paper-with-me

홈 › Papers

3D Object Detection Using Scale Invariant and Feature Reweighting Networks

2019-01-08 · Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang

3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results. On the one hand, a PointSIFT module is utilized to improve the performance of 3D segmentation. It can capture the information from different orientations in space and the robustness to different scale shapes. On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module. This module reweights channel features and estimates the 3D bounding boxes more effectively. Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse.

📄 PDF Abstract BibTeX arXiv:1901.02237

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object Detectionobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
Squeeze-and-Excitation Block The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Kaiming Initialization 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Source-Free Object Detection with Detection Transformer

2025-10-13 · Huizai Yao, Sicheng Zhao, Shuo Lu, Hui Chen 외 arxiv

Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data. Most existing SFOD approaches are either confined t…

Contrastive LearningObject Detection

Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting

2021-01-01 · ICCV 2021 10 · Lei Zhu, Ke Xu, Zhanghan Ke, Rynson W.H. Lau

While CNNs achieved remarkable progress in shadow detection, they tend to make mistakes in dark non-shadow regions and relatively bright shadow regions. They are also susceptible to brightness change. These two pheno…

Shadow Detection

I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors

2021-03-25 · CVPR 2021 1 · Chaoqi Chen, Zebiao Zheng, Yue Huang, Xinghao Ding 외

Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based ins…

Region Proposal

Boost UAV-based Ojbect Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning

2024-05-24 · Fan Liu, Liang Yao, Chuanyi Zhang, Ting Wu 외

Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage …

Disentanglementobject-detectionObject Detection

Few-shot Object Detection via Feature Reweighting

2018-12-05 · ICCV 2019 10 · Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu 외

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can lear…

Few-Shot LearningFew-Shot Object DetectionImage ClassificationMeta-Learning+3