paper-with-me

홈 › Papers

Patch Refinement -- Localized 3D Object Detection

2019-10-09 · Johannes Lehner, Andreas Mitterecker, Thomas Adler, Markus Hofmarcher, Bernhard Nessler, Sepp Hochreiter

We introduce Patch Refinement a two-stage model for accurate 3D object detection and localization from point cloud data. Patch Refinement is composed of two independently trained Voxelnet-based networks, a Region Proposal Network (RPN) and a Local Refinement Network (LRN). We decompose the detection task into a preliminary Bird's Eye View (BEV) detection step and a local 3D detection step. Based on the proposed BEV locations by the RPN, we extract small point cloud subsets ("patches"), which are then processed by the LRN, which is less limited by memory constraints due to the small area of each patch. Therefore, we can apply encoding with a higher voxel resolution locally. The independence of the LRN enables the use of additional augmentation techniques and allows for an efficient, regression focused training as it uses only a small fraction of each scene. Evaluated on the KITTI 3D object detection benchmark, our submission from January 28, 2019, outperformed all previous entries on all three difficulties of the class car, using only 50 % of the available training data and only LiDAR information.

📄 PDF Abstract BibTeX arXiv:1910.04093

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionObjectobject-detectionObject DetectionRegion Proposal

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Similar Papers 제목 키워드 기반

DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks

2021-02-05 · Chong Xiang, Prateek Mittal

State-of-the-art object detectors are vulnerable to localized patch hiding attacks, where an adversary introduces a small adversarial patch to make detectors miss the detection of salient objects. The patch attacker can …

image-classificationImage ClassificationObjectobject-detection+2

Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models

2026-01-28 · Yuhao Sun, Chengyi Cai, Jiacheng Zhang, Zesheng Ye 외 arxiv

Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of pre-trained vision-language models (e.g., CLIP). However, we find…

Adversarial Patch Attack for Ship Detection via Localized Augmentation

2025-08-29 · Chun Liu, Panpan Ding, Zheng Zheng, Hailong Wang 외 arxiv

Current ship detection techniques based on remote sensing imagery primarily rely on the object detection capabilities of deep neural networks (DNNs). However, DNNs are vulnerable to adversarial patch attacks, which can l…

Object Detection

Context Refinement for Object Detection

2018-09-01 · ECCV 2018 9 · Zhe Chen, Shaoli Huang, DaCheng Tao

Current two-stage object detectors, which consists of a region proposal stage and a refinement stage, may produce unreliable results due to ill-localized proposed regions. To address this problem, we propose a context re…

Objectobject-detectionObject DetectionRegion Proposal

Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks

2022-08-19 · Husheng Han, Xing Hu, Kaidi Xu, Pucheng Dang 외

DNN-based video object detection (VOD) powers autonomous driving and video surveillance industries with rising importance and promising opportunities. However, adversarial patch attack yields huge concern in live vision …

Adversarial AttackAutonomous DrivingFeature ImportanceObject+3