CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection

• URL: http://arxiv.org/abs/2204.00325v2
• Date: Mon, 4 Apr 2022 04:45:36 GMT
• Title: CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection
• Authors: Yanan Zhang, Jiaxin Chen, Di Huang
• Abstract summary: We propose Contrastively Augmented Transformer for multi-modal 3D object Detection (CAT-Det) CAT-Det adopts a two-stream structure consisting of a Pointformer (PT) branch, an Imageformer (IT) branch along with a Cross-Modal Transformer (CMT) module. We propose an effective One-way Multi-modal Data Augmentation (OMDA) approach via hierarchical contrastive learning at both the point and object levels.
• Score: 32.06145370498289
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In autonomous driving, LiDAR point-clouds and RGB images are two major data modalities with complementary cues for 3D object detection. However, it is quite difficult to sufficiently use them, due to large inter-modal discrepancies. To address this issue, we propose a novel framework, namely Contrastively Augmented Transformer for multi-modal 3D object Detection (CAT-Det). Specifically, CAT-Det adopts a two-stream structure consisting of a Pointformer (PT) branch, an Imageformer (IT) branch along with a Cross-Modal Transformer (CMT) module. PT, IT and CMT jointly encode intra-modal and inter-modal long-range contexts for representing an object, thus fully exploring multi-modal information for detection. Furthermore, we propose an effective One-way Multi-modal Data Augmentation (OMDA) approach via hierarchical contrastive learning at both the point and object levels, significantly improving the accuracy only by augmenting point-clouds, which is free from complex generation of paired samples of the two modalities. Extensive experiments on the KITTI benchmark show that CAT-Det achieves a new state-of-the-art, highlighting its effectiveness.

Related papers

• LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving [52.83707400688378]
  LargeAD is a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets. Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds to generate high-quality contrastive samples. Our approach delivers significant performance improvements over state-of-the-art methods in both linear probing and fine-tuning tasks for both LiDAR-based segmentation and object detection.
  arXiv  Detail & Related papers  (2025-01-07T18:59:59Z)
• SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection [73.49799596304418]
  This paper introduces a new task called Multi-Modal datasets and Multi-Task Object Detection (M2Det) for remote sensing. It is designed to accurately detect horizontal or oriented objects from any sensor modality. This task poses challenges due to 1) the trade-offs involved in managing multi-modal modelling and 2) the complexities of multi-task optimization.
  arXiv  Detail & Related papers  (2024-12-30T02:47:51Z)
• PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest [65.48057241587398]
  PoIFusion is a framework to fuse information of RGB images and LiDAR point clouds at the points of interest (PoIs) Our approach maintains the view of each modality and obtains multi-modal features by computation-friendly projection and computation. We conducted extensive experiments on nuScenes and Argoverse2 datasets to evaluate our approach.
  arXiv  Detail & Related papers  (2024-03-14T09:28:12Z)
• Bi-directional Adapter for Multi-modal Tracking [67.01179868400229]
  We propose a novel multi-modal visual prompt tracking model based on a universal bi-directional adapter. We develop a simple but effective light feature adapter to transfer modality-specific information from one modality to another. Our model achieves superior tracking performance in comparison with both the full fine-tuning methods and the prompt learning-based methods.
  arXiv  Detail & Related papers  (2023-12-17T05:27:31Z)
• UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation [113.35352122662752]
  We present an efficient multi-modal backbone for outdoor 3D perception named UniTR. UniTR processes a variety of modalities with unified modeling and shared parameters. UniTR is also a fundamentally task-agnostic backbone that naturally supports different 3D perception tasks.
  arXiv  Detail & Related papers  (2023-08-15T12:13:44Z)
• MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving [15.36416000750147]
  We propose a multi-modal 3D semantic segmentation model (MSeg3D) with joint intra-modal feature extraction and inter-modal feature fusion. MSeg3D still shows robustness and improves the LiDAR-only baseline.
  arXiv  Detail & Related papers  (2023-03-15T13:13:03Z)
• PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection [3.691671505269693]
  Most multi-modal detection methods perform even worse than LiDAR-only methods. A Pseudo Point Cloud Generation Network is proposed to convert image information by pseudo points. The features of LiDAR points and pseudo points from image can be deeply fused under a unified point-based representation.
  arXiv  Detail & Related papers  (2023-01-18T04:35:49Z)
• FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection [11.962073589763676]
  Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm. The sparsity of point clouds, especially for the points far away, makes it difficult for the LiDAR-only refinement module to accurately recognize and locate objects. We propose a novel multi-modality two-stage approach named FusionRCNN, which effectively and efficiently fuses point clouds and camera images in the Regions of Interest(RoI) FusionRCNN significantly improves the strong SECOND baseline by 6.14% mAP on baseline, and outperforms competing two-stage approaches.
  arXiv  Detail & Related papers  (2022-09-22T02:07:25Z)
• AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection [17.526914782562528]
  We propose AutoAlignV2, a faster and stronger multi-modal 3D detection framework, built on top of AutoAlign. Our best model reaches 72.4 NDS on nuScenes test leaderboard, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-07-21T06:17:23Z)
• EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection [56.03081616213012]
  We propose EPNet++ for multi-modal 3D object detection by introducing a novel Cascade Bi-directional Fusion(CB-Fusion) module. The proposed CB-Fusion module boosts the plentiful semantic information of point features with the image features in a cascade bi-directional interaction fusion manner. The experiment results on the KITTI, JRDB and SUN-RGBD datasets demonstrate the superiority of EPNet++ over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-21T10:48:34Z)

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.