MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection

Lu, Xin; Li, Quanquan; Li, Buyu; Yan, Junjie

doi:10.1007/978-3-030-58568-6_32

Cited by 51 publications

(22 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, some of these approaches are slightly different as they employ a unique focal loss or pixel-wise classification to achieve a higher detection accuracy in real-time. On the other hand, Fast Regions with CNN (R-CNN) [249], Faster R-CNN [596], Mask R-CNN [297], MimicDet [459] are the most common examples of a Two-stage object detector. Generally the first stage in these Two-stage object detection model consists of a Region Proposal Network (RPN), where in the second stage the candidate region proposals are classified based on the feature maps.…”

Section: Task Formulationmentioning

confidence: 99%

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey

Wörmann¹,

Bogdoll²,

Bührle³

et al. 2022

Preprint

View full text Add to dashboard Cite

The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.Acknowledgement: The research leading to these results is funded by the German Federal Ministry for Economic Affairs and Climate Action within the project "KI Wissen -Entwicklung von Methoden für die Einbindung von Wissen in maschinelles Lernen". The authors would like to thank the consortium for the successful cooperation.

show abstract

Section: Task Formulationmentioning

confidence: 99%

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey

Wörmann¹,

Bogdoll²,

Bührle³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning-based object detection methods can be divided into two groups: one-stage (unified) and two-stage (region-based). 53 In the two-stage techniques, which are the basis of R-CNN-based methods and also known as region proposal network (RPN), 54 object candidates are determined first. Then a CNN model is fed with candidate objects rescaled to a fixed size.…”

Section: Object Detection Modelsmentioning

confidence: 99%

False positive repression: Data centric pipeline for object detection in brain MRI

Terzı

Azgınoglu

Terzi

2021

Concurrency and Computation

View full text Add to dashboard Cite

One of the problems that often arise during the application of medical research to real life is the high number of false positive cases. This situation causes experts to be warned with false alarms unnecessarily and increases their workload. This study proposes a new data centric approach to reduce bias-based false positive predictions in brain MRI-specific medical object detection applications. The proposed method has been tested using two different datasets: Gazi Brains 2020 and BraTS 2020, and three different deep learning-based object detection models: Mask R-CNN, YOLOv5, and EfficientDet. According to the results, the proposed pipeline outperformed the classical pipeline, up to 18% on the Gazi Brains 2020 dataset, and up to 24% on the BraTS 2020 dataset for mean specificity value without much change in sensitivity metric. It means that the proposed pipeline reduces false positive rates due to bias in real-life applications and it can help to reduce the workload of experts.

show abstract

“…RetinaNet [47] proposed focal loss to solve the problem of class imbalance to improve the detection accuracy. Xinlu et al [48] proposed a novel and effective framework, MimicDet, which has a shared backbone for one-stage and two-stage detectors, then it branches into two heads which are well designed to have compatible features for mimicking, to train a detector by directly imitating two-stage functions. However, most of the above detectors rely on manually set anchor boxes to achieve the detection task.…”

Section: A Cnn-based Detectorsmentioning

confidence: 99%

Transformed Dynamic Feature Pyramid for Small Object Detection

Hong

Yang²,

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The low resolution and less feature information of small targets make it difficult to recognize and locate, which greatly hinders the improvement of object detection accuracy. In this paper, an object detection model (TDFP) based on CNN and transformer was established, which combines local and global context to establish the connection between features. In the proposed transformed dynamic feature pyramid network, a transformer module was designed to dynamically transform and fuse the multi-scale features generated by the backbone to generate a transformed feature pyramid with richer multi-scale features and context information. In this transformation process, gate block is used to dynamically select single-scale transformation or cross-scale transformation to achieve optimal style of transformation and fusion of multiscale features. The experimental results show that the model improves the small targets detection accuracy based on CNN and transformer. Based on the backbone ResNeXt-101, TDFP achieves 46.2% AP and 26.3% APS on MS COCO, and takes the amount of computation as a loss constraint to achieve a better balance between detection accuracy and computational complexity.

show abstract

MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection

Cited by 51 publications

References 25 publications

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey

False positive repression: Data centric pipeline for object detection in brain MRI

Transformed Dynamic Feature Pyramid for Small Object Detection

Contact Info

Product

Resources

About