A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network
[article]
2020
arXiv
pre-print
Preserved Fulltext
This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly ...
Hierarchical-Split Block contains many hierarchical split and concatenate connections within one single residual block. We find multi-scale features is of great importance for numerous vision tasks. ...
Meanwhile, we propose a network named HS-ResNet, which consists of several Hierarchical-Split blocks. ...
arXiv:2010.07621v1
fatcat:ivc7t4jhpbbd5p3omofzoily2m
CS-HSNet:A Cross-Siamese Change Detection Network Based On Hierarchical-Split Attention
2021
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Finally, we propose a hierarchical-split block for generating multi-scale feature representations in a coarse-to-fine fashion. ...
residual block. ...
In particular, our hierarchicalsplit attention module could be plugged into majority convolutional neural networks. ...
doi:10.1109/jstars.2021.3113831
fatcat:vfo37a36efgvpjogctq2emldo4
Calibrated Convolution with Gaussian of Difference
2022
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Attention mechanisms are widely used for Convolutional Neural Networks (CNNs) when performing various visual tasks. ...
During experimental tests on various datasets, the method increased the ResNet50-based classification accuracy from 76.40% to 77.87% on the ImageNet dataset, and the tests generally confirmed that CCGD ...
Res2Net [21] and HS-ResNet [22] build upon ResNet by having a fine-grained hierarchical split and concatenated connections within a single residual block. ...
doi:10.3390/app12136570
fatcat:cd4owkn325dw5hjw7v35otdzuq
The HCCL System for the NIST SRE21
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We denote the methods that work directly on speech to eliminate the relatively explicit mismatches collectively as data adaptation methods. ...
Furthermore, some popular back-ends domain adaptation algorithms are deployed on speaker embeddings to alleviate speaker performance degradation caused by the implicit mismatch. ...
We use our implementation of ECAPA-TDNN with the following parameters: the number of HS-ResNet blocks are set to 4 with dilation values 2,3,4,5 for blocks; the number of channels and embedding size are ...
arXiv:2207.04676v1
fatcat:zdh25e2fr5g5blhhvjuppstsdu
SRNet: Scale-aware Representation Learning Network for Dense Crowd Counting
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To decrease the amount of calculation required while maintaining the improved accuracy, HS-ResNet [19] was recently proposed; in this model, the Hierarchical-Split Block(HSB) separation feature is divided ...
[37] combined a multi-scale convolutional neural network (generator) and an adversarial network (discriminator) to generate a high-quality density map and adapt crowd counting in complex crowd scenes ...
doi:10.1109/access.2021.3115963
fatcat:tgb2oyh6rvdd7mzmodrqwrjnoe
Explore Long-Range Context feature for Speaker Verification
[article]
2021
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose the combination of the Hierarchical-Split block(HS-block) and the Depthwise Separable Self-Attention(DSSA) module to capture richer multi-range context speaker features from a ...
Specifically, the HS-block splits the feature map and filters into several groups and stacks them in one block, which enlarges the receptive fields(RFs) locally. ...
. • we introduce a novel Hierarchical-Split block to enlarge the RFs in a single block for SV tasks, named HS-resnet. • we propose an innovative plug-and-play module based on the attention mechanism, DSSA ...
doi:10.48550/arxiv.2112.07134
fatcat:dehr6kj2offvljezywekbthj6m