R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object (2019-08-15T00:00:00.000000Z)

TL;DR

This paper proposes an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity and designs a feature refinement module to improve detection performance by getting more accurate features.

Abstract

Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. Though considerable progress has been made, for practical settings, there still exist challenges for rotating objects with large aspect ratio, dense distribution and category extremely imbalance. In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity. Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features. The key idea of feature refinement module is to re-encode the position information of the current refined bounding box to the corresponding feature points through pixel-wise feature interpolation to realize feature reconstruction and alignment. For more accurate rotation estimation, an approximate SkewIoU loss is proposed to solve the problem that the calculation of SkewIoU is not derivable. Experiments on three popular remote sensing public datasets DOTA, HRSC2016, UCAS-AOD as well as one scene text dataset ICDAR2015 show the effectiveness of our approach. The source code is available at https://github.com/Thinklab-SJTU/R3Det_Tensorflow and is also integrated in our open source rotation detection benchmark: https://github.com/yangxue0827/RotationDetection.

Authors

Xue Yang

6 papers

Junchi Yan

17 papers

Qingqing Liu

1 papers

TL;DR

Abstract

Authors

References71 items

PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments

Dynamic Refinement Network for Oriented and Densely Packed Object Detection

Rotation-aware and multi-scale convolutional neural network for object detection in remote sensing images

Objects detection for remote sensing images based on polar coordinates

Oriented Objects as pairs of Middle Lines

Mask OBB: A Semantic Attention-Based Mask Oriented Bounding Box Representation for Multi-Category Object Detection in Aerial Images

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

Feature-Attentioned Object Detection in Remote Sensing Imagery

Propose-and-Attend Single Shot Detector

Rethinking Classification and Localization for Cascade R-CNN

Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection

Adaptive Period Embedding for Representing Oriented Objects in Aerial Images

Omnidirectional Scene Text Detection with Sequential-free Box Discretization

Learning RoI Transformer for Oriented Object Detection in Aerial Images

Building detection in high spatial resolution remote sensing imagery with the U-Rotation Detection Network

CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

Hybrid Task Cascade for Instance Segmentation

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

A Ship Rotation Detection Model in Remote Sensing Images Based on Feature Fusion Pyramid Network and Deep Reinforcement Learning

SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects

Selective Refinement Network for High Performance Face Detection

Toward Arbitrary-Oriented Ship Detection With Rotated Region Proposal and Discrimination Networks

Dual Refinement Network for Single-Shot Object Detection

Dual Refinement Networks for Accurate and Fast Object Detection in Real-World Scenes

Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery

Object Detection with Head Direction in Remote Sensing Images Based on Rotational Region CNN

Rotation-Sensitive Regression for Oriented Scene Text Detection

Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation

TextBoxes++: A Single-Shot Oriented Scene Text Detector

FOTS: Fast Oriented Text Spotting with a Unified Network

Cascade R-CNN: Delving Into High Quality Object Detection

DOTA: A Large-Scale Dataset for Object Detection in Aerial Images

Learning a Rotation Invariant Detector with Rotatable Bounding Box

Light-Head R-CNN: In Defense of Two-Stage Object Detector

Single-Shot Refinement Neural Network for Object Detection

Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks

Focal Loss for Dense Object Detection

R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection

EAST: An Efficient and Accurate Scene Text Detector

Deep Direct Regression for Multi-oriented Scene Text Detection

Mask R-CNN

Detecting Oriented Text in Natural Images by Linking Segments

Deformable Convolutional Networks

Arbitrary-Oriented Scene Text Detection via Rotation Proposals

A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines

DSSD : Deconvolutional Single Shot Detector

YOLO9000: Better, Faster, Stronger

Feature Pyramid Networks for Object Detection

TextBoxes: A Fast Text Detector with a Single Deep Neural Network

Aggregated Residual Transformations for Deep Neural Networks

Detecting Text in Natural Image with Connectionist Text Proposal Network

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Stacked Hourglass Networks for Human Pose Estimation

Deep Residual Learning for Image Recognition

Orientation robust object detection in aerial images using deep convolutional neural network

SSD: Single Shot MultiBox Detector

ICDAR 2015 competition on Robust Reading

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

ImageNet classification with deep convolutional neural networks

Baselines

Single Shot Anchor Refinement Network for Oriented Object Detection in Optical Remote Sensing Imagery

FDDB: A benchmark for face detection in unconstrained settings

This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Tensorflow: a System for Large-scale Machine Learning Tensorflow: a System for Large-scale Machine Learning

Field of Study

Journal Information

Name

Volume

Venue Information