SC-RPN: A Strong Correlation Learning Framework for Region Proposal
Reads0
Chats0
TLDR
Wang et al. as discussed by the authors proposed a two-stage strong correlation learning framework, abbreviated as SC-RPN, which aims to set up stronger relationship among different modules in the region proposal task.Abstract:
Current state-of-the-art two-stage detectors heavily rely on region proposals to guide the accurate detection for objects. In previous region proposal approaches, the interaction between different functional modules is correlated weakly, which limits or decreases the performance of region proposal approaches. In this paper, we propose a novel two-stage strong correlation learning framework, abbreviated as SC-RPN, which aims to set up stronger relationship among different modules in the region proposal task. Firstly, we propose a Light-weight IoU-Mask branch to predict intersection-over-union (IoU) mask and refine region classification scores as well, it is used to prevent high-quality region proposals from being filtered. Furthermore, a sampling strategy named Size-Aware Dynamic Sampling (SADS) is proposed to ensure sampling consistency between different stages. In addition, point-based representation is exploited to generate region proposals with stronger fitting ability. Without bells and whistles, SC-RPN achieves AR1000 14.5% higher than that of Region Proposal Network (RPN), surpassing all the existing region proposal approaches. We also integrate SC-RPN into Fast R-CNN and Faster R-CNN to test its effectiveness on object detection task, the experimental results achieve a gain of 3.2% and 3.8% in terms of mAP compared to the original ones.read more
Citations
More filters
Journal ArticleDOI
Diagnosis of Alzheimer’s disease via an attention-based multi-scale convolutional neural network
TL;DR: Wang et al. as mentioned in this paper proposed a multi-scale convolutional neural network (MSCNet) to enhance the model's feature representation ability, and a channel attention mechanism was introduced to improve the interdependence between channels and adaptively recalibrate the channel direction's characteristic response.
Journal ArticleDOI
An effective risk identification method for power fence operation based on neighborhood correlation network and vector calculation
TL;DR: In this paper, the authors proposed a risk identification method based on neighborhood correlation networks and vector calculation to determine the safety area of a power operation site by detecting the key targets of fence operation.
Journal ArticleDOI
Deep learning based object detection for resource constrained devices: Systematic review, future trends and challenges ahead
Vidya Kamath,A. Renuka +1 more
TL;DR: In this paper , the authors identify current trends in resource-constrained applications for deep learning-based object detectors in terms of the technique used to create the model, the type of input image involved, the device used, and the specific application addressed by the model.
Journal ArticleDOI
TransWeaver: Weave Image Pairs for Class Agnostic Common Object Detection
TL;DR: TransWeaver as mentioned in this paper takes image pairs as input and flexibly captures the inherent correlation between candidate objects from two images, which can further describe the commonality of image pairs at the object level.
Journal ArticleDOI
TransWeaver: Weave Image Pairs for Class Agnostic Common Object Detection
TL;DR: TransWeaver as discussed by the authors takes image pairs as input and flexibly captures the inherent correlation between candidate objects from two images, which can further describe the commonality of image pairs at the object level.
References
More filters
Book ChapterDOI
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
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.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Proceedings ArticleDOI
You Only Look Once: Unified, Real-Time Object Detection
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Journal ArticleDOI
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 ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.