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/DER w/o Pruning

DER w/o Pruning

Reported on 10 benchmarks across 1 task · 1 paper · 9 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
# M Params· 2021-03-31
116.89
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy· 2021-03-31
68.84
best: 85.5 (kNN-CLIP)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy Top-5· 2021-03-31
88.17
best: 88.59 (DyTox)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet - 10 steps
Final Accuracy· 2021-03-31
60.16
best: 63.34 (DyTox)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet - 10 steps
Final Accuracy Top-5· 2021-03-31
82.86
best: 84.49 (DyTox)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet100 - 10 steps
# M Params· 2021-03-31
112.27
best: 116.54 (TCIL)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy· 2021-03-31
77.18
best: 85.1 (kNN-CLIP)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy Top-5· 2021-03-31
93.23
best: 94.17 (TCIL)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet100 - 10 steps
Final Accuracy· 2021-03-31
66.7
best: 69.1 (DyTox)
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonImageNet100 - 10 steps
Final Accuracy Top-5· 2021-03-31
87.52
best: 88.84 (TCIL)
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788