CVFeb 29, 2024

SeMoLi: What Moves Together Belongs Together

arXiv:2402.19463v214 citationsh-index: 24CVPR
AI Analysis

This addresses the problem of reducing manual supervision for object detection in autonomous driving, representing a novel method rather than an incremental improvement.

The paper tackles semi-supervised 3D object detection in Lidar data by using data-driven motion cues to pseudo-label object instances, achieving a 57.5 AP with a +14 improvement over prior work.

We tackle semi-supervised object detection based on motion cues. Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as supervisory signals to train 3D object detectors in Lidar data without manual supervision. We re-think this approach and suggest that both, object detection, as well as motion-inspired pseudo-labeling, can be tackled in a data-driven manner. We leverage recent advances in scene flow estimation to obtain point trajectories from which we extract long-term, class-agnostic motion patterns. Revisiting correlation clustering in the context of message passing networks, we learn to group those motion patterns to cluster points to object instances. By estimating the full extent of the objects, we obtain per-scan 3D bounding boxes that we use to supervise a Lidar object detection network. Our method not only outperforms prior heuristic-based approaches (57.5 AP, +14 improvement over prior work), more importantly, we show we can pseudo-label and train object detectors across datasets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes