# Image Classification on Office-Home OOD (test) Source: [Image Classification on Office-Home OOD (test)]() Collection index: [llms.txt]() Data updated: 2026-06-01T09:14:48.893Z Evaluation of Image Classification performance on the Out-of-Distribution (OOD) test split of the Office-Home dataset, focusing on generalization metrics. 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) | Office-Home OOD (test) | | Metric | Accuracy (Acc.) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 (Acc.)](): Higher is better; unit: PERCENT. - [Expected Calibration Error (ECE)](): Lower is better; unit: SCALAR. - [Temperature Scaling ECE (TS-ECE)](): Lower is better; unit: SCALAR. - [CECE](): Lower is better; unit: SCALAR. - [Average Calibration Error (ACE)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy (Acc.) | Result date | Report paper | | --- | --- | --- | --- | | CE | 34.2 | Not recorded | 68fa7af41e209131cea85f3e | | DFL | 34.17 | Not recorded | 68fa7af41e209131cea85f3e | | FGR | 34.03 | Not recorded | 68fa7af41e209131cea85f3e | | FLSD-53 | 33.31 | Not recorded | 68fa7af41e209131cea85f3e | | BSCE-GRA | 32.55 | Not recorded | 68fa7af41e209131cea85f3e | ### CE Accuracy (Acc.): 34.2. Result ID: 6a1d4d17fbc373592c16bd76. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"leave-one-domain-out"}. This record does not assert independent reproduction. ### DFL Accuracy (Acc.): 34.17. Result ID: 6a1d4d17fbc373592c16bd78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"leave-one-domain-out"}. This record does not assert independent reproduction. ### FGR Accuracy (Acc.): 34.03. Result ID: 6a1d4d17fbc373592c16bd7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"leave-one-domain-out"}. This record does not assert independent reproduction. ### FLSD-53 Accuracy (Acc.): 33.31. Result ID: 6a1d4d17fbc373592c16bd77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"leave-one-domain-out"}. This record does not assert independent reproduction. ### BSCE-GRA Accuracy (Acc.): 32.55. Result ID: 6a1d4d17fbc373592c16bd79. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"leave-one-domain-out"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.