AGO-Net: Association-Guided 3D Point Cloud Object Detection Network

TL;DR

AGO-Net introduces an association-guided 3D detection framework inspired by human recognition, utilizing domain adaptation and attention mechanisms to improve detection of occluded and distant objects in LiDAR point clouds, achieving state-of-the-art results.

Contribution

The paper proposes a novel 3D detection framework that employs domain adaptation and attention-based feature re-weighting, enhancing robustness to occlusion and distance without extra inference cost.

Findings

Achieves state-of-the-art accuracy on KITTI benchmark.

Improves detection of occluded and distant objects.

Validates versatility across nuScenes and Waymo datasets.

Abstract

The human brain can effortlessly recognize and localize objects, whereas current 3D object detection methods based on LiDAR point clouds still report inferior performance for detecting occluded and distant objects: the point cloud appearance varies greatly due to occlusion, and has inherent variance in point densities along the distance to sensors. Therefore, designing feature representations robust to such point clouds is critical. Inspired by human associative recognition, we propose a novel 3D detection framework that associates intact features for objects via domain adaptation. We bridge the gap between the perceptual domain, where features are derived from real scenes with sub-optimal representations, and the conceptual domain, where features are extracted from augmented scenes that consist of non-occlusion objects with rich detailed information. A feasible method is investigated to construct conceptual scenes without external datasets. We further introduce an attention-based re-weighting module that adaptively strengthens the feature adaptation of more informative regions. The network's feature enhancement ability is exploited without introducing extra cost during inference, which is plug-and-play in various 3D detection frameworks. We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed. Experiments on nuScenes and Waymo datasets also validate the versatility of our method.