https://github.com/zhuoxiao-chen/mos
공식 코드MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 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.
MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding
A Real-Time Wrong-Way Vehicle Detection Based on YOLO and Centroid Tracking
Progressive Hard-case Mining across Pyramid Levels for Object Detection
FADet: A Multi-sensor 3D Object Detection Network based on Local Featured Attention
A Flying Bird Object Detection Method for Surveillance Video
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature Integration
Uncertainty Aware Human-machine Collaboration in Camouflaged Object Detection
SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Staging
Enhancing Sound Source Localization via False Negative Elimination
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
Suppress-and-Refine Framework for End-to-End 3D Object Detection
Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundary
Boundless: Generating Photorealistic Synthetic Data for Object Detection in Urban Streetscapes
Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers
Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection
AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection
SU-SAM: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes
Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation
PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection
Zero-Shot Aerial Object Detection with Visual Description Regularization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.