# Traffic Sign Detection on Tsinghua-Tencent 100K (test) Source: [Traffic Sign Detection on Tsinghua-Tencent 100K (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:22.548Z Evaluation of Traffic Sign Detection performance on the test split of the Tsinghua-Tencent 100K dataset, typically reporting accuracy and recall broken down by object size. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Traffic Sign Detection | | Dataset (including any stated split) | Tsinghua-Tencent 100K (test) | | Metric | Accuracy (Overall) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy (Overall)](): Higher is better; unit: PERCENT. - [Accuracy (Small)](): Higher is better; unit: PERCENT. - [Accuracy (Medium)](): Higher is better; unit: PERCENT. - [Accuracy (Large)](): Higher is better; unit: PERCENT. - [Recall (Small)](): Higher is better; unit: PERCENT. - [Recall (Medium)](): Higher is better; unit: PERCENT. - [Recall (Large)](): Higher is better; unit: PERCENT. - [Recall (Overall)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Overall) | Result date | Report paper | | --- | --- | --- | --- | | Meng | 0.9 | Not recorded | 68fa64dd1e209131cea06de3 | | Li | 0.89 | Not recorded | 68fa64dd1e209131cea06de3 | | Zhu | 0.88 | Not recorded | 68fa64dd1e209131cea06de3 | | Ours | 0.68 | Not recorded | 68fa64dd1e209131cea06de3 | ### Meng Accuracy (Overall): 0.9. Result ID: 698c90720b614d12cff1a21a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approach":"Image pyramid and sliding window"}. This record does not assert independent reproduction. ### Li Accuracy (Overall): 0.89. Result ID: 698c90720b614d12cff1a219. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Zhu Accuracy (Overall): 0.88. Result ID: 698c90720b614d12cff1a218. [Reporting paper]() Recorded evaluation configuration: {"Framework":"OverFeat \[38\]"}. This record does not assert independent reproduction. ### Ours Accuracy (Overall): 0.68. Result ID: 698c90720b614d12cff1a21b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Hierarchical Deep Architecture","Training":"Mini-Batch Selection","Mechanism":"Background Threshold"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.