Update README in configs.

README.md

@@ -145,21 +145,21 @@ This project is released under the [Apache 2.0 license](LICENSE).
 ## Projects in OpenMMLab
 
 * [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab foundational library for computer vision.
-* [MIM](https://github.com/open-mmlab/mim): MIM Installs OpenMMLab Packages.
+* [MIM](https://github.com/open-mmlab/mim): MIM installs OpenMMLab packages.
 * [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab image classification toolbox and benchmark.
 * [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark.
-* [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab next-generation platform for general 3D object detection.
+* [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.
+* [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark.
 * [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.
-* [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab next-generation action understanding toolbox and benchmark.
-* [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.
+* [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox.
 * [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.
-* [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.
-* [MMOCR](https://github.com/open-mmlab/mmocr): A comprehensive toolbox for text detection, recognition and understanding.
-* [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab next-generation toolbox for generative models.
-* [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark.
-* [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab fewshot learning toolbox and benchmark.
 * [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 3D human parametric model toolbox and benchmark.
 * [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab self-supervised learning toolbox and benchmark.
 * [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab model compression toolbox and benchmark.
+* [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab fewshot learning toolbox and benchmark.
+* [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark.
+* [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.
+* [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark.
+* [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.
+* [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox.
 * [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab model deployment framework.
-* [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark.

README_zh-CN.md

@@ -141,23 +141,23 @@ MMRotate 是一款由不同学校和公司共同贡献的开源项目。我们
 
 * [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab 计算机视觉基础库
 * [MIM](https://github.com/open-mmlab/mim): MIM 是 OpenMMlab 项目、算法、模型的统一入口
-* [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab 图像分类工具箱与测试基准
-* [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 检测工具箱与测试基准
-* [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用3D目标检测平台
-* [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab 语义分割工具箱与测试基准
-* [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab 新一代视频理解工具箱与测试基准
-* [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab 一体化视频目标感知平台
-* [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab 姿态估计工具箱与测试基准
-* [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab 图像视频编辑工具箱
+* [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab 图像分类工具箱
+* [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 目标检测工具箱
+* [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用 3D 目标检测平台
+* [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab 旋转框检测工具箱与测试基准
+* [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab 语义分割工具箱
 * [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab 全流程文字检测识别理解工具包
-* [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab 新一代生成模型工具箱
-* [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab 光流估计工具箱与测试基准
-* [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab 少样本学习工具箱与测试基准
+* [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab 姿态估计工具箱
 * [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 人体参数化模型工具箱与测试基准
 * [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab 自监督学习工具箱与测试基准
 * [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab 模型压缩工具箱与测试基准
+* [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab 少样本学习工具箱与测试基准
+* [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab 新一代视频理解工具箱
+* [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab 一体化视频目标感知平台
+* [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab 光流估计工具箱与测试基准
+* [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab 图像视频编辑工具箱
+* [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab 图片视频生成模型工具箱
 * [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab 模型部署框架
-* [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab 旋转框检测工具箱与测试基准
 
 ## 欢迎加入 OpenMMLab 社区
 

configs/cfa/README.md

@@ -3,7 +3,9 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/cfa.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/cfa.png" width="800"/>
+</div>
 
 Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects. In this paper, we propose a convex-hull feature adaptation (CFA) approach for configuring convolutional features in accordance with oriented and densely packed object layouts. CFA is rooted in convex-hull feature representation, which defines a set of dynamically predicted feature points guided by the convex intersection over union (CIoU) to bound the extent of objects. CFA pursues optimal feature assignment by constructing convex-hull sets and dynamically splitting positive or negative convex-hulls. By simultaneously considering overlapping convex-hulls and objects and penalizing convex-hulls shared by multiple objects, CFA alleviates spatial feature aliasing towards optimal feature adaptation. Experiments on DOTA and SKU110KR datasets show that CFA significantly outperforms the baseline approach, achieving new state-of-the-art detection performance.
 

configs/gliding_vertex/README.md

@@ -3,7 +3,10 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/gv.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/gv.png" width="800"/>
+</div>
+
 Object detection has recently experienced substantial progress. Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts. In this paper, we propose a simple yet effective framework to detect multi-oriented objects. Instead of directly regressing the four vertices, we glide the vertex of the horizontal bounding box on each corresponding side to accurately describe a multi-oriented object. Specifically, We regress four length ratios characterizing the relative gliding offset on each corresponding side. This may facilitate the offset learning and avoid the confusion issue of sequential label points for oriented objects. To further remedy the confusion issue for nearly horizontal objects, we also introduce an obliquity factor based on area ratio between the object and its horizontal bounding box, guiding the selection of horizontal or oriented detection for each object. We add these five extra target variables to the regression head of rotated faster R-CNN, which requires ignorable extra computation time. Extensive experimental results demonstrate that without bells and whistles, the proposed method achieves superior performances on multiple multi-oriented object detection benchmarks including object detection in aerial images, scene text detection, pedestrian detection in fisheye images.
 
