PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector

• URL: http://arxiv.org/abs/2211.02386v1
• Date: Fri, 4 Nov 2022 11:38:30 GMT
• Title: PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector
• Authors: Xinxin Wang, Guanzhong Wang, Qingqing Dang, Yi Liu, Xiaoguang Hu, Dianhai Yu
• Abstract summary: PP-YOLOE-R is an anchor-free rotated object detector based on PP-YOLOE. PP-YOLOE-R-l and PP-YOLOE-R-x achieve 78.14 and 78.28 mAP on DOTA 1.0 dataset with single-scale training and testing. PP-YOLOE-R-x surpasses all anchor-free methods and demonstrates competitive performance to state-of-the-art anchor-based two-stage models.
• Score: 14.263912554269435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Arbitrary-oriented object detection is a fundamental task in visual scenes involving aerial images and scene text. In this report, we present PP-YOLOE-R, an efficient anchor-free rotated object detector based on PP-YOLOE. We introduce a bag of useful tricks in PP-YOLOE-R to improve detection precision with marginal extra parameters and computational cost. As a result, PP-YOLOE-R-l and PP-YOLOE-R-x achieve 78.14 and 78.28 mAP respectively on DOTA 1.0 dataset with single-scale training and testing, which outperform almost all other rotated object detectors. With multi-scale training and testing, PP-YOLOE-R-l and PP-YOLOE-R-x further improve the detection precision to 80.02 and 80.73 mAP. In this case, PP-YOLOE-R-x surpasses all anchor-free methods and demonstrates competitive performance to state-of-the-art anchor-based two-stage models. Further, PP-YOLOE-R is deployment friendly and PP-YOLOE-R-s/m/l/x can reach 69.8/55.1/48.3/37.1 FPS respectively on RTX 2080 Ti with TensorRT and FP16-precision. Source code and pre-trained models are available at https://github.com/PaddlePaddle/PaddleDetection, which is powered by https://github.com/PaddlePaddle/Paddle.

Related papers

• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF [47.960563851948514]
  We investigate an efficient implementation of RLHF using low-rank adaptation (LoRA) Our implementation achieves better performance than the publicly-released AlpacaFarm checkpoint with full model fine-tuning. We release our code and pretrained checkpoints to facilitate future research on more efficient RLHF.
  arXiv  Detail & Related papers  (2023-09-16T17:31:36Z)
• EdgeYOLO: An Edge-Real-Time Object Detector [69.41688769991482]
  This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS 2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone 2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia
  arXiv  Detail & Related papers  (2023-02-15T06:05:14Z)
• PP-YOLOE: An evolved version of YOLO [4.9022682894446685]
  We present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL. As a result, PP-YOLOE-l achieves 51.4 mAP on COCO test-dev and 78.1 FPS on Tesla V100, yielding a remarkable improvement of (+1.9 AP, +13.35% speed up) and (+1.3 AP, +24.96%
  arXiv  Detail & Related papers  (2022-03-30T12:31:39Z)
• In Defense of Kalman Filtering for Polyp Tracking from Colonoscopy Videos [15.377310026794854]
  Real-time and robust automatic detection of polyps from colonoscopy videos are essential tasks to help improve the performance of doctors during this exam. The current focus of the field is on the development of accurate but inefficient detectors that will not enable a real-time application. We propose a Kalman filtering tracker that can work together with powerful, but efficient detectors, enabling the implementation of real-time polyp detectors.
  arXiv  Detail & Related papers  (2022-01-27T11:25:58Z)
• Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation [79.78017059539526]
  We propose a new heatmap-free keypoint estimation method in which individual keypoints and sets of spatially related keypoints (i.e., poses) are modeled as objects within a dense single-stage anchor-based detection framework. In experiments, we observe that KAPAO is significantly faster and more accurate than previous methods, which suffer greatly from heatmap post-processing. Our large model, KAPAO-L, achieves an AP of 70.6 on the Microsoft COCO Keypoints validation set without test-time augmentation.
  arXiv  Detail & Related papers  (2021-11-16T15:36:44Z)
• Oriented R-CNN for Object Detection [61.78746189807462]
  This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN. 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.
  arXiv  Detail & Related papers  (2021-08-12T12:47:43Z)
• Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge [57.647371468876116]
  We introduce our real-time 2D object detection system for the realistic autonomous driving scenario. Our detector is built on a newly designed YOLO model, called YOLOX. On the Argoverse-HD dataset, our system achieves 41.0 streaming AP, which surpassed second place by 7.8/6.1 on detection-only track/fully track, respectively.
  arXiv  Detail & Related papers  (2021-07-27T06:36:06Z)
• PP-YOLOv2: A Practical Object Detector [13.262416549127664]
  We evaluate a collection of existing refinements to improve the performance of PP-YOLO. By combining multiple effective refinements, we boost PP-YOLO's performance from 45.9% mAP to 49.5% mAP. In terms of speed, PP-YOLOv2 runs in 68.9FPS at 640x640 input size.
  arXiv  Detail & Related papers  (2021-04-21T08:55:37Z)
• RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection [0.0]
  RMOPP is a statistically driven, post-processing algorithm that allows for simultaneous optimization of precision and recall. We provide a compelling test case on YOLOv2 using the MS-COCO dataset.
  arXiv  Detail & Related papers  (2021-02-09T00:02:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.