SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.04556 · ICCV · 2023

FocalFormer3D : Focusing on Hard Instance for 3D Object Detection

Anima Anandkumar, Hong Kong, Zhiding Yu, Caltech, Jose Alvarez, Jiaya Jia, Yilun Chen, Yukang Chen, Shiyi Lan

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

False negatives (FN) in 3D object detection, e.g., missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomous driving. While being fatal, this issue is understudied in many current 3D detection methods. In this work, we propose Hard Instance Probing (HIP), a general pipeline that identifies FN in a multi-stage manner and guides the models to focus on excavating difficult instances. For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall. FocalFormer3D features a multi-stage query generation to discover hard objects and a box-level transformer decoder to efficiently distinguish objects from massive object candidates. Experimental results on the nuScenes and Waymo datasets validate the superior performance of FocalFormer3D. The advantage leads to strong performance on both detection and tracking, in both Li-DAR and multi-modal settings. Notably, FocalFormer3D achieves a 70.5 mAP and 73.9 NDS on nuScenes detection benchmark, while the nuScenes tracking benchmark shows 72.1 AMOTA, both ranking 1st place on the nuScenes LiDAR leaderboard. Our code is available at https: //github.com/NVlabs/FocalFormer3D.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.04556")
get_code_for_paper("2308.04556")
have("2308.04556")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2308.04556.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2308.04556.svg)](https://syntology.ai/paper/2308.04556)

Connect an agent — have() is free.