Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286974920> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4286974920 abstract "Tensor networks are efficient factorisations of high-dimensional tensors into a network of lower-order tensors. They have been most commonly used to model entanglement in quantum many-body systems and more recently are witnessing increased applications in supervised machine learning. In this work, we formulate image segmentation in a supervised setting with tensor networks. The key idea is to first lift the pixels in image patches to exponentially high-dimensional feature spaces and using a linear decision hyper-plane to classify the input pixels into foreground and background classes. The high-dimensional linear model itself is approximated using the matrix product state (MPS) tensor network. The MPS is weight-shared between the non-overlapping image patches resulting in our strided tensor network model. The performance of the proposed model is evaluated on three 2D- and one 3D- biomedical imaging datasets. The performance of the proposed tensor network segmentation model is compared with relevant baseline methods. In the 2D experiments, the tensor network model yields competitive performance compared to the baseline methods while being more resource efficient." @default.
- W4286974920 created "2022-07-25" @default.
- W4286974920 creator A5008183217 @default.
- W4286974920 creator A5035269577 @default.
- W4286974920 creator A5061736984 @default.
- W4286974920 creator A5063821969 @default.
- W4286974920 date "2021-09-15" @default.
- W4286974920 modified "2023-10-17" @default.
- W4286974920 title "Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks" @default.
- W4286974920 doi "https://doi.org/10.48550/arxiv.2109.07138" @default.
- W4286974920 hasPublicationYear "2021" @default.
- W4286974920 type Work @default.
- W4286974920 citedByCount "0" @default.
- W4286974920 crossrefType "posted-content" @default.
- W4286974920 hasAuthorship W4286974920A5008183217 @default.
- W4286974920 hasAuthorship W4286974920A5035269577 @default.
- W4286974920 hasAuthorship W4286974920A5061736984 @default.
- W4286974920 hasAuthorship W4286974920A5063821969 @default.
- W4286974920 hasBestOaLocation W42869749201 @default.
- W4286974920 hasConcept C113315163 @default.
- W4286974920 hasConcept C115961682 @default.
- W4286974920 hasConcept C121332964 @default.
- W4286974920 hasConcept C124504099 @default.
- W4286974920 hasConcept C138885662 @default.
- W4286974920 hasConcept C153180895 @default.
- W4286974920 hasConcept C154945302 @default.
- W4286974920 hasConcept C155281189 @default.
- W4286974920 hasConcept C160633673 @default.
- W4286974920 hasConcept C17349429 @default.
- W4286974920 hasConcept C202444582 @default.
- W4286974920 hasConcept C2524010 @default.
- W4286974920 hasConcept C2776401178 @default.
- W4286974920 hasConcept C33923547 @default.
- W4286974920 hasConcept C41008148 @default.
- W4286974920 hasConcept C41895202 @default.
- W4286974920 hasConcept C51255310 @default.
- W4286974920 hasConcept C62520636 @default.
- W4286974920 hasConcept C84114770 @default.
- W4286974920 hasConcept C89600930 @default.
- W4286974920 hasConceptScore W4286974920C113315163 @default.
- W4286974920 hasConceptScore W4286974920C115961682 @default.
- W4286974920 hasConceptScore W4286974920C121332964 @default.
- W4286974920 hasConceptScore W4286974920C124504099 @default.
- W4286974920 hasConceptScore W4286974920C138885662 @default.
- W4286974920 hasConceptScore W4286974920C153180895 @default.
- W4286974920 hasConceptScore W4286974920C154945302 @default.
- W4286974920 hasConceptScore W4286974920C155281189 @default.
- W4286974920 hasConceptScore W4286974920C160633673 @default.
- W4286974920 hasConceptScore W4286974920C17349429 @default.
- W4286974920 hasConceptScore W4286974920C202444582 @default.
- W4286974920 hasConceptScore W4286974920C2524010 @default.
- W4286974920 hasConceptScore W4286974920C2776401178 @default.
- W4286974920 hasConceptScore W4286974920C33923547 @default.
- W4286974920 hasConceptScore W4286974920C41008148 @default.
- W4286974920 hasConceptScore W4286974920C41895202 @default.
- W4286974920 hasConceptScore W4286974920C51255310 @default.
- W4286974920 hasConceptScore W4286974920C62520636 @default.
- W4286974920 hasConceptScore W4286974920C84114770 @default.
- W4286974920 hasConceptScore W4286974920C89600930 @default.
- W4286974920 hasLocation W42869749201 @default.
- W4286974920 hasOpenAccess W4286974920 @default.
- W4286974920 hasPrimaryLocation W42869749201 @default.
- W4286974920 hasRelatedWork W1993357040 @default.
- W4286974920 hasRelatedWork W2027450165 @default.
- W4286974920 hasRelatedWork W2129270445 @default.
- W4286974920 hasRelatedWork W2149860324 @default.
- W4286974920 hasRelatedWork W2151600032 @default.
- W4286974920 hasRelatedWork W2165979125 @default.
- W4286974920 hasRelatedWork W2171960551 @default.
- W4286974920 hasRelatedWork W2507402573 @default.
- W4286974920 hasRelatedWork W2588502955 @default.
- W4286974920 hasRelatedWork W2739874619 @default.
- W4286974920 isParatext "false" @default.
- W4286974920 isRetracted "false" @default.
- W4286974920 workType "article" @default.