A Survey of Deep Learning-based Object Detection

Jiao, Licheng; Zhang, Fan; Liu, Fang; Yang, Shuyuan; Li, Lingling; Feng, Zhixi; Qu, Rong

doi:10.48550/arxiv.1907.09408

Cited by 12 publications

(11 citation statements)

References 180 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first two terms on the right hand side of ( 5) can be seen as a classification loss for visibility, while the last term corresponds to a regression loss of location estimation. The sum of classification and regression losses is also widely used in object detection [39].…”

Section: Luvli Lossmentioning

confidence: 99%

LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood

Kumar

Marks

Mou

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

122

106

View full text Add to dashboard Cite

Modern face alignment methods have become quite accurate at predicting the locations of facial landmarks, but they do not typically estimate the uncertainty of their predicted locations nor predict whether landmarks are visible. In this paper, we present a novel framework for jointly predicting landmark locations, associated uncertainties of these predicted locations, and landmark visibilities. We model these as mixed random variables and estimate them using a deep network trained with our proposed Location, Uncertainty, and Visibility Likelihood (LUVLi) loss. In addition, we release an entirely new labeling of a large face alignment dataset with over 19,000 face images in a full range of head poses. Each face is manually labeled with the ground-truth locations of 68 landmarks, with the additional information of whether each landmark is unoccluded, self-occluded (due to extreme head poses), or externally occluded. Not only does our joint estimation yield accurate estimates of the uncertainty of predicted landmark locations, but it also yields state-of-the-art estimates for the landmark locations themselves on multiple standard face alignment datasets. Our method's estimates of the uncertainty of predicted landmark locations could be used to automatically identify input images on which face alignment fails, which can be critical for downstream tasks.

show abstract

Section: Luvli Lossmentioning

confidence: 99%

LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood

Kumar

Marks

Mou

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

122

106

View full text Add to dashboard Cite

show abstract

“…Since this is undesired in real-time applications, other researchers have focused on designing lightweight backbones such as MobileNets [39], which are also less accurate. In general, finding the optimal speed/accuracy balance in a backbone architecture is a difficult task that highly depends on the problem to be addressed [40].…”

Section: Related Workmentioning

confidence: 99%

Enhancing object detection for autonomous driving by optimizing anchor generation and addressing class imbalance

et al. 2021

View full text Add to dashboard Cite

Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of such detection frameworks in specific applications such as autonomous driving is yet an area to be addressed. This study presents an enhanced 2D object detector based on Faster R-CNN that is better suited for the context of autonomous vehicles. Two main aspects are improved: the anchor generation procedure and the performance drop in minority classes. The default uniform anchor configuration is not suitable in this scenario due to the perspective projection of the vehicle cameras. Therefore, we propose a perspective-aware methodology that divides the image into key regions via clustering and uses evolutionary algorithms to optimize the base anchors for each of them. Furthermore, we add a module that enhances the precision of the second-stage header network by including the spatial information of the candidate regions proposed in the first stage. We also explore different re-weighting strategies to address the foreground-foreground class imbalance, showing that the use of a reduced version of focal loss can significantly improve the detection of difficult and underrepresented objects in two-stage detectors. Finally, we design an ensemble model to combine the strengths of the different learning strategies. Our proposal is evaluated with the Waymo Open Dataset, which is the most extensive and diverse up to date. The results demonstrate an average accuracy improvement of 6.13% mAP when using the best single model, and of 9.69% mAP with the ensemble. The proposed modifications over the Faster R-CNN do not increase computational cost and can easily be extended to optimize other anchor-based detection frameworks.

show abstract

“…Dense object detection: In recent years, object detection has been successfully tackled using deep learning [10]. But the first improvement in dense object detection was made with introduction of focal-loss [16].…”

Section: Related Workmentioning

confidence: 99%

Semi-supervised Learning for Dense Object Detection in Retail Scenes

Chauhan¹,

Varadarajan²,

Srivastava³

2021

Preprint

View full text Add to dashboard Cite

Retail scenes usually contain densely packed high number of objects in each image. Standard object detection techniques use fully supervised training methodology. This is highly costly as annotating a large dense retail object detection dataset involves an order of magnitude more effort compared to standard datasets. Hence, we propose semisupervised learning to effectively use the large amount of unlabeled data available in the retail domain. We adapt a popular self supervised method called noisy student initially proposed for object classification to the task of dense object detection. We show that using unlabeled data with the noisy student training methodology, we can improve the state of the art on precise detection of objects in densely packed retail scenes. We also show that performance of the model increases as you increase the amount of unlabeled data.

show abstract

A Survey of Deep Learning-based Object Detection

Cited by 12 publications

References 180 publications

LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood

LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood

Enhancing object detection for autonomous driving by optimizing anchor generation and addressing class imbalance

Semi-supervised Learning for Dense Object Detection in Retail Scenes

Contact Info

Product

Resources

About