# Selective Classification on ImageNet-C Original (test) Source: [Selective Classification on ImageNet-C Original (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:52:39.023Z Evaluation of Selective Classification performance on the test split of the ImageNet-C Original dataset, measured using metrics A and N. 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 | Selective Classification | | Dataset (including any stated split) | ImageNet-C Original (test) | | Metric | Metric A | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Metric A](): Higher is better; unit: PERCENT. - [Metric N](): Lower is better; unit: SCALAR. ## Recorded results | Method | Metric A | Result date | Report paper | | --- | --- | --- | --- | | MDS | 58.3 | Not recorded | 68fa78a61e209131cea79954 | | KNN | 46.2 | Not recorded | 68fa78a61e209131cea79954 | | SIRC | 40.5 | Not recorded | 68fa78a61e209131cea79954 | | Δ-KNN | 33.9 | Not recorded | 68fa78a61e209131cea79954 | | Energy | 27.8 | Not recorded | 68fa78a61e209131cea79954 | | Δ-MDS | 27.3 | Not recorded | 68fa78a61e209131cea79954 | | MaxLogit | 24.5 | Not recorded | 68fa78a61e209131cea79954 | | MSP | 22.6 | Not recorded | 68fa78a61e209131cea79954 | | RLog | 22.4 | Not recorded | 68fa78a61e209131cea79954 | | Δ-KNN-RLog | 22.2 | Not recorded | 68fa78a61e209131cea79954 | | Δ-MDS-RLog | 21.9 | Not recorded | 68fa78a61e209131cea79954 | ### MDS Metric A: 58.3. Result ID: 699a67995698665ec4efe4d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### KNN Metric A: 46.2. Result ID: 699a67995698665ec4efe4d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### SIRC Metric A: 40.5. Result ID: 699a67995698665ec4efe4d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-KNN Metric A: 33.9. Result ID: 699a67995698665ec4efe4d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Energy Metric A: 27.8. Result ID: 699a67995698665ec4efe4d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-MDS Metric A: 27.3. Result ID: 699a67995698665ec4efe4d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### MaxLogit Metric A: 24.5. Result ID: 699a67995698665ec4efe4d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### MSP Metric A: 22.6. Result ID: 699a67995698665ec4efe4d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### RLog Metric A: 22.4. Result ID: 699a67995698665ec4efe4d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-KNN-RLog Metric A: 22.2. Result ID: 699a67995698665ec4efe4da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-MDS-RLog Metric A: 21.9. Result ID: 699a67995698665ec4efe4d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.