# Image Classification on iNaturalist Challenge 2018 (test) Source: [Image Classification on iNaturalist Challenge 2018 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:22.144Z Evaluation of Image Classification performance on the test split of the iNaturalist Challenge 2018 dataset, typically measured by Top-3 Error. 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 | Image Classification | | Dataset (including any stated split) | iNaturalist Challenge 2018 (test) | | Metric | Top-3 Error Rate | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 8 of 8 | | 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 - [Top-3 Error Rate](): Lower is better; unit: PERCENT. ## Recorded results | Method | Top-3 Error Rate | Result date | Report paper | | --- | --- | --- | --- | | Fusion III | 13.068 | Not recorded | 68fa682b1e209131cea1a7af | | Fusion II | 13.409 | Not recorded | 68fa682b1e209131cea1a7af | | Deep Learning Analytics | 14.214 | Not recorded | 68fa682b1e209131cea1a7af | | Fusion I | 14.625 | Not recorded | 68fa682b1e209131cea1a7af | | iSQRT-COV-Net | 14.704 | Not recorded | 68fa682b1e209131cea1a7af | | iSQRT-COV-Net | 15.038 | Not recorded | 68fa682b1e209131cea1a7af | | ResNet-152 | 16.024 | Not recorded | 68fa682b1e209131cea1a7af | | ResNet-152 | 16.623 | Not recorded | 68fa682b1e209131cea1a7af | ### Fusion III Top-3 Error Rate: 13.068. Result ID: 698d5ef58b517eb43320fe3c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ensemble":"Fusion I + Fusion II"}. This record does not assert independent reproduction. ### Fusion II Top-3 Error Rate: 13.409. Result ID: 698d5ef58b517eb43320fe3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ensemble":"3 x iSQRT-COV-Net Model"}. This record does not assert independent reproduction. ### Deep Learning Analytics Top-3 Error Rate: 14.214. Result ID: 698d5ef58b517eb43320fe3d. [Reporting paper]() Recorded evaluation configuration: {"status":"Runner-up"}. This record does not assert independent reproduction. ### Fusion I Top-3 Error Rate: 14.625. Result ID: 698d5ef58b517eb43320fe3a. [Reporting paper]() Recorded evaluation configuration: {"ensemble":"3 x ResNet-152 Model"}. This record does not assert independent reproduction. ### iSQRT-COV-Net Top-3 Error Rate: 14.704. Result ID: 698d5ef58b517eb43320fe39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input resolution":"392x392"}. This record does not assert independent reproduction. ### iSQRT-COV-Net Top-3 Error Rate: 15.038. Result ID: 698d5ef58b517eb43320fe38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input resolution":"320x320"}. This record does not assert independent reproduction. ### ResNet-152 Top-3 Error Rate: 16.024. Result ID: 698d5ef58b517eb43320fe37. [Reporting paper]() Recorded evaluation configuration: {"input resolution":"392x392"}. This record does not assert independent reproduction. ### ResNet-152 Top-3 Error Rate: 16.623. Result ID: 698d5ef58b517eb43320fe36. [Reporting paper]() Recorded evaluation configuration: {"input resolution":"320x320"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.