Acquisition of Localization Confidence for Accurate Object Detection

Jiang, Borui; Luo, Ruixuan; Mao, Jiayuan; Xiao, Tete; Jiang, Yuning

doi:10.48550/arxiv.1807.11590

Cited by 33 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For all the two-stage detection methods, one intersection-over-union (IoU) threshold is required to classify the predicted positive bounding box with the negative bounding box. However, it has been shown that a lower IoU threshold could provide more bounding boxes with a lower precision, which induces a lower recall rate, while a higher IoU threshold could provide fewer bounding boxes with a higher precision, which induces the under detection [28]. To Our study implemented a deep learning-based method for the automatic detection of osteochondral lesions of the talus for the first time.…”

Section: Discussionmentioning

confidence: 99%

Automatic Detection of Osteochondral Lesions of the Talus via Deep Learning

Wang

Li²,

Zhu

et al. 2022

Front. Phys.

View full text Add to dashboard Cite

Screening of osteochondral lesions of the talus (OLTs) from MR imags usually requires time and efforts, and in most case lesions with small size are often missed in clinical practice. Thereore, it puts forward higher requirements for a more efficient OLTs screening method. To develop an automatic screening system for osteochondral lesions of the talus (OLTs), we collected 92 MRI images of patients with ankle pain from Qilu Hospital of Shandong University and proposed an AI (artificial intelligence) aided lesion screening system, which is automatic and based on deep learning method. A two-stage detection method based on the cascade R-CNN model was proposed to significantly improve the detection performance by taking advantage of multiple intersection-over-union thresholds. The backbone network was based on ResNet50, which was a state-of-art convolutional neural network model in image classification task. Multiple regression using cascaded detection heads was applied to further improve the detection precision. The mean average precision (mAP) that is adopted as major metrics in the paper and mean average recall (mAR) was selected to evaluate the performance of the model. Our proposed method has an average precision of 0.950, 0.975, and 0.550 for detecting the talus, gaps and lesions, respectively, and the mAP, mAR was 0.825, 0.930. Visualization of our network performance demonstrated the effectiveness of the model, which implied that accurate detection performance on these tasks could be further used in real clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Detection of Osteochondral Lesions of the Talus via Deep Learning

Wang

Li²,

Zhu

et al. 2022

Front. Phys.

View full text Add to dashboard Cite

show abstract

“…With ResNet-101-FPN backbone, ShapeMask outperforms RetinaNet and Mask R-CNN, and is among the best reported approaches using the same backbone. With a larger backbone, ShapeMask achieves comparable performance to SNIP and trails PANet by 2 point without using any techniques from[4,21,44]. This shows that ShapeMask can function as a competitive object detector.…”

mentioning

confidence: 83%

“…Using ResNet-101-NAS-FPN, ShapeMask achieves 45.4 AP which is comparable to SNIP and behind PANet by 2.0 AP. Note that ShapeMask does not apply many existing detection improvement methods [4,21,44]. This shows that ShapeMask can function as a competitive object detector as well.…”

Section: Appendix B: Object Detectionmentioning

confidence: 99%

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

Kuo

Angelova

Malik

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

131

View full text Add to dashboard Cite

Instance segmentation aims to detect and segment individual objects in a scene. Most existing methods rely on precise mask annotations of every category. However, it is difficult and costly to segment objects in novel categories because a large number of mask annotations is required. We introduce ShapeMask, which learns the intermediate concept of object shape to address the problem of generalization in instance segmentation to novel categories. Shape-Mask starts with a bounding box detection and gradually refines it by first estimating the shape of the detected object through a collection of shape priors. Next, ShapeMask refines the coarse shape into an instance level mask by learning instance embeddings. The shape priors provide a strong cue for object-like prediction, and the instance embeddings model the instance specific appearance information. Shape-Mask significantly outperforms the state-of-the-art by 6.4 and 3.8 AP when learning across categories, and obtains competitive performance in the fully supervised setting. It is also robust to inaccurate detections, decreased model capacity, and small training data. Moreover, it runs efficiently with 150ms inference time and trains within 11 hours on TPUs. With a larger backbone model, ShapeMask increases the gap with state-of-the-art to 9.4 and 6.2 AP across categories. Code will be released.

show abstract

“…Depending on the pipeline, most of the object detection techniques could be divided into two categories, i.e., onestage method [16,14,17] and two-stage method [5,7,4,18,6,2,11,12,15,1,9,8]. Generally speaking, the one-stage methods focus on the detection speed while the dominant merit of the two-stage methods is the detection precision.…”

Section: Introductionmentioning

confidence: 99%

“…Another track of improving focuses on boosting precision of detectors [11,12,15,1,9,8]. As we know, the series of R-CNN based methods uses the same feature maps to handle both the large and small objects, and consequently cannot adapt the object scales.…”

Section: Introductionmentioning

confidence: 99%

Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance

Gao,

Bu,

et al. 2018

Preprint

View full text Add to dashboard Cite

This report demonstrates our solution for the Open Images 2018 Challenge. Based on our detailed analysis on the Open Images Datasets (OID), it is found that there are four typical features: large-scale, hierarchical tag system, severe annotation incompleteness and data imbalance. Considering these characteristics, an amount of strategies are employed, including SNIPER, soft sampling, class-aware sampling (CAS), hierarchical non-maximumsuppression (HNMS) and so on. In virtue of these effective strategies, and further using the powerful SENet154 armed with feature pyramid module and deformable ROIalign as the backbone, our best single model could achieve a mAP of 56.9%. After a further ensemble with 9 models, the final mAP is boosted to 62.2% in the public leaderboard (ranked the 2nd place) and 58.6% in the private leaderboard (ranked the 3rd place, slightly inferior to the 1st place by only 0.04 point).

show abstract

Acquisition of Localization Confidence for Accurate Object Detection

Cited by 33 publications

References 19 publications

Automatic Detection of Osteochondral Lesions of the Talus via Deep Learning

Automatic Detection of Osteochondral Lesions of the Talus via Deep Learning

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance

Contact Info

Product

Resources

About