VAT (ECCV)

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Image MatchingonPF-WILLOW
PCK· 2022-07-22
81.6
best: 84.3 (LDMCorrespondences)
SOTA
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation arXiv:2207.10866
Semantic correspondenceonPF-WILLOW
PCK· 2022-07-22
81.6
best: 84.3 (LDMCorrespondences)
SOTA
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation arXiv:2207.10866
Image MatchingonSPair-71k
PCK· 2022-07-22
55.5
best: 85.6 (GeoAware-SC (Supervised, AP-10K P.T.))
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation arXiv:2207.10866
Image MatchingonPF-PASCAL
PCK· 2022-07-22
92.3
best: 95.8 (DINOv2)
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation arXiv:2207.10866
Semantic correspondenceonSPair-71k
PCK· 2022-07-22
55.5
best: 85.6 (GeoAware-SC (Supervised, AP-10K P.T.))
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation arXiv:2207.10866
Semantic correspondenceonPF-PASCAL
PCK· 2022-07-22
92.3
best: 95.8 (DINOv2)
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation arXiv:2207.10866