https://github.com/vribeiro1/skin-lesion-segmentation-agreement
공식 코드Handling Inter-Annotator Agreement for Automated Skin Lesion Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Handling Inter-Annotator Agreement for Automated Skin Lesion Segmentation
Semi-Supervised Segmentation of Functional Tissue Units at the Cellular Level
A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI
Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement
Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation
CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation
SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
Weakly Supervised Image Segmentation Beyond Tight Bounding Box Annotations
LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning
Progressive Dual Priori Network for Generalized Breast Tumor Segmentation
MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet
1st Place Solution for PSG competition with ECCV'22 SenseHuman Workshop
RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation
Deep Semantic Model Fusion for Ancient Agricultural Terrace Detection
GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP
Deep Residual Learning for Instrument Segmentation in Robotic Surgery
Learning to Adapt Structured Output Space for Semantic Segmentation
TotalSegmentator: robust segmentation of 104 anatomical structures in CT images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.