Robust3D-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 categories, but retraining from scratch incurs prohibitive costs. Therefore, adopting class-incremental learning (CIL) becomes particularly essential. However, real-world 3D point cloud data often include corrupted samples, which poses significant challenges for existing CIL methods and leads to more severe forgetting on corrupted data. To address these challenges, we consider the scenario in which a CIL model can be updated using point clouds with unknown corruption to better simulate real-world conditions. Inspired by Farthest Point Sampling, we propose a novel exemplar selection strategy that effectively preserves intra-class diversity when selecting replay exemplars, mitigating forgetting induced by data corruption. Furthermore, we introduce a point cloud downsampling-based replay method to utilize the limited replay buffer memory more efficiently, thereby further enhancing the model's continual learning ability. Extensive experiments demonstrate that our method improves the performance of replay-based CIL baselines by 2% to 11%, proving its effectiveness and promising potential for real-world 3D applications.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous Drivingclass-incremental learningClass Incremental LearningContinual LearningIncremental LearningSimilar Papers 제목 키워드 기반
Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments
Incremental 3D object perception is a critical step toward embodied intelligence in dynamic indoor environments. However, existing incremental 3D detection methods rely on extensive annotations of novel classes for satis…
Novel Object Detection3D Object DetectionThalamo-cortical spiking model of incremental learning combining perception, context and NREM-sleep-mediated noise-resilience
The brain exhibits capabilities of fast incremental learning from few noisy examples, as well as the ability to associate similar memories in autonomously-created categories and to combine contextual hints with sensory p…
Incremental LearningIncremental Learning for Robot Perception through HRI
Scene understanding and object recognition is a difficult to achieve yet crucial skill for robots. Recently, Convolutional Neural Networks (CNN), have shown success in this task. However, there is still a gap between the…
Incremental LearningObjectobject-detectionObject Detection+2Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation
Generalized Few-shot Semantic Segmentation (GFSS) extends Few-shot Semantic Segmentation (FSS) to simultaneously segment unseen classes and seen classes during evaluation. Previous works leverage additional branch or pro…
Few-Shot Semantic SegmentationGeneralized Few-Shot Semantic SegmentationSegmentationSemantic SegmentationClass-Incremental Motion Forecasting
Motion forecasting enables autonomous vehicles to anticipate scene evolution by predicting the future trajectories of dynamic agents. However, existing approaches typically assume a closed-world setting with a fixed obje…
Autonomous VehiclesMotion Forecasting