# Low-shot Classification on ImageNet (unseen) Source: [Low-shot Classification on ImageNet (unseen)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:23.018Z Evaluation of Low-shot Classification performance on the specified unseen subset of the ImageNet dataset, measured using Top-5 Accuracy. 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 | Low-shot Classification | | Dataset (including any stated split) | ImageNet (unseen) | | Metric | Top-5 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-5 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FEAT | 83.6 | Not recorded | 68fa6a211e209131cea262a3 | | PMN | 82.6 | Not recorded | 68fa6a211e209131cea262a3 | | FEAT | 81.2 | Not recorded | 68fa6a211e209131cea262a3 | | PMN | 80.1 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 80 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 78.1 | Not recorded | 68fa6a211e209131cea262a3 | | FEAT | 76 | Not recorded | 68fa6a211e209131cea262a3 | | PMN | 75.9 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 74.4 | Not recorded | 68fa6a211e209131cea262a3 | | FEAT | 65.4 | Not recorded | 68fa6a211e209131cea262a3 | | PMN | 65.2 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 64 | Not recorded | 68fa6a211e209131cea262a3 | | FEAT | 53.8 | Not recorded | 68fa6a211e209131cea262a3 | | PMN | 53.3 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 49.6 | Not recorded | 68fa6a211e209131cea262a3 | ### FEAT Top-5 Accuracy: 83.6. Result ID: 698e12b0ffc3901de09a93c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"20-Shot"}. This record does not assert independent reproduction. ### PMN Top-5 Accuracy: 82.6. Result ID: 698e12b0ffc3901de09a93c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"20-Shot"}. This record does not assert independent reproduction. ### FEAT Top-5 Accuracy: 81.2. Result ID: 698e12b0ffc3901de09a93c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"10-Shot"}. This record does not assert independent reproduction. ### PMN Top-5 Accuracy: 80.1. Result ID: 698e12b0ffc3901de09a93bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"10-Shot"}. This record does not assert independent reproduction. ### ProtoNet Top-5 Accuracy: 80. Result ID: 698e12b0ffc3901de09a93bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"20-Shot"}. This record does not assert independent reproduction. ### ProtoNet Top-5 Accuracy: 78.1. Result ID: 698e12b0ffc3901de09a93ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"10-Shot"}. This record does not assert independent reproduction. ### FEAT Top-5 Accuracy: 76. Result ID: 698e12b0ffc3901de09a93c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"5-Shot"}. This record does not assert independent reproduction. ### PMN Top-5 Accuracy: 75.9. Result ID: 698e12b0ffc3901de09a93be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"5-Shot"}. This record does not assert independent reproduction. ### ProtoNet Top-5 Accuracy: 74.4. Result ID: 698e12b0ffc3901de09a93b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"5-Shot"}. This record does not assert independent reproduction. ### FEAT Top-5 Accuracy: 65.4. Result ID: 698e12b0ffc3901de09a93c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"2-Shot"}. This record does not assert independent reproduction. ### PMN Top-5 Accuracy: 65.2. Result ID: 698e12b0ffc3901de09a93bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"2-Shot"}. This record does not assert independent reproduction. ### ProtoNet Top-5 Accuracy: 64. Result ID: 698e12b0ffc3901de09a93b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"2-Shot"}. This record does not assert independent reproduction. ### FEAT Top-5 Accuracy: 53.8. Result ID: 698e12b0ffc3901de09a93c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"1-Shot"}. This record does not assert independent reproduction. ### PMN Top-5 Accuracy: 53.3. Result ID: 698e12b0ffc3901de09a93bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"1-Shot"}. This record does not assert independent reproduction. ### ProtoNet Top-5 Accuracy: 49.6. Result ID: 698e12b0ffc3901de09a93b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Shots":"1-Shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.