https://github.com/huyquoctrinh/kdas
공식 코드KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation
KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation
Refined Deep Neural Network and U-Net for Polyps Segmentation
Scribble-supervised Cell Segmentation Using Multiscale Contrastive Regularization
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation
Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation
Dual Prototype Attention for Unsupervised Video Object Segmentation
Guided Slot Attention for Unsupervised Video Object Segmentation
Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation
Leveraging Hidden Positives for Unsupervised Semantic Segmentation
Balanced Energy Regularization Loss for Out-of-distribution Detection
Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation
Learning Implicit Feature Alignment Function for Semantic Segmentation
Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
Infrastructure Crack Segmentation: Boundary Guidance Method and Benchmark Dataset
Efficient Regional Memory Network for Video Object Segmentation
JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds
VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation
LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
A New Perspective to Boost Performance Fairness for Medical Federated Learning
Conditional Reconstruction for Open-set Semantic Segmentation
FuSS: Fusing Superpixels for Improved Segmentation Consistency
FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator
Neural Embedding Compression For Efficient Multi-Task Earth Observation Modelling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.