default.
- W4288732030 hasConceptScore W4288732030C41008148 @default.
- W4288732030 hasConceptScore W4288732030C57830394 @default.
- W4288732030 hasConceptScore W4288732030C94625758 @default.
- W4288732030 hasLocation W42887320301 @default.
- W4288732030 hasOpenAccess W4288732030 @default.
- W4288732030 hasPrimaryLocation W42887320301 @default.
- W4288732030 hasRelatedWork W11338565 @default.
- W4288732030 hasRelatedWork W13176313 @default.
- W4288732030 hasRelatedWork W13303319 @default.
- W4288732030 hasRelatedWork W2651071 @default.
- W4288732030 hasRelatedWork W368576 @default.
- W4288732030 hasRelatedWork W4179021 @default.
- W4288732030 hasRelatedWork W5005022 @default.
- W4288732030 hasRelatedWork W6921400 @default.
- W4288732030 hasRelatedWork W7890312 @default.
- W4288732030 hasRelatedWork W868042 @default.
- W4288732030 isParatext "false" @default.
- W4288732030 isRetracted "false" @default.
- W4288732030 workType "article" @default.