CCD-ViT-Tiny

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Computer Vision2 results

Scene ParsingonSVTP
Accuracy· uses extra data· 2022-11-01
91.6
best: 98.6 (DTrOCR 105M)
Self-supervised Character-to-Character Distillation for Text Recognition arXiv:2211.00288
Scene Text RecognitiononSVTP
Accuracy· uses extra data· 2022-11-01
91.6
best: 98.6 (DTrOCR 105M)
Self-supervised Character-to-Character Distillation for Text Recognition arXiv:2211.00288

Audio1 result

2D Semantic SegmentationonSVTP
Accuracy· uses extra data· 2022-11-01
91.6
best: 98.6 (DTrOCR 105M)
Self-supervised Character-to-Character Distillation for Text Recognition arXiv:2211.00288