2023 · 13 citations · 46 references
ComputingComputer ScienceCurriculumComputer VisionMachine LearningRobot VisionManipulation LearningObject DetectionObject ManipulationObject RecognitionPoint Cloud ProcessingScene Understanding3D Object DetectionAblation StudiesData Augmentation For Robot LearningHeuristicsLidar-based PerceptionModel Performance AnalysisModel Performance EvaluationPoint Cloud Object Detection
This paper explores the potential of curriculum learning in LiDAR-based 3D object detection by proposing a curricular object manipulation (COM) framework. The framework embeds the curricular training strategy into both the loss design and the augmentation process. For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages. On top of the widely-used augmentation technique called GT-Aug in Li-DAR detection tasks, we propose a novel COMAug strategy which first clusters objects in ground-truth database based on well-designed heuristics. Group-level difficulties rather than individual ones are then predicted and updated during training for stable results. Model performance and generalization capabilities can be improved by sampling and augmenting progressively more difficult objects into the training samples. Extensive experiments and ablation studies reveal the superior and generality of the proposed framework. The code is available at https://github.com/ZZY816/COM.
46
Focal Loss for Dense Object Detection
Tsung-Yi Lin, Priya Goyal, Ross Girshick et al. · 2017 · 25.7K citations
Are we ready for autonomous driving? The KITTI vision benchmark suite
Andreas Geiger, P Lenz, R. Urtasun · 2012 · 14.4K citations
Yoshua Bengio, Jérôme Louradour, Ronan Collobert et al. · 2009 · 5K citations · Full text
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Yin Zhou, Oncel Tuzel · 2018 · 4.6K citations
CenterNet: Keypoint Triplets for Object Detection
Kaiwen Duan, Song Bai, Lingxi Xie et al. · 2019 · 3.5K citations