HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

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
GeoAware-SC (Supervised, AP-10K P.T.)85.6Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
GeoAware-SC (Supervised)82.9Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
SD+DINO (Supervised)74.6A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
GeoAware-SC + CleanDIFT (Zero-Shot)70.0CleanDIFT: Diffusion Features without Noise
GeoAware-SC (Zero-Shot)68.5Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
SD+DINO + CleanDIFT (Zero-Shot)64.8CleanDIFT: Diffusion Features without Noise
IFCAT64.4Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
SD+DINO (Zero-shot)64.0A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
DIFT + CleanDIFT (Zero-Shot)61.4CleanDIFT: Diffusion Features without Noise
CATs++59.8CATs++: Boosting Cost Aggregation with Convolutions and Transformers
VAT (ECCV)55.5Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
VAT54.2Cost Aggregation Is All You Need for Few-Shot Segmentation
TransforMatcher53.7TransforMatcher: Match-to-Match Attention for Semantic Correspondence
MMNet50.4Multi-scale Matching Networks for Semantic Correspondence
CATs49.9CATs: Cost Aggregation Transformers for Visual Correspondence
CHM46.3Convolutional Hough Matching Networks
LDMCorrespondences45.4Unsupervised Semantic Correspondence Using Stable Diffusion
DHPF37.3Learning to Compose Hypercolumns for Visual Correspondence
SCOT35.6Semantic Correspondence as an Optimal Transport Problem
ANCNet30.1Correspondence Networks with Adaptive Neighbourhood Consensus
0 of 21 row(s) selected.
Semantic Correspondence On Spair 71K | SOTA | HyperAI超神经