https://github.com/DLWK/EANet
Rethinking Atrous Convolution for Semantic 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.
Rethinking Atrous Convolution for Semantic Image Segmentation
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing
CE-Net: Context Encoder Network for 2D Medical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Masked-attention Mask Transformer for Universal Image Segmentation
ResUNet++: An Advanced Architecture for Medical Image Segmentation
Stan: Small tumor-aware network for breast ultrasound image segmentation
Region-of-interest guided Supervoxel Inpainting for Self-supervision
Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
Self-Supervised Model Adaptation for Multimodal Semantic Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
HAKE: A Knowledge Engine Foundation for Human Activity Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.