https://github.com/davidzhangyuanhan/bamboo
공식 코드Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images
ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes
TIDE: A General Toolbox for Identifying Object Detection Errors
A positive feedback method based on F-measure value for Salient Object Detection
BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction
Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
VOS: Learning What You Don't Know by Virtual Outlier Synthesis
Unsupervised Learning of Object Keypoints for Perception and Control
Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection
Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Review
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers
Patch-based Selection and Refinement for Early Object Detection
ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
Instance Segmentation and Teeth Classification in Panoramic X-rays
Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset
SODFormer: Streaming Object Detection with Transformer Using Events and Frames
Uncertainty for Identifying Open-Set Errors in Visual Object Detection
A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
SamLP: A Customized Segment Anything Model for License Plate Detection
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.