paper-with-me

Papers

RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation

2021-10-21 · Adriano Cardace, Riccardo Spezialetti, Pierluigi Zama Ramirez, Samuele Salti, Luigi Di Stefano

Unsupervised Domain Adaptation (UDA) for point cloud classification is an emerging research problem with relevant practical motivations. Reliance on multi-task learning to align features across domains has been the standard way to tackle it. In this paper, we take a different path and propose RefRec, the first approach to investigate pseudo-labels and self-training in UDA for point clouds. We present two main innovations to make self-training effective on 3D data: i) refinement of noisy pseudo-labels by matching shape descriptors that are learned by the unsupervised task of shape reconstruction on both domains; ii) a novel self-training protocol that learns domain-specific decision boundaries and reduces the negative impact of mislabelled target samples and in-domain intra-class variability. RefRec sets the new state of the art in both standard benchmarks used to test UDA for point cloud classification, showcasing the effectiveness of self-training for this important problem.

📄 PDF Abstract BibTeX arXiv:2110.11036

Code (1)

cvlab-unibo/refrec 공식 구현 pytorch

Tasks

Domain AdaptationMulti-Task LearningPoint Cloud ClassificationUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation

2026-04-08 · Donghyeon Kwon, Taegyu Park, Suha Kwak arxiv

Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. To tackle this chronic issue, we introduce RePL, a novel framework that e…

LIDAR Semantic Segmentation

Semantically Informed Multiview Surface Refinement

2017-06-26 · ICCV 2017 10 · Maros Blaha, Mathias Rothermel, Martin R. Oswald, Torsten Sattler 외

We present a method to jointly refine the geometry and semantic segmentation of 3D surface meshes. Our method alternates between updating the shape and the semantic labels. In the geometry refinement step, the mesh is de…

3D geometry3D ReconstructionSegmentationSemantic Segmentation

Self-supervised Disentanglement of Disease Effects from Aging in 3D Medical Shapes

2026-03-16 · Jakaria Rabbi, Nilanjan Ray, Dana Cobzas arxiv

Disentangling pathological changes from physiological aging in 3D medical shapes is crucial for developing interpretable biomarkers and patient stratification. However, this separation is challenging when diagnosis label…

FuRPE: Learning Full-body Reconstruction from Part Experts

2022-11-30 · Zhaoxin Fan, Yuqing Pan, Hao Xu, Zhenbo Song 외

In the field of full-body reconstruction, the scarcity of annotated data often impedes the efficacy of prevailing methods. To address this issue, we introduce FuRPE, a novel framework that employs part-experts and an ing…

Learning Articulated Shape with Keypoint Pseudo-labels from Web Images

2023-04-27 · CVPR 2023 1 · Anastasis Stathopoulos, Georgios Pavlakos, Ligong Han, Dimitris Metaxas

This paper shows that it is possible to learn models for monocular 3D reconstruction of articulated objects (e.g., horses, cows, sheep), using as few as 50-150 images labeled with 2D keypoints. Our proposed approach invo…

3D ReconstructionKeypoint EstimationObject