https://github.com/TencentYoutuResearch/PedestrianDetection-NohNMS
공식 코드NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination
A Pseudo-Boolean Polynomials Approach for Image Edge Detection
Zero-Shot Grounding of Objects from Natural Language Queries
Leveraging edge detection and neural networks for better UAV localization
On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited
Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network
Federated Learning with Heterogeneous Data Handling for Robust Vehicular Object Detection
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction
SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo
MonoLSS: Learnable Sample Selection For Monocular 3D Detection
HRCenterNet: An Anchorless Approach to Chinese Character Segmentation in Historical Documents
TrackMe:A Simple and Effective Multiple Object Tracking Annotation Tool
Role of Spatial Context in Adversarial Robustness for Object Detection
SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
Complementary Random Masking for RGB-Thermal Semantic Segmentation
BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving
CBNet: A Composite Backbone Network Architecture for Object Detection
DynamicDet: A Unified Dynamic Architecture for Object Detection
OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.