https://github.com/leonardoaraujosantos/seg_atrous
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
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling
Rethinking Atrous Convolution for Semantic Image Segmentation
Boundary-Aware Network for Fast and High-Accuracy Portrait Segmentation
End-to-End Semi-Supervised Object Detection with Soft Teacher
EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes
Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.