FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907118596> ?p ?o ?g. }

• W2907118596 abstract "During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving and augmented reality. However, to train CNNs requires a considerable amount of data, which is difficult to collect and laborious to annotate. Recent advances in computer graphics make it possible to train CNNs on photo-realistic synthetic imagery with computer-generated annotations. Despite this, the domain mismatch between the real images and the synthetic data hinders the models' performance. Hence, we propose a curriculum-style learning approach to minimizing the domain gap in urban scene semantic segmentation. The curriculum domain adaptation solves easy tasks first to infer necessary properties about the target domain; in particular, the first task is to learn global label distributions over images and local distributions over landmark superpixels. These are easy to estimate because images of urban scenes have strong idiosyncrasies (e.g., the size and spatial relations of buildings, streets, cars, etc.). We then train a segmentation network, while regularizing its predictions in the target domain to follow those inferred properties. In experiments, our method outperforms the baselines on two datasets and two backbone networks. We also report extensive ablation studies about our approach." @default.
• W2907118596 created "2019-01-11" @default.
• W2907118596 creator A5017319429 @default.
• W2907118596 creator A5022802322 @default.
• W2907118596 creator A5041472400 @default.
• W2907118596 creator A5076117344 @default.
• W2907118596 date "2018-12-24" @default.
• W2907118596 modified "2023-09-30" @default.
• W2907118596 title "A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes" @default.
• W2907118596 cites W123476658 @default.
• W2907118596 cites W1542723449 @default.
• W2907118596 cites W1565327149 @default.
• W2907118596 cites W1606858007 @default.
• W2907118596 cites W1660353176 @default.
• W2907118596 cites W1686810756 @default.
• W2907118596 cites W1722318740 @default.
• W2907118596 cites W1745334888 @default.
• W2907118596 cites W1783315696 @default.
• W2907118596 cites W1821462560 @default.
• W2907118596 cites W1852255964 @default.
• W2907118596 cites W1861492603 @default.
• W2907118596 cites W1903029394 @default.
• W2907118596 cites W1910772337 @default.
• W2907118596 cites W1913356549 @default.
• W2907118596 cites W1938929646 @default.
• W2907118596 cites W1945608308 @default.
• W2907118596 cites W1982696459 @default.
• W2907118596 cites W1992455269 @default.
• W2907118596 cites W2031342017 @default.
• W2907118596 cites W2033547469 @default.
• W2907118596 cites W2037227137 @default.
• W2907118596 cites W2083544878 @default.
• W2907118596 cites W2090923791 @default.
• W2907118596 cites W2100001370 @default.
• W2907118596 cites W2100588357 @default.
• W2907118596 cites W2104068492 @default.
• W2907118596 cites W2111963040 @default.
• W2907118596 cites W2112796928 @default.
• W2907118596 cites W2115403315 @default.
• W2907118596 cites W2115579991 @default.
• W2907118596 cites W2125215748 @default.
• W2907118596 cites W2128053425 @default.
• W2907118596 cites W2147238549 @default.
• W2907118596 cites W2149466042 @default.
• W2907118596 cites W2151103935 @default.
• W2907118596 cites W2153423793 @default.
• W2907118596 cites W2154368244 @default.
• W2907118596 cites W2158815628 @default.
• W2907118596 cites W2159291411 @default.
• W2907118596 cites W2163605009 @default.
• W2907118596 cites W2165698076 @default.
• W2907118596 cites W2171943915 @default.
• W2907118596 cites W2186827065 @default.
• W2907118596 cites W2212660284 @default.
• W2907118596 cites W2214409633 @default.
• W2907118596 cites W2216125271 @default.
• W2907118596 cites W2221898772 @default.
• W2907118596 cites W2257483379 @default.
• W2907118596 cites W2274287116 @default.
• W2907118596 cites W2294370754 @default.
• W2907118596 cites W2296073425 @default.
• W2907118596 cites W2311110368 @default.
• W2907118596 cites W2340897893 @default.
• W2907118596 cites W2384495648 @default.
• W2907118596 cites W2397830550 @default.
• W2907118596 cites W2412782625 @default.
• W2907118596 cites W2431874326 @default.
• W2907118596 cites W2487365028 @default.
• W2907118596 cites W2492904644 @default.
• W2907118596 cites W2560023338 @default.
• W2907118596 cites W2562192638 @default.
• W2907118596 cites W2590953969 @default.
• W2907118596 cites W2609077090 @default.
• W2907118596 cites W2613546176 @default.
• W2907118596 cites W2615547864 @default.
• W2907118596 cites W2739759330 @default.
• W2907118596 cites W2766897166 @default.
• W2907118596 cites W2769672616 @default.
• W2907118596 cites W2781228439 @default.
• W2907118596 cites W2798964604 @default.
• W2907118596 cites W2884366600 @default.
• W2907118596 cites W2889900721 @default.
• W2907118596 cites W2891728491 @default.
• W2907118596 cites W2895168809 @default.
• W2907118596 cites W2895281799 @default.
• W2907118596 cites W2949212125 @default.
• W2907118596 cites W2949907962 @default.
• W2907118596 cites W2950420147 @default.
• W2907118596 cites W2951103356 @default.
• W2907118596 cites W2952147788 @default.
• W2907118596 cites W2952295876 @default.
• W2907118596 cites W2952542181 @default.
• W2907118596 cites W2962687275 @default.
• W2907118596 cites W2962793481 @default.
• W2907118596 cites W2962808524 @default.
• W2907118596 cites W2962850830 @default.
• W2907118596 cites W2962867954 @default.
• W2907118596 cites W2962976523 @default.
• W2907118596 cites W2963107255 @default.
• W2907118596 cites W2963120918 @default.

• next