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/PackNet

PackNet

Reported on 7 benchmarks across 1 task · 1 paper · 2 SOTA

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

Methodology7 results

Continual LearningonCUBS (Fine-grained 6 Tasks)
Accuracy· 2017-11-15
80.41
best: 84.26 (CondConvContinual)
SOTA
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning arXiv:1711.05769
Continual LearningonCifar100 (20 tasks)
Average Accuracy· 2017-11-15
67.5
best: 94.99 (Model Zoo-Continual)
SOTA
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning arXiv:1711.05769
Continual LearningonSketch (Fine-grained 6 Tasks)
Accuracy· 2017-11-15
76.17
best: 80.77 (CondConvContinual)
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning arXiv:1711.05769
Continual LearningonStanford Cars (Fine-grained 6 Tasks)
Accuracy· 2017-11-15
86.11
best: 92.8 (CPG)
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning arXiv:1711.05769
Continual LearningonWikiart (Fine-grained 6 Tasks)
Accuracy· 2017-11-15
69.4
best: 78.32 (CondConvContinual)
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning arXiv:1711.05769
Continual LearningonImageNet (Fine-grained 6 Tasks)
Accuracy· 2017-11-15
75.71
best: 76.16 (ProgressiveNet)
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning arXiv:1711.05769
Continual LearningonFlowers (Fine-grained 6 Tasks)
Accuracy· 2017-11-15
93.04
best: 97.16 (CondConvContinual)
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning arXiv:1711.05769