Text Spotting On Icdar 2015
評価指標
F-measure (%) - Generic Lexicon
F-measure (%) - Strong Lexicon
F-measure (%) - Weak Lexicon
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | F-measure (%) - Generic Lexicon | F-measure (%) - Strong Lexicon | F-measure (%) - Weak Lexicon |
|---|---|---|---|
| text-perceptron-towards-end-to-end-arbitrary | 65.1 | 80.5 | 76.6 |
| fots-fast-oriented-text-spotting-with-a | 62.2 | 83.6 | 74.5 |
| deepsolo-let-transformer-decoder-with | 76.9 | 86.8 | 81.9 |
| deepsolo-let-transformer-decoder-with | 79.1 | 88.0 | 83.5 |
| abcnet-v2-adaptive-bezier-curve-network-for | 73.0 | 82.7 | 78.5 |
| spts-single-point-text-spotting | 65.8 | 77.5 | 70.2 |
| text-spotting-transformers | 73.6 | 85.2 | 79.4 |
| deepsolo-let-transformer-decoder-with | 79.5 | 88.1 | 83.9 |
| mango-a-mask-attention-guided-one-stage-scene | 67.3 | 81.8 | 78.9 |
| swintextspotter-scene-text-spotting-via | 70.5 | 83.9 | 77.3 |
| towards-unified-scene-text-spotting-based-on | 80.3 | 89.0 | 84.1 |
| textdragon-an-end-to-end-framework-for | 65.2 | 82.5 | 78.3 |
| mask-textspotter-v3-segmentation-proposal | 74.2 | 83.3 | 78.1 |
| spts-v2-single-point-scene-text-spotting | 72.6 | 82.3 | 77.7 |
| a3s-adversarial-learning-of-semantic | 79.6 | 84.8 | 83.7 |
| pgnet-real-time-arbitrarily-shaped-text | 63.5 | 83.3 | 78.3 |
| decoupling-recognition-from-detection-single | 74.5 | 85.6 | 81.7 |
| glass-global-to-local-attention-for-scene | 76.3 | 84.7 | 80.1 |