Matches in SemOpenAlex for { <https://semopenalex.org/work/W2531897166> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2531897166 endingPage "24" @default.
- W2531897166 startingPage "15" @default.
- W2531897166 abstract "Of late, neural networks and Multiple Instance Learning (MIL) are both attractive topics in the research areas related to Artificial Intelligence. Deep neural networks have achieved great successes in supervised learning problems, and MIL as a typical weakly-supervised learning method is effective for many applications in computer vision, biometrics, natural language processing, and so on. In this article, we revisit Multiple Instance Neural Networks (MINNs) that the neural networks aim at solving the MIL problems. The MINNs perform MIL in an end-to-end manner, which take bags with a various number of instances as input and directly output the labels of bags. All of the parameters in a MINN can be optimized via back-propagation. Besides revisiting the old MINNs, we propose a new type of MINN to learn bag representations, which is different from the existing MINNs that focus on estimating instance label. In addition, recent tricks developed in deep learning have been studied in MINNs; we find deep supervision is effective for learning better bag representations. In the experiments, the proposed MINNs achieve state-of-the-art or competitive performance on several MIL benchmarks. Moreover, it is extremely fast for both testing and training, for example, it takes only 0.0003 s to predict a bag and a few seconds to train on MIL datasets on a moderate CPU." @default.
- W2531897166 created "2016-10-21" @default.
- W2531897166 creator A5032279676 @default.
- W2531897166 creator A5034061393 @default.
- W2531897166 creator A5037191476 @default.
- W2531897166 creator A5039363991 @default.
- W2531897166 creator A5084584527 @default.
- W2531897166 date "2018-02-01" @default.
- W2531897166 modified "2023-10-16" @default.
- W2531897166 title "Revisiting multiple instance neural networks" @default.
- W2531897166 cites W1937059634 @default.
- W2531897166 cites W1966385142 @default.
- W2531897166 cites W2010792435 @default.
- W2531897166 cites W2016589492 @default.
- W2531897166 cites W2064675550 @default.
- W2531897166 cites W2110119381 @default.
- W2531897166 cites W2112796928 @default.
- W2531897166 cites W2136922672 @default.
- W2531897166 cites W2149648623 @default.
- W2531897166 cites W2194775991 @default.
- W2531897166 cites W2248800885 @default.
- W2531897166 cites W2510004850 @default.
- W2531897166 doi "https://doi.org/10.1016/j.patcog.2017.08.026" @default.
- W2531897166 hasPublicationYear "2018" @default.
- W2531897166 type Work @default.
- W2531897166 sameAs 2531897166 @default.
- W2531897166 citedByCount "278" @default.
- W2531897166 countsByYear W25318971662017 @default.
- W2531897166 countsByYear W25318971662018 @default.
- W2531897166 countsByYear W25318971662019 @default.
- W2531897166 countsByYear W25318971662020 @default.
- W2531897166 countsByYear W25318971662021 @default.
- W2531897166 countsByYear W25318971662022 @default.
- W2531897166 countsByYear W25318971662023 @default.
- W2531897166 crossrefType "journal-article" @default.
- W2531897166 hasAuthorship W2531897166A5032279676 @default.
- W2531897166 hasAuthorship W2531897166A5034061393 @default.
- W2531897166 hasAuthorship W2531897166A5037191476 @default.
- W2531897166 hasAuthorship W2531897166A5039363991 @default.
- W2531897166 hasAuthorship W2531897166A5084584527 @default.
- W2531897166 hasBestOaLocation W25318971662 @default.
- W2531897166 hasConcept C108583219 @default.
- W2531897166 hasConcept C119857082 @default.
- W2531897166 hasConcept C120665830 @default.
- W2531897166 hasConcept C121332964 @default.
- W2531897166 hasConcept C147168706 @default.
- W2531897166 hasConcept C154945302 @default.
- W2531897166 hasConcept C192209626 @default.
- W2531897166 hasConcept C2984842247 @default.
- W2531897166 hasConcept C41008148 @default.
- W2531897166 hasConcept C50644808 @default.
- W2531897166 hasConceptScore W2531897166C108583219 @default.
- W2531897166 hasConceptScore W2531897166C119857082 @default.
- W2531897166 hasConceptScore W2531897166C120665830 @default.
- W2531897166 hasConceptScore W2531897166C121332964 @default.
- W2531897166 hasConceptScore W2531897166C147168706 @default.
- W2531897166 hasConceptScore W2531897166C154945302 @default.
- W2531897166 hasConceptScore W2531897166C192209626 @default.
- W2531897166 hasConceptScore W2531897166C2984842247 @default.
- W2531897166 hasConceptScore W2531897166C41008148 @default.
- W2531897166 hasConceptScore W2531897166C50644808 @default.
- W2531897166 hasFunder F4320321001 @default.
- W2531897166 hasFunder F4320334995 @default.
- W2531897166 hasLocation W25318971661 @default.
- W2531897166 hasLocation W25318971662 @default.
- W2531897166 hasLocation W25318971663 @default.
- W2531897166 hasOpenAccess W2531897166 @default.
- W2531897166 hasPrimaryLocation W25318971661 @default.
- W2531897166 hasRelatedWork W2799384463 @default.
- W2531897166 hasRelatedWork W2953061907 @default.
- W2531897166 hasRelatedWork W3000197790 @default.
- W2531897166 hasRelatedWork W3032952384 @default.
- W2531897166 hasRelatedWork W3034302643 @default.
- W2531897166 hasRelatedWork W3193857078 @default.
- W2531897166 hasRelatedWork W3208304128 @default.
- W2531897166 hasRelatedWork W4225394202 @default.
- W2531897166 hasRelatedWork W4298287631 @default.
- W2531897166 hasRelatedWork W4377865163 @default.
- W2531897166 hasVolume "74" @default.
- W2531897166 isParatext "false" @default.
- W2531897166 isRetracted "false" @default.
- W2531897166 magId "2531897166" @default.
- W2531897166 workType "article" @default.