Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313182397> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4313182397 abstract "In this paper, we address the problem of unsupervised domain adaptation where we ask to infer a low target risk classifier, while labeled data are only available from the source domain. Our proposed approach, called DA-OTP, aims to learn a gradual subspace alignment of the source and target domains through Supervised Locality Preserving Projection, so that projected data in the joint low-dimensional latent subspace can be domain-invariant and easily separable. However, this objective can be rather challenging to achieve because of the absence of labeled data in the target domain. To overcome this conundrum, we use an incremental label propagation technique based on optimal transport, which performs selective pseudo-labeling in the target domain. The selected pseudo-labeled target samples are then combined with labeled source samples to learn in a self-training fashion a robust classifier after the incremental subspace alignment. Experiments show the competitiveness of the proposed approach across contemporary state-of-the-art methods over a range of domain adaptation problems. We make our code publicly available. <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> Code is available at: https://github.com/DA-OTP/DA-OTP" @default.
- W4313182397 created "2023-01-06" @default.
- W4313182397 creator A5019338743 @default.
- W4313182397 creator A5023482831 @default.
- W4313182397 creator A5064884942 @default.
- W4313182397 date "2022-07-18" @default.
- W4313182397 modified "2023-10-15" @default.
- W4313182397 title "Incremental Unsupervised Domain Adaptation Through Optimal Transport" @default.
- W4313182397 cites W1594039573 @default.
- W4313182397 cites W2024194293 @default.
- W4313182397 cites W2096943734 @default.
- W4313182397 cites W2194775991 @default.
- W4313182397 cites W2463762378 @default.
- W4313182397 cites W2584886900 @default.
- W4313182397 cites W2616287544 @default.
- W4313182397 cites W2627183927 @default.
- W4313182397 cites W2884771968 @default.
- W4313182397 cites W2963240485 @default.
- W4313182397 cites W2963756240 @default.
- W4313182397 cites W2964934387 @default.
- W4313182397 cites W2996787432 @default.
- W4313182397 cites W3092552955 @default.
- W4313182397 cites W3200946631 @default.
- W4313182397 cites W4206270237 @default.
- W4313182397 cites W4206471589 @default.
- W4313182397 doi "https://doi.org/10.1109/ijcnn55064.2022.9892735" @default.
- W4313182397 hasPublicationYear "2022" @default.
- W4313182397 type Work @default.
- W4313182397 citedByCount "0" @default.
- W4313182397 crossrefType "proceedings-article" @default.
- W4313182397 hasAuthorship W4313182397A5019338743 @default.
- W4313182397 hasAuthorship W4313182397A5023482831 @default.
- W4313182397 hasAuthorship W4313182397A5064884942 @default.
- W4313182397 hasConcept C111919701 @default.
- W4313182397 hasConcept C119857082 @default.
- W4313182397 hasConcept C134306372 @default.
- W4313182397 hasConcept C153180895 @default.
- W4313182397 hasConcept C154945302 @default.
- W4313182397 hasConcept C177264268 @default.
- W4313182397 hasConcept C199360897 @default.
- W4313182397 hasConcept C2776145971 @default.
- W4313182397 hasConcept C2776434776 @default.
- W4313182397 hasConcept C2776760102 @default.
- W4313182397 hasConcept C32834561 @default.
- W4313182397 hasConcept C33923547 @default.
- W4313182397 hasConcept C36503486 @default.
- W4313182397 hasConcept C41008148 @default.
- W4313182397 hasConcept C43126263 @default.
- W4313182397 hasConcept C70710897 @default.
- W4313182397 hasConcept C95623464 @default.
- W4313182397 hasConceptScore W4313182397C111919701 @default.
- W4313182397 hasConceptScore W4313182397C119857082 @default.
- W4313182397 hasConceptScore W4313182397C134306372 @default.
- W4313182397 hasConceptScore W4313182397C153180895 @default.
- W4313182397 hasConceptScore W4313182397C154945302 @default.
- W4313182397 hasConceptScore W4313182397C177264268 @default.
- W4313182397 hasConceptScore W4313182397C199360897 @default.
- W4313182397 hasConceptScore W4313182397C2776145971 @default.
- W4313182397 hasConceptScore W4313182397C2776434776 @default.
- W4313182397 hasConceptScore W4313182397C2776760102 @default.
- W4313182397 hasConceptScore W4313182397C32834561 @default.
- W4313182397 hasConceptScore W4313182397C33923547 @default.
- W4313182397 hasConceptScore W4313182397C36503486 @default.
- W4313182397 hasConceptScore W4313182397C41008148 @default.
- W4313182397 hasConceptScore W4313182397C43126263 @default.
- W4313182397 hasConceptScore W4313182397C70710897 @default.
- W4313182397 hasConceptScore W4313182397C95623464 @default.
- W4313182397 hasLocation W43131823971 @default.
- W4313182397 hasOpenAccess W4313182397 @default.
- W4313182397 hasPrimaryLocation W43131823971 @default.
- W4313182397 hasRelatedWork W2016349419 @default.
- W4313182397 hasRelatedWork W2341113105 @default.
- W4313182397 hasRelatedWork W2998705539 @default.
- W4313182397 hasRelatedWork W3035557009 @default.
- W4313182397 hasRelatedWork W3046182208 @default.
- W4313182397 hasRelatedWork W3047553723 @default.
- W4313182397 hasRelatedWork W4220857334 @default.
- W4313182397 hasRelatedWork W4285121199 @default.
- W4313182397 hasRelatedWork W4313182397 @default.
- W4313182397 hasRelatedWork W98693656 @default.
- W4313182397 isParatext "false" @default.
- W4313182397 isRetracted "false" @default.
- W4313182397 workType "article" @default.