Research map / Continual learning / Online and replay-based
Continual Learning: Forget-Free Winning Subnetworks for Video Representations
Haeyong Kang, Jaehong Yoon, Sung Ju Hwang, Chang D. Yoo
Read the paperCheck 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 |
|---|---|---|---|
| add Fourier Subneural Operator (FSO) | WSN (c=50%) · CIFAR-100 Split (TIL) | accuracy: 77.67 -> 79.00 | Improved |
| add FSO | WSN (c=50%) · TinyImageNet (TIL) | accuracy: 69.88 -> 72.04 | Improved |
| add FSO | WSN (c=50%) · CIFAR-100 Superclass (TIL) | accuracy: 61.58 -> 61.70 | No clear effect |
| add FSO | WSN (c=70%) · Seq-CIFAR100 (TaIL) | accuracy: 46.24 -> 77.12 | Improved |
| add FSO | WSN (c=70%) · Seq-CIFAR10 (TaIL) | accuracy: 94.67 -> 94.90 | Improved |
| add FSO | WSN (c=70%) · Seq-TinyImageNet (TaIL) | accuracy: 18.98 -> 20.90 | Improved |
| add loss decoupling (LODE) | WSN + FSO (c=70%) · Seq-CIFAR100 (TaIL) | accuracy: 77.12 -> 78.25 | Improved |
| add FSO | SoftNet (c=90%) · CIFAR-100 FSCIL (session 9) | accuracy: 54.76 -> 56.00 | Improved |
| add FSO | SoftNet (c=85%) · miniImageNet FSCIL (session 9) | accuracy: 53.92 -> 54.80 | Improved |
| add FSO | SoftNet (c=90%) · CUB-200-2011 FSCIL (session 11) | accuracy: 56.75 -> 56.84 | No clear effect |
| use soft mask (SoftNet) instead of binary mask (ablation) | WSN (c=90%) · CIFAR-100 FSCIL (session 9) | accuracy: 53.92 -> 54.76 | Improved |
| add FSO | WSN (c=99%) · ImageNet-1K | top-1 accuracy: 69.46 -> 70.63 | 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 1 of 1 shared result
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
- On the Soft-Subnetwork for Few-Shot Class Incremental Learning (ICLR 2023 · similarity 0.91)
- Forget-free Continual Learning with Winning Subnetworks (ICML 2022 · similarity 0.91)
- CRNet: A Fast Continual Learning Framework With Random Theory (TPAMI 2023 · similarity 0.87)
- TinySubNets: An Efficient and Low Capacity Continual Learning Strategy (AAAI 2025 · similarity 0.86)
- MIND: Multi-Task Incremental Network Distillation (AAAI 2024 · similarity 0.86)
- Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning (ICML 2024 · similarity 0.85)
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.
