https://github.com/johnwlambert/argoverse_cbgs_kf_tracker
Class-balanced Grouping and Sampling for Point Cloud 3D 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.
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
U-Net: Convolutional Networks for Biomedical Image Segmentation
LambdaNetworks: Modeling Long-Range Interactions Without Attention
Towards Deep Learning Models Resistant to Adversarial Attacks
Soft-NMS -- Improving Object Detection With One Line of Code
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
U-Net: Convolutional Networks for Biomedical Image Segmentation
RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
U-Net: Convolutional Networks for Biomedical Image Segmentation
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
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
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
The Effects of Super-Resolution on Object Detection Performance in Satellite Imagery
RepMet: Representative-based metric learning for classification and one-shot object detection
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
Rich feature hierarchies for accurate object detection and semantic segmentation
Rich feature hierarchies for accurate object detection and semantic segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.