发帖
雷达卡
200+即插即用模块代码
(99 Bytes, 需要: RMB 19 元)
10种动态注意力创新机制
12种魔改特征融合（附代码+模型）
13种交叉注意力机制融合
14篇时间序列异常检测论文、工具和数据集
17种CNN+Transformer融合方法
37种多尺度特征融合模块
82个即插即用缝合模块
8个时间序列注意力模块及其变体
深度学习模型涨点必备的23个注意力机制
深度学习调参指南中文版.pdf
没有代码就是没有公布！！！.txt
A FREE LUNCH FROM VIT ADAPTIVE ATTENTION MULTI-SCALE FUSION TRANSFORMER FOR FINE-GRAINED VISUAL RECOGNITION
AAU-net An Adaptive Attention U-net for Breast Lesions Segmentation in Ultrasound Images
Adaptive Attention for Sparse-based Long-sequence Transformer
BiFormer Vision Transformer with Bi-Level Routing Attention
Dynamic Attentive Graph Learning for Image Restoration
Dynamic DETR End-to-End Object Detection with Dynamic Attention
Gaussian Adaptive Attention is All You Need Robust Contextual Representations Across Multiple Modalities
Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention
MV-Swin-T MAMMOGRAM CLASSIFICATION WITH MULTI-VIEW SWIN TRANSFORMER
PDFormer Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction
已选中13个文件/文件夹
1.Densenet
10.SPP-net
11.PSP-net
12.ECA-Net
2.Resnet
3.CBP
4.SENet
5.GCNet
6.DANet
7.PANet
8.FPN
9.ASPP
【预览检索】深度学习
已选中14个文件/文件夹
2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision
CaEGCN Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering
CCNet Criss-Cross Attention for Semantic Segmentation
CreativeSynth Creative Blending and Synthesis of Visual Arts based on Multimodal Diffusion
Cross-Interaction Hierarchical Attention Networks for Urban Anomaly Prediction
ICAFusion Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
MMViT Multiscale Multiview Vision Transformers
Multi-Modality Cross Attention Network for Image and Sentence Matching
Prompt-to-Prompt Image Editing with Cross Attention Control
Rethinking Cross-Attention for Infrared and Visible Image Fusion
SPEECH EMOTION RECOGNITION WITH CO-ATTENTION BASED MULTI-LEVEL ACOUSTIC INFORMATION
Training-Free Layout Control with Cross-Attention Guidance
Transformer-XL Attentive Language Models Beyond a Fixed-Length Context
没有代码就是作者未公布.txt
已选中15个文件/文件夹
ANOMALY BERT 自我监督的Transformer 用于使用数据进行时间序列异常检测退化方案
DCdetector 双注意对比表示学习用于时间序列异常检测
Microsof的时间序列异常检测服务
TODS一种自动时间序列异常值检测系统
TranAD-用于异常检测的深度变压器网络多变量时间序列数据
对多时间序列异常检测的图形增强规范化
多变量时间序列异常检测与解释使用分层互度量和时间嵌入
给无监督时间序列异常检测校准的一级分类
基于图神经网络的多变量时间序列异常检测
具有自监督的自适应记忆网络无监督异常检测的学习
时间序列的无监督模型选择异常检测
时间序列异常检测的深度学习研究综述
时态数据的异常点检测研究综述
异常转换器-时间序列异常关联差异检测
工具和数据集.pdf
保存到：
我的网盘
已选中18个文件/文件夹
An Efficient Hybrid CNN-Transformer Approach for Remote Sensing Super-Resolution
BEFUnet A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation
Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation
Conformer Local Features Coupling Global Representations for Visual Recognition
CTMANet_A_CNN-Transformer_Hybrid_Semantic_Segmentation_Network_for_Fine-Grained_Airport_Extraction_in_Complex_SAR_Scenes
DeMT Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction
Learned Image Compression with Mixed Transformer-CNN Architectures
Lite-Mono A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
