paper-with-me

Papers

Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification

2022-04-03 · Sung Hwan Mun, Jee-weon Jung, Min Hyun Han, Nam Soo Kim

The majority of recent state-of-the-art speaker verification architectures adopt multi-scale processing and frequency-channel attention mechanisms. Convolutional layers of these models typically have a fixed kernel size, e.g., 3 or 5. In this study, we further contribute to this line of research utilising a selective kernel attention (SKA) mechanism. The SKA mechanism allows each convolutional layer to adaptively select the kernel size in a data-driven fashion. It is based on an attention mechanism which exploits both frequency and channel domain. We first apply existing SKA module to our baseline. Then we propose two SKA variants where the first variant is applied in front of the ECAPA-TDNN model and the other is combined with the Res2net backbone block. Through extensive experiments, we demonstrate that our two proposed SKA variants consistently improves the performance and are complementary when tested on three different evaluation protocols.

📄 PDF Abstract BibTeX arXiv:2204.01005

Code (1)

msh9184/ska-tdnn 공식 구현 pytorch

Tasks

Speaker Verification

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
Residual Connection 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Kaiming Initialization 설명 없음
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Res2Net Block A Res2Net Block is an image model block that constructs hierarchical residual-like connections within one single [residual…

Similar Papers 제목 키워드 기반

Enhanced Feature Extraction for IoT Network Intrusion Detection Using GNNs and KAN

2026-07-03 · Long Zhao, Shixun Ji, Bin Cheng, Bin He arxiv

Recent advancements in the Internet of Things (IoT) emphasize the urgent need for advanced network security, as IoT networks feature dynamic topologies, imbalanced traffic, and complex attack patterns. Unlike general IT …

Network Intrusion Detection

Selective Kernel Networks

2019-03-15 · CVPR 2019 6 · Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size…

Image Classification

PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning

2026-02-24 · Xinyong Cai, Changbin Sun, Yong Wang, Hongyu Yang 외 arxiv

Spatiotemporal predictive learning (STPL) aims to forecast future frames from past observations and is essential across a wide range of applications. Compared with recurrent or hybrid architectures, pure convolutional mo…

Emphasizing Crucial Features for Efficient Image Restoration

2024-05-19 · Hu Gao, Bowen Ma, Ying Zhang, Jingfan Yang 외

Image restoration is a challenging ill-posed problem which estimates latent sharp image from its degraded counterpart. Although the existing methods have achieved promising performance by designing novelty architecture o…

Image Restoration

SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion

2025-03-03 · CVPR 2025 1 · Xuan Zhu, Jijun Xiang, Xianqi Wang, Longliang Liu 외

Lightweight direct Time-of-Flight (dToF) sensors are ideal for 3D sensing on mobile devices. However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth ma…

Depth Completion