List your company
ResearchFormerly WizWand

Instance Segmentation on COCO (APm, APm@.50, APm@.75)

45.9AP^mTransNeXt-Base
38.82840.66442.544.336Jan 17, 2023Mar 10, 2023May 2, 2023Jun 23, 2023Aug 15, 2023Oct 6, 2023Nov 28, 2023
Updated 8mo ago

Evaluation results

MethodLinks
TransNeXt-BaseEncoder size (M)=89.7, #Params. (M)=109.2, Framework=Mask R-CNN, Schedule=1x2023.1145.970.549.7
TransNext-SmallEncoder size (M)=49.7, #Params. (M)=69.3, Framework=Mask R-CNN, Schedule=1x2023.1145.569.849.1
TransNeXt-TinyEncoder size (M)=28.2, #Params. (M)=47.9, Framework=Mask R-CNN, Schedule=1x2023.1144.668.648.1
InternImage-BEncoder size (M)=97, #Params. (M)=115, Framework=Mask R-CNN, Schedule=1x2023.114467.847.4
SMT-BEncoder size (M)=32, #Params. (M)=51.7, Framework=Mask R-CNN, Schedule=1x2023.114467.647.4
CSWin-BEncoder size (M)=78, #Params. (M)=97, Framework=Mask R-CNN, Schedule=1x2023.1143.967.847.3
BiFormer-BEncoder size (M)=56.8, #Params. (M)=76.3, Framework=Mask R-CNN, Schedule=1x2023.1143.767.647.1
FocalNet-B (LRF)Encoder size (M)=88.7, #Params. (M)=111.4, Framework=Mask R-CNN, Schedule=1x2023.1143.567.946.7
InternImage-SEncoder size (M)=50, #Params. (M)=69, Framework=Mask R-CNN, Schedule=1x2023.1143.367.146.7
BiFormer-SEncoder size (M)=25.5, #Params. (M)=45.2, Framework=Mask R-CNN, Schedule=1x2023.1143.266.846.5
CSWin-SEncoder size (M)=35, #Params. (M)=54, Framework=Mask R-CNN, Schedule=1x2023.1143.267.146.2
FocalNet-S (LRF)Encoder size (M)=50.3, #Params. (M)=72.3, Framework=Mask R-CNN, Schedule=1x2023.1143.167.446.2
SMT-SEncoder size (M)=20.5, #Params. (M)=40, Framework=Mask R-CNN, Schedule=1x2023.114366.646.1
PVTv2-B4Encoder size (M)=62.6, #Params. (M)=82.2, Framework=Mask R-CNN, Schedule=1x2023.1142.766.146.1
RILSBackbone=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=252023.0142.666.845.8
PVTv2-B3Encoder size (M)=45.2, #Params. (M)=64.9, Framework=Mask R-CNN, Schedule=1x2023.1142.565.745.7
InternImage-TEncoder size (M)=30, #Params. (M)=49, Framework=Mask R-CNN, Schedule=1x2023.1142.566.145.8
PVTv2-B5Encoder size (M)=82, #Params. (M)=101.6, Framework=Mask R-CNN, Schedule=1x2023.1142.565.746
MAEBackbone=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=252023.0142.465.846.4
MAE+CLIPBackbone=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=252023.0142.466.245.7
Swin-BEncoder size (M)=87.8, #Params. (M)=107.1, Framework=Mask R-CNN, Schedule=1x2023.1142.36645.5
CSWin-TEncoder size (M)=23, #Params. (M)=42, Framework=Mask R-CNN, Schedule=1x2023.1142.265.645.4
Swin-SEncoder size (M)=49.6, #Params. (M)=69.1, Framework=Mask R-CNN, Schedule=1x2023.1142.165.845.2
CLIPBackbone=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=252023.014265.945.1
FocalNet-T (LRF)Encoder size (M)=28.6, #Params. (M)=48.9, Framework=Mask R-CNN, Schedule=1x2023.1141.565.144.5
SLIPBackbone=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=252023.0141.565.144.1
PVTv2-B2Encoder size (M)=25.4, #Params. (M)=45.3, Framework=Mask R-CNN, Schedule=1x2023.1141.264.244.4
Swin-TEncoder size (M)=28.3, #Params. (M)=47.8, Framework=Mask R-CNN, Schedule=1x2023.1139.161.642