msra-td500 is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for msra-td500.
Fps is the reported evaluation metric for msra-td500. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | FAST-T-512 | verified | 137.2 | 2021 | Paper ↗Code ↗ | Looks wrong? |
| 02 | DBNet++ (ResNet-18) (512) | verified | 80 | 2022 | Paper ↗Code ↗ | Looks wrong? |
| 03 | FAST-T-736 | verified | 79.6 | 2021 | Paper ↗Code ↗ | Looks wrong? |
| 04 | FAST-S-736 | verified | 72 | 2021 | Paper ↗Code ↗ | Looks wrong? |
| 05 | FAST-B-736 | verified | 56.8 | 2021 | Paper ↗Code ↗ | Looks wrong? |
| 06 | DBNet++ (ResNet-18) (736) | verified | 55 | 2022 | Paper ↗Code ↗ | Looks wrong? |
| 07 | DBNet++ (ResNet-50) (736) | verified | 29 | 2022 | Paper ↗Code ↗ | Looks wrong? |
| 08 | MixNet | verified | 15.2 | 2023 | Paper ↗Code ↗ | Looks wrong? |
Precision is the reported evaluation metric for msra-td500. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.
F Measure is the reported evaluation metric for msra-td500. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.
Recall is the reported evaluation metric for msra-td500. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.