English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent years have witnessed huge successes in 3D object detection torecognize common objects for autonomous driving (e.g., vehicles andpedestrians). However, most methods rely heavily on a large amount ofwell-labeled training data. This limits their capability of detecting rarefine-grained objects (e.g., police cars and ambulances), which is important forspecial cases, such as emergency rescue, and so on. To achieve simultaneousdetection for both common and rare objects, we propose a novel task, calledgeneralized few-shot 3D object detection, where we have a large amount oftraining data for common (base) objects, but only a few data for rare (novel)classes. Specifically, we analyze in-depth differences between images and pointclouds, and then present a practical principle for the few-shot setting in the3D LiDAR dataset. To solve this task, we propose a simple and effectivedetection framework, including (1) an incremental fine-tuning method to extendexisting 3D detection models to recognize both common and rare objects, and (2)a sample adaptive balance loss to alleviate the issue of long-tailed datadistribution in autonomous driving scenarios. On the nuScenes dataset, weconduct sufficient experiments to demonstrate that our approach cansuccessfully detect the rare (novel) classes that contain only a few trainingdata, while also maintaining the detection accuracy of common objects.

Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving