Instance Segmentation on COD10K v3 (test)
45.3APDCNet
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DCNetLearning Paradigm=closed-set supervised learning, Params (Millions)=53.4/53.42023.12 | 45.3 | 70.7 | 47.5 | |
| UQFormerLearning Paradigm=closed-set supervised learning, Params (Millions)=37.5/37.52023.12 | 45.2 | 71.6 | 46.6 | |
| OVCIS (task-specific)Learning Paradigm=closed-set supervised learning, Fine-tuning=true, Params (Millions)=28.7/1522.72023.12 | 45.1 | 71.1 | 47.4 | |
| CamoFALearning Paradigm=closed-set supervised learning2023.12 | 43.5 | 74.9 | 42.7 | |
| OSFormerLearning Paradigm=closed-set supervised learning, Params (Millions)=46.6/46.62023.12 | 41 | 71.1 | 40.8 | |
| MSPNetLearning Paradigm=closed-set supervised learning, Params (Millions)=48.1/48.12023.12 | 39.7 | 69.8 | 39.8 | |
| Mask2FormerLearning Paradigm=closed-set supervised learning, Params (Millions)=43.9/43.92023.12 | 39.4 | 67.7 | 38.5 | |
| MaskFormerLearning Paradigm=closed-set supervised learning, Params (Millions)=45.0/45.02023.12 | 38.2 | 65.1 | 37.9 | |
| SOLOv2Learning Paradigm=closed-set supervised learning, Params (Millions)=46.2/46.22023.12 | 32.5 | 63.2 | 29.9 | |
| CondInstLearning Paradigm=closed-set supervised learning, Params (Millions)=34.1/34.12023.12 | 30.6 | 63.6 | 26.1 | |
| MS R-CNNLearning Paradigm=closed-set supervised learning, Params (Millions)=60.0/60.62023.12 | 30.1 | 57.2 | 28.7 | |
| Mask TransfinerLearning Paradigm=closed-set supervised learning, Params (Millions)=44.3/44.32023.12 | 28.7 | 56.3 | 26.4 | |
| QueryInstLearning Paradigm=closed-set supervised learning, Params (Millions)=172.5/172.52023.12 | 28.5 | 60.1 | 23.1 | |
| BlendMaskLearning Paradigm=closed-set supervised learning, Params (Millions)=35.8/35.82023.12 | 28.2 | 56.4 | 25.2 | |
| HTCLearning Paradigm=closed-set supervised learning, Params (Millions)=76.9/76.92023.12 | 28.1 | 56.3 | 25.1 | |
| SOTRLearning Paradigm=closed-set supervised learning, Params (Millions)=63.1/63.12023.12 | 27.9 | 58.7 | 24.1 | |
| Cascade R-CNNLearning Paradigm=closed-set supervised learning, Params (Millions)=71.7/71.72023.12 | 25.3 | 56.1 | 21.3 | |
| Mask R-CNNLearning Paradigm=closed-set supervised learning, Params (Millions)=43.9/43.92023.12 | 25 | 55.5 | 20.4 | |
| YOLACTLearning Paradigm=closed-set supervised learning, Params (Millions)=35.3/35.32023.12 | 24.3 | 53.3 | 19.7 | |
| OVCISLearning Paradigm=open-vocab T2I, Fine-tuning=false, Params (Millions)=28.7/1522.72023.12 | 23.9 | 44.3 | 23.1 | |
| ODISELearning Paradigm=open-vocab T2I, Fine-tuning=false, Params (Millions)=28.1/1522.12023.12 | 21.1 | 37.8 | 20.5 | |
| TPNetLearning Paradigm=open-vocab VLM, Fine-tuning=false, Params (Millions)=71.78/71.782023.12 | 18.3 | 41.8 | 14.3 | |
| X-DecoderLearning Paradigm=open-vocab VLM, Fine-tuning=false, Params (Millions)=38.3/38.32023.12 | 7.7 | 12.9 | 7.5 | |
| SEEMLearning Paradigm=open-vocab VLM, Fine-tuning=false, Params (Millions)=415.3/415.32023.12 | 6.6 | 10.8 | 6.5 | |
| OpenSeeDLearning Paradigm=open-vocab VLM, Fine-tuning=false, Params (Millions)=116.2/116.22023.12 | 6.1 | 10.4 | 5.9 | |
| MasQCLIPLearning Paradigm=open-vocab VLM, Fine-tuning=false, Params (Millions)=375.2/357.22023.12 | 4.1 | 7.7 | 5.8 | |
| MaskCLIPLearning Paradigm=open-vocab VLM, Fine-tuning=false, Params (Millions)=542.0/542.02023.12 | 3.3 | 5.9 | 4.1 |