Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images
arXiv:2209.02200 · doi:10.1109/TNNLS.2024.3367331
Abstract
Arbitrary-oriented object detection (AOOD) has been widely applied to locate and classify objects with diverse orientations in remote sensing images. However, the inconsistent features for the localization and classification tasks in AOOD models may lead to ambiguity and low-quality object predictions, which constrains the detection performance. In this article, an AOOD method called task-wise sampling convolutions (TS-Conv) is proposed. TS-Conv adaptively samples task-wise features from respective sensitive regions and maps these features together in alignment to guide a dynamic label assignment for better predictions. Specifically, sampling positions of the localization convolution in TS-Conv are supervised by the oriented bounding box (OBB) prediction associated with spatial coordinates, while sampling positions and convolutional kernel of the classification convolution are designed to be adaptively adjusted according to different orientations for improving the orientation robustness of features. Furthermore, a dynamic task-consistent-aware label assignment (DTLA) strategy is developed to select optimal candidate positions and assign labels dynamically according to ranked task-aware scores obtained from TS-Conv. Extensive experiments on several public datasets covering multiple scenes, multimodal images, and multiple categories of objects demonstrate the effectiveness, scalability, and superior performance of the proposed TS-Conv.
arXiv comment15 pages, 13 figures, 11 tables
References in corpus (15)
- YOLOX: Exceeding YOLO Series in 2021
- Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
- Gliding vertex on the horizontal bounding box for multi-oriented object detection
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
- Anchor-free Oriented Proposal Generator for Object Detection
- CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
- Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
- AutoAssign: Differentiable Label Assignment for Dense Object Detection
- A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
- Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
- PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
- G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection
- The KFIoU Loss for Rotated Object Detection
- LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images