paper-with-me

홈 › Papers

LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation

2021-03-16 · Jingdao Chen, Zsolt Kira, Yong K. Cho

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation methods are mostly class-specific, many of which are tuned to work with specific object categories and may not be generalizable to different types of scenes. This research proposes a learnable region growing method for class-agnostic point cloud segmentation, specifically for the task of instance label prediction. The proposed method is able to segment any class of objects using a single deep neural network without any assumptions about their shapes and sizes. The deep neural network is trained to predict how to add or remove points from a point cloud region to morph it into incrementally more complete regions of an object instance. Segmentation results on the S3DIS and ScanNet datasets show that the proposed method outperforms competing methods by 1%-9% on 6 different evaluation metrics.

📄 PDF Abstract BibTeX arXiv:2103.09160

Code (1)

jingdao/learn_region_grow 공식 구현 tf

Tasks

Instance SegmentationMORPHPoint Cloud SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

2022-12-31 · CVPR 2023 1 · Jiaming Zhang, Xingjun Ma, Qi Yi, Jitao Sang 외

There is a growing interest in developing unlearnable examples (UEs) against visual privacy leaks on the Internet. UEs are training samples added with invisible but unlearnable noise, which have been found can prevent un…

Data Poisoning

Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding

2022-03-17 · Joachim Nyborg, Charlotte Pelletier, Ira Assent

Large-scale crop type classification is a task at the core of remote sensing efforts with applications of both economic and ecological importance. Current state-of-the-art deep learning methods are based on self-attentio…

Crop ClassificationTime SeriesTime Series Analysis

Stability and List-Replicability for Agnostic Learners

2025-01-09 · Ari Blondal, Shan Gao, Hamed Hatami, Pooya Hatami

Two seminal papers--Alon, Livni, Malliaris, Moran (STOC 2019) and Bun, Livni, and Moran (FOCS 2020)--established the equivalence between online learnability and globally stable PAC learnability in binary classification. …

Binary Classification

Adversarially Robust PAC Learnability of Real-Valued Functions

2022-06-26 · Idan Attias, Steve Hanneke

We study robustness to test-time adversarial attacks in the regression setting with $\ell_p$ losses and arbitrary perturbation sets. We address the question of which function classes are PAC learnable in this setting. We…

regression

CLIP-Joint-Detect: End-to-End Joint Training of Object Detectors with Contrastive Vision-Language Supervision

2025-12-28 · Behnam Raoufi, Hossein Sharify, Mohamad Mahdee Ramezanee, Khosrow Hajsadeghi 외 arxiv

Conventional object detectors rely on cross-entropy classification, which can be vulnerable to class imbalance and label noise. We propose CLIP-Joint-Detect, a simple and detector-agnostic framework that integrates CLIP-…