Multi‐scale feature learning and temporal probing strategy for one‐stage temporal action localization

2021 ◽  
Author(s):  
Leiyue Yao ◽  
Wei Yang ◽  
Wei Huang ◽  
Nan Jiang ◽  
Bingbing Zhou
Keyword(s):  
Feature Learning ◽  
Scale Feature ◽  
Multi Scale ◽  
One Stage ◽  
Action Localization ◽  
Temporal Action

scholarly journals Graph convolutional neural network for multi-scale feature learning

2020 ◽  
Vol 194 ◽  
pp. 102881
Author(s):  
Michael Edwards ◽  
Xianghua Xie ◽  
Robert I. Palmer ◽  
Gary K.L. Tam ◽  
Rob Alcock ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Feature Learning ◽  
Scale Feature ◽  
Multi Scale

scholarly journals Broad-UNet: Multi-scale feature learning for nowcasting tasks

2021 ◽  
Author(s):  
Jesús García Fernández ◽  
Siamak Mehrkanoon
Keyword(s):  
Feature Learning ◽  
Scale Feature ◽  
Multi Scale

Person re-identification based on multi-scale feature learning

2021 ◽  
pp. 107281
Author(s):  
Yueying Li ◽  
Li Liu ◽  
Lei Zhu ◽  
Huaxiang Zhang
Keyword(s):  
Feature Learning ◽  
Scale Feature ◽  
Multi Scale

scholarly journals MSF-Net: Multi-Scale Feature Learning Network for Classification of Surface Defects of Multifarious Sizes

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5125
Author(s):  
Pengcheng Xu ◽  
Zhongyuan Guo ◽  
Lei Liang ◽  
Xiaohang Xu
Keyword(s):  
Defect Detection ◽  
Surface Defects ◽  
Receptive Fields ◽  
Feature Learning ◽  
Learning Ability ◽  
Detection Methods ◽  
Feature Maps ◽  
Scale Feature ◽  
Learning Network ◽  
Multi Scale

In the field of surface defect detection, the scale difference of product surface defects is often huge. The existing defect detection methods based on Convolutional Neural Networks (CNNs) are more inclined to express macro and abstract features, and the ability to express local and small defects is insufficient, resulting in an imbalance of feature expression capabilities. In this paper, a Multi-Scale Feature Learning Network (MSF-Net) based on Dual Module Feature (DMF) extractor is proposed. DMF extractor is mainly composed of optimized Concatenated Rectified Linear Units (CReLUs) and optimized Inception feature extraction modules, which increases the diversity of feature receptive fields while reducing the amount of calculation; the feature maps of the middle layer with different sizes of receptive fields are merged to increase the richness of the receptive fields of the last layer of feature maps; the residual shortcut connections, batch normalization layer and average pooling layer are used to replace the fully connected layer to improve training efficiency, and make the multi-scale feature learning ability more balanced at the same time. Two representative multi-scale defect data sets are used for experiments, and the experimental results verify the advancement and effectiveness of the proposed MSF-Net in the detection of surface defects with multi-scale features.

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Semantic Segmentation

2021 ◽  
Author(s):  
Zhuoying Wang ◽  
Yongtao Wang ◽  
Zhi Tang ◽  
Yangyan Li ◽  
Ying Chen ◽  
...  
Keyword(s):  
Feature Learning ◽  
Semantic Segmentation ◽  
Scale Feature ◽  
Multi Scale ◽  
Transfer Operation

Contextual Multi-Scale Feature Learning for Person Re-Identification

2020 ◽  
Author(s):  
Baoyu Fan ◽  
Li Wang ◽  
Runze Zhang ◽  
Zhenhua Guo ◽  
Yaqian Zhao ◽  
...  
Keyword(s):  
Feature Learning ◽  
Scale Feature ◽  
Multi Scale

scholarly journals AugFPN: Improving Multi-Scale Feature Learning for Object Detection

2020 ◽  
Author(s):  
Chaoxu Guo ◽  
Bin Fan ◽  
Qian Zhang ◽  
Shiming Xiang ◽  
Chunhong Pan
Keyword(s):  
Object Detection ◽  
Feature Learning ◽  
Scale Feature ◽  
Multi Scale

scholarly journals Adaptive Weighted Multi-Level Fusion of Multi-Scale Features: A New Approach to Pedestrian Detection

2021 ◽  
Vol 13 (2) ◽  
pp. 38
Author(s):  
Yao Xu ◽  
Qin Yu
Keyword(s):  
Deep Learning ◽  
Feature Fusion ◽  
Pedestrian Detection ◽  
Feature Maps ◽  
Scale Feature ◽  
Multi Scale ◽  
One Stage ◽  
Current State ◽  
Multi Level ◽  
Feature Utilization

Great achievements have been made in pedestrian detection through deep learning. For detectors based on deep learning, making better use of features has become the key to their detection effect. While current pedestrian detectors have made efforts in feature utilization to improve their detection performance, the feature utilization is still inadequate. To solve the problem of inadequate feature utilization, we proposed the Multi-Level Feature Fusion Module (MFFM) and its Multi-Scale Feature Fusion Unit (MFFU) sub-module, which connect feature maps of the same scale and different scales by using horizontal and vertical connections and shortcut structures. All of these connections are accompanied by weights that can be learned; thus, they can be used as adaptive multi-level and multi-scale feature fusion modules to fuse the best features. Then, we built a complete pedestrian detector, the Adaptive Feature Fusion Detector (AFFDet), which is an anchor-free one-stage pedestrian detector that can make full use of features for detection. As a result, compared with other methods, our method has better performance on the challenging Caltech Pedestrian Detection Benchmark (Caltech) and has quite competitive speed. It is the current state-of-the-art one-stage pedestrian detection method.

Sign in / Sign up

Export Citation Format

Share Document