FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3086458417> ?p ?o ?g. }

• W3086458417 endingPage "384" @default.
• W3086458417 startingPage "361" @default.
• W3086458417 abstract "Recently proposed methods for weakly-supervised semantic segmentation have achieved impressive performance in predicting pixel classes despite being trained with only image labels which lack positional information. Because image annotations are cheaper and quicker to generate, weak supervision is more practical than full supervision for training segmentation algorithms. These methods have been predominantly developed to solve the background separation and partial segmentation problems presented by natural scene images and it is unclear whether they can be simply transferred to other domains with different characteristics, such as histopathology and satellite images, and still perform well. This paper evaluates state-of-the-art weakly-supervised semantic segmentation methods on natural scene, histopathology, and satellite image datasets and analyzes how to determine which method is most suitable for a given dataset. Our experiments indicate that histopathology and satellite images present a different set of problems for weakly-supervised semantic segmentation than natural scene images, such as ambiguous boundaries and class co-occurrence. Methods perform well for datasets they were developed on, but tend to perform poorly on other datasets. We present some practical techniques for these methods on unseen datasets and argue that more work is needed for a generalizable approach to weakly-supervised semantic segmentation. Our full code implementation is available on GitHub: https://github.com/lyndonchan/wsss-analysis." @default.
• W3086458417 created "2020-09-21" @default.
• W3086458417 creator A5059152392 @default.
• W3086458417 creator A5073426758 @default.
• W3086458417 creator A5047785348 @default.
• W3086458417 date "2020-09-14" @default.
• W3086458417 modified "2023-10-06" @default.
• W3086458417 title "A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains" @default.
• W3086458417 cites W1495267108 @default.
• W3086458417 cites W1528789833 @default.
• W3086458417 cites W1566579818 @default.
• W3086458417 cites W1783315696 @default.
• W3086458417 cites W1861492603 @default.
• W3086458417 cites W1901129140 @default.
• W3086458417 cites W1903029394 @default.
• W3086458417 cites W1913356549 @default.
• W3086458417 cites W1927251054 @default.
• W3086458417 cites W1937937026 @default.
• W3086458417 cites W1969624577 @default.
• W3086458417 cites W1980038761 @default.
• W3086458417 cites W1995460724 @default.
• W3086458417 cites W2022508996 @default.
• W3086458417 cites W2031489346 @default.
• W3086458417 cites W2090518410 @default.
• W3086458417 cites W2098140880 @default.
• W3086458417 cites W2110243528 @default.
• W3086458417 cites W2122394460 @default.
• W3086458417 cites W2125215748 @default.
• W3086458417 cites W2132031490 @default.
• W3086458417 cites W2144794286 @default.
• W3086458417 cites W2161185676 @default.
• W3086458417 cites W2194775991 @default.
• W3086458417 cites W22040386 @default.
• W3086458417 cites W2221898772 @default.
• W3086458417 cites W2282915343 @default.
• W3086458417 cites W2288892845 @default.
• W3086458417 cites W2294643827 @default.
• W3086458417 cites W2295107390 @default.
• W3086458417 cites W2302302587 @default.
• W3086458417 cites W2306289963 @default.
• W3086458417 cites W2337429362 @default.
• W3086458417 cites W2340897893 @default.
• W3086458417 cites W2342880667 @default.
• W3086458417 cites W2412782625 @default.
• W3086458417 cites W2432020924 @default.
• W3086458417 cites W2435090885 @default.
• W3086458417 cites W2509858278 @default.
• W3086458417 cites W2515717359 @default.
• W3086458417 cites W2516803306 @default.
• W3086458417 cites W2519610629 @default.
• W3086458417 cites W2561196672 @default.
• W3086458417 cites W2565639579 @default.
• W3086458417 cites W2592905743 @default.
• W3086458417 cites W2600144439 @default.
• W3086458417 cites W2605214291 @default.
• W3086458417 cites W2606788270 @default.
• W3086458417 cites W2618999197 @default.
• W3086458417 cites W2737258237 @default.
• W3086458417 cites W2738853914 @default.
• W3086458417 cites W2741609385 @default.
• W3086458417 cites W2781228439 @default.
• W3086458417 cites W2782347622 @default.
• W3086458417 cites W2798376494 @default.
• W3086458417 cites W2799124825 @default.
• W3086458417 cites W2799738340 @default.
• W3086458417 cites W2804199516 @default.
• W3086458417 cites W2892614179 @default.
• W3086458417 cites W2896983355 @default.
• W3086458417 cites W2899319425 @default.
• W3086458417 cites W2901139858 @default.
• W3086458417 cites W2901458284 @default.
• W3086458417 cites W2914568698 @default.
• W3086458417 cites W2914836117 @default.
• W3086458417 cites W2939781831 @default.
• W3086458417 cites W2948885921 @default.
• W3086458417 cites W2955058313 @default.
• W3086458417 cites W2962758679 @default.
• W3086458417 cites W2962858109 @default.
• W3086458417 cites W2962862396 @default.
• W3086458417 cites W2962867364 @default.
• W3086458417 cites W2963311325 @default.
• W3086458417 cites W2963537460 @default.
• W3086458417 cites W2963803174 @default.
• W3086458417 cites W2963934324 @default.
• W3086458417 cites W2964054038 @default.
• W3086458417 cites W2964070329 @default.
• W3086458417 cites W2964309882 @default.
• W3086458417 cites W2969710780 @default.
• W3086458417 cites W2980189057 @default.
• W3086458417 cites W2982507557 @default.
• W3086458417 cites W2982805640 @default.
• W3086458417 cites W3106105822 @default.
• W3086458417 cites W4246070010 @default.
• W3086458417 cites W55768394 @default.
• W3086458417 cites W611457968 @default.
• W3086458417 cites W73112891 @default.
• W3086458417 doi "https://doi.org/10.1007/s11263-020-01373-4" @default.
• W3086458417 hasPublicationYear "2020" @default.

• next