https://github.com/pwc-1/Paper-9/tree/main/1/vitdet
Exploring Plain Vision Transformer Backbones for Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Exploring Plain Vision Transformer Backbones for Object Detection
YOLOSA: Object detection based on 2D local feature superimposed self-attention
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection
YOLOSA: Object detection based on 2D local feature superimposed self-attention
RandAugment: Practical automated data augmentation with a reduced search space
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
GroupViT: Semantic Segmentation Emerges from Text Supervision
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
MinneApple: A Benchmark Dataset for Apple Detection and Segmentation
MinneApple: A Benchmark Dataset for Apple Detection and Segmentation
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
U-Net: Convolutional Networks for Biomedical Image Segmentation
High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers
R-FCN: Object Detection via Region-based Fully Convolutional Networks
R-FCN: Object Detection via Region-based Fully Convolutional Networks
R-FCN: Object Detection via Region-based Fully Convolutional Networks
R-FCN: Object Detection via Region-based Fully Convolutional Networks
Multi-scale Location-aware Kernel Representation for Object Detection
R-FCN: Object Detection via Region-based Fully Convolutional Networks
R-FCN: Object Detection via Region-based Fully Convolutional Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.