Incremental Learning on ImageNet100 - 10 steps
Metric: Average Incremental Accuracy (higher is better)
Metric: Average Incremental Accuracy (higher is better)
| # | Model↕ | Average Incremental Accuracy▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | kNN-CLIP | 85.1 | Yes | Revisiting a kNN-based Image Classification Syst... | 2022-04-03 | - |
| 2 | RMM (ResNet-18) | 78.47 | No | RMM: Reinforced Memory Management for Class-Incr... | 2023-01-14 | Code |
| 3 | FOSTER | 77.75 | No | FOSTER: Feature Boosting and Compression for Cla... | 2022-04-10 | Code |
| 4 | TCIL | 77.66 | No | Resolving Task Confusion in Dynamic Expansion Ar... | 2022-12-29 | Code |
| 5 | TCIL-Lite | 77.5 | No | Resolving Task Confusion in Dynamic Expansion Ar... | 2022-12-29 | Code |
| 6 | DER w/o Pruning | 77.18 | No | DER: Dynamically Expandable Representation for C... | 2021-03-31 | Code |
| 7 | DyTox | 77.15 | No | DyTox: Transformers for Continual Learning with ... | 2021-11-22 | Code |
| 8 | DER | 76.12 | No | DER: Dynamically Expandable Representation for C... | 2021-03-31 | Code |