Matches in SemOpenAlex for { <https://semopenalex.org/work/W3164702102> ?p ?o ?g. }
- W3164702102 abstract "Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial training or involve the self-learning that utilizes pseudo labels to conduct supervised training. The former always suffers from the unstable training caused by adversarial training and only focuses on the inter-domain gap that ignores intra-domain knowledge. The latter tends to put overconfident label prediction on wrong categories, which propagates errors to more samples. To solve these problems, we propose a two-stage adaptive semantic segmentation method based on the local Lipschitz constraint that satisfies both domain alignment and domain-specific exploration under a unified principle. In the first stage, we propose the local Lipschitzness regularization as the objective function to align different domains by exploiting intra-domain knowledge, which explores a promising direction for non-adversarial adaptive semantic segmentation. In the second stage, we use the local Lipschitzness regularization to estimate the probability of satisfying Lipschitzness for each pixel, and then dynamically sets the threshold of pseudo labels to conduct self-learning. Such dynamical self-learning effectively avoids the error propagation caused by noisy labels. Optimization in both stages is based on the same principle, i.e., the local Lipschitz constraint, so that the knowledge learned in the first stage can be maintained in the second stage. Further, due to the model-agnostic property, our method can easily adapt to any CNN-based semantic segmentation networks. Experimental results demonstrate the excellent performance of our method on standard benchmarks." @default.
- W3164702102 created "2021-06-07" @default.
- W3164702102 creator A5067244216 @default.
- W3164702102 creator A5091130234 @default.
- W3164702102 date "2021-05-27" @default.
- W3164702102 modified "2023-09-27" @default.
- W3164702102 title "Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint." @default.
- W3164702102 cites W1731081199 @default.
- W3164702102 cites W1901129140 @default.
- W3164702102 cites W1903029394 @default.
- W3164702102 cites W1983320747 @default.
- W3164702102 cites W2059979378 @default.
- W3164702102 cites W2098136027 @default.
- W3164702102 cites W2101210369 @default.
- W3164702102 cites W2113290770 @default.
- W3164702102 cites W2136504847 @default.
- W3164702102 cites W2140234018 @default.
- W3164702102 cites W2165698076 @default.
- W3164702102 cites W2194775991 @default.
- W3164702102 cites W2340897893 @default.
- W3164702102 cites W2412782625 @default.
- W3164702102 cites W2431874326 @default.
- W3164702102 cites W2487365028 @default.
- W3164702102 cites W2560647685 @default.
- W3164702102 cites W2593768305 @default.
- W3164702102 cites W2594718649 @default.
- W3164702102 cites W2600148249 @default.
- W3164702102 cites W2600383743 @default.
- W3164702102 cites W2601686579 @default.
- W3164702102 cites W2630837129 @default.
- W3164702102 cites W2739748921 @default.
- W3164702102 cites W2792767783 @default.
- W3164702102 cites W2799012717 @default.
- W3164702102 cites W2895168809 @default.
- W3164702102 cites W2895281799 @default.
- W3164702102 cites W2944141891 @default.
- W3164702102 cites W2945979290 @default.
- W3164702102 cites W2962687275 @default.
- W3164702102 cites W2962782553 @default.
- W3164702102 cites W2962808524 @default.
- W3164702102 cites W2962970380 @default.
- W3164702102 cites W2963052201 @default.
- W3164702102 cites W2963107255 @default.
- W3164702102 cites W2963449430 @default.
- W3164702102 cites W2963865469 @default.
- W3164702102 cites W2963977471 @default.
- W3164702102 cites W2964159205 @default.
- W3164702102 cites W2964227007 @default.
- W3164702102 cites W2964277612 @default.
- W3164702102 cites W2969893028 @default.
- W3164702102 cites W2978968642 @default.
- W3164702102 cites W2981429991 @default.
- W3164702102 cites W2981540341 @default.
- W3164702102 cites W2981624307 @default.
- W3164702102 cites W2981925632 @default.
- W3164702102 cites W2985406498 @default.
- W3164702102 cites W2985836869 @default.
- W3164702102 cites W2986831462 @default.
- W3164702102 cites W2991327923 @default.
- W3164702102 cites W2998607115 @default.
- W3164702102 cites W2999725795 @default.
- W3164702102 cites W3015522062 @default.
- W3164702102 cites W3034247804 @default.
- W3164702102 cites W3034417116 @default.
- W3164702102 cites W3035160371 @default.
- W3164702102 cites W3102977943 @default.
- W3164702102 cites W3107502112 @default.
- W3164702102 cites W3119635706 @default.
- W3164702102 hasPublicationYear "2021" @default.
- W3164702102 type Work @default.
- W3164702102 sameAs 3164702102 @default.
- W3164702102 citedByCount "0" @default.
- W3164702102 crossrefType "posted-content" @default.
- W3164702102 hasAuthorship W3164702102A5067244216 @default.
- W3164702102 hasAuthorship W3164702102A5091130234 @default.
- W3164702102 hasConcept C11413529 @default.
- W3164702102 hasConcept C119857082 @default.
- W3164702102 hasConcept C134306372 @default.
- W3164702102 hasConcept C153180895 @default.
- W3164702102 hasConcept C154945302 @default.
- W3164702102 hasConcept C22324862 @default.
- W3164702102 hasConcept C2524010 @default.
- W3164702102 hasConcept C2776036281 @default.
- W3164702102 hasConcept C2776135515 @default.
- W3164702102 hasConcept C33923547 @default.
- W3164702102 hasConcept C36503486 @default.
- W3164702102 hasConcept C37736160 @default.
- W3164702102 hasConcept C41008148 @default.
- W3164702102 hasConcept C89600930 @default.
- W3164702102 hasConceptScore W3164702102C11413529 @default.
- W3164702102 hasConceptScore W3164702102C119857082 @default.
- W3164702102 hasConceptScore W3164702102C134306372 @default.
- W3164702102 hasConceptScore W3164702102C153180895 @default.
- W3164702102 hasConceptScore W3164702102C154945302 @default.
- W3164702102 hasConceptScore W3164702102C22324862 @default.
- W3164702102 hasConceptScore W3164702102C2524010 @default.
- W3164702102 hasConceptScore W3164702102C2776036281 @default.
- W3164702102 hasConceptScore W3164702102C2776135515 @default.
- W3164702102 hasConceptScore W3164702102C33923547 @default.
- W3164702102 hasConceptScore W3164702102C36503486 @default.