https://github.com/MindCode-4/code-1/tree/main/vit_hybrid
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
OneFormer: One Transformer to Rule Universal Image Segmentation
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
DINOv2 based Self Supervised Learning For Few Shot Medical Image Segmentation
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
ViTs for SITS: Vision Transformers for Satellite Image Time Series
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.