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/DyTox

DyTox

Reported on 10 benchmarks across 1 task · 1 paper · 5 SOTA

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

Methodology10 results

Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy· 2021-11-22
71.29
best: 85.5 (kNN-CLIP)
SOTA
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy Top-5· 2021-11-22
88.59
SOTA
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet - 10 steps
Final Accuracy· 2021-11-22
63.34
SOTA
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet - 10 steps
Final Accuracy Top-5· 2021-11-22
84.49
SOTA
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet100 - 10 steps
Final Accuracy· 2021-11-22
69.1
SOTA
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet - 10 steps
# M Params· 2021-11-22
11.36
best: 116.89 (DER w/o Pruning)
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet100 - 10 steps
# M Params· 2021-11-22
11.01
best: 116.54 (TCIL)
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy· 2021-11-22
77.15
best: 85.1 (kNN-CLIP)
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy Top-5· 2021-11-22
92.04
best: 94.17 (TCIL)
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326
Incremental LearningonImageNet100 - 10 steps
Final Accuracy Top-5· 2021-11-22
87.98
best: 88.84 (TCIL)
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion arXiv:2111.11326