Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TCIL-Lite

TCIL-Lite

Reported on 11 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology11 results

Incremental LearningonCIFAR100B020Step(5ClassesPerStep)
Average Incremental Accuracy· 2022-12-29
75.47
best: 76.95 (View-Batch(DER))
SOTA
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonCIFAR-100 - 50 classes + 10 steps of 5 classes
Average Incremental Accuracy· 2022-12-29
73.5
best: 73.72 (TCIL)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonCIFAR-100 - 50 classes + 5 steps of 10 classes
Average Incremental Accuracy· 2022-12-29
74.3
best: 74.88 (TCIL)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonCIFAR100-B0(10steps of 10 classes)
Average Incremental Accuracy· 2022-12-29
76.74
best: 78.12 (View-Batch(DER))
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonCIFAR-100-B0(5steps of 20 classes)
Average Incremental Accuracy· 2022-12-29
76.96
best: 79.23 (View-Batch(TCIL))
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonImageNet100 - 10 steps
# M Params· 2022-12-29
26.36
best: 116.54 (TCIL)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy· 2022-12-29
77.5
best: 85.1 (kNN-CLIP)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy Top-5· 2022-12-29
93.6
best: 94.17 (TCIL)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonImageNet100 - 10 steps
Final Accuracy· 2022-12-29
67.3
best: 69.1 (DyTox)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonImageNet100 - 10 steps
Final Accuracy Top-5· 2022-12-29
87.94
best: 88.84 (TCIL)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284
Incremental LearningonCIFAR-100 - 50 classes + 2 steps of 25 classes
Average Incremental Accuracy· 2022-12-29
74.95
best: 76.42 (TCIL)
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning arXiv:2212.14284