Codesota · Models · TextBPN++ (ResNet-50)Zhang et al. (HCIILAB)3 results · 1 benchmarks
Model card

TextBPN++ (ResNet-50).

Zhang et al. (HCIILAB)open-sourceUnknown paramsResNet-50 + Boundary Transformer (single-scale, no DCN)

TextBPN++ ResNet-50 single-scale variant without DCN. arXiv:2205.05320. T-MM 2023.

§ 01 · Benchmarks

Every benchmark TextBPN++ (ResNet-50) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01icdar-2017-mltComputer Vision · Scene Text Detectionf-measure72.3%#12/172022-05-11source ↗
02icdar-2017-mltComputer Vision · Scene Text Detectionprecision80.5%#12/182022-05-11source ↗
03icdar-2017-mltComputer Vision · Scene Text Detectionrecall65.7%#14/182022-05-11source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where TextBPN++ (ResNet-50) actually performs.

Computer Vision
1
benchmark
avg rank #12.7
§ 03 · Papers

1 paper with results for TextBPN++ (ResNet-50).

  1. 2022-05-11· Computer Vision· 3 results

    Arbitrary Shape Text Detection via Boundary Transformer

§ 05 · Sources & freshness

Where these numbers come from.

arxiv
3
results
3 of 3 rows marked verified.