# Image Classification on ImageNet-LT ILSVRC2012 (test) Source: [Image Classification on ImageNet-LT ILSVRC2012 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:15.827Z Evaluation of Image Classification performance on the test split of the ImageNet-LT ILSVRC2012 dataset, measured using Top-1 Accuracy stratified by shot count (Few-shot, Medium-shot, Many-shot). 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 ILSVRC2012 (test) | | Metric | Top-1 Accuracy (Overall) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 Accuracy (Overall)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Many-shot)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Medium-shot)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Few-shot)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (Overall) | Result date | Report paper | | --- | --- | --- | --- | | OLTR | 35.6 | Not recorded | 68fa68251e209131cea1a42f | | Feature Space Augmentation | 35.3 | Not recorded | 68fa68251e209131cea1a42f | | Feature Space Augmentation | 35.2 | Not recorded | 68fa68251e209131cea1a42f | | Lifted Loss | 30.8 | Not recorded | 68fa68251e209131cea1a42f | | Range Loss | 30.7 | Not recorded | 68fa68251e209131cea1a42f | | FL | 30.5 | Not recorded | 68fa68251e209131cea1a42f | | FSLWF | 28.4 | Not recorded | 68fa68251e209131cea1a42f | | Plain Model | 20.9 | Not recorded | 68fa68251e209131cea1a42f | ### OLTR Top-1 Accuracy (Overall): 35.6. Result ID: 698d5c558b517eb43320ead6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch"}. This record does not assert independent reproduction. ### Feature Space Augmentation Top-1 Accuracy (Overall): 35.3. Result ID: 698d5c558b517eb43320ead8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch","Loss":"Focal Loss"}. This record does not assert independent reproduction. ### Feature Space Augmentation Top-1 Accuracy (Overall): 35.2. Result ID: 698d5c558b517eb43320ead7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch","Loss":"Cross-Entropy"}. This record does not assert independent reproduction. ### Lifted Loss Top-1 Accuracy (Overall): 30.8. Result ID: 698d5c558b517eb43320ead2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch"}. This record does not assert independent reproduction. ### Range Loss Top-1 Accuracy (Overall): 30.7. Result ID: 698d5c558b517eb43320ead4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch"}. This record does not assert independent reproduction. ### FL Top-1 Accuracy (Overall): 30.5. Result ID: 698d5c558b517eb43320ead3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch"}. This record does not assert independent reproduction. ### FSLWF Top-1 Accuracy (Overall): 28.4. Result ID: 698d5c558b517eb43320ead5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch"}. This record does not assert independent reproduction. ### Plain Model Top-1 Accuracy (Overall): 20.9. Result ID: 698d5c558b517eb43320ead1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Setting":"From scratch"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.