TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection
Not on the map. Why?
Abstract (arXiv)
We present a novel approach for oriented object detection, named TricubeNet, which localizes oriented objects using visual cues (i.e., heatmap) instead of oriented box offsets regression. We represent each object as a 2D Tricube kernel and extract bounding boxes using simple image-processing algorithms. Our approach is able to (1) obtain well-arranged boxes from visual cues, (2) solve the angle discontinuity problem, and (3) can save computational complexity due to our anchor-free modeling. To further boost the performance, we propose some effective techniques for size-invariant loss, reducing false detections, extracting rotation-invariant features, and heatmap refinement. To demonstrate the effectiveness of our TricubeNet, we experiment on various tasks for weakly-occluded oriented object detection: detection in an aerial image, densely packed object image, and text image. The extensive experimental results show that our TricubeNet is quite effective for oriented object detection. Code is available at https://github.com/qjadud1994/TricubeNet.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 41 of its 52 references that are in the map. First posted on arXiv 23 Apr 2021.
Builds on
41 of 52 references.
References · 41
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2015SSD: Single Shot MultiBox Detectorcited by 3,125
- 2015Fast R-CNNcited by 2,930
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
- 2016YOLO9000: Better, Faster, Strongercited by 1,429
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
- 2019Objects as Pointscited by 1,172
29 more
- 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
- 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
- 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
- 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
- 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
- 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
- 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
- 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
- 2019Character Region Awareness for Text Detectioncited by 273
- 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
- 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 193
- 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
- 2019Feature Selective Anchor-Free Module for Single-Shot Object Detectioncited by 139
- 2019Gliding vertex on the horizontal bounding box for multi-oriented object detectioncited by 134
- 2018TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapescited by 114
- 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105
- 2018Rotation-Sensitive Regression for Oriented Scene Text Detectioncited by 88
- 2017Detecting Oriented Text in Natural Images by Linking Segmentscited by 80
- 2019Learning Modulated Loss for Rotated Object Detectioncited by 73
- 2020Dynamic Refinement Network for Oriented and Densely Packed Object Detectioncited by 72
- 2019Precise Detection in Densely Packed Scenescited by 62
- 2018PixelLink: Detecting Scene Text via Instance Segmentationcited by 60
- 2018Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networkscited by 54
- 2017R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detectioncited by 51
- 2018Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagerycited by 46
- 2019Arbitrary Shape Scene Text Detection with Adaptive Text Region Representationcited by 45
- 2018Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentationcited by 42
- 2016Multi-Oriented Text Detection with Fully Convolutional Networkscited by 36
- 2018Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Networkcited by 13
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 1.
2 papers.