Class-incremental classification on CIFAR100 10 tasks
89.8Average AccuracySeGP-CL (Ours)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SeGP-CL (Ours)Replay=false, Backbone=CLIP-ViT-B/162026.03 | 89.8 | 84.6 | |
| SeGP-CL-onlyCLIPReplay=false, Backbone=CLIP-ViT-B/162026.03 | 88.2 | 83.2 | |
| DMNSPPublication=ICCV’25, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 87.1 | 79.9 | |
| MG-CLIPPublication=ICCV’25, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 87 | 80.6 | |
| RAPFPublication=ECCV’24, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 86.2 | 79 | |
| CLAPPublication=NeurIPS’24, Replay=true, Backbone=CLIP-ViT-B/162026.03 | 86.1 | 78.2 | |
| DesCLIPPublication=TMM’26, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 85.6 | 78.7 | |
| MoE-AdapterPublication=CVPR’24, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 85.4 | 78.4 | |
| PROOFPublication=TPAMI’25, Replay=true, Backbone=CLIP-ViT-B/162026.03 | 84.9 | 76.3 | |
| CLG-CBMPublication=CVPR’25, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 84.9 | 76.9 | |
| ENGINEPublication=ICCV’25, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 82.1 | 73.1 | |
| L2P++Publication=CVPR’22, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 81.9 | 73.1 | |
| DualPromptPublication=ECCV’22, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 81.5 | 72.5 | |
| SLCAPublication=ICCV’23, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 80.5 | 67.6 | |
| CODA PromptPublication=CVPR’23, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 77 | 62.3 | |
| Aper-AdapterPublication=IJCV’24, Replay=false, Backbone=CLIP-ViT-B/162026.03 | 75.8 | 65.5 |