Research map / Continual learning / Online and replay-based
Incremental Object Learning From Contiguous Views
Check 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 |
|---|---|---|---|
| allow repeated exposures to previously seen objects | incremental learning algorithms · CRIB-Toys-200 | incremental accuracy | Helped |
| allow repeated exposures | iCaRL-PT-ND and E2EIL-PT-ND · CRIB-Toys-50 | incremental accuracy | Helped |
| allow repeated exposures to new instances from the same category | iCaRL-PT-ND · CRIB-ShapeNet-20 | incremental accuracy | Helped |
| repeat category images across learning exposures | iCaRL-PT-ND · CIFAR-20 | incremental accuracy | Helped |
| use distillation loss instead of no distillation loss (ablation) | iCaRL-PT · CRIB-Toys-200, single exposures | incremental accuracy | Hurt |
| use distillation loss instead of no distillation loss (ablation) | E2EIL-PT · CRIB-Toys-200, single exposures | incremental accuracy | No clear effect |
| use distillation loss instead of no distillation loss (ablation) | iCaRL-PT · CRIB-Toys-200, repeated exposures | incremental accuracy | Hurt |
| increase exemplar set size (ablation) | iCaRL-PT-ND · CRIB-Toys-50 | incremental accuracy | No clear effect |
| increase exemplar set size (ablation) | E2EIL-PT-ND · CRIB-Toys-50 | incremental accuracy | Helped |
| increase learning exposure length (ablation) | iCaRL-PT-ND unsupervised baseline · CRIB-Toys unsupervised repeated exposures | incremental accuracy | Helped |
| increase learning exposure length (ablation) | iCaRL-PT-ND unsupervised baseline · CRIB-Toys unsupervised repeated exposures | percentage of objects discovered | Mixed |
Closest papers by meaning
- Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models (NeurIPS 2024 · similarity 0.85)
- Learning from an Infant’s Visual Experience (AAAI 2024 · similarity 0.84)
- Revisiting Generative Replay for Class Incremental Object Detection (CVPR 2025 · similarity 0.84)
- Object Concepts Emerge from Motion (NeurIPS 2025 · similarity 0.84)
- REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning (NeurIPS 2025 · similarity 0.83)
- MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model Construction (ICLR 2025 · 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.