Object Detection On Coco 2017

mAP

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif

Nom du modèle	mAP
unireplknet-a-universal-perception-large	54.3
biformer-vision-transformer-with-bi-level	48.6
stochastic-subsampling-with-average-pooling	-
paint-transformer-feed-forward-neural	-
maxvit-multi-axis-vision-transformer	-
yolo-drone-airborne-real-time-detection-of	35.45
unireplknet-a-universal-perception-large	51.7
unireplknet-a-universal-perception-large	54.8
dat-spatially-dynamic-vision-transformer-with	-
debiformer-vision-transformer-with-deformable	48.5
maxvit-multi-axis-vision-transformer	-
mixmim-mixed-and-masked-image-modeling-for	52.2
on-the-ideal-number-of-groups-for-isometric	-
biformer-vision-transformer-with-bi-level	47.8
unireplknet-a-universal-perception-large	53
debiformer-vision-transformer-with-deformable	47.5
dat-spatially-dynamic-vision-transformer-with	-
benchmark-for-generic-product-detection-a	-
unireplknet-a-universal-perception-large	56.4
debiformer-vision-transformer-with-deformable	47.1
debiformer-vision-transformer-with-deformable	45.6
maxvit-multi-axis-vision-transformer	-
mixmim-mixed-and-masked-image-modeling-for	54.1
unireplknet-a-universal-perception-large	55.8