https://github.com/nihalsid/ViewAL
공식 코드ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation
Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis
Deep Learning for Morphological Identification of Extended Radio Galaxies using Weak Labels
DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation
FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation
TGANet: Text-guided attention for improved polyp segmentation
Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation
EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation
Text and Click inputs for unambiguous open vocabulary instance segmentation
Segmentation-guided MRI reconstruction for meaningfully diverse reconstructions
Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features
Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation
RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments
Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation
Interpretability-guided Data Augmentation for Robust Segmentation in Multi-centre Colonoscopy Data
Spatial-Frequency Dual Progressive Attention Network For Medical Image Segmentation
Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentation
EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models
UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation
NamedMask: Distilling Segmenters from Complementary Foundation Models
Unsupervised Salient Object Detection with Spectral Cluster Voting
Instance Segmentation for Autonomous Log Grasping in Forestry Operations
CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory
Distillation Learning Guided by Image Reconstruction for One-Shot Medical Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.