paper-with-me

Papers

Global Context Aware RCNN for Object Detection

2020-12-04 · Wenchao Zhang, Chong Fu, Haoyu Xie, Mai Zhu, Ming Tie, Junxin Chen

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively. Specifically, we leverage the dense connection to improve the information flow of the global context at different stages in the top-down process of FPN, and further use the attention mechanism to refine the global context at each level in the feature pyramid. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach.

📄 PDF Abstract BibTeX arXiv:2012.02637

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

GCA 설명 없음
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
FPN 설명 없음

Similar Papers 제목 키워드 기반

Dense Global Context Aware RCNN for Object Detection

2021-01-01 · Wenchao Zhang, Haoyu Xie, Mai Zhu, Chong Fu

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However,…

Objectobject-detectionObject Detection

Reasoning-RCNN: Unifying Adaptive Global Reasoning Into Large-Scale Object Detection

2019-06-01 · CVPR 2019 6 · Hang Xu, Chenhan Jiang, Xiaodan Liang, Liang Lin 외

In this paper, we address the large-scale object detection problem with thousands of categories, which poses severe challenges due to long-tail data distributions, heavy occlusions, and class ambiguities. However, the do…

Objectobject-detectionObject Detection

Attentive Contexts for Object Detection

2016-03-24 · Jianan Li, Yunchao Wei, Xiaodan Liang, Jian Dong 외

Modern deep neural network based object detection methods typically classify candidate proposals using their interior features. However, global and local surrounding contexts that are believed to be valuable for object d…

Objectobject-detectionObject Detection

Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection

2016-08-18 · Youbao Tang, Xiangqian Wu, Wei Bu

This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, t…

Saliency DetectionSaliency Prediction

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

2020-02-18 · Hang Xu, Linpu Fang, Xiaodan Liang, Wenxiong Kang 외

The dominant object detection approaches treat each dataset separately and fit towards a specific domain, which cannot adapt to other domains without extensive retraining. In this paper, we address the problem of designi…

AllObjectobject-detectionObject Detection+1