Infrared Image Generation By Pix2pix Based on Multi-receptive Field Feature Fusion

Jointly using spatial and spectral information has been widely applied to hyperspectral image (HSI) classification. Especially, convolutional neural networks (CNN) have gained attention in recent years due to their detailed representation of features. However, most of CNN-based HSI classification methods mainly use patches as input classifier. This limits the range of use for spatial neighbor information and reduces processing efficiency in training and testing. To overcome this problem, we propose an image-based classification framework that is efficient and straightforward. Based on this framework, we propose a multiscale spatial-spectral CNN for HSIs (HyMSCN) to integrate both multiple receptive fields fused features and multiscale spatial features at different levels. The fused features are exploited using a lightweight block called the multiple receptive field feature block (MRFF), which contains various types of dilation convolution. By fusing multiple receptive field features and multiscale spatial features, the HyMSCN has comprehensive feature representation for classification. Experimental results from three real hyperspectral images prove the efficiency of the proposed framework. The proposed method also achieves superior performance for HSI classification.

Download Full-text

FRFB: Integrate Receptive Field Block Into Feature Fusion Net for Single Shot Multibox Detector

2018 14th International Conference on Semantics, Knowledge and Grids (SKG) ◽

10.1109/skg.2018.00032 ◽

2018 ◽

Cited By ~ 1

Author(s):

Yu Zhu ◽

Jiong Mu ◽

Haibo Pu ◽

Baiyi Shu

Keyword(s):

Receptive Field ◽

Feature Fusion ◽

Single Shot

Download Full-text

Small-Scale Face Detection Based on Improved R-FCN

Applied Sciences ◽

10.3390/app10124177 ◽

2020 ◽

Vol 10 (12) ◽

pp. 4177

Author(s):

Chaowei Tang ◽

Shiyu Chen ◽

Xu Zhou ◽

Shuai Ruan ◽

Haotian Wen

Keyword(s):

Receptive Field ◽

Face Detection ◽

Feature Fusion ◽

Selection Method ◽

Local Information ◽

Small Scale ◽

Average Precision ◽

Convolutional Network ◽

High Layer ◽

Novel Method

Face detection is an important basic technique for face-related applications, such as face analysis, recognition, and reconstruction. Images in unconstrained scenes may contain many small-scale faces. The features that the detector can extract from small-scale faces are limited, which will cause missed detection and greatly reduce the precision of face detection. Therefore, this study proposes a novel method to detect small-scale faces based on region-based fully convolutional network (R-FCN). First, we propose a novel R-FCN framework with the ability of feature fusion and receptive field adaptation. Second, a bottom-up feature fusion branch is established to enrich the local information of high-layer features. Third, a receptive field adaptation block (RFAB) is proposed to ensure that the receptive field can be adaptively selected to strengthen the expression ability of features. Finally, we improve the anchor setting method and adopt soft non-maximum suppression (SoftNMS) as the selection method of candidate boxes. Experimental results show that average precision for small-scale face detection of R-FCN with feature fusion branch and RFAB (RFAB-f-R-FCN) is improved by 0.8%, 2.9%, and 11% on three subsets of Wider Face compared with that of R-FCN.

Download Full-text