Research map / Continual learning / Class-incremental
Fast Online Incremental Learning on Mixture Streaming Data
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 cluster centers plus Cholesky-based QR (FLDA/QR) instead of LDA/QR-type batch methods | batch LDA · ORL | computation time (s): 0.12 -> 0.01 | Helped |
| FLDA/QR vs NLDA/QR | batch LDA · AWA | computation time (s): 0.38 -> 0.01 | Helped |
| FLDA/QR vs IDR/QR batch | batch LDA · ORL | classification accuracy (%): 95.32 -> 93.35 | Hurt |
| FLDA/QR vs NLDA/QR | batch LDA · Tr23 | classification accuracy (%): 67.00 -> 86.00 | Helped |
| FLDA/QR vs NLDA/QR | batch LDA · AWA | classification accuracy (%): 88.22 -> 86.56 | Hurt |
| IFLDA/QR Gram-Schmidt update vs rank-one QR updating (ILDA/QR) | incremental LDA · ORL | computation time (s): 6.102 -> 1.104 | Helped |
| IFLDA/QR vs ILDA/QR | incremental LDA · Tr23 | computation time (s): 0.024 -> 0.005 | Helped |
| IFLDA/QR vs ILDA/QR | incremental LDA · ORL | classification accuracy (%): 95.00 -> 92.25 | Hurt |
| IFLDA/QR vs IDR/QR | incremental LDA · Tr23 | classification accuracy (%): 61.67 -> 74.80 | Helped |
| IFLDA/QR vs IDR/QR | incremental LDA · ORL | classification accuracy (%): 92.50 -> 92.25 | No clear effect |
Closest papers by meaning
- Low Precision Streaming PCA (NeurIPS 2025 · similarity 0.83)
- Continual Learning Using a Kernel-Based Method Over Foundation Models (AAAI 2025 · similarity 0.83)
- DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning (AAAI 2024 · similarity 0.82)
- Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement (AAAI 2024 · similarity 0.81)
- MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound (NeurIPS 2026 · similarity 0.81)
- Online Boosting Adaptive Learning under Concept Drift for Multistream Classification (AAAI 2024 · similarity 0.81)
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.