Research map / Continual learning / Class-incremental
Rectification-Based Knowledge Retention for Continual Learning
Pravendra Singh, Pratik Mazumder, Piyush Rai, Vinay P. Namboodiri
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 RKR instead of CCLL | CIFAR-100 task-incremental learning with LeNet · CIFAR-100 | accuracy: 5.87% | Improved |
| Use RKR instead of CCLL | ImageNet-1K task-incremental learning · ImageNet-1K | top-5 accuracy: 3.1% | Improved |
| Use RKR instead of LZSL | incremental generalized zero-shot learning · aPY, AWA1, CUB, and SUN | H: 5.65%, 6.91%, 6.33%, and 2.53% | Improved |
| Add weight rectifications (ablation) | RKR · CIFAR-100, LeNet | accuracy: 62.3% -> 69.6% | Improved |
| Add weight rectifications (ablation) | RKR · CIFAR-100, ResNet-18 | accuracy: 79.2% -> 87.6% | Improved |
| Add output scaling (ablation) | RKR · CIFAR-100, LeNet | accuracy: 69.1% -> 69.6% | Improved |
| Add output scaling (ablation) | RKR · CIFAR-100, ResNet-18 | accuracy: 87.5% -> 87.6% | Improved |
| Add weight rectifications (ablation) | RKR · AWA1, CUB, and SUN | H: 6.8%, 9.28%, and 6.24% | Improved |
| Add output scaling (ablation) | RKR · AWA1, CUB, and SUN | H: 3.71%, 4.57%, and 3.59% | Improved |
| Initialize rectification and scaling parameters from the previous task instead of from scratch (ablation) | RKR · CIFAR-100, ResNet-18 | accuracy: 1.45% | Improved |
| Initialize rectification and scaling parameters from the previous task instead of randomly (ablation) | RKR · AWA1, CUB, and SUN | H: 3.72%, 7.57%, and 7.14% | Improved |
| Increase K from 1 to 2 (ablation) | RKR · CIFAR-100, ResNet-18 | accuracy: 85.55% -> 87.60% | Improved |
Closest papers by meaning
- Rectification-Based Knowledge Retention for Task Incremental Learning (TPAMI 2022 · similarity 0.97)
- RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks (ICLR 2025 · similarity 0.88)
- Compacting, Picking and Growing for Unforgetting Continual Learning (NeurIPS 2019 · similarity 0.88)
- A continual learning survey: Defying forgetting in classification tasks (TPAMI 2021 · similarity 0.88)
- Incremental Task Learning with Incremental Rank Updates (ECCV 2022 · similarity 0.88)
- Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks (NeurIPS 2024 · similarity 0.87)
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.
