https://github.com/sfu-mial/dermsynth3d
공식 코드DermSynth3D: Synthesis of in-the-wild Annotated Dermatology Images
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
DermSynth3D: Synthesis of in-the-wild Annotated Dermatology Images
Segmentation Style Discovery: Application to Skin Lesion Images
Human-in-the-Loop Segmentation of Multi-species Coral Imagery
Single Frame Semantic Segmentation Using Multi-Modal Spherical Images
Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation
CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
Language Guided Domain Generalized Medical Image Segmentation
Learnable Weight Initialization for Volumetric Medical Image Segmentation
Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing
FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection
DiffuseExpand: Expanding dataset for 2D medical image segmentation using diffusion models
Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
SwinVFTR: A Novel Volumetric Feature-learning Transformer for 3D OCT Fluid Segmentation
ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation
Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.