# Long-tailed Image Classification on CIFAR-100 (IF=100) (test) Source: [Long-tailed Image Classification on CIFAR-100 (IF=100) (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:19.335Z Evaluation of Image Classification performance on the test split of CIFAR-100 configured with a 100x long-tail imbalance factor, measured using metrics categorized by class frequency (Many, Med, Few) and overall accuracy (Acc). 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) | Long-tailed CIFAR-100 (imbalance factor 100) (test) | | Metric | Accuracy (Many Classes) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 Classes)](): Higher is better; unit: PERCENT. - [Accuracy (Medium Classes)](): Higher is better; unit: PERCENT. - [Accuracy (Few Classes)](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Many Classes) | Result date | Report paper | | --- | --- | --- | --- | | CE | 65.5 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | DRO-LT | 65 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | DRO-LT | 64.7 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | SSL | 64.1 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | DRO-LT | 64.1 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | DRO-LT | 61.9 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | OLTR | 61.8 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | T-norm | 61.4 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | LDAM Loss | 61 | Not recorded | 68fa6b2d1e209131cea2c9d1 | | smDragon | 60.5 | Not recorded | 68fa6b2d1e209131cea2c9d1 | ### CE Accuracy (Many Classes): 65.5. Result ID: 698e695fffc3901de09d60d7. [Reporting paper]() Recorded evaluation configuration: {"reproduced":"true"}. This record does not assert independent reproduction. ### DRO-LT Accuracy (Many Classes): 65. Result ID: 698e695fffc3901de09d60df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"e\[n\]"}. This record does not assert independent reproduction. ### DRO-LT Accuracy (Many Classes): 64.7. Result ID: 698e695fffc3901de09d60e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"Learnable"}. This record does not assert independent reproduction. ### SSL Accuracy (Many Classes): 64.1. Result ID: 698e695fffc3901de09d60dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reproduced":"true"}. This record does not assert independent reproduction. ### DRO-LT Accuracy (Many Classes): 64.1. Result ID: 698e695fffc3901de09d60de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"Shared"}. This record does not assert independent reproduction. ### DRO-LT Accuracy (Many Classes): 61.9. Result ID: 698e695fffc3901de09d60dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0 (ERM)"}. This record does not assert independent reproduction. ### OLTR Accuracy (Many Classes): 61.8. Result ID: 698e695fffc3901de09d60d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### T-norm Accuracy (Many Classes): 61.4. Result ID: 698e695fffc3901de09d60da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LDAM Loss Accuracy (Many Classes): 61. Result ID: 698e695fffc3901de09d60d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### smDragon Accuracy (Many Classes): 60.5. Result ID: 698e695fffc3901de09d60db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.