 

configs/gwd/README.md

@@ -3,7 +3,9 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/gwd.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/gwd.png" width="800"/>
+</div>
 
 Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2- D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even there is no overlapping between two rotating bounding boxes which is often the case for small object detection. Thanks to its three unique properties, GWD can also elegantly solve the boundary discontinuity and square-like problem regardless how the bounding box is defined. Experiments on five datasets using different detectors show the effectiveness of our approach.
 

configs/kfiou/README.md

@@ -2,7 +2,10 @@
 
 <!-- [ALGORITHM] -->
 ## Abstract
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/kfiou.png)
+
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/kfiou.png" width="800"/>
+</div>
 
 Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is
 readily adopted and well fits with the detection metrics. In contrast, rotation detectors often involve a more

configs/kld/README.md

@@ -3,7 +3,9 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/kld.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/kld.png" width="800"/>
+</div>
 
 Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection due to the limitation of current regression loss design, especially for objects with large aspect ratios. Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection. We show that one essential challenge is how to modulate the coupled parameters in the rotation regression loss, as such the estimated parameters can influence to each other during the dynamic joint optimization, in an adaptive and synergetic way. Specifically, we first convert the rotated bounding box into a 2-D Gaussian distribution, and then calculate the Kullback-Leibler Divergence (KLD) between the Gaussian distributions as the regression loss. By analyzing the gradient of each parameter, we show that KLD (and its derivatives) can dynamically adjust the parameter gradients according to the characteristics of the object. For instance, it will adjust the importance (gradient weight) of the angle parameter according to the aspect ratio. This mechanism can be vital for high-precision detection as a slight angle error would cause a serious accuracy drop for large aspect ratios objects. More importantly, we have proved that KLD is scale invariant. We further show that the KLD loss can be degenerated into the popular $l_{n}$-norm loss for horizontal detection. Experimental results on seven datasets using different detectors show its consistent superiority
 

configs/oriented_rcnn/README.md

@@ -3,7 +3,9 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/oriented_rcnn.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/oriented_rcnn.png" width="800"/>
+</div>
 
 Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes. This diminishes the detectors’ speed, thereby becoming the computational bottleneck in advanced oriented object detection systems. This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN, which is a general two-stage oriented detector with promising accuracy and efficiency. To be specific, in the first stage, we propose an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner. The second stage is oriented R-CNN head for refining oriented Regions of Interest (oriented RoIs) and recognizing them.
 

configs/r3det/README.md

@@ -3,7 +3,9 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/r3det.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/r3det.png" width="800"/>
+</div>
 
 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.
 

configs/redet/README.md

@@ -3,7 +3,9 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/redet.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/redet.png" width="800"/>
+</div>
 
 Recently, object detection in aerial images has gained much attention in computer vision. Different from objects in natural images, aerial objects are often distributed with arbitrary orientation. Therefore, the detector requires more parameters to encode the orientation information, which are often highly redundant and inefficient. Moreover, as ordinary CNNs do not explicitly model the orientation variation, large amounts of rotation augmented data is needed to train an accurate object detector. In this paper, we propose a Rotation-equivariant Detector (ReDet) to address these issues, which explicitly encodes rotation equivariance and rotation invariance. More precisely, we incorporate rotation-equivariant networks into the detector to extract rotation-equivariant features, which can accurately predict the orientation and lead to a huge reduction of model size. Based on the rotation-equivariant features, we also present Rotation-invariant RoI Align (RiRoI Align), which adaptively extracts rotation-invariant features from equivariant features according to the orientation of RoI. Extensive experiments on several challenging aerial image datasets DOTA-v1.0, DOTA-v1.5 and HRSC2016, show that our method can achieve state-of-the-art performance on the task of aerial object detection. Compared with previous best results, our ReDet gains 1.2, 3.5 and 2.6 mAP on DOTA-v1.0, DOTA-v1.5 and HRSC2016 respectively while reducing the number of parameters by 60% (313 Mb vs. 121 Mb).
 

configs/roi_trans/README.md

@@ -3,7 +3,9 @@
 <!-- [ALGORITHM] -->
 ## Abstract
 
-![illustration](https://raw.githubusercontent.com/zytx121/image-host/main/imgs/roi_trans.png)
+<div align=center>
+<img src="https://raw.githubusercontent.com/zytx121/image-host/main/imgs/roi_trans.png" width="800"/>
+</div>
 
 Object detection in aerial images is an active yet challenging task in computer vision because of the bird’s-eye view perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. In this paper, we propose a RoI Transformer to address these problems. The core idea of RoI Transformer is to apply spatial transformations on RoIs and learn the transformation parameters under the supervision of oriented bounding box (OBB) annotations. RoI Transformer is with lightweight and can be easily embedded into detectors for oriented object detection. Simply apply the RoI Transformer to light-head RCNN has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer