https://github.com/MindSpore-scientific/code-13/tree/main/PolyLoss
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Translation Consistent Semi-supervised Segmentation for 3D Medical Images
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
U-Net: Convolutional Networks for Biomedical Image Segmentation
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities
MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
Masked-attention Mask Transformer for Universal Image Segmentation
SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
U-Net: Convolutional Networks for Biomedical Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.