Multi-task approach based on combined CNN-transformer for efficient segmentation and classification of breast tumors in ultrasound images
Official PyTorch implementation of Rethinking Mobile Block for Efficient Attention-based Models
ScribFormer Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation
SSNet_A_Novel_Transformer_and_CNN_Hybrid_Network_for_Remote_Sensing_Semantic_Segmentation
TabCtNet Target-aware bilateral CNN-transformer network for single object tracking in satellite videos
TCNet_Multiscale_Fusion_of_Transformer_and_CNN_for_Semantic_Segmentation_of_Remote_Sensing_Images
This is the official code for LEFormer A Hybrid CNN-Transformer Architecture for Accurate Lake Extraction from Remote Sensing Imagery
Transfer Learning for Microstructure Segmentation with CS-UNet A Hybrid Algorithm with Transformer and CNN Encoders
TransXNet Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition
没有代码的就是没有公布！！！.txt
保存到：
我的网盘
已选中37个文件/文件夹
AlignMiF：用于激光雷达-相机联合合成的几何对齐多模态隐式场
BiViT：极度压缩的二值化视觉Transformer
CancerUniT：利用大量 CT 扫描数据建立单个统一模型以实现对八大主要癌症的有效检测、分割和诊断
CORE：用于多智能体感知的协同重建
CRNet：用于统一图像恢复和增强任务的细节保留网络
DeepInteraction 通过模态交互的三维物体检测
DI-V2X：学习域不变表示以支持车路协同3D目标检测
DiffPose：用于基于视频的人体姿态估计的时空扩散模型。
DistillBEV：通过跨模态知识蒸馏提升多摄像头三维目标检测
EgoObjects：用于细粒度对象理解的大规模以自我为中心的数据集
Elite360D：通过语义和距离感知的双向投影融合实现高效的 360 度深度估计
Gold-YOLO：通过聚合-分发机制的高效目标检测器
Point-M2AE 用于分层点云预训练的多尺度掩码自编码器
RCBEVDet：用于 3D 目标检测的鸟瞰视角下的雷达 - 相机融合
SED：一种用于开放词汇表语义分割的简单编码器-解码器
SFOD：脉冲融合对象检测器
StreamingFlow：通过神经常微分方程对异步多模态数据流进行流式占用预测
SurroundOcc：用于自动驾驶的多摄像头三维占用预测
ViT-CoMer：用于密集预测的具有卷积多尺度特征交互的视觉 Transformer
VSFormer：用于对应点修剪的视觉-空间融合Transformer
WDiscOOD：通过白化线性判别分析进行分布外检测
《神奇动物在哪里：用双 SAM 分割任何海洋动物》
尺度感知调制遇见Transformer
多智能体协同感知的时空域感知
基于Transformer的高分辨率培养皿图像中微生物的检测
焦点调制网络
可靠的冲突性多视角学习
面向统一自动驾驶的多任务协同训练中的有效自适应
深度傅里叶上采样
四维无监督对象发现
通过持续预训练迈向地理空间基础模型
通过可靠、多样且类别平衡的伪标签重新审视领域自适应三维目标检测
伪标签校准的半监督多模态实体对齐
细粒度原型蒸馏用于小样本目标检测
学习发现和检测对象
用于二分图像分割的多视图聚合网络
在互联自动驾驶汽车中通过混合特征融合进行协同语义占用预测
保存到：
我的网盘
已选中6个文件/文件夹
mamba
卷积
频域
特征融合
下采样
注意力
已选中5个文件/文件夹
Convolutional State Space Models for Long-Range Spatiotemporal Modeling
MambaIR
MambaTab
nnMamba
ZigMa
已选中20个文件/文件夹
AKConv
AsymmetricConv
Chasing Higher FLOPS for Faster Neural Networks
CondConv
CoordGate
DO-Conv
DynamicConv
Efficient Deformable ConvNets Rethinking Dynamic and Sparse Operator for Vision Applications
EfficientMod
GhostNet
HetConv
Improving Convolutional Networks with Self-Calibrated Convolutions
Involution
KernelWarehouseTowards Parameter-EffcientDynamic Convolution
OctaveConv
Omni-Dimensional Dynamic Convolution
REFCONV RE-PARAMETERIZED REFOCUSING CONVOLUTION FOR POWERFUL CONVNETS
ResNeStBlock
SCCony Spatial and Channel Reconstruction Convolution for Feature Redundancy
UniRepLKNet
已选中9个文件/文件夹
Adaptive Fourier Neural Operators Efficient Token Mixers for Transformers
Adaptive Frequency Filters As Efficient Global Token Mixers
FFT-Based Dynamic Token Mixer for Vision
FlashFFTConv Efficient Convolutions for Long Sequences with Tensor Cores
FOURCASTNET A GLOBAL DATA-DRIVEN HIGH-RESOLUTION
FourierGNN Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
