https://github.com/canerozer/qct
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
U-Net: Convolutional Networks for Biomedical Image Segmentation
Rethinking Bottleneck Structure for Efficient Mobile Network Design
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
VinVL: Revisiting Visual Representations in Vision-Language Models
RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
Towards Deep Learning Models Resistant to Adversarial Attacks
Towards Deep Learning Models Resistant to Adversarial Attacks
Data-dependent Initializations of Convolutional Neural Networks
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
U-Net: Convolutional Networks for Biomedical Image Segmentation
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Rich feature hierarchies for accurate object detection and semantic segmentation
Rich feature hierarchies for accurate object detection and semantic segmentation
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.