Publicación:
SALIENCY DETECTION FROM SUBITIZING PROCESSING

Vista sencilla de ítem
dc.creatorCAROLA ANDREA FIGUEROA FLORES
dc.date2023
dc.date.accessioned2025-01-10T15:35:29Z
dc.date.available2025-01-10T15:35:29Z
dc.date.issued2023
dc.description.abstractMOST OF THE SALIENCY METHODS ARE EVALUATED FOR THEIR ABILITY TO GENERATE SALIENCY MAPS, AND NOT FOR THEIR FUNCTIONALITY IN A COMPLETE VISION PIPELINE, FOR INSTANCE, IMAGE CLASSIFICATION OR SALIENT OBJECT SUBITIZING. IN THIS WORK, WE INTRODUCE SALIENCY SUBITIZING AS THE WEAK SUPERVISION. THIS TASK IS INSPIRED BY THE ABILITY OF PEOPLE TO QUICKLY AND ACCURATELY IDENTIFY THE NUMBER OF ITEMS WITHIN THE SUBITIZING RANGE (E.G., 1 TO 4 DIFFERENT TYPES OF THINGS). THIS MEANS THAT THE SUBITIZING INFORMATION WILL TELL US THE NUMBER OF FEATURED OBJECTS IN A GIVEN IMAGE. TO THIS END, WE PROPOSE A SALIENCY SUBITIZING PROCESS (SSP) AS A FIRST APPROXIMATION TO LEARN SALIENCY DETECTION, WITHOUT THE NEED FOR ANY UNSUPERVISED METHODS OR SOME RANDOM SEEDS. WE CONDUCT EXTENSIVE EXPERIMENTS ON TWO BENCHMARK DATASETS (TORONTO AND SID4VAM). THE EXPERIMENTAL RESULTS SHOW THAT OUR METHOD OUTPERFORMS OTHER WEAKLY SUPERVISED METHODS AND EVEN PERFORMS COMPARABLE TO SOME FULLY SUPERVISED METHODS AS A FIRST APPROXIMATION.
dc.formatapplication/pdf
dc.identifier.doi10.5772/intechopen.108552
dc.identifier.urihttps://repositorio.ubiobio.cl/handle/123456789/12735
dc.languagespa
dc.publisherVISION SENSORS RECENT ADVANCE (INTECHOPEN)
dc.relation.uri10.5772/intechopen.108552
dc.rightsPUBLICADA
dc.subjectsubitizing
dc.subjectsaliency
dc.subjectprediction
dc.subjectobject recognition
dc.subjectneural
dc.subjectnetwork
dc.subjectdeep learning and convolutional
dc.titleSALIENCY DETECTION FROM SUBITIZING PROCESSING
dc.typeCAPÍTULO DE LIBRO
dspace.entity.typePublication
ubb.EstadoPUBLICADA
ubb.Otra ReparticionDEPARTAMENTO DE CIENCIAS DE LA COMPUTACION Y TECNOLOGIA DE LA INFORMACION.
ubb.SedeCHILLÁN
Archivos
Colecciones
Libros y capítulos de libro