FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176692018> ?p ?o ?g. }

• W3176692018 abstract "Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which operates on the low-level information intrinsic to an image. In this work, we utilize higher-level information from the behavior of a trained object detector, by seeking the smallest areas of the image from which the object detector produces almost the same result as it does from the whole image. These areas constitute a bounding-box attribution map (BBAM), which identifies the target object in its bounding box and thus serves as pseudo ground-truth for weakly supervised semantic and instance segmentation. This approach significantly outperforms recent comparable techniques on both the PASCAL VOC and MS COCO benchmarks in weakly supervised semantic and instance segmentation. In addition, we provide a detailed analysis of our method, offering deeper insight into the behavior of the BBAM." @default.
• W3176692018 created "2021-07-05" @default.
• W3176692018 creator A5001243382 @default.
• W3176692018 creator A5011743659 @default.
• W3176692018 creator A5052589445 @default.
• W3176692018 creator A5086877012 @default.
• W3176692018 date "2021-06-01" @default.
• W3176692018 modified "2023-10-10" @default.
• W3176692018 title "BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation" @default.
• W3176692018 cites W1495267108 @default.
• W3176692018 cites W1536680647 @default.
• W3176692018 cites W1849277567 @default.
• W3176692018 cites W1861492603 @default.
• W3176692018 cites W2031489346 @default.
• W3176692018 cites W2108598243 @default.
• W3176692018 cites W2124351162 @default.
• W3176692018 cites W2144794286 @default.
• W3176692018 cites W2161236525 @default.
• W3176692018 cites W2168804568 @default.
• W3176692018 cites W2216125271 @default.
• W3176692018 cites W2221898772 @default.
• W3176692018 cites W2295107390 @default.
• W3176692018 cites W2412782625 @default.
• W3176692018 cites W2552414813 @default.
• W3176692018 cites W2600144439 @default.
• W3176692018 cites W2613718673 @default.
• W3176692018 cites W2626639386 @default.
• W3176692018 cites W2795148578 @default.
• W3176692018 cites W2795574923 @default.
• W3176692018 cites W2795628365 @default.
• W3176692018 cites W2798683932 @default.
• W3176692018 cites W2799124825 @default.
• W3176692018 cites W2805977310 @default.
• W3176692018 cites W2884822772 @default.
• W3176692018 cites W2894666165 @default.
• W3176692018 cites W2899771611 @default.
• W3176692018 cites W2905110727 @default.
• W3176692018 cites W2932869281 @default.
• W3176692018 cites W2940181122 @default.
• W3176692018 cites W2949088214 @default.
• W3176692018 cites W2950373644 @default.
• W3176692018 cites W2951746655 @default.
• W3176692018 cites W2952529067 @default.
• W3176692018 cites W2954087924 @default.
• W3176692018 cites W2954400107 @default.
• W3176692018 cites W2955278847 @default.
• W3176692018 cites W2956648669 @default.
• W3176692018 cites W2963037989 @default.
• W3176692018 cites W2963207607 @default.
• W3176692018 cites W2963346885 @default.
• W3176692018 cites W2963351448 @default.
• W3176692018 cites W2963715038 @default.
• W3176692018 cites W2964121744 @default.
• W3176692018 cites W2965207973 @default.
• W3176692018 cites W2967958187 @default.
• W3176692018 cites W2970005358 @default.
• W3176692018 cites W2970727289 @default.
• W3176692018 cites W2970856480 @default.
• W3176692018 cites W2978240584 @default.
• W3176692018 cites W2980189057 @default.
• W3176692018 cites W2982093251 @default.
• W3176692018 cites W2986384370 @default.
• W3176692018 cites W2988157455 @default.
• W3176692018 cites W2991083560 @default.
• W3176692018 cites W2997076984 @default.
• W3176692018 cites W2997851315 @default.
• W3176692018 cites W3003507346 @default.
• W3176692018 cites W3082755608 @default.
• W3176692018 cites W3085685449 @default.
• W3176692018 cites W3101609372 @default.
• W3176692018 cites W3106250896 @default.
• W3176692018 cites W3107653507 @default.
• W3176692018 cites W3109073404 @default.
• W3176692018 cites W3119344692 @default.
• W3176692018 cites W3177958285 @default.
• W3176692018 cites W611457968 @default.
• W3176692018 doi "https://doi.org/10.1109/cvpr46437.2021.00267" @default.
• W3176692018 hasPublicationYear "2021" @default.
• W3176692018 type Work @default.
• W3176692018 sameAs 3176692018 @default.
• W3176692018 citedByCount "58" @default.
• W3176692018 countsByYear W31766920182021 @default.
• W3176692018 countsByYear W31766920182022 @default.
• W3176692018 countsByYear W31766920182023 @default.
• W3176692018 crossrefType "proceedings-article" @default.
• W3176692018 hasAuthorship W3176692018A5001243382 @default.
• W3176692018 hasAuthorship W3176692018A5011743659 @default.
• W3176692018 hasAuthorship W3176692018A5052589445 @default.
• W3176692018 hasAuthorship W3176692018A5086877012 @default.
• W3176692018 hasBestOaLocation W31766920182 @default.
• W3176692018 hasConcept C115961682 @default.
• W3176692018 hasConcept C124504099 @default.
• W3176692018 hasConcept C146849305 @default.
• W3176692018 hasConcept C147037132 @default.
• W3176692018 hasConcept C153180895 @default.
• W3176692018 hasConcept C154945302 @default.
• W3176692018 hasConcept C160633673 @default.
• W3176692018 hasConcept C199360897 @default.
• W3176692018 hasConcept C2776151529 @default.
• W3176692018 hasConcept C2781238097 @default.

• next