Research map / Continual learning / Class-incremental
High-dimension Prototype is a Better Incremental Object Detection Learner
Yanjie Wang, Liqun Chen, Tianming Zhao, Tao Zhang, Guodong Wang, Luxin Yan, Sheng Zhong, Jiahuan Zhou, Xu Zou
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes high-dimension prototypes to mitigate catastrophic forgetting in incremental object detection, addressing knowledge shift from invisible previous-task data.
Problem
Incremental object detection must overcome catastrophic forgetting in both recognition and localization; knowledge distillation alone suffers from knowledge shift because previous-task data is invisible during later training.
Approach
Uses high-dimensional prototypes as stored representations of previous-task knowledge to counter knowledge shift in distillation-based incremental object detection; details beyond the abstract are not available.
Closest papers by meaning
- Alleviating Catastrophic Forgetting of Incremental Object Detection via Within-Class and Between-Class Knowledge Distillation (ICCV 2023 · similarity 0.92)
- Gradient Decomposition and Alignment for Incremental Object Detection (ICCV 2025 · similarity 0.90)
- Incremental Object Detection via Future-Aware Decoupled Cross-Head Distillation (CVPR 2026 · similarity 0.90)
- YOLO-IOD: Towards Real Time Incremental Object Detection (AAAI 2026 · similarity 0.90)
- Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector (ICML 2025 · similarity 0.88)
- DCA: Dividing and Conquering Amnesia in Incremental Object Detection (AAAI 2025 · similarity 0.88)
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.
