Semantic Correspondence On Spair 71K

评估指标

PCK

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
GeoAware-SC (Supervised, AP-10K P.T.)	85.6	Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
GeoAware-SC (Supervised)	82.9	Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
SD+DINO (Supervised)	74.6	A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
GeoAware-SC + CleanDIFT (Zero-Shot)	70.0	CleanDIFT: Diffusion Features without Noise
GeoAware-SC (Zero-Shot)	68.5	Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
SD+DINO + CleanDIFT (Zero-Shot)	64.8	CleanDIFT: Diffusion Features without Noise
IFCAT	64.4	Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence	-
SD+DINO (Zero-shot)	64.0	A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
DIFT + CleanDIFT (Zero-Shot)	61.4	CleanDIFT: Diffusion Features without Noise
CATs++	59.8	CATs++: Boosting Cost Aggregation with Convolutions and Transformers
VAT (ECCV)	55.5	Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
VAT	54.2	Cost Aggregation Is All You Need for Few-Shot Segmentation
TransforMatcher	53.7	TransforMatcher: Match-to-Match Attention for Semantic Correspondence
MMNet	50.4	Multi-scale Matching Networks for Semantic Correspondence
CATs	49.9	CATs: Cost Aggregation Transformers for Visual Correspondence
CHM	46.3	Convolutional Hough Matching Networks
LDMCorrespondences	45.4	Unsupervised Semantic Correspondence Using Stable Diffusion
DHPF	37.3	Learning to Compose Hypercolumns for Visual Correspondence
SCOT	35.6	Semantic Correspondence as an Optimal Transport Problem	-
ANCNet	30.1	Correspondence Networks with Adaptive Neighbourhood Consensus

0 of 21 row(s) selected.