Research map / Continual learning / Class-incremental
On the Soft-Subnetwork for Few-Shot Class Incremental Learning
Haeyong Kang, Jaehong Yoon, Sultan Rizky Hikmawan Madjid, 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 |
|---|---|---|---|
| use a soft minor subnetwork instead of a hard subnetwork at c=50% (ablation) | SoftNet · CIFAR-100 session 9 | classification accuracy: 54.32 -> 55.33 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=80% (ablation) | SoftNet · CIFAR-100 session 9 | classification accuracy: 54.31 -> 54.94 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=90% (ablation) | SoftNet · CIFAR-100 session 9 | classification accuracy: 53.92 -> 54.76 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=80% (ablation) | SoftNet · miniImageNet session 9 | classification accuracy: 52.74 -> 54.34 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=87% (ablation) | SoftNet · miniImageNet session 9 | classification accuracy: 53.47 -> 54.68 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=90% (ablation) | SoftNet · miniImageNet session 9 | classification accuracy: 53.07 -> 54.14 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=88% (ablation) | SoftNet · CUB-200-2011 session 11 | classification accuracy: 55.20 -> 56.64 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=90% (ablation) | SoftNet · CUB-200-2011 session 11 | classification accuracy: 55.30 -> 56.75 | Improved |
| use a soft minor subnetwork instead of a hard subnetwork at c=93% (ablation) | SoftNet · CUB-200-2011 session 11 | classification accuracy: 55.18 -> 56.28 | Improved |
| use SoftNet rather than ALICE | ResNet18 FSCIL · CIFAR-100 session 9 | classification accuracy: 54.10 -> 55.33 | Improved |
| use SoftNet rather than ALICE | ResNet18 FSCIL · miniImageNet session 9 | classification accuracy: 55.70 -> 54.68 | Hurt |
| use SoftNet rather than ALICE | ResNet18 FSCIL · CUB-200-2011 session 11 | classification accuracy: 60.10 -> 56.75 | Hurt |
Closest papers by meaning
- Continual Learning: Forget-Free Winning Subnetworks for Video Representations (TPAMI 2024 · similarity 0.91)
- Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation (CVPR 2023 · similarity 0.87)
- MIND: Multi-Task Incremental Network Distillation (AAAI 2024 · similarity 0.86)
- Adaptive Decision Boundary for Few-Shot Class-Incremental Learning (AAAI 2025 · similarity 0.85)
- M2SD:Multiple Mixing Self-Distillation for Few-Shot Class-Incremental Learning (AAAI 2024 · similarity 0.85)
- Attraction Diminishing and Distributing for Few-Shot Class-Incremental Learning (CVPR 2025 · 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.
