Research map / Continual learning / Class-incremental
FLAR: A Unified Prototype Framework for Few-Sample Lifelong Active Recognition
Lei Fan, Peixi Xiong, Wei Wei, Ying Wu
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 learned prototype-based policy instead of random view selection | FLAR active recognition agent · SUN360 (26 categories) | accuracy at t=5 (average): 62.3 -> 71.1 | Improved |
| use prototype reward and prototype representation instead of Look-Ahead reward | FLAR active recognition agent · SUN360 (26 categories) | accuracy at t=2 (current): 59.8 -> 61.5 | Improved |
| use learned policy instead of largest-step movement | FLAR active recognition agent · SUN360 (26 categories) | accuracy at t=5 (current): 52.4 -> 69.9 | Improved |
| increase new-category training samples from k=5 to k=10 (ablation) | FLAR · SUN360 class-incremental | accuracy | No clear effect |
| increase new-category training samples from k=3 to k=5 (ablation) | FLAR · SUN360 class-incremental | accuracy | Improved |
| vary stored exemplars m=1,3,5 (ablation) | FLAR · SUN360 class-incremental | accuracy | No clear effect |
| use incremental learning with prototypes instead of imbalanced direct training | FLAR · SUN360 class-incremental | accuracy at t=5 | Improved |
Closest papers by meaning
- Few-Shot Continual Active Learning by a Robot (NeurIPS 2022 · similarity 0.87)
- Active Learning for Continual Learning: Keeping the Past Alive in the Present (ICLR 2025 · similarity 0.85)
- Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception (CVPR 2024 · similarity 0.84)
- OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection (CVPR 2026 · similarity 0.84)
- Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees (AAAI 2024 · similarity 0.83)
- Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations (CVPR 2024 · similarity 0.83)
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.
