Journal Article10.1007/S10489-020-02037-Z
Context augmentation for object detection
Jiaxu Leng,Ying Liu +1 more
10
TL;DR: A context augmentation algorithm that fully utilizes contextual information to generate high-quality region proposals and detection results and effectively improves the quality of region proposals as well as recognition results is proposed.
read more
Abstract: Current two-stage object detectors, which mainly consist of a region proposal stage and a proposal recognition stage, may produce unreliable results for objects appearing with little information such as small and occluded objects. This is caused by poor region proposals and inaccurate proposal recognition. To address this problem, we propose a context augmentation algorithm that fully utilizes contextual information to generate high-quality region proposals and detection results. First, Region proposals are produced by two steps: 1) generate a coarse set of region proposals, some of which are reliable and some of which are ambiguous, and 2) the ambiguous region proposals are re-estimated using appearance and geometry information with respect to the reliable region proposals from step 1). Second, similar types of pair-wise relations between region proposals are used to produce global feature information associated with the region proposals in order to enhance recognition results. In practice, our method effectively improves the quality of region proposals as well as recognition results. Empirical studies show that the proposed context augmentation yields substantial and consistent improvements over baseline Faster R-CNN. Moreover, there is around 1.3% mAP improvement over Mask R-CNN on COCO dataset.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Occluded prohibited object detection in X-ray images with global Context-aware Multi-Scale feature Aggregation
TL;DR: Wang et al. as discussed by the authors designed a learnable Gabor convolutional layer to enhance the network's capability to capture the edge and contour information of object, and a Spatial Attention (SA) mechanism is then designed to weight the output features of the Gabor CNN layer.
30
DSCA: A Dual Semantic Correlation Alignment Method for domain adaptation object detection
yinsai guo,Hang Yu,Shaorong Xie,Liyan Ma,Xinzhi Cao,Xiangfeng Luo +5 more
TL;DR: This paper proposes DSCA, a dual semantic correlation alignment method for domain adaptation object detection, which leverages context and class correlation semantic information to improve detection accuracy in adverse weather or occlusion scenarios, outperforming state-of-the-art methods.
21
A context- and level-aware feature pyramid network for object detection with attention mechanism
TL;DR: This paper proposes an improved object detector based on context- and level-aware feature pyramid networks, where it exhibits superior performances than other state-of-the-art works.
6
End-to-End Network for Pedestrian Detection, Tracking and Re-Identification in Real-Time Surveillance System
TL;DR: Wang et al. as mentioned in this paper combined the detector and re-ID models into a single end-to-end network by introducing a new track branch to YOLOv5 architecture for tracking.
Fine segmentation and difference-aware shape adjustment for category-level 6DoF object pose estimation
Chongpei Liu,Wei Sun,Jian Liu,Xing Zhang,Shimeng Fan,Qiankun Fu +5 more
- 13 Jul 2023
TL;DR: A difference-aware shape adjustment network (DASAN) is proposed to model shape differences between the object instance and mean shape by feature subtraction with an attention mechanism and an RGB-D feature fusion-based object segmentation method that uses a coarse-to-fine framework for coarse and fine segmentation is proposed.
4
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
- 06 Sep 2014
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
SSD: Single Shot MultiBox Detector
Wei Liu,Dragomir Anguelov,Dumitru Erhan,Christian Szegedy,Scott Reed,Cheng-Yang Fu,Alexander C. Berg +6 more
- 08 Oct 2016
TL;DR: The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.