https://github.com/canoe-z/petdet
공식 코드PETDet: Proposal Enhancement for Two-Stage Fine-Grained 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.
PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection
Frequency-based Matcher for Long-tailed Semantic Segmentation
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding
ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only
Towards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network
NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors
labelCloud: A Lightweight Domain-Independent Labeling Tool for 3D Object Detection in Point Clouds
EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Improving the Detection of Small Oriented Objects in Aerial Images
Making Vision Transformers Efficient from A Token Sparsification View
Hybrid Knowledge Routed Modules for Large-scale Object Detection
Harmonizing Transferability and Discriminability for Adapting Object Detectors
Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos
RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection
Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving
UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
BlendTorch: A Real-Time, Adaptive Domain Randomization Library
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.