Matches in SemOpenAlex for { <https://semopenalex.org/work/W2915962332> ?p ?o ?g. }
- W2915962332 endingPage "3738" @default.
- W2915962332 startingPage "3728" @default.
- W2915962332 abstract "Inspired by the recent successes of deep architecture, the auto-encoder and its variants have been intensively explored on image clustering and classification tasks by learning effective feature representations. Conventional auto-encoder attempts to uncover the data's intrinsic structure, by constraining the output to be as much identical to the input as possible, which denotes that the hidden representation could faithfully reconstruct the input data. One issue that arises, however, is that such representations might not be optimized for specific tasks, e.g., image classification and clustering, since it compresses not only the discriminative information but also a lot of redundant or even noise within data. In other words, not all hidden units would benefit the specific tasks, while partial units are mainly used to represent the task-irrelevant patterns. In this paper, a general framework named discerning feature supported encoder (DFSE) is proposed, which integrates the auto-encoder and feature selection together into a unified model. Specifically, the feature selection is adapted to learned hidden-layer features to capture the task-relevant ones from the task-irrelevant ones. Meanwhile, the selected hidden units could in turn encode more discriminability only on the selected task-relevant units. To this end, our proposed algorithm can generate more effective image representation by distinguishing the task-relevant features from the task-irrelevant ones. Two scenarios of the experiments on image classification and clustering are conducted to evaluate our algorithm. The experiments on several benchmarks demonstrate that our method can achieve better performance over the state-of-the-art approaches in two scenarios." @default.
- W2915962332 created "2019-03-02" @default.
- W2915962332 creator A5005819096 @default.
- W2915962332 creator A5080534131 @default.
- W2915962332 creator A5083458247 @default.
- W2915962332 date "2019-08-01" @default.
- W2915962332 modified "2023-09-26" @default.
- W2915962332 title "Discerning Feature Supported Encoder for Image Representation" @default.
- W2915962332 cites W140777655 @default.
- W2915962332 cites W1920962657 @default.
- W2915962332 cites W1925417509 @default.
- W2915962332 cites W1937777952 @default.
- W2915962332 cites W1975900269 @default.
- W2915962332 cites W2007588387 @default.
- W2915962332 cites W2011494630 @default.
- W2915962332 cites W2066757459 @default.
- W2915962332 cites W2087107531 @default.
- W2915962332 cites W2097486709 @default.
- W2915962332 cites W2100495367 @default.
- W2915962332 cites W2101267652 @default.
- W2915962332 cites W2121647436 @default.
- W2915962332 cites W2129630294 @default.
- W2915962332 cites W2130949063 @default.
- W2915962332 cites W2139280638 @default.
- W2915962332 cites W2155759509 @default.
- W2915962332 cites W2157785665 @default.
- W2915962332 cites W2166089138 @default.
- W2915962332 cites W2273827415 @default.
- W2915962332 cites W2552765257 @default.
- W2915962332 cites W2767404761 @default.
- W2915962332 cites W3148981562 @default.
- W2915962332 cites W82869218 @default.
- W2915962332 doi "https://doi.org/10.1109/tip.2019.2900646" @default.
- W2915962332 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30802860" @default.
- W2915962332 hasPublicationYear "2019" @default.
- W2915962332 type Work @default.
- W2915962332 sameAs 2915962332 @default.
- W2915962332 citedByCount "5" @default.
- W2915962332 countsByYear W29159623322021 @default.
- W2915962332 countsByYear W29159623322022 @default.
- W2915962332 countsByYear W29159623322023 @default.
- W2915962332 crossrefType "journal-article" @default.
- W2915962332 hasAuthorship W2915962332A5005819096 @default.
- W2915962332 hasAuthorship W2915962332A5080534131 @default.
- W2915962332 hasAuthorship W2915962332A5083458247 @default.
- W2915962332 hasBestOaLocation W29159623321 @default.
- W2915962332 hasConcept C104317684 @default.
- W2915962332 hasConcept C111919701 @default.
- W2915962332 hasConcept C118505674 @default.
- W2915962332 hasConcept C138885662 @default.
- W2915962332 hasConcept C148483581 @default.
- W2915962332 hasConcept C153180895 @default.
- W2915962332 hasConcept C154945302 @default.
- W2915962332 hasConcept C162324750 @default.
- W2915962332 hasConcept C17744445 @default.
- W2915962332 hasConcept C185592680 @default.
- W2915962332 hasConcept C187736073 @default.
- W2915962332 hasConcept C199539241 @default.
- W2915962332 hasConcept C2776359362 @default.
- W2915962332 hasConcept C2776401178 @default.
- W2915962332 hasConcept C2780451532 @default.
- W2915962332 hasConcept C41008148 @default.
- W2915962332 hasConcept C41895202 @default.
- W2915962332 hasConcept C52622490 @default.
- W2915962332 hasConcept C55493867 @default.
- W2915962332 hasConcept C59404180 @default.
- W2915962332 hasConcept C66746571 @default.
- W2915962332 hasConcept C73555534 @default.
- W2915962332 hasConcept C94625758 @default.
- W2915962332 hasConcept C97931131 @default.
- W2915962332 hasConceptScore W2915962332C104317684 @default.
- W2915962332 hasConceptScore W2915962332C111919701 @default.
- W2915962332 hasConceptScore W2915962332C118505674 @default.
- W2915962332 hasConceptScore W2915962332C138885662 @default.
- W2915962332 hasConceptScore W2915962332C148483581 @default.
- W2915962332 hasConceptScore W2915962332C153180895 @default.
- W2915962332 hasConceptScore W2915962332C154945302 @default.
- W2915962332 hasConceptScore W2915962332C162324750 @default.
- W2915962332 hasConceptScore W2915962332C17744445 @default.
- W2915962332 hasConceptScore W2915962332C185592680 @default.
- W2915962332 hasConceptScore W2915962332C187736073 @default.
- W2915962332 hasConceptScore W2915962332C199539241 @default.
- W2915962332 hasConceptScore W2915962332C2776359362 @default.
- W2915962332 hasConceptScore W2915962332C2776401178 @default.
- W2915962332 hasConceptScore W2915962332C2780451532 @default.
- W2915962332 hasConceptScore W2915962332C41008148 @default.
- W2915962332 hasConceptScore W2915962332C41895202 @default.
- W2915962332 hasConceptScore W2915962332C52622490 @default.
- W2915962332 hasConceptScore W2915962332C55493867 @default.
- W2915962332 hasConceptScore W2915962332C59404180 @default.
- W2915962332 hasConceptScore W2915962332C66746571 @default.
- W2915962332 hasConceptScore W2915962332C73555534 @default.
- W2915962332 hasConceptScore W2915962332C94625758 @default.
- W2915962332 hasConceptScore W2915962332C97931131 @default.
- W2915962332 hasFunder F4320306076 @default.
- W2915962332 hasFunder F4320338281 @default.
- W2915962332 hasIssue "8" @default.
- W2915962332 hasLocation W29159623321 @default.