https://github.com/automl/GoLU
공식 코드Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics
GOOD: Exploring Geometric Cues for Detecting Objects in an Open World
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors
Formal Verification of Deep Neural Networks for Object Detection
BOrg: A Brain Organoid-Based Mitosis Dataset for Automatic Analysis of Brain Diseases
A Satellite Imagery Dataset for Long-Term Sustainable Development in United States Cities
Benchmarking performance of object detection under image distortions in an uncontrolled environment
CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer Vision
Move to See Better: Self-Improving Embodied Object Detection
Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection
A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection Training
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection
Privacy-Preserving Autoencoder for Collaborative Object Detection
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings
Hard hat wearing detection based on head keypoint localization
End-to-End Human Object Interaction Detection with HOI Transformer
Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity
STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.