DetMatch：2Dと3Dの半教師あり物体検出を統合するデュアルティーチャーフレームワーク
DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection
RGB画像と点群の相補性を活かし、2Dと3Dの半教師あり物体検出を統合的に学習するフレームワークを提案。両センサーで検出された物体を基に高品質な擬似ラベルを生成し、単一モダリティの誤り伝播を抑制する。
著者: Jinhyung Park, Chenfeng Xu, Yiyang Zhou, Masayoshi Tomizuka, Wei Zhan
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
While numerous 3D detection works leverage the complementary relationship between RGB images and point clouds, developments in the broader framework of semi-supervised object recognition remain uninfluenced by multi-modal fusion. Current methods develop independent pipelines for 2D and 3D semi-supervised learning despite the availability of paired image and point cloud frames. Observing that the distinct characteristics of each sensor cause them to be biased towards detecting different objects, we propose DetMatch, a flexible framework for joint semi-supervised learning on 2D and 3D modalities. By identifying objects detected in both sensors, our pipeline generates a cleaner, more robust set of pseudo-labels that both demonstrates stronger performance and stymies single-modality error propagation. Further, we leverage the richer semantics of RGB images to rectify incorrect 3D class predictions and improve localization of 3D boxes. Evaluating on the challenging KITTI and Waymo datasets, we improve upon strong semi-supervised learning methods and observe higher quality pseudo-labels. Code will be released at https://github.com/Divadi/DetMatch
