ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis
ConvTimeNet is a versatile model for time series analysis, combining the strengths of convolutional and Transformer networks to achieve superior performance.
IMG2IMU: Translating Knowledge from Large-Scale Images to IMU Sensing Applications
이 논문은 대규모 이미지로부터 IMU 감지 응용 프로그램으로 지식을 전이하는 방법을 제안합니다.
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
Sparse CNNs can outperform transformers in 3D semantic segmentation with adaptivity.
TrafficGPT: Deep Learning Model for Traffic Analysis and Generation
Pre-trained TrafficGPT model with linear attention mechanism enhances traffic analysis and generation tasks.
Improving Knowledge Distillation using Orthogonal Projections by Roy Miles, Ismail Elezi, and Jiankang Deng at Huawei Noah’s Ark Lab
The authors propose a novel constrained feature distillation method based on orthogonal projections and task-specific normalization to enhance knowledge transfer in deep learning models. By enforcing the preservation of feature similarity through orthogonal projections, they achieve significant performance improvements across various tasks.
The VampPrior Mixture Model: Advancing Deep Learning for scRNA-seq Analysis
The author introduces the VampPrior Mixture Model (VMM) as a novel prior for deep latent variable models, aiming to improve clustering performance in scRNA-seq analysis through simultaneous integration and clustering.
A Comprehensive Survey of Convolutional Neural Networks in Deep Learning: Applications, Challenges, and Future Trends
The authors explore various types of CNNs, their applications, challenges, and future trends to accelerate research progress in the domain.
© 2024 by Linnk AI