https://github.com/eatbeanss/CSWin-UNet
공식 코드CSWin-UNet: Transformer UNet with Cross-Shaped Windows for 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.
CSWin-UNet: Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation
The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs
Benchmarking Unsupervised Object Representations for Video Sequences
Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer
Task-agnostic Out-of-Distribution Detection Using Kernel Density Estimation
LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms
ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
Tackling the Class Imbalance Problem of Deep Learning Based Head and Neck Organ Segmentation
Capturing Omni-Range Context for Omnidirectional Segmentation
Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentation
ReshapeIT: Reliable Shape Interaction with Implicit Template for Anatomical Structure Reconstruction
PASS:Test-Time Prompting to Adapt Styles and Semantic Shapes in Medical Image Segmentation
Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation
MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders
Mesh Convolution with Continuous Filters for 3D Surface Parsing
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
Imbalanced Medical Image Segmentation with Pixel-dependent Noisy Labels
ERNet: Unsupervised Collective Extraction and Registration in Neuroimaging Data
Restore Anything Pipeline: Segment Anything Meets Image Restoration
Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.