# Image Classification on ImageNet-100-LT (test) Source: [Image Classification on ImageNet-100-LT (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:19.354Z Evaluation of Image Classification performance on the test split of the 100-class Long-Tailed ImageNet dataset, typically measured across different class frequency groups (Many, Medium, Few). 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-100-LT (test) | | Metric | Accuracy (Many) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 (Many)](): Higher is better; unit: PERCENT. - [Accuracy (Medium)](): Higher is better; unit: PERCENT. - [Accuracy (Few)](): Higher is better; unit: PERCENT. - [Std Dev Accuracy](): Lower is better; unit: SCALAR. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Many) | Result date | Report paper | | --- | --- | --- | --- | | MAK | 78 | Not recorded | 68fa6b601e209131cea2dd72 | | MAK | 76.1 | Not recorded | 68fa6b601e209131cea2dd72 | | random | 75.7 | Not recorded | 68fa6b601e209131cea2dd72 | | MAK | 74.7 | Not recorded | 68fa6b601e209131cea2dd72 | | random | 74.6 | Not recorded | 68fa6b601e209131cea2dd72 | | random | 73.8 | Not recorded | 68fa6b601e209131cea2dd72 | | K-center | 73.6 | Not recorded | 68fa6b601e209131cea2dd72 | | K-center | 73 | Not recorded | 68fa6b601e209131cea2dd72 | | None | 71.2 | Not recorded | 68fa6b601e209131cea2dd72 | | MAK | 59 | Not recorded | 68fa6b601e209131cea2dd72 | | MAK | 57.4 | Not recorded | 68fa6b601e209131cea2dd72 | | random | 57.4 | Not recorded | 68fa6b601e209131cea2dd72 | | MAK | 56.8 | Not recorded | 68fa6b601e209131cea2dd72 | | random | 56.6 | Not recorded | 68fa6b601e209131cea2dd72 | | random | 55.5 | Not recorded | 68fa6b601e209131cea2dd72 | | K-center | 55 | Not recorded | 68fa6b601e209131cea2dd72 | | K-center | 54.2 | Not recorded | 68fa6b601e209131cea2dd72 | | None | 52.6 | Not recorded | 68fa6b601e209131cea2dd72 | ### MAK Accuracy (Many): 78. Result ID: 698e82c6ffc3901de09e396b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"20K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### MAK Accuracy (Many): 76.1. Result ID: 698e82c6ffc3901de09e3967. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"10K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### random Accuracy (Many): 75.7. Result ID: 698e82c6ffc3901de09e3969. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"20K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### MAK Accuracy (Many): 74.7. Result ID: 698e82c6ffc3901de09e3971. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling dataset":"IPM","Budget":"10K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### random Accuracy (Many): 74.6. Result ID: 698e82c6ffc3901de09e3963. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"10K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### random Accuracy (Many): 73.8. Result ID: 698e82c6ffc3901de09e396d. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"IPM","Budget":"10K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### K-center Accuracy (Many): 73.6. Result ID: 698e82c6ffc3901de09e3965. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"10K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### K-center Accuracy (Many): 73. Result ID: 698e82c6ffc3901de09e396f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling dataset":"IPM","Budget":"10K","Protocol":"linear separability"}. This record does not assert independent reproduction. ### None Accuracy (Many): 71.2. Result ID: 698e82c6ffc3901de09e3961. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"None","Protocol":"linear separability"}. This record does not assert independent reproduction. ### MAK Accuracy (Many): 59. Result ID: 698e82c6ffc3901de09e396c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"20K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### MAK Accuracy (Many): 57.4. Result ID: 698e82c6ffc3901de09e3968. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"10K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### random Accuracy (Many): 57.4. Result ID: 698e82c6ffc3901de09e396a. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"20K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### MAK Accuracy (Many): 56.8. Result ID: 698e82c6ffc3901de09e3972. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling dataset":"IPM","Budget":"10K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### random Accuracy (Many): 56.6. Result ID: 698e82c6ffc3901de09e3964. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"10K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### random Accuracy (Many): 55.5. Result ID: 698e82c6ffc3901de09e396e. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"IPM","Budget":"10K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### K-center Accuracy (Many): 55. Result ID: 698e82c6ffc3901de09e3966. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling dataset":"IN900","Budget":"10K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### K-center Accuracy (Many): 54.2. Result ID: 698e82c6ffc3901de09e3970. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling dataset":"IPM","Budget":"10K","Protocol":"few-shot"}. This record does not assert independent reproduction. ### None Accuracy (Many): 52.6. Result ID: 698e82c6ffc3901de09e3962. [Reporting paper]() Recorded evaluation configuration: {"Sampling dataset":"None","Protocol":"few-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.