HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋컨퍼런스백과사전SOTALLM 모델
전체 검색
소개
HyperAI초신경

Instance Segmentation On Coco Minival

평가 지표

APL
APM
APS
mask AP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표
모델 이름APLAPMAPSmask AP
x-volution-on-the-unification-of-convolution53.14019.237.2
improved-multiscale-vision-transformers-for---50.5
xcit-cross-covariance-image-transformers---43.7
internimage-exploring-large-scale-vision---44.5
bottleneck-transformers-for-visual---40.7
queryinst-parallelly-supervised-mask-query68.352.630.848.9
detrs-with-collaborative-hybrid-assignments74.659.738.956.6
eva-exploring-the-limits-of-masked-visual72.058.437.655.0
cbnetv2-a-composite-backbone-network---51.8
res2net-a-new-multi-scale-backbone53.737.915.735.6
swin-transformer-hierarchical-vision---50.4
resnest-split-attention-networks---46.25
vision-transformer-adapter-for-dense---52.2
elsa-enhanced-local-self-attention-for-vision---44.4
exploring-plain-vision-transformer-backbones---52
a-novel-region-of-interest-extraction-layer48.73919.135.8
x-paste-revisit-copy-paste-at-scale-with-clip---48.8
swin-transformer-v2-scaling-up-capacity-and---53.7
improved-multiscale-vision-transformers-for---46.2
path-aggregation-network-for-instance---37.8
resnest-split-attention-networks---44.5
resnest-split-attention-networks---41.56
masked-attention-mask-transformer-for---50.1
mask-scoring-r-cnn---39.1
elsa-enhanced-local-self-attention-for-vision---43.0
bottleneck-transformers-for-visual---44.4
swin-transformer-hierarchical-vision---49.5
moat-alternating-mobile-convolution-and---49.3
vision-transformer-adapter-for-dense---54.2
moat-alternating-mobile-convolution-and---49.0
adaptively-connected-neural-networks---35.2
end-to-end-semi-supervised-object-detection---51.9
dilated-neighborhood-attention-transformer---50.8
bottleneck-transformers-for-visual---43.7
exploring-plain-vision-transformer-backbones---53.1
focal-self-attention-for-local-global---50.9
internimage-exploring-large-scale-vision---43.7
simple-copy-paste-is-a-strong-data---46.8
recursively-refined-r-cnn-instance-42.822.640.2
mask-dino-towards-a-unified-transformer-based-1---52.6
general-object-foundation-model-for-images---54.2
mask-dino-towards-a-unified-transformer-based-1---54.5
moat-alternating-mobile-convolution-and---44.6
simple-copy-paste-is-a-strong-data---48.9
mask-scoring-r-cnn---36.0
the-devil-is-in-the-labels-semantic---41.4
mask-frozen-detr-high-quality-instance72.958.4 37.254.9
internimage-exploring-large-scale-vision---48.8
moat-alternating-mobile-convolution-and---47.4
general-object-foundation-model-for-images---53.0
moat-alternating-mobile-convolution-and---43.3
vision-transformer-adapter-for-dense---52.5
recursively-refined-r-cnn-instance52.84120.438.2
non-local-neural-networks---37.1
2103-15358---45.7
could-giant-pretrained-image-models-extract---51.6
centermask-real-time-anchor-free-instance-1---42.5
internimage-exploring-large-scale-vision74.458.437.955.4
xcit-cross-covariance-image-transformers---43.0
a-novel-region-of-interest-extraction-layer51.24120.237.2
190807919---41.0
recursively-refined-r-cnn-instance56.143.622.340.4
global-context-networks---44.7
hiera-a-hierarchical-vision-transformer---48.6
internimage-exploring-large-scale-vision----
yolact-real-time-instance-segmentation---29.9
moat-alternating-mobile-convolution-and---50.3
improved-multiscale-vision-transformers-for---47.1
hybrid-task-cascade-for-instance-segmentation---38.2
mpvit-multi-path-vision-transformer-for-dense---47.0
mask-scoring-r-cnn---38.2
attentive-normalization---40.2
vit-comer-vision-transformer-with---55.9
improved-multiscale-vision-transformers-for---48.5
resnest-split-attention-networks---44.21
cbnetv2-a-composite-backbone-network---51
mpvit-multi-path-vision-transformer-for-dense---45.8
end-to-end-semi-supervised-object-detection---52.5
2103-15358---45.1
recursively-refined-r-cnn-instance54.342.120.739.1
davit-dual-attention-vision-transformers---44.3
moat-alternating-mobile-convolution-and---47.0
internimage-exploring-large-scale-vision---48.5
non-local-neural-networks---35.5
res2net-a-new-multi-scale-backbone---41.3
gcnet-non-local-networks-meet-squeeze---40.9
deep-high-resolution-representation-learning---41.0
weight-standardization56.0841.7318.3238.34
moat-alternating-mobile-convolution-and---45.0
spinenet-learning-scale-permuted-backbone-for---46.1
non-local-neural-networks---40.3
general-object-foundation-model-for-images---48.4
centermask-real-time-anchor-free-instance-1---40.2