XCiT-S24/8

Reported on 6 benchmarks across 6 tasks · 1 paper

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

Methodology4 results

3DonCOCO minival
box AP· 2021-06-17
48.1
best: 66 (PE_spatial (DETA))
XCiT: Cross-Covariance Image Transformers arXiv:2106.09681
2D ClassificationonCOCO minival
box AP· 2021-06-17
48.1
best: 66 (PE_spatial (DETA))
XCiT: Cross-Covariance Image Transformers arXiv:2106.09681
2D Object DetectiononCOCO minival
box AP· 2021-06-17
48.1
best: 66 (PE_spatial (DETA))
XCiT: Cross-Covariance Image Transformers arXiv:2106.09681
16konCOCO minival
box AP· 2021-06-17
48.1
best: 66 (PE_spatial (DETA))
XCiT: Cross-Covariance Image Transformers arXiv:2106.09681

Computer Vision2 results

Object DetectiononCOCO minival
box AP· 2021-06-17
48.1
best: 66 (PE_spatial (DETA))
XCiT: Cross-Covariance Image Transformers arXiv:2106.09681
Instance SegmentationonCOCO minival
mask AP· 2021-06-17
43
best: 56.6 (Co-DETR)
XCiT: Cross-Covariance Image Transformers arXiv:2106.09681