Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987564546> ?p ?o ?g. }
- W2987564546 abstract "Although deep CNNs have brought significant improvement to image saliency detection, most CNN based models are sensitive to distortion such as compression and noise. In this paper, we propose an end-to-end generic salient object segmentation model called Metric Expression Network (MEnet) to deal with saliency detection with the tolerance of distortion. Within MEnet, a new topological metric space is constructed, whose implicit metric is determined by the deep network. As a result, we manage to group all the pixels in the observed image semantically within this latent space into two regions: a salient region and a non-salient region. With this architecture, all feature extractions are carried out at the pixel level, enabling fine granularity of output boundaries of the salient objects. What's more, we try to give a general analysis for the noise robustness of the network in the sense of Lipschitz and Jacobian literature. Experiments demonstrate that robust salient maps facilitating object segmentation can be generated by the proposed metric. Tests on several public benchmarks show that MEnet has achieved desirable performance. Furthermore, by direct computation and measuring the robustness, the proposed method outperforms previous CNN-based methods on distorted inputs." @default.
- W2987564546 created "2019-11-22" @default.
- W2987564546 creator A5005221942 @default.
- W2987564546 creator A5009351219 @default.
- W2987564546 creator A5025614619 @default.
- W2987564546 creator A5040162395 @default.
- W2987564546 creator A5053730462 @default.
- W2987564546 creator A5063481044 @default.
- W2987564546 creator A5088676221 @default.
- W2987564546 date "2018-05-15" @default.
- W2987564546 modified "2023-09-26" @default.
- W2987564546 title "Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation" @default.
- W2987564546 cites W1492747439 @default.
- W2987564546 cites W1538842650 @default.
- W2987564546 cites W1588168368 @default.
- W2987564546 cites W1836465849 @default.
- W2987564546 cites W1894057436 @default.
- W2987564546 cites W1901129140 @default.
- W2987564546 cites W1903029394 @default.
- W2987564546 cites W1942214758 @default.
- W2987564546 cites W1947031653 @default.
- W2987564546 cites W1948751323 @default.
- W2987564546 cites W1950117310 @default.
- W2987564546 cites W1982075130 @default.
- W2987564546 cites W1996326832 @default.
- W2987564546 cites W2002781701 @default.
- W2987564546 cites W2023240564 @default.
- W2987564546 cites W2028327943 @default.
- W2987564546 cites W2037954058 @default.
- W2987564546 cites W2039313011 @default.
- W2987564546 cites W2045775567 @default.
- W2987564546 cites W2055180303 @default.
- W2987564546 cites W2068042582 @default.
- W2987564546 cites W2076434944 @default.
- W2987564546 cites W2091632079 @default.
- W2987564546 cites W2100470808 @default.
- W2987564546 cites W2102605133 @default.
- W2987564546 cites W2109824782 @default.
- W2987564546 cites W2112796928 @default.
- W2987564546 cites W2121927366 @default.
- W2987564546 cites W2128340050 @default.
- W2987564546 cites W2135442311 @default.
- W2987564546 cites W2155893237 @default.
- W2987564546 cites W2161236525 @default.
- W2987564546 cites W2169632643 @default.
- W2987564546 cites W2293332611 @default.
- W2987564546 cites W2338972621 @default.
- W2987564546 cites W2461475918 @default.
- W2987564546 cites W2509486428 @default.
- W2987564546 cites W2527419008 @default.
- W2987564546 cites W2605161420 @default.
- W2987564546 cites W2744613561 @default.
- W2987564546 cites W2748583036 @default.
- W2987564546 cites W2780708736 @default.
- W2987564546 cites W2963032190 @default.
- W2987564546 cites W2963881378 @default.
- W2987564546 cites W2963906836 @default.
- W2987564546 cites W3106250896 @default.
- W2987564546 doi "https://doi.org/10.48550/arxiv.1805.05638" @default.
- W2987564546 hasPublicationYear "2018" @default.
- W2987564546 type Work @default.
- W2987564546 sameAs 2987564546 @default.
- W2987564546 citedByCount "1" @default.
- W2987564546 countsByYear W29875645462019 @default.
- W2987564546 crossrefType "posted-content" @default.
- W2987564546 hasAuthorship W2987564546A5005221942 @default.
- W2987564546 hasAuthorship W2987564546A5009351219 @default.
- W2987564546 hasAuthorship W2987564546A5025614619 @default.
- W2987564546 hasAuthorship W2987564546A5040162395 @default.
- W2987564546 hasAuthorship W2987564546A5053730462 @default.
- W2987564546 hasAuthorship W2987564546A5063481044 @default.
- W2987564546 hasAuthorship W2987564546A5088676221 @default.
- W2987564546 hasBestOaLocation W29875645461 @default.
- W2987564546 hasConcept C104317684 @default.
- W2987564546 hasConcept C134306372 @default.
- W2987564546 hasConcept C153180895 @default.
- W2987564546 hasConcept C154945302 @default.
- W2987564546 hasConcept C160633673 @default.
- W2987564546 hasConcept C162324750 @default.
- W2987564546 hasConcept C176217482 @default.
- W2987564546 hasConcept C185592680 @default.
- W2987564546 hasConcept C21547014 @default.
- W2987564546 hasConcept C22324862 @default.
- W2987564546 hasConcept C2780719617 @default.
- W2987564546 hasConcept C31972630 @default.
- W2987564546 hasConcept C33923547 @default.
- W2987564546 hasConcept C41008148 @default.
- W2987564546 hasConcept C55493867 @default.
- W2987564546 hasConcept C63479239 @default.
- W2987564546 hasConcept C89600930 @default.
- W2987564546 hasConceptScore W2987564546C104317684 @default.
- W2987564546 hasConceptScore W2987564546C134306372 @default.
- W2987564546 hasConceptScore W2987564546C153180895 @default.
- W2987564546 hasConceptScore W2987564546C154945302 @default.
- W2987564546 hasConceptScore W2987564546C160633673 @default.
- W2987564546 hasConceptScore W2987564546C162324750 @default.
- W2987564546 hasConceptScore W2987564546C176217482 @default.
- W2987564546 hasConceptScore W2987564546C185592680 @default.
- W2987564546 hasConceptScore W2987564546C21547014 @default.
- W2987564546 hasConceptScore W2987564546C22324862 @default.