# Image Classification on ImageNet OOD DEEPNETS-1M (test) Source: [Image Classification on ImageNet OOD DEEPNETS-1M (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:23.607Z Evaluation of Image Classification performance on the test split of the ImageNet OOD DEEPNETS-1M dataset, reporting accuracy across specific model configurations (WIDE, DEEP, DENSE, BN-FREE, RESNET, VIT). 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) | ImageNet OOD DEEPNETS-1M (test) | | Metric | Top-5 Accuracy (RESNET) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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-5 Accuracy (RESNET)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (WIDE)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (DEEP)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (DENSE)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (BN-FREE)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (VIT)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-5 Accuracy (RESNET) | Result date | Report paper | | --- | --- | --- | --- | | SGD (100 epochs) | 92.9 | Not recorded | 68fa6b1b1e209131cea2c408 | | SGD (10000 steps) | 49 | Not recorded | 68fa6b1b1e209131cea2c408 | | SGD (5000 steps) | 34.8 | Not recorded | 68fa6b1b1e209131cea2c408 | | GHN-1 | 6.9 | Not recorded | 68fa6b1b1e209131cea2c408 | | GHN-2 | 5.3 | Not recorded | 68fa6b1b1e209131cea2c408 | | SGD (1 step) | 0.5 | Not recorded | 68fa6b1b1e209131cea2c408 | ### SGD (100 epochs) Top-5 Accuracy (RESNET): 92.9. Result ID: 698e5dbeffc3901de09cfb58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of updates":"1000k","GPU compute time (sec)":"6e5\*","CPU compute time (sec)":"6e7\*"}. This record does not assert independent reproduction. ### SGD (10000 steps) Top-5 Accuracy (RESNET): 49. Result ID: 698e5dbeffc3901de09cfb57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of updates":"10k","GPU compute time (sec)":"4e3","CPU compute time (sec)":"6e4"}. This record does not assert independent reproduction. ### SGD (5000 steps) Top-5 Accuracy (RESNET): 34.8. Result ID: 698e5dbeffc3901de09cfb56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of updates":"5k","GPU compute time (sec)":"2e3","CPU compute time (sec)":"3e4"}. This record does not assert independent reproduction. ### GHN-1 Top-5 Accuracy (RESNET): 6.9. Result ID: 698e5dbeffc3901de09cfb53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of updates":"1","GPU compute time (sec)":"0.3","CPU compute time (sec)":"0.5"}. This record does not assert independent reproduction. ### GHN-2 Top-5 Accuracy (RESNET): 5.3. Result ID: 698e5dbeffc3901de09cfb54. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of updates":"1","GPU compute time (sec)":"0.3","CPU compute time (sec)":"0.7"}. This record does not assert independent reproduction. ### SGD (1 step) Top-5 Accuracy (RESNET): 0.5. Result ID: 698e5dbeffc3901de09cfb55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of updates":"1","GPU compute time (sec)":"0.4","CPU compute time (sec)":"6.0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.