Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector

@article{Du2020SelectiveFC,
  title={Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector},
  author={Chen Du and Chunheng Wang and Cunzhao Shi and Baihua Xiao},
  journal={Pattern Recognit. Lett.},
  year={2020},
  volume={129},
  pages={108-114}
}

Figures and Tables from this paper

Multi-Layer Convolutional Features Concatenation With Semantic Feature Selector for Vein Recognition
TLDR
A novel multi-layer convolutional features’ concatenation with semantic feature selector is proposed for vein recognition and a series of rigorous experiments on two lab-made vein databases is conducted to verify the effectiveness and feasibility of the model.
An effective modular approach for crowd counting in an image using convolutional neural networks
TLDR
A hierarchical dense dilated deep pyramid feature extraction through convolution neural network (CNN) for single image crowd counting (HDPF) that is very effective to propagate the extracted feature from lower dilated convolutional layers (DCLs) to middle and higher DCLs, which result in better estimation accuracy.
Spatial-Aware Network for Hyperspectral Image Classification
TLDR
An efficient deep learning-based HSI classification method, namely, spatial-aware network (SANet), which is able not only to aware local spatial structures using side window filtering framework, but also to learn discriminative features making use of the hierarchical architecture and limited label information.
Using Feature Fusion and Parameter Optimization of Dual-input Convolutional Neural Network for Face Gender Recognition
TLDR
The experimental results show that in the dual-input CNN experiment, average accuracy rates of 99.98% and 99.11% on the CIA and MORPH data sets are achieved, respectively, which is superior to the traditional feature fusion method.
Bridge-Tower: Building Bridges Between Encoders in Vision-Language Representation Learning
TLDR
The proposed BRIDGE-TOWER, pre-trained with only 4M images, achieves state-of-the-art performance on various downstream vision-language tasks and introduces multiple bridge layers that build a connection between the top layers of uni- modal encoders and each layer of the cross-modal encoder.
Leaf Recognition Based on Joint Learning Multiloss of Multimodel Convolutional Neural Networks: A Testing for Vietnamese Herb
TLDR
A new modification of multi-CNN ensemble training is investigated by combining multiloss functions from state-of-the-art deep CNN architectures for leaf image recognition by introducing a multimodel approach based on a combination of loss functions from the EfficientNet and MobileNet to generalize aMultiloss function.
Concrete crack segmentation based on convolution–deconvolution feature fusion with holistically nested networks
TLDR
A concrete crack segmentation network based on convolution–deconvolution feature fusion with holistically nested networks is proposed that achieves better segmentation results for cracks of different widths but is also more robust.
Multi-frame feature-fusion-based model for violence detection
TLDR
A novel method to detect fights or violent actions based on learning both the spatial and temporal features from equally spaced sequential frames of a video, using the proposed feature fusion method to take into account the motion information.
Improving Accuracy and Efficiency of Object Detection Algorithms Using Multiscale Feature Aggregation Plugins
TLDR
These plugins are generic and can be easily merged with the baseline models, which avoids the need for retraining the model, and also remove the semantic ambiguity and background noise arising from feature fusion of low and high layers representation.
...
...

References

SHOWING 1-10 OF 65 REFERENCES
Attention to Scale: Scale-Aware Semantic Image Segmentation
TLDR
An attention mechanism that learns to softly weight the multi-scale features at each pixel location is proposed, which not only outperforms averageand max-pooling, but allows us to diagnostically visualize the importance of features at different positions and scales.
Feature Pyramid Networks for Object Detection
TLDR
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Densely Connected Convolutional Networks
TLDR
The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
TLDR
A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi- scale object detection, which is learned end-to-end, by optimizing a multi-task loss.
Residual Attention Network for Image Classification
TLDR
The proposed Residual Attention Network is a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion and can be easily scaled up to hundreds of layers.
Striving for Simplicity: The All Convolutional Net
TLDR
It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks.
SRM: A Style-Based Recalibration Module for Convolutional Neural Networks
TLDR
A Style-based Recalibration Module (SRM), a simple yet effective architectural unit, which adaptively recalibrates intermediate feature maps by exploiting their styles and effectively enhances the representational ability of a CNN.
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
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.
Deeply-Supervised Nets
TLDR
The proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent, and extends techniques from stochastic gradient methods to analyze the algorithm.
...
...