https://github.com/mseg-dataset/mseg-semantic
High-Resolution Representations for Labeling Pixels and Regions
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
High-Resolution Representations for Labeling Pixels and Regions
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
Rethinking Atrous Convolution for Semantic Image Segmentation
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.