Research map / Continual learning / Class-incremental
Incremental Learning via Rate Reduction
Ziyang Wu, Christina Baek, Chong You, Yi Ma
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use incremental ReduNet instead of the strongest reported baseline, iCaRL | class-incremental learning · MNIST Task 5 | accuracy: 0.7 -> 0.961 | Improved |
| Use incremental ReduNet instead of the strongest reported baseline, iCaRL | class-incremental learning · CIFAR-10 Task 5 | accuracy: 0.48 -> 0.539 | Improved |
| Use ReduNet rather than the baseline methods | class-incremental learning · CIFAR-10 Task 1 | accuracy: 0.989 -> 0.875 | Hurt |
| Train incrementally with ReduNet rather than joint-training unavailable-data methods | ReduNet · class-incremental learning without old examples | catastrophic forgetting | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- iCaRL — iCaRL: Incremental Classifier and Representation Learning (CVPR 2017) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Class-Incremental Learning: Survey and Performance Evaluation on Image Classification (TPAMI 2022 · similarity 0.89)
- End-to-End Incremental Learning (ECCV 2018 · similarity 0.89)
- Semantic Drift Compensation for Class-Incremental Learning (CVPR 2020 · similarity 0.89)
- Class-Incremental Learning by Knowledge Distillation With Adaptive Feature Consolidation (CVPR 2022 · similarity 0.88)
- Incremental Learning of Object Detectors Without Catastrophic Forgetting (ICCV 2017 · similarity 0.88)
- Incremental Learning Using Conditional Adversarial Networks (ICCV 2019 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
