Publicación:
HALLUCINATING SALIENCY MAPS FOR FINE-GRAINED IMAGE CLASSIFICATION FOR LIMITED DATA DOMAINS

Vista sencilla de ítem
dc.creatorCAROLA ANDREA FIGUEROA FLORES
dc.date2021
dc.date.accessioned2025-01-10T15:20:49Z
dc.date.available2025-01-10T15:20:49Z
dc.date.issued2021
dc.description.abstractMOST OF THE SALIENCY METHODS ARE EVALUATED ON THEIRABILITY TO GENERATE SALIENCY MAPS, AND NOT ON THEIR FUNCTIONALITY INA COMPLETE VISION PIPELINE, LIKE FOR INSTANCE, IMAGE CLASSI?CATION.IN THE CURRENT PAPER, WE PROPOSE AN APPROACH WHICH DOES NOTREQUIRE EXPLICIT SALIENCY MAPS TO IMPROVE IMAGE CLASSI?CATION,BUT THEY ARE LEARNED IMPLICITELY, DURING THE TRAINING OF AN END-TO-END IMAGE CLASSI?CATION TASK. WE SHOW THAT OUR APPROACHOBTAINS SIMILAR RESULTS AS THE CASE WHEN THE SALIENCY MAPSARE PROVIDED EXPLICITELY. COMBINING RGB DATA WITH SALIENCYMAPS REPRESENTS A SIGNI?CANT ADVANTAGE FOR OBJECT RECOGNITION,ESPECIALLY FOR THE CASE WHEN TRAINING DATA IS LIMITED. WE VALIDATEOUR METHOD ON SEVERAL DATASETS FOR ?NE-GRAINED CLASSI?CATIONTASKS (FLOWERS, BIRDS AND CARS). IN ADDITION, WE SHOW THAT OURSALIENCY ESTIMATION METHOD, WHICH IS TRAINED WITHOUT ANY SALIENCYGROUNDTRUTH DATA, OBTAINS COMPETITIVE RESULTS ON REAL IMAGESALIENCY BENCHMARK (TORONTO), AND OUTPERFORMS DEEP SALIENCYMODELS WITH SYNTHETIC IMAGES (SID4VAM).
dc.formatapplication/pdf
dc.identifier.doi10.48550/arXiv.2007.12562
dc.identifier.urihttps://repositorio.ubiobio.cl/handle/123456789/11580
dc.languagespa
dc.publisherIN PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS
dc.relation.uri10.48550/arXiv.2007.12562
dc.rightsPUBLICADA
dc.titleHALLUCINATING SALIENCY MAPS FOR FINE-GRAINED IMAGE CLASSIFICATION FOR LIMITED DATA DOMAINS
dc.typeARTÍCULO
dspace.entity.typePublication
ubb.EstadoPUBLICADA
ubb.Otra ReparticionDEPARTAMENTO DE CIENCIAS DE LA COMPUTACION Y TECNOLOGIA DE LA INFORMACION.
ubb.SedeCHILLÁN
Archivos
Colecciones
Artículos científicos