Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Zhang, Hongkai; Chang, Hong; Ma, Bingpeng; Wang, Naiyan; Chen, Xilin

doi:10.1007/978-3-030-58555-6_16

Cited by 380 publications

(178 citation statements)

References 37 publications

Supporting

Mentioning

178

Contrasting

Order By: Relevance

“…is spectacular toolbox contains loads of configurations of state-of-the-art object detectors. First, we convert our database into COCO type and then start training with several well-known detectors, including Faster R-CNN [59], Mask R-CNN [60], RetinaNet [61], CornerNet [62], YOLACT [63], Cascade R-CNN [64], and Dynamic R-CNN [65] in order to compare the performance between them and the proposed YOLOv3. Images are also resized into different sizes depending on the input layer of each detector.…”

Section: Resultsmentioning

confidence: 99%

Real‐Time Human Ear Detection Based on the Joint of Yolo and RetinaFace

Quoc

Hoang

2021

Complexity

View full text Add to dashboard Cite

Biometric traits gradually proved their importance in real-life applications, especially in identification field. Among the available biometric traits, the unique shape of the human ear has also received loads of attention from scientists through the years. Hence, numerous ear-based approaches have been proposed with promising performance. With these methods, plenty problems can be solve by the distinctiveness of ear features, such as recognizing human with mask or diagnose ear-related diseases. As a complete identification system requires an effective detector for real-time application, and the current richness and variety of ear detection algorithms are poor due to the small and complex shape of human ears. In this paper, we introduce a new human ear detection pipeline based on the YOLOv3 detector. A well-known face detector named RetinaFace is also added in the detection system to narrow the regions of interest and enhance the accuracy. The proposed method is evaluated on an unconstrained dataset, which shows its effectiveness.

show abstract

Section: Resultsmentioning

confidence: 99%

Real‐Time Human Ear Detection Based on the Joint of Yolo and RetinaFace

Quoc

Hoang

2021

Complexity

View full text Add to dashboard Cite

show abstract

“…For instance, some works think that additional angle setting could cases serious imbalance problem [34], and explored some sampling strategy [35] to solve it. Some works [15]- [18] have assessed the quality of label assignment and proposed some metric method acts on IoU to alleviate the improper label assignment. Considering the shortcoming of feature misalignment in existing refined single-stage detector, [9] designed a feature refinement module, which can re-encode more features information to improve detection performance.…”

Section: Regression Problems In Angle-based Methodsmentioning

confidence: 99%

“…As discussed above, regression uncertainty means that the predictions of angle-based method could be uncertain, which will futher hurt the instability of the regression process. Previous methods usually heal the regression uncertainty problem by adding complex limits to the loss function [13], [15]- [18]. Different from previous approaches, our work explores a novel projection-based method, which uses six-parameter to describe rotated bounding box: two points position on the projected line (one center point (x, y) and one chosen vertex (|u|, |v|)), a projection ratio ρ and a quadrant label α, named as ProjBB.…”

Section: Introductionmentioning

confidence: 99%

Bounding Box Projection for Regression Uncertainty in Oriented Object Detection

Xiang

Tang³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Oriented object detection has recently attracted increasing attention for its importance in aerial image processing. Popular detection methods for oriented and densely packed objects usually utilize the rotation angle to reduce the overlap of bounding boxes over the horizontal line. However, those anglebased methods remain challenging due to the angular periodicity and regression inconsistent, which are uniformly summarized as regression uncertainty. Previous methods usually heal the regression uncertainty problem by adding complex limits on the loss function. In this paper, instead of expressing accurate oriented information by the rotation angle, we propose a novel projection-based method that employs six-parameter to describe rotated bounding box: two points position on the projected line(one center point and one chosen vertex), a projection ratio and a quadrant label, named as ProjBB. ProjBB is angle-free and has three main advantages: i) More accurate angle distance without periodicity; ii) Projection ratio which is aspect ratio sensitive; iii) Theoretical uniqueness guarantee. Extensive experiments on two large-scale public aerial image datasets(i.e. DOTA and HRSC2016) and the scene text dataset ICDAR2015 show the competitive results of our proposed approach.

show abstract

“…Chen et al [23] combined the GIOU loss and soft-NMS in Faster R-CNN to detect the ships of SAR images. To deal with the imbalance issues in training procedure, Focus loss [19] firstly took hard negative mining mechanism into one-stage detection model; Libra R-CNN [24] proposed a balanced L1 loss to solve the imbalance issues in three aspects; Dynamic R-CNN [33] uses a changeable β values of Smooth L1 loss to dynamically focus on hard samples; DR loss [25] introduced distribution ranking mechanism to choose the hard candidates; Others like RefineDet++ [34], Guided Anchoring [26] and FCOS model [30] are also some effective methods. In order to save the human labor for dataset annotation, Li et al [35] proposed a weakly supervised deep learning (WSDL) method for remote sensing object detection without costly bounding box annotation.…”

Section: Related Work a Object Detectionmentioning

confidence: 99%

Scale-Sensitive IOU Loss: An Improved Regression Loss Function in Remote Sensing Object Detection

Zhang

2021

IEEE Access

View full text Add to dashboard Cite

Regression loss function in object detection model plays a important factor during training procedure. The IoU based loss functions, such as CIOU loss, achieve remarkable performance, but still have some inherent shortages that may cause slow convergence speed. The paper proposes a Scale-Sensitive IOU(SIOU) loss for the object detection in multi-scale targets, especially the remote sensing images to solve the problem where the gradients of current loss functions tend to be smooth and cannot distinguish some special bounding boxes during training procedure in multi-scale object detection, which may cause unreasonable loss value calculation and impact the convergence speed. A new geometric factor affecting the loss value calculation, namely area difference, is introduced to extend the existing three factors in CIOU loss; By introducing an area regulatory factor γ to the loss function, it could adjust the loss values of the bounding boxes and distinguish different boxes quantitatively. Furthermore, we also apply our SIOU loss to the oriented bounding box detection and get better optimization. Through extensive experiments, the detection accuracies of YOLOv4, Faster R-CNN and SSD with SIOU loss improve much more than the previous loss functions on two horizontal bounding box datasets, i.e, NWPU VHR-10 and DIOR, and on the oriented bounding box dataset, DOTA, which are all remote sensing datasets. Therefore, the proposed loss function has the state-of-the-art performance on multi-scale object detection.

show abstract

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Cited by 380 publications

References 37 publications

Real‐Time Human Ear Detection Based on the Joint of Yolo and RetinaFace

Real‐Time Human Ear Detection Based on the Joint of Yolo and RetinaFace

Bounding Box Projection for Regression Uncertainty in Oriented Object Detection

Scale-Sensitive IOU Loss: An Improved Regression Loss Function in Remote Sensing Object Detection

Contact Info

Product

Resources

About