Global Filter Networks for Image Classification
SpectFormer Frequency and Attention is what you need in a Vision Transformer
TIMESNET TEMPORAL 2D-VARIATION MODELING
已选中13个文件/文件夹
Adaptive Fusion Techniques for Multimodal Data
CentralNeta Multilayer Approach forMultimodal Fusion
COMPOUND MULTI-BRANCH FEATURE FUSION FORREAL IMAGE RESTORATION
Domain Generalization for Activity Recognition viaAdaptive Feature Fusion
DSSD Deconvolutional Single Shot Detector
Effcient Low-rank Multimodal Fusion with Modality-Specifc Factors
Feature Pyramid Networks for Object Detection
FSSD Feature Fusion Single Shot Multibox Detector
LARGE-SCALE CONTRASTIVE LANGUAGE.AUDIO PRETRAINING WITFEATURE FUSION AND KEYWORD.TO-CAPTION AUGMENTATION
Learning Spatial Fusion for Single-Shot Object Detection
Multimodal Topic Learning for Video Recommendation
Rethinking Atrous Convolution for Semantic Image Segmentation
Tensor Fusion Network for Multimodal Sentiment Analysis
已选中8个文件/文件夹
AutoFocusFormer Image Segmentation off the Grid
Correlated and Multi-frequency Diffusion Modeling for Highly Under-sampled MRI Reconstruction
FastICENet A real-time and accurate semantic segmentation model for aerial remote sensing river ice image
FouriDown Factoring Down-Sampling into Shuffling and Superposing
Global Context Vision Transformers
LUM-ViT Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
No More Strided Convolutions or Pooling A Novel CNN Architecture for Low-Resolution Images and Small Objects
PUERT Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
已选中28个文件/文件夹
A2-Nets Double Attention Networks
Activating More Pixels in Image Super-Resolution Transformer
Agent Attention On the Integration of Softmax and Linear Attention
An Empirical Evaluation of Generic Convolutional and Recurrent Networks
BiFormer Vision Transformer with Bi-Level Routing Attention
CBAM Convolutional Block Attention Module
CenterMask Real-Time Anchor-Free Instance Segmentation
CityCAN
ECA-Net Efficient Channel Attention for Deep Convolutional Neural Networks
Efficient Multi-Scale Attention Module with Cross-Spatial Learning
FECAM
Gather-Excite Exploiting Feature Context inConvolutional Neural Networks
Global Attention Mechanism Retain Information toEnhance Channel-Spatial Interactions
Global Context Networks
Large Selective Kernel Network for Remote Sensing Object Detection
Learning Dynamics and Heterogeneity ofSpatial-Temporal Graph Data for TrafficForecasting
Non-local Neural Networks
Non-stationary Transformers
On the Integration of Self-Attention and Convolution
Polarized Self-Attention Towards High-quality Pixel-wise Regression
PYRAFORMER LOW-COMPLEXITY PYRAMIDAL
REVERSIBLE COLUMN NETWORKS
SEAFORMER
Selective Kernel Networks
Self-supervised Equivariant Attention Mechanismfor Weakly Supervised Semantic Segmentation
Squeeze-and-Excitation Networks
Triformer
UnetTSF A Better Performance Linear Complexity Time Series Prediction Model
保存到：
我的网盘
已选中7个文件/文件夹
金字塔时间注意力
频率增强信道注意力机制
去平稳化注意力
时间卷积模块
时间趋势感知注意力
线性时间预测
因果时间注意力
京公网安备 11010802022788号
