Papers for incremental learning to avoid catastrophic forgetting on object detection.

• Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation (CVPR 2022) [paper] [code]

• Incremental Object Detection via Meta-Learning (TPAMI 2021) [paper] [code]
• Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection (NeurIPS 2021) [paper]
• Wanderlust: Online Continual Object Detection in the Real World (ICCV 2021) [paper]
• Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning (ICCV 2021) [paper] [code]
• Towards Open World Object Detection (CVPR 2021) [paper] [code] [video]

• Incremental Few-Shot Object Detection (CVPR 2020) [paper]
• RODEO: Replay for Online Object Detection (BMVC 2020) [paper] [code]

• An End-to-End Architecture for Class-Incremental Object Detection with Knowledge Distillation (IEEE ICME 2019) [paper]

• Incremental Learning of Object Detectors Without Catastrophic Forgetting (ICCV 2017) [paper]
• iCaRL: Incremental classifier and Representation Learning (CVPR 2017) [paper] [code]

• Learning without Forgetting (ECCV 2016) [paper] [code]

• Distilling the Knowledge in a Neural Network（NIPS 2014）[paper]

Knowledge distillation can be used for object detection.

• Focal and Global Knowledge Distillation for Detectors (CVPR 2022) [paper] [code]
• Localization Distillation for Dense Object Detection （CVPR 2022） [paper] [code]
• Decoupled Knowledge Distillation （CVPR 2022）[paper] [code]
• Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation （AAAI 2022）[paper]

• G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation (ICCV 2021) [paper]
• End-to-End Semi-Supervised Object Detection with Soft Teacher (ICCV 2021)[papaer] [code]
• Distilling Knowledge via Knowledge Review (CVPR 2021) [paper] [code]
• General Instance Distillation for Object Detection (CVPR 2021) [paper]
• Distilling Object Detectors via Decoupled Features (CVPR 2021) [paper] [code]
• Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors (ICLR 2021) [paper] [code]

• Distilling Object Detectors with Fine-grained Feature Imitation (CVPR 2019) [paper] [code]

• Learning Efficient Object Detection Models with Knowledge Distillation (NIPS 2017) [paper]