FocalFormer3D : Focusing on Hard Instance for 3D Object Detection

• URL: http://arxiv.org/abs/2308.04556v1
• Date: Tue, 8 Aug 2023 20:06:12 GMT
• Title: FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
• Authors: Yilun Chen, Zhiding Yu, Yukang Chen, Shiyi Lan, Animashree Anandkumar, Jiaya Jia, Jose Alvarez
• Abstract summary: False negatives (FN) in 3D object detection can lead to potentially dangerous situations in autonomous driving. In this work, we propose Hard Instance Probing (HIP), a general pipeline that identifies textitFN in a multi-stage manner. We instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects.
• Score: 97.56185033488168
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: False negatives (FN) in 3D object detection, {\em 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 \textit{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 LiDAR 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 \url{https://github.com/NVlabs/FocalFormer3D}.

Related papers

• STONE: A Submodular Optimization Framework for Active 3D Object Detection [20.54906045954377]
  Key requirement for training an accurate 3D object detector is the availability of a large amount of LiDAR-based point cloud data. This paper proposes a unified active 3D object detection framework, for greatly reducing the labeling cost of training 3D object detectors.
  arXiv  Detail & Related papers  (2024-10-04T20:45:33Z)
• TR3D: Towards Real-Time Indoor 3D Object Detection [6.215404942415161]
  TR3D is a fully-convolutional 3D object detection model trained end-to-end. To take advantage of both point cloud and RGB inputs, we introduce an early fusion of 2D and 3D features. Our model with early feature fusion, which we refer to as TR3D+FF, outperforms existing 3D object detection approaches on the SUN RGB-D dataset.
  arXiv  Detail & Related papers  (2023-02-06T15:25:50Z)
• SparseDet: Towards End-to-End 3D Object Detection [12.3069609175534]
  We propose SparseDet for end-to-end 3D object detection from point cloud. As a new detection paradigm, SparseDet maintains a fixed set of learnable proposals to represent latent candidates. SparseDet achieves highly competitive detection accuracy while running with a more efficient speed of 34.5 FPS.
  arXiv  Detail & Related papers  (2022-06-02T09:49:53Z)
• A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds [50.54083964183614]
  It is non-trivial to perform accurate target-specific detection since the point cloud of objects in raw LiDAR scans is usually sparse and incomplete. We propose DMT, a Detector-free Motion prediction based 3D Tracking network that totally removes the usage of complicated 3D detectors.
  arXiv  Detail & Related papers  (2022-03-08T17:49:07Z)
• Embracing Single Stride 3D Object Detector with Sparse Transformer [63.179720817019096]
  In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. We propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network.
  arXiv  Detail & Related papers  (2021-12-13T02:12:02Z)
• 3D-VField: Learning to Adversarially Deform Point Clouds for Robust 3D Object Detection [111.32054128362427]
  In safety-critical settings, robustness on out-of-distribution and long-tail samples is fundamental to circumvent dangerous issues. We substantially improve the generalization of 3D object detectors to out-of-domain data by taking into account deformed point clouds during training. We propose and share open source CrashD: a synthetic dataset of realistic damaged and rare cars.
  arXiv  Detail & Related papers  (2021-12-09T08:50:54Z)
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection [78.71826145162092]
  We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark.
  arXiv  Detail & Related papers  (2021-03-09T10:51:24Z)
• PLUME: Efficient 3D Object Detection from Stereo Images [95.31278688164646]
  Existing methods tackle the problem in two steps: first depth estimation is performed, a pseudo LiDAR point cloud representation is computed from the depth estimates, and then object detection is performed in 3D space. We propose a model that unifies these two tasks in the same metric space. Our approach achieves state-of-the-art performance on the challenging KITTI benchmark, with significantly reduced inference time compared with existing methods.
  arXiv  Detail & Related papers  (2021-01-17T05:11:38Z)
• 3D for Free: Crossmodal Transfer Learning using HD Maps [36.70550754737353]
  We leverage the large class-taxonomies of modern 2D datasets and the robustness of state-of-the-art 2D detection methods. We mine a collection of 1151 unlabeled, multimodal driving logs from an autonomous vehicle. We show that detector performance increases as we mine more unlabeled data.
  arXiv  Detail & Related papers  (2020-08-24T17:54:51Z)
• Weakly Supervised 3D Object Detection from Point Clouds [27.70180601788613]
  3D object detection aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors rely on annotated 3D bounding boxes during training, while these annotations could be expensive to obtain and only accessible in limited scenarios. We propose VS3D, a framework for weakly supervised 3D object detection from point clouds without using any ground truth 3D bounding box for training.
  arXiv  Detail & Related papers  (2020-07-28T03:30:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.