Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287996940> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4287996940 abstract "Real-world visual data often exhibits a long-tailed distribution, where some ''head'' classes have a large number of samples, yet only a few samples are available for ''tail'' classes. Such imbalanced distribution causes a great challenge for learning a deep neural network, which can be boiled down into a dilemma: on the one hand, we prefer to increase the exposure of tail class samples to avoid the excessive dominance of head classes in the classifier training. On the other hand, oversampling tail classes makes the network prone to over-fitting, since head class samples are often consequently under-represented. To resolve this dilemma, in this paper, we propose a simple-yet-effective auxiliary learning approach. The key idea is to split a network into a classifier part and a feature extractor part, and then employ different training strategies for each part. Specifically, to promote the awareness of tail-classes, a class-balanced sampling scheme is utilised for training both the classifier and the feature extractor. For the feature extractor, we also introduce an auxiliary training task, which is to train a classifier under the regular random sampling scheme. In this way, the feature extractor is jointly trained from both sampling strategies and thus can take advantage of all training data and avoid the over-fitting issue. Apart from this basic auxiliary task, we further explore the benefit of using self-supervised learning as the auxiliary task. Without using any bells and whistles, our model achieves superior performance over the state-of-the-art solutions." @default.
- W4287996940 created "2022-07-26" @default.
- W4287996940 creator A5006294869 @default.
- W4287996940 creator A5016722530 @default.
- W4287996940 creator A5049078993 @default.
- W4287996940 creator A5070976480 @default.
- W4287996940 date "2019-12-09" @default.
- W4287996940 modified "2023-10-16" @default.
- W4287996940 title "To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions" @default.
- W4287996940 hasPublicationYear "2019" @default.
- W4287996940 type Work @default.
- W4287996940 citedByCount "0" @default.
- W4287996940 crossrefType "posted-content" @default.
- W4287996940 hasAuthorship W4287996940A5006294869 @default.
- W4287996940 hasAuthorship W4287996940A5016722530 @default.
- W4287996940 hasAuthorship W4287996940A5049078993 @default.
- W4287996940 hasAuthorship W4287996940A5070976480 @default.
- W4287996940 hasBestOaLocation W42879969401 @default.
- W4287996940 hasConcept C105795698 @default.
- W4287996940 hasConcept C117978034 @default.
- W4287996940 hasConcept C119857082 @default.
- W4287996940 hasConcept C127413603 @default.
- W4287996940 hasConcept C153180895 @default.
- W4287996940 hasConcept C154945302 @default.
- W4287996940 hasConcept C185429906 @default.
- W4287996940 hasConcept C197323446 @default.
- W4287996940 hasConcept C21880701 @default.
- W4287996940 hasConcept C2776257435 @default.
- W4287996940 hasConcept C2985139394 @default.
- W4287996940 hasConcept C31258907 @default.
- W4287996940 hasConcept C33923547 @default.
- W4287996940 hasConcept C41008148 @default.
- W4287996940 hasConcept C50644808 @default.
- W4287996940 hasConcept C95623464 @default.
- W4287996940 hasConceptScore W4287996940C105795698 @default.
- W4287996940 hasConceptScore W4287996940C117978034 @default.
- W4287996940 hasConceptScore W4287996940C119857082 @default.
- W4287996940 hasConceptScore W4287996940C127413603 @default.
- W4287996940 hasConceptScore W4287996940C153180895 @default.
- W4287996940 hasConceptScore W4287996940C154945302 @default.
- W4287996940 hasConceptScore W4287996940C185429906 @default.
- W4287996940 hasConceptScore W4287996940C197323446 @default.
- W4287996940 hasConceptScore W4287996940C21880701 @default.
- W4287996940 hasConceptScore W4287996940C2776257435 @default.
- W4287996940 hasConceptScore W4287996940C2985139394 @default.
- W4287996940 hasConceptScore W4287996940C31258907 @default.
- W4287996940 hasConceptScore W4287996940C33923547 @default.
- W4287996940 hasConceptScore W4287996940C41008148 @default.
- W4287996940 hasConceptScore W4287996940C50644808 @default.
- W4287996940 hasConceptScore W4287996940C95623464 @default.
- W4287996940 hasLocation W42879969401 @default.
- W4287996940 hasOpenAccess W4287996940 @default.
- W4287996940 hasPrimaryLocation W42879969401 @default.
- W4287996940 hasRelatedWork W11389402 @default.
- W4287996940 hasRelatedWork W13426584 @default.
- W4287996940 hasRelatedWork W4680410 @default.
- W4287996940 hasRelatedWork W5602347 @default.
- W4287996940 hasRelatedWork W6001892 @default.
- W4287996940 hasRelatedWork W6680660 @default.
- W4287996940 hasRelatedWork W8198582 @default.
- W4287996940 hasRelatedWork W8657122 @default.
- W4287996940 hasRelatedWork W8978006 @default.
- W4287996940 hasRelatedWork W2925925 @default.
- W4287996940 isParatext "false" @default.
- W4287996940 isRetracted "false" @default.
- W4287996940 workType "article" @default.