Research map / Continual learning / Online and replay-based
FearNet: Brain-Inspired Model for Incremental Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FearNet's dual-memory system with pseudorehearsal and BLA selection | FearNet · CIFAR-100 | Ω_all: 0.879 -> 0.947 | Helped |
| Use FearNet's dual-memory system with pseudorehearsal and BLA selection | FearNet · CUB-200 | Ω_all: 0.864 -> 0.891 | Helped |
| Use FearNet's dual-memory system with pseudorehearsal and BLA selection | FearNet · AudioSet | Ω_all: 0.879 -> 0.932 | Helped |
| Replace full class covariance matrices with diagonal covariance matrices (ablation) | FearNet · CIFAR-100 | Ω_all: 0.959 -> 0.800 | Hurt |
| Increase exemplars per class from 20 to 100 (ablation) | iCaRL · CIFAR-100 | Ω_all: 0.749 -> 0.822 | Helped |
| Increase exemplars per class from 20 to 100 (ablation) | iCaRL · CUB-200 | Ω_all: 0.864 -> 0.882 | Helped |
| Increase exemplars per class from 20 to 100 (ablation) | iCaRL · AudioSet | Ω_all: 0.733 -> 0.771 | Helped |
| Use oracle memory-location selection instead of BLA (ablation) | FearNet · CIFAR-100 | Ω_all: 0.947 -> 1.002 | Helped |
| Use oracle memory-location selection instead of BLA (ablation) | FearNet · CUB-200 | Ω_all: 0.891 -> 0.936 | Helped |
| Use oracle memory-location selection instead of BLA (ablation) | FearNet · AudioSet | Ω_all: 0.932 -> 0.972 | Helped |
| Replace binary MLP BLA with Isolation Forest (ablation) | FearNet · CIFAR-100 | Ω_all: 0.947 -> 0.368 | Hurt |
| Replace binary MLP BLA with Elliptic Envelope (ablation) | FearNet · CIFAR-100 | Ω_all: 0.947 -> 0.541 | Hurt |
Closest papers by meaning
- NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning (CVPR 2024 · similarity 0.85)
- A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks (ICLR 2024 · similarity 0.85)
- ALADE-SNN: Adaptive Logit Alignment in Dynamically Expandable Spiking Neural Networks for Class Incremental Learning (AAAI 2025 · similarity 0.85)
- Long-Tail Class Incremental Learning via Independent Sub-prototype Construction (CVPR 2024 · similarity 0.84)
- MIND: Multi-Task Incremental Network Distillation (AAAI 2024 · similarity 0.84)
- Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning (ICML 2024 · similarity 0.84)
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.