# Image Classification on ImageNet-LT Backward Shifted (test) Source: [Image Classification on ImageNet-LT Backward Shifted (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:49.657Z Evaluation of Image Classification performance on the test split of the ImageNet-LT Backward Shifted dataset, reporting Top-1 Accuracy metrics based on specific Inverse Ranking (IR) thresholds (IR=2, 5, 10, 25, 50). 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-LT Backward Shifted (test) | | Metric | Top-1 Acc | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 37 of 37 | | 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-1 Acc](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (IR=2)](): Higher is better; unit: SCALAR. - [Top-1 Accuracy (IR=5)](): Higher is better; unit: SCALAR. - [Top-1 Accuracy (IR=10)](): Higher is better; unit: SCALAR. - [Top-1 Accuracy (IR=25)](): Higher is better; unit: SCALAR. - [Top-1 Accuracy (IR=50)](): Higher is better; unit: SCALAR. - [Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Acc | Result date | Report paper | | --- | --- | --- | --- | | DiVE | 49.42 | Not recorded | 68fa6acb1e209131cea2a4a4 | | DiVE | 49.29 | Not recorded | 68fa6acb1e209131cea2a4a4 | | DiVE | 49.15 | Not recorded | 68fa6acb1e209131cea2a4a4 | | BSCE | 47.09 | Not recorded | 68fa6acb1e209131cea2a4a4 | | BSCE | 46.81 | Not recorded | 68fa6acb1e209131cea2a4a4 | | BSCE | 46.74 | Not recorded | 68fa6acb1e209131cea2a4a4 | | DiVE | 45.69 | Not recorded | 68fa6acb1e209131cea2a4a4 | | CE | 45.57 | Not recorded | 68fa6acb1e209131cea2a4a4 | | CE | 45.41 | Not recorded | 68fa6acb1e209131cea2a4a4 | | CE | 45.03 | Not recorded | 68fa6acb1e209131cea2a4a4 | | BSCE | 43.18 | Not recorded | 68fa6acb1e209131cea2a4a4 | | DiVE | 43.17 | Not recorded | 68fa6acb1e209131cea2a4a4 | | DiVE | 41.55 | Not recorded | 68fa6acb1e209131cea2a4a4 | | BSCE | 40.89 | Not recorded | 68fa6acb1e209131cea2a4a4 | | BSCE | 39.31 | Not recorded | 68fa6acb1e209131cea2a4a4 | | CE | 30.7 | Not recorded | 68fa6acb1e209131cea2a4a4 | | CE | 26.54 | Not recorded | 68fa6acb1e209131cea2a4a4 | | CE | 23.95 | Not recorded | 68fa6acb1e209131cea2a4a4 | ### DiVE Top-1 Acc: 49.42. Result ID: 699ad1d75698665ec460df9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### DiVE Top-1 Acc: 49.29. Result ID: 699ad1d75698665ec460dfa8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### DiVE Top-1 Acc: 49.15. Result ID: 699ad1d75698665ec460dfa2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### BSCE Top-1 Acc: 47.09. Result ID: 699ad1d75698665ec460dfa7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### BSCE Top-1 Acc: 46.81. Result ID: 699ad1d75698665ec460df9b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### BSCE Top-1 Acc: 46.74. Result ID: 699ad1d75698665ec460dfa1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### DiVE Top-1 Acc: 45.69. Result ID: 699ad1d75698665ec460df99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### CE Top-1 Acc: 45.57. Result ID: 699ad1d75698665ec460df9a. [Reporting paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### CE Top-1 Acc: 45.41. Result ID: 699ad1d75698665ec460dfa6. [Reporting paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### CE Top-1 Acc: 45.03. Result ID: 699ad1d75698665ec460dfa0. [Reporting paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction. ### BSCE Top-1 Acc: 43.18. Result ID: 699ad1d75698665ec460df98. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### DiVE Top-1 Acc: 43.17. Result ID: 699ad1d75698665ec460df9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### DiVE Top-1 Acc: 41.55. Result ID: 699ad1d75698665ec460dfa5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### BSCE Top-1 Acc: 40.89. Result ID: 699ad1d75698665ec460df9e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### BSCE Top-1 Acc: 39.31. Result ID: 699ad1d75698665ec460dfa4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### CE Top-1 Acc: 30.7. Result ID: 699ad1d75698665ec460df97. [Reporting paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### CE Top-1 Acc: 26.54. Result ID: 699ad1d75698665ec460df9d. [Reporting paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. ### CE Top-1 Acc: 23.95. Result ID: 699ad1d75698665ec460dfa3. [Reporting paper]() Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.