paper-with-me

Papers

Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation

2024-07-11 · Zeyang Zhao, Qilong Xue, Yuhang He, Yifan Bai, Xing Wei, Yihong Gong

This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects, providing detailed shape descriptions. 2) Axes define the primary directionalities of objects, providing essential orientation cues crucial for precise detection. The point-axis representation decouples location and rotation, addressing the loss discontinuity issues commonly encountered in traditional bounding box-based approaches. For effective optimization without introducing additional annotations, we propose the max-projection loss to supervise point set learning and the cross-axis loss for robust axis representation learning. Further, leveraging this representation, we present the Oriented DETR model, seamlessly integrating the DETR framework for precise point-axis prediction and end-to-end detection. Experimental results demonstrate significant performance improvements in oriented object detection tasks.

📄 PDF Abstract BibTeX arXiv:2407.08489

Code (1)

zhaozeyang108/Oriented-DETR pytorch

Tasks

object-detectionObject DetectionObject Detection In Aerial ImagesOriented Object DetectionRepresentation Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Improving the Detection of Small Oriented Objects in Aerial Images

2024-01-12 · Chandler Timm C. Doloriel, Rhandley D. Cajote

Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly…

Instance Segmentationobject-detectionObject DetectionOriented Object Detection+1

Detection of pose orientation across single and multiple axes in case of 3D face images

2013-09-18 · Parama Bagchi, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu

In this paper, we propose a new approach that takes as input a 3D face image across X, Y and Z axes as well as both Y and X axes and gives output as its pose i.e. it tells whether the face is oriented with respect the X,…

Oriented RepPoints for Aerial Object Detection

2021-05-24 · CVPR 2022 1 · Wentong Li, Yijie Chen, Kaixuan Hu, Jianke Zhu

In contrast to the generic object, aerial targets are often non-axis aligned with arbitrary orientations having the cluttered surroundings. Unlike the mainstreamed approaches regressing the bounding box orientations, thi…

ObjectObject DetectionObject Detection In Aerial ImagesOne-stage Anchor-free Oriented Object Detection+1

ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection

2023-03-09 · Ying Zeng, Yushi Chen, Xue Yang, Qingyun Li 외

Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model. We argue that AP$_{50}$ is inherently unsuitable for oriented object detection due to its large tolerance …

Objectobject-detectionObject DetectionOriented Object Detection

ClusterFusion: Leveraging Radar Spatial Features for Radar-Camera 3D Object Detection in Autonomous Vehicles

2023-09-07 · Irfan Tito Kurniawan, Bambang Riyanto Trilaksono

Thanks to the complementary nature of millimeter wave radar and camera, deep learning-based radar-camera 3D object detection methods may reliably produce accurate detections even in low-visibility conditions. This makes …

3D Object DetectionAutonomous Vehiclesobject-detectionObject Detection