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

• 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)
• Weakly Aligned Feature Fusion for Multimodal Object Detection [52.15436349488198]
  multimodal data often suffer from the position shift problem, i.e., the image pair is not strictly aligned. This problem makes it difficult to fuse multimodal features and puzzles the convolutional neural network (CNN) training. In this article, we propose a general multimodal detector named aligned region CNN (AR-CNN) to tackle the position shift problem.
  arXiv  Detail & Related papers  (2022-04-21T02:35:23Z)
• 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)
• M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers [78.48081972698888]
  We present M3DeTR, which combines different point cloud representations with different feature scales based on multi-scale feature pyramids. M3DeTR is the first approach that unifies multiple point cloud representations, feature scales, as well as models mutual relationships between point clouds simultaneously using transformers.
  arXiv  Detail & Related papers  (2021-04-24T06:48:23Z)

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.