Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection

• URL: http://arxiv.org/abs/2406.10115v3
• Date: Tue, 15 Oct 2024 14:54:01 GMT
• Title: Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection
• Authors: Mehar Khurana, Neehar Peri, James Hays, Deva Ramanan,
• Abstract summary: State-of-the-art 3D object detectors are often trained on massive labeled datasets. Recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. We propose a shelf-supervised approach for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data.
• Score: 52.66283064389691
• License:
• Abstract: State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. Contemporary methods adapt best-practices for self-supervised learning from the image domain to point clouds (such as contrastive learning). However, publicly available 3D datasets are considerably smaller and less diverse than those used for image-based self-supervised learning, limiting their effectiveness. We do note, however, that such 3D data is naturally collected in a multimodal fashion, often paired with images. Rather than pre-training with only self-supervised objectives, we argue that it is better to bootstrap point cloud representations using image-based foundation models trained on internet-scale data. Specifically, we propose a shelf-supervised approach (e.g. supervised with off-the-shelf image foundation models) for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. Pre-training 3D detectors with such pseudo-labels yields significantly better semi-supervised detection accuracy than prior self-supervised pretext tasks. Importantly, we show that image-based shelf-supervision is helpful for training LiDAR-only, RGB-only and multi-modal (RGB + LiDAR) detectors. We demonstrate the effectiveness of our approach on nuScenes and WOD, significantly improving over prior work in limited data settings. Our code is available at https://github.com/meharkhurana03/cm3d

Related papers

• Training an Open-Vocabulary Monocular 3D Object Detection Model without 3D Data [57.53523870705433]
  We propose a novel open-vocabulary monocular 3D object detection framework, dubbed OVM3D-Det. OVM3D-Det does not require high-precision LiDAR or 3D sensor data for either input or generating 3D bounding boxes. It employs open-vocabulary 2D models and pseudo-LiDAR to automatically label 3D objects in RGB images, fostering the learning of open-vocabulary monocular 3D detectors.
  arXiv  Detail & Related papers  (2024-11-23T21:37:21Z)
• Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps [8.897884780881535]
  LiDAR-based 3D object detectors often fail to adapt well to target domains with different sensor configurations. Recent studies suggest that pre-trained backbones can be learned in a self-supervised manner with large-scale unlabeled LiDAR frames. We propose a novel method, called Domain Adaptive Distill-Tuning (DADT), to adapt a pre-trained model with limited target data.
  arXiv  Detail & Related papers  (2024-10-02T08:22:42Z)
• View-to-Label: Multi-View Consistency for Self-Supervised 3D Object Detection [46.077668660248534]
  We propose a novel approach to self-supervise 3D object detection purely from RGB sequences alone. Our experiments on KITTI 3D dataset demonstrate performance on par with state-of-the-art self-supervised methods.
  arXiv  Detail & Related papers  (2023-05-29T09:30:39Z)
• Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency [78.76508318592552]
  Monocular 3D object detection has become a mainstream approach in automatic driving for its easy application. Most current methods still rely on 3D point cloud data for labeling the ground truths used in the training phase. We propose a new weakly supervised monocular 3D objection detection method, which can train the model with only 2D labels marked on images.
  arXiv  Detail & Related papers  (2023-03-15T15:14:00Z)
• Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving [91.39625612027386]
  We propose a novel task, called generalized few-shot 3D object detection, where we have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes. Specifically, we analyze in-depth differences between images and point clouds, and then present a practical principle for the few-shot setting in the 3D LiDAR dataset. To solve this task, we propose an incremental fine-tuning method to extend existing 3D detection models to recognize both common and rare objects.
  arXiv  Detail & Related papers  (2023-02-08T07:11:36Z)
• An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection [72.30883544352918]
  We investigate whether pseudo-labels can provide effective supervision for the baseline models under varying settings. We achieve 20.23 AP for moderate level on the KITTI-3D testing set without bells and whistles, improving the baseline model by 6.03 AP. We hope this work can provide insights for the image-based 3D detection community under a semi-supervised setting.
  arXiv  Detail & Related papers  (2022-08-15T12:17:46Z)
• Self-Supervised Pretraining of 3D Features on any Point-Cloud [40.26575888582241]
  We present a simple self-supervised pertaining method that can work with any 3D data without 3D registration. We evaluate our models on 9 benchmarks for object detection, semantic segmentation, and object classification, where they achieve state-of-the-art results and can outperform supervised pretraining.
  arXiv  Detail & Related papers  (2021-01-07T18:55:21Z)
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding [107.02479689909164]
  In this work, we aim at facilitating research on 3D representation learning. We measure the effect of unsupervised pre-training on a large source set of 3D scenes.
  arXiv  Detail & Related papers  (2020-07-21T17:59:22Z)

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.