https://github.com/mindspore-ai/models/tree/master/research/cv/vnet
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
Polarized Self-Attention: Towards High-quality Pixel-wise Regression
SA-Net: Shuffle Attention for Deep Convolutional Neural Networks
Augmenting Convolutional networks with attention-based aggregation
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Deep High-Resolution Representation Learning for Visual Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.