Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

2022-05-07 · Prajval Kumar Murali, Cong Wang, Ravinder Dahiya, Mohsen Kaboli

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense point clouds and performance drops significantly for sparse point clouds. Unsupervised domain adaption allows to minimise the discrepancy between dense and sparse point clouds with minimal unlabelled sparse point clouds, thereby saving additional sparse data collection, annotation and retraining costs. In this work, we propose a novel method for point cloud based object recognition with competitive performance with state-of-art methods on dense and sparse point clouds while being trained only with dense point clouds.

📄 PDF Abstract BibTeX arXiv:2205.03654

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object Recognition Autonomous Vehicles Domain AdaptationObjectObject Recognition

Object-based (yet Class-agnostic) Video Domain Adaptation

2023-11-29 · Dantong Niu, Amir Bar, Roei Herzig, Trevor Darrell 외

Existing video-based action recognition systems typically require dense annotation and struggle in environments when there is significant distribution shift relative to the training data. Current methods for video domain…

Action Recognition Domain Adaptation Object

Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection

2022-11-23 · Tianyu Wang, Xiaowei Hu, Zhengzhe Liu, Chi-Wing Fu

LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Yet, small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a n…

3D Object Detection Domain Adaptation object-detection Object Detection+1

Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation

2021-07-30 · ICCV 2021 10 · Duo Peng, Yinjie Lei, Wen Li, Pingping Zhang 외

Domain adaptation is critical for success when confronting with the lack of annotations in a new domain. As the huge time consumption of labeling process on 3D point cloud, domain adaptation for 3D semantic segmentation …

3D Semantic Segmentation Domain Adaptation Semantic Segmentation

PISA: A Pseudo-Individual Source-Domain Feature Adaptation Framework for Test-Time Open-Vocabulary Object Detection

2026-08-14 · Ziyan He, Xiongtai Yang, Tao Wang arxiv

Open-vocabulary object detection test-time adaptation (OVOD-TTA) aims to address the performance degradation that pre-trained base models suffer when encountering image-domain shifts. Existing source-free OVOD-TTA method…

Test-time Adaptation Object Detection

Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data

2020-08-03 · Adrian Lopez-Rodriguez, Benjamin Busam, Krystian Mikolajczyk

Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground truth annotations for depth completion settings can be difficult and, at the same time, a significant domain g…

Depth Completion Domain Adaptation