Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083376489> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3083376489 abstract "Multiple Instance Learning (MIL) involves predicting a single label for a bag of instances, given positive or negative labels at bag-level, without accessing to label for each instance in the training phase. Since a positive bag contains both positive and negative instances, it is often required to detect positive instances (key instances) when a set of instances is categorized as a positive bag. The attention-based deep MIL model is a recent advance in both bag-level classification and key instance detection (KID). However, if the positive and negative instances in a positive bag are not clearly distinguishable, the attention-based deep MIL model has limited KID performance as the attention scores are skewed to few positive instances. In this paper, we present a method to improve the attention-based deep MIL model in the task of KID. The main idea is to use the neural network inversion to find which instances made contribution to the bag-level prediction produced by the trained MIL model. Moreover, we incorporate a sparseness constraint into the neural network inversion, leading to the sparse network inversion which is solved by the proximal gradient method. Numerical experiments on an MNIST-based image MIL dataset and two real-world histopathology datasets verify the validity of our method, demonstrating the KID performance is significantly improved while the performance of bag-level prediction is maintained." @default.
- W3083376489 created "2020-09-11" @default.
- W3083376489 creator A5000943286 @default.
- W3083376489 creator A5021591715 @default.
- W3083376489 creator A5045521125 @default.
- W3083376489 creator A5066589962 @default.
- W3083376489 date "2020-09-07" @default.
- W3083376489 modified "2023-10-11" @default.
- W3083376489 title "Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning" @default.
- W3083376489 cites W1546047689 @default.
- W3083376489 cites W2010792435 @default.
- W3083376489 cites W2029231546 @default.
- W3083376489 cites W2077437848 @default.
- W3083376489 cites W2096331886 @default.
- W3083376489 cites W2100556411 @default.
- W3083376489 cites W2108745803 @default.
- W3083376489 cites W2110119381 @default.
- W3083376489 cites W2112796928 @default.
- W3083376489 cites W2115672776 @default.
- W3083376489 cites W2133288557 @default.
- W3083376489 cites W2154318594 @default.
- W3083376489 cites W2170356277 @default.
- W3083376489 cites W2312404985 @default.
- W3083376489 cites W2404780394 @default.
- W3083376489 cites W24402856 @default.
- W3083376489 cites W2523246573 @default.
- W3083376489 cites W2531897166 @default.
- W3083376489 cites W2533452169 @default.
- W3083376489 cites W2964069537 @default.
- W3083376489 cites W2964121744 @default.
- W3083376489 cites W3002641258 @default.
- W3083376489 doi "https://doi.org/10.48550/arxiv.2009.02909" @default.
- W3083376489 hasPublicationYear "2020" @default.
- W3083376489 type Work @default.
- W3083376489 sameAs 3083376489 @default.
- W3083376489 citedByCount "0" @default.
- W3083376489 crossrefType "posted-content" @default.
- W3083376489 hasAuthorship W3083376489A5000943286 @default.
- W3083376489 hasAuthorship W3083376489A5021591715 @default.
- W3083376489 hasAuthorship W3083376489A5045521125 @default.
- W3083376489 hasAuthorship W3083376489A5066589962 @default.
- W3083376489 hasBestOaLocation W30833764891 @default.
- W3083376489 hasConcept C108583219 @default.
- W3083376489 hasConcept C109007969 @default.
- W3083376489 hasConcept C119857082 @default.
- W3083376489 hasConcept C124101348 @default.
- W3083376489 hasConcept C151730666 @default.
- W3083376489 hasConcept C153180895 @default.
- W3083376489 hasConcept C154945302 @default.
- W3083376489 hasConcept C1893757 @default.
- W3083376489 hasConcept C190502265 @default.
- W3083376489 hasConcept C26517878 @default.
- W3083376489 hasConcept C38652104 @default.
- W3083376489 hasConcept C41008148 @default.
- W3083376489 hasConcept C50644808 @default.
- W3083376489 hasConcept C86803240 @default.
- W3083376489 hasConceptScore W3083376489C108583219 @default.
- W3083376489 hasConceptScore W3083376489C109007969 @default.
- W3083376489 hasConceptScore W3083376489C119857082 @default.
- W3083376489 hasConceptScore W3083376489C124101348 @default.
- W3083376489 hasConceptScore W3083376489C151730666 @default.
- W3083376489 hasConceptScore W3083376489C153180895 @default.
- W3083376489 hasConceptScore W3083376489C154945302 @default.
- W3083376489 hasConceptScore W3083376489C1893757 @default.
- W3083376489 hasConceptScore W3083376489C190502265 @default.
- W3083376489 hasConceptScore W3083376489C26517878 @default.
- W3083376489 hasConceptScore W3083376489C38652104 @default.
- W3083376489 hasConceptScore W3083376489C41008148 @default.
- W3083376489 hasConceptScore W3083376489C50644808 @default.
- W3083376489 hasConceptScore W3083376489C86803240 @default.
- W3083376489 hasLocation W30833764891 @default.
- W3083376489 hasOpenAccess W3083376489 @default.
- W3083376489 hasPrimaryLocation W30833764891 @default.
- W3083376489 hasRelatedWork W2167735388 @default.
- W3083376489 hasRelatedWork W2248239756 @default.
- W3083376489 hasRelatedWork W2597787948 @default.
- W3083376489 hasRelatedWork W2787767549 @default.
- W3083376489 hasRelatedWork W2889587233 @default.
- W3083376489 hasRelatedWork W2904372345 @default.
- W3083376489 hasRelatedWork W2951786554 @default.
- W3083376489 hasRelatedWork W2963510064 @default.
- W3083376489 hasRelatedWork W3186840088 @default.
- W3083376489 hasRelatedWork W4287064118 @default.
- W3083376489 isParatext "false" @default.
- W3083376489 isRetracted "false" @default.
- W3083376489 magId "3083376489" @default.
- W3083376489 workType "article" @default.