CLIP4STR-B (DataComp-1B)

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 ParsingonIIIT5k
Accuracy· uses extra data· 2023-05-23
99.5
best: 99.6 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014
Scene Text RecognitiononIIIT5k
Accuracy· uses extra data· 2023-05-23
99.5
best: 99.6 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014

Audio1 result

2D Semantic SegmentationonIIIT5k
Accuracy· uses extra data· 2023-05-23
99.5
best: 99.6 (CLIP4STR-L (DataComp-1B))
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model arXiv:2305.14014