Object Detection on SSDD
71.5AP (Box)DynamicVis-L
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DynamicVis-L2025.03 | 71.5 | 97.8 | 85.2 | |
| DynamicVis-B2025.03 | 70.8 | 97.7 | 87.1 | |
| RS4D (box)Backbone=SSM, Params (M)=33.20, bb-Params (M)=11.75, bb-FLOPs (G)=108.82026.06 | 70.7 | 97.4 | 86.4 | |
| RSPrompter-anchor2025.03 | 70.4 | 97.7 | 86.2 | |
| Cascade Mask RCNNBackbone=ResNet50, Params (M)=77.02, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 70.4 | 97.5 | 85.9 | |
| RSPrompter (anchor)Backbone=ViT-Base, Params (M)=117.09, bb-Params (M)=89.67, bb-FLOPs (G)=9722026.06 | 70.4 | 97.7 | 86.2 | |
| SAM-detBackbone=ViT-Base, Params (M)=135.08, bb-Params (M)=89.67, bb-FLOPs (G)=9722026.06 | 70 | 95.8 | 85.3 | |
| RS4D (prompt)Backbone=SSM, Params (M)=38.83, bb-Params (M)=11.75, bb-FLOPs (G)=108.82026.06 | 69.7 | 96.6 | 83.2 | |
| HTC2025.03 | 69.3 | 97.1 | 85.7 | |
| HTCBackbone=ResNet50, Params (M)=46.59, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 69.3 | 97.1 | 85.7 | |
| DynamicVis-L‡2025.03 | 68.9 | 97.7 | 84.2 | |
| SAM-seg (Mask RCNN)Backbone=ViT-Base, Params (M)=309.69, bb-Params (M)=89.67, bb-FLOPs (G)=9722026.06 | 68.7 | 97.2 | 84.3 | |
| CondInst2025.03 | 68.1 | 92.4 | 85.5 | |
| CondInstBackbone=ResNet50, Params (M)=34.16, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 68.1 | 92.4 | 85.5 | |
| MS R-CNN2025.03 | 67.8 | 95.3 | 85.9 | |
| MS RCNNBackbone=ResNet50, Params (M)=60.74, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 67.8 | 95.3 | 85.9 | |
| Mask R-CNN2025.03 | 67.7 | 95.6 | 84.9 | |
| DynamicVis-L†2025.03 | 67.7 | 97.7 | 82 | |
| Mask RCNNBackbone=ResNet50, Params (M)=44.18, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 67.7 | 95.6 | 84.9 | |
| CATNet2025.03 | 67.5 | 96.8 | — | |
| CATNetBackbone=ResNet50, Params (M)=54.77, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 67.5 | 96.8 | 80.4 | |
| DynamicVis-B‡2025.03 | 67 | 97.6 | 81.3 | |
| SCNet2025.03 | 66.9 | 92.5 | 82.5 | |
| SCNetBackbone=ResNet50, Params (M)=94.80, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 66.9 | 92.5 | 82.5 | |
| HQ-ISNet2025.03 | 66.6 | 95.9 | 80.2 | |
| DynamicVis-B†2025.03 | 66.6 | 97.8 | 78 | |
| HQ-ISNetBackbone=ResNet50, Params (M)=80.56, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 66.6 | 95.9 | 80.2 | |
| RSPrompter-query2025.03 | 66 | 95.6 | 78.7 | |
| RSPrompter (query)Backbone=ViT-Base, Params (M)=101.02, bb-Params (M)=89.67, bb-FLOPs (G)=9722026.06 | 66 | 95.6 | 78.7 | |
| SAM-seg (Mask2Former)Backbone=ViT-Base, Params (M)=112.16, bb-Params (M)=89.67, bb-FLOPs (G)=9722026.06 | 63 | 94.9 | 75.6 | |
| BoxInst2025.03 | 62.8 | 96.2 | 74.7 | |
| BoxInstBackbone=ResNet50, Params (M)=35.14, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 62.8 | 96.2 | 74.7 | |
| Mask2Former2025.03 | 62.7 | 90.7 | 75.6 | |
| Mask2FormerBackbone=ResNet50, Params (M)=44.02, bb-Params (M)=25.56, bb-FLOPs (G)=172.692026.06 | 62.7 | 90.7 | 75.6 | |
| ViTDetBackbone=Swin-Huge, Params (M)=679.42, bb-Params (M)=655.58, bb-FLOPs (G)=375.102026.06 | 62.4 | 95.1 | 73 | |
| SwinV2 (HTC++)Backbone=SwinV2-Huge, Params (M)=709.09, bb-Params (M)=655.14, bb-FLOPs (G)=303.372026.06 | 59.4 | 85.5 | 76.8 | |
| SAM-clsBackbone=ViT-Base2026.06 | 43.2 | 70.8 | 48.8 | |
| CBNetv2Backbone=Swin-Tiny, Params (M)=75.58, bb-Params (M)=28.30, bb-FLOPs (G)=12.472026.06 | 40.6 | 62.7 | 48.5 |