Transferable Class Statistics and Multi-scale Feature Approximation for 3D Object Detection

2025-08-16 · Hao Peng, Hong Sang, Yajing Ma, Ping Qiu, Chao Ji arxiv

This paper investigates multi-scale feature approximation and transferable features for object detection from point clouds. Multi-scale features are critical for object detection from point clouds. However, multi-scale feature learning usually involves multiple neighborhood searches and scale-aware layers, which can hinder efforts to achieve lightweight models and may not be conducive to research constrained by limited computational resources. This paper approximates point-based multi-scale features from a single neighborhood based on knowledge distillation. To compensate for the loss of constructive diversity in a single neighborhood, this paper designs a transferable feature embedding mechanism. Specifically, class-aware statistics are employed as transferable features given the small computational cost. In addition, this paper introduces the central weighted intersection over union for localization to alleviate the misalignment brought by the center offset in optimization. Note that the method presented in this paper saves computational costs. Extensive experiments on public datasets demonstrate the effectiveness of the proposed method.

📄 PDF Abstract BibTeX arXiv:2508.11951

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation 3D Object Detection Point Clouds

ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation

2020-09-07 · Sicheng Zhao, Yezhen Wang, Bo Li, Bichen Wu 외

Due to its robust and precise distance measurements, LiDAR plays an important role in scene understanding for autonomous driving. Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotat…

Autonomous Driving Domain Adaptation Point Cloud Segmentation Scene Understanding+1

Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

2018-11-12 · Jun Wen, Risheng Liu, Nenggan Zheng, Qian Zheng 외

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature align…

Domain Adaptation Unsupervised Domain Adaptation

Learning Multiple Tasks with Multilinear Relationship Networks

2015-06-06 · NeurIPS 2017 12 · Mingsheng Long, Zhangjie Cao, Jian-Min Wang, Philip S. Yu

Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific along deep networks, a fundamental problem …

Multi-Task Learning

Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization

2021-06-30 · Marin Scalbert, Maria Vakalopoulou, Florent Couzinié-Devy

Multi-Source Unsupervised Domain Adaptation (multi-source UDA) aims to learn a model from several labeled source domains while performing well on a different target domain where only unlabeled data are available at train…

Contrastive Learning Domain Adaptation Multi-Source Unsupervised Domain Adaptation Unsupervised Domain Adaptation

Learning Transferable Features with Deep Adaptation Networks

2015-02-10 · Mingsheng Long, Yue Cao, Jian-Min Wang, Michael. I. Jordan

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along …

Domain Adaptation image-classification Image Classification Multi-Source Unsupervised Domain Adaptation