Learning on the Fly: Replay-Based Continual Object Perception for Indoor Drones
Autonomous agents such as indoor drones must learn new object classes in real-time while limiting catastrophic forgetting, motivating Class-Incremental Learning (CIL). However, most unmanned aerial vehicle (UAV) datasets focus on outdoor scenes and offer limited temporally coherent indoor videos. We introduce an indoor dataset of $14,400$ frames capturing inter-drone and ground vehicle footage, annotated via a semi-automatic workflow with a $98.6\%$ first-pass labeling agreement before final manual verification. Using this dataset, we benchmark 3 replay-based CIL strategies: Experience Replay (ER), Maximally Interfered Retrieval (MIR), and Forgetting-Aware Replay (FAR), using YOLOv11-nano as a resource-efficient detector for deployment-constrained UAV platforms. Under tight memory budgets ($5-10\%$ replay), FAR performs better than the rest, achieving an average accuracy (ACC, $mAP_{50-95}$ across increments) of $82.96\%$ with $5\%$ replay. Gradient-weighted class activation mapping (Grad-CAM) analysis shows attention shifts across classes in mixed scenes, which is associated with reduced localization quality for drones. The experiments further demonstrate that replay-based continual learning can be effectively applied to edge aerial systems. Overall, this work contributes an indoor UAV video dataset with preserved temporal coherence and an evaluation of replay-based CIL under limited replay budgets. Project page: https://spacetime-vision-robotics-laboratory.github.io/learning-on-the-fly-cl
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningContinual LearningSimilar Papers 제목 키워드 기반
From Photons to Physics: Autonomous Indoor Drones and the Future of Objective Property Assessment
The convergence of autonomous indoor drones with physics-aware sensing technologies promises to transform property assessment from subjective visual inspection to objective, quantitative measurement. This comprehensive r…
Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replay
The integration of Unmanned Aerial Vehicles (UAVs) into Search and Rescue (SAR) missions presents a promising avenue for enhancing operational efficiency and effectiveness. However, the success of these missions is not s…
Multi-Objective Reinforcement Learningreinforcement-learningReinforcement LearningTrajectory PlanningSelf-Improving Semantic Perception for Indoor Localisation
We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fixed models, we propose a framework in wh…
2D Semantic SegmentationContinual LearningRobust3D-CIL: Robust Class-Incremental Learning for 3D Perception
3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models must continuously adapt to new data and emerging object categori…
Autonomous Drivingclass-incremental learningClass Incremental LearningContinual Learning+1Rethinking Transfer in Continual Learning: A Replay-Based Realisation
Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch. Existing methods, whether rehearsal-based (replaying stored past data) or rehearsal-fre…
Continual Learning