https://github.com/looooongchen/sortedap
공식 코드SortedAP: Rethinking evaluation metrics for instance segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
SortedAP: Rethinking evaluation metrics for instance segmentation
PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud
A Fair Ranking and New Model for Panoptic Scene Graph Generation
Efficient 3D Brain Tumor Segmentation with Axial-Coronal-Sagittal Embedding
The Second-place Solution for CVPR VISION 23 Challenge Track 1 -- Data Effificient Defect Detection
Similarity-Aware Fusion Network for 3D Semantic Segmentation
Mapping Semantic Segmentation to Point Clouds Using Structure from Motion for Forest Analysis
Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation
DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences
PHTrans: Parallelly Aggregating Global and Local Representations for Medical Image Segmentation
Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation
MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
Deep mineralogical segmentation of thin section images based on QEMSCAN maps
RECALL: Replay-based Continual Learning in Semantic Segmentation
DAMamba: Vision State Space Model with Dynamic Adaptive Scan
Entropy-based measure of rock sample heterogeneity derived from micro-CT images
VREM-FL: Mobility-Aware Computation-Scheduling Co-Design for Vehicular Federated Learning
A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation
End-to-end video instance segmentation via spatial-temporal graph neural networks
Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images
ASAM: Boosting Segment Anything Model with Adversarial Tuning
Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection
Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation
Novel Class Discovery for 3D Point Cloud Semantic Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.