Table 2.
Performance comparisons of fashion parsing methods (in %) [28]
| Method | Dataaset | Evaluation Metrics | |||||||
|---|---|---|---|---|---|---|---|---|---|
| mIOU | aPA | mAGR | Acc. | Fg.acc. | Avg.prec. | Avg.recall | AVG.F-1 | ||
| Yamaguchi et al., [93] | ATR [39] | – | – | – | 88.96 | 62.18 | 52.75 | 49.43 | 44.76 |
| Liang et al., [10] | – | – | – | 91.11 | 71.04 | 71.69 | 60.5 | 64.38 | |
| Co-CNN [39] | – | – | – | 96.02 | 83.57 | 84.95 | 77.66 | 80.14 | |
| Yamaguchi et al., [93] | Fashionista [93] | – | – | – | 89.98 | 65.66 | 54.87 | 51.16 | 46.80 |
| Liang et al., [10] | – | – | – | 92.33 | 76.54 | 73.93 | 66.49 | 69.30 | |
| Co-CNN [39] | – | – | – | 97.06 | 89.15 | 87.83 | 81.73 | 83.78 | |
| CE2P [64] | LIP [13] | 53.10 | – | – | 63.20 | – | – | – | – |
| Wang et al., [85] | 57.74 | – | – | 68.80 | – | – | – | – | |
| Co-CNN [39] | ATR [39] | – | 96.02 | – | – | 83.57 | 84.95 | 77.66 | 80.14 |
| TGPNet [47] | – | 96.45 | – | – | 87.91 | 83.36 | 80.22 | 81.76 | |
| Wang et al., [85] | – | 96.26 | – | – | 87.91 | 84.62 | 86.41 | 85.51 | |