https://github.com/imatif17/acia
공식 코드Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
AirShot: Efficient Few-Shot Detection for Autonomous Exploration
Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation
YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality
A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News
UMAD: University of Macau Anomaly Detection Benchmark Dataset
Real Time Bangladeshi Sign Language Detection using Faster R-CNN
YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID
ALBench: A Framework for Evaluating Active Learning in Object Detection
Pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks
Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning
Find the Funding: Entity Linking with Incomplete Funding Knowledge Bases
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
BITE: Textual Backdoor Attacks with Iterative Trigger Injection
Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
A High-Resolution Dataset for Instance Detection with Multi-View Instance Capture
DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks
InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation
Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models
CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring
Towards Real-world Event-guided Low-light Video Enhancement and Deblurring
Supervised Contrastive Learning for Interpretable Long-Form Document Matching
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.