Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950483904> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2950483904 abstract "Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this difficulty by presenting a multi-utility learning framework for structured prediction that can learn from training instances with different forms of supervision. We propose a unified technique for inferring the loss functions most suitable for quantifying the consistency of solutions with the given weak annotation. We demonstrate the effectiveness of our framework on the challenging semantic image segmentation problem for which a wide variety of annotations can be used. For instance, the popular training datasets for semantic segmentation are composed of images with hard-to-generate full pixel labellings, as well as images with easy-to-obtain weak annotations, such as bounding boxes around objects, or image-level labels that specify which object categories are present in an image. Experimental evaluation shows that the use of annotation-specific loss functions dramatically improves segmentation accuracy compared to the baseline system where only one type of weak annotation is used." @default.
- W2950483904 created "2019-06-27" @default.
- W2950483904 creator A5013834379 @default.
- W2950483904 creator A5028940329 @default.
- W2950483904 creator A5050994666 @default.
- W2950483904 creator A5059004658 @default.
- W2950483904 date "2014-06-23" @default.
- W2950483904 modified "2023-09-28" @default.
- W2950483904 title "Multi-utility Learning: Structured-output Learning with Multiple Annotation-specific Loss Functions" @default.
- W2950483904 cites W1528789833 @default.
- W2950483904 cites W1536616638 @default.
- W2950483904 cites W1542723449 @default.
- W2950483904 cites W1999478155 @default.
- W2950483904 cites W2007668764 @default.
- W2950483904 cites W2026581312 @default.
- W2950483904 cites W2031248101 @default.
- W2950483904 cites W2064985253 @default.
- W2950483904 cites W2100588357 @default.
- W2950483904 cites W2105842272 @default.
- W2950483904 cites W2106122512 @default.
- W2950483904 cites W2110158442 @default.
- W2950483904 cites W2143516773 @default.
- W2950483904 cites W2147102238 @default.
- W2950483904 cites W2147196093 @default.
- W2950483904 cites W2151103935 @default.
- W2950483904 cites W2158427031 @default.
- W2950483904 cites W2182277027 @default.
- W2950483904 cites W2182705849 @default.
- W2950483904 cites W2533218643 @default.
- W2950483904 cites W2951041490 @default.
- W2950483904 cites W1971410590 @default.
- W2950483904 hasPublicationYear "2014" @default.
- W2950483904 type Work @default.
- W2950483904 sameAs 2950483904 @default.
- W2950483904 citedByCount "0" @default.
- W2950483904 crossrefType "posted-content" @default.
- W2950483904 hasAuthorship W2950483904A5013834379 @default.
- W2950483904 hasAuthorship W2950483904A5028940329 @default.
- W2950483904 hasAuthorship W2950483904A5050994666 @default.
- W2950483904 hasAuthorship W2950483904A5059004658 @default.
- W2950483904 hasConcept C115961682 @default.
- W2950483904 hasConcept C119857082 @default.
- W2950483904 hasConcept C136197465 @default.
- W2950483904 hasConcept C147037132 @default.
- W2950483904 hasConcept C153180895 @default.
- W2950483904 hasConcept C154945302 @default.
- W2950483904 hasConcept C1667742 @default.
- W2950483904 hasConcept C199579030 @default.
- W2950483904 hasConcept C22367795 @default.
- W2950483904 hasConcept C2776321320 @default.
- W2950483904 hasConcept C2776436953 @default.
- W2950483904 hasConcept C2781238097 @default.
- W2950483904 hasConcept C41008148 @default.
- W2950483904 hasConcept C63584917 @default.
- W2950483904 hasConcept C89600930 @default.
- W2950483904 hasConceptScore W2950483904C115961682 @default.
- W2950483904 hasConceptScore W2950483904C119857082 @default.
- W2950483904 hasConceptScore W2950483904C136197465 @default.
- W2950483904 hasConceptScore W2950483904C147037132 @default.
- W2950483904 hasConceptScore W2950483904C153180895 @default.
- W2950483904 hasConceptScore W2950483904C154945302 @default.
- W2950483904 hasConceptScore W2950483904C1667742 @default.
- W2950483904 hasConceptScore W2950483904C199579030 @default.
- W2950483904 hasConceptScore W2950483904C22367795 @default.
- W2950483904 hasConceptScore W2950483904C2776321320 @default.
- W2950483904 hasConceptScore W2950483904C2776436953 @default.
- W2950483904 hasConceptScore W2950483904C2781238097 @default.
- W2950483904 hasConceptScore W2950483904C41008148 @default.
- W2950483904 hasConceptScore W2950483904C63584917 @default.
- W2950483904 hasConceptScore W2950483904C89600930 @default.
- W2950483904 hasOpenAccess W2950483904 @default.
- W2950483904 hasRelatedWork W1600847575 @default.
- W2950483904 hasRelatedWork W2109256565 @default.
- W2950483904 hasRelatedWork W2552369821 @default.
- W2950483904 hasRelatedWork W2770949838 @default.
- W2950483904 hasRelatedWork W2896107389 @default.
- W2950483904 hasRelatedWork W2901667482 @default.
- W2950483904 hasRelatedWork W2963934231 @default.
- W2950483904 hasRelatedWork W2997742385 @default.
- W2950483904 hasRelatedWork W3044881747 @default.
- W2950483904 hasRelatedWork W3049355345 @default.
- W2950483904 hasRelatedWork W3109141632 @default.
- W2950483904 hasRelatedWork W3112016055 @default.
- W2950483904 hasRelatedWork W3134006171 @default.
- W2950483904 hasRelatedWork W3139559957 @default.
- W2950483904 hasRelatedWork W3163811911 @default.
- W2950483904 hasRelatedWork W3164729310 @default.
- W2950483904 hasRelatedWork W3172949220 @default.
- W2950483904 hasRelatedWork W3176777339 @default.
- W2950483904 hasRelatedWork W3200603690 @default.
- W2950483904 hasRelatedWork W3094292185 @default.
- W2950483904 isParatext "false" @default.
- W2950483904 isRetracted "false" @default.
- W2950483904 magId "2950483904" @default.
- W2950483904 workType "article" @default.