# Image Classification on ImageNet (Accuracy and Input Resolution) Source: [Image Classification on ImageNet (Accuracy and Input Resolution)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:58.338Z Evaluation of Image Classification performance on the standard ImageNet dataset, reporting Top-1 Accuracy alongside the associated input resolution metric (e.g., pixel count). 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 | | Metric | Top-1 Accuracy | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Input Resolution (Pixels)](): Higher is better; unit: SIZE. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | STAM (DeiT-Base) | 80.78 | Not recorded | 68fa6c341e209131cea32ce9 | | STAM (DeiT-Small (default)) | 78.25 | Not recorded | 68fa6c341e209131cea32ce9 | | STAM (DeiT-Small (default)) | 76.35 | Not recorded | 68fa6c341e209131cea32ce9 | | STAM (DeiT-Base) | 76.13 | Not recorded | 68fa6c341e209131cea32ce9 | | PatchDrop | 76 | Not recorded | 68fa6c341e209131cea32ce9 | | GFNet | 75.93 | Not recorded | 68fa6c341e209131cea32ce9 | | TNet | 74.62 | Not recorded | 68fa6c341e209131cea32ce9 | | STN | 71.4 | Not recorded | 68fa6c341e209131cea32ce9 | | Saccader | 70.31 | Not recorded | 68fa6c341e209131cea32ce9 | | DRAM | 67.5 | Not recorded | 68fa6c341e209131cea32ce9 | ### STAM (DeiT-Base) Top-1 Accuracy: 80.78. Result ID: 698ef6653a6c314849f41116. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attention used complete image":"No","Classification used complete image":"No","Evaluation Criterion":"Equivalent sensing to PatchDrop","Time steps (t)":26}. This record does not assert independent reproduction. ### STAM (DeiT-Small (default)) Top-1 Accuracy: 78.25. Result ID: 698ef6653a6c314849f41115. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attention used complete image":"No","Classification used complete image":"No","Evaluation Criterion":"Equivalent sensing to PatchDrop","Time steps (t)":26}. This record does not assert independent reproduction. ### STAM (DeiT-Small (default)) Top-1 Accuracy: 76.35. Result ID: 698ef6653a6c314849f41113. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attention used complete image":"No","Classification used complete image":"No","Evaluation Criterion":"Equivalent accuracy to PatchDrop","Time steps (t)":19}. This record does not assert independent reproduction. ### STAM (DeiT-Base) Top-1 Accuracy: 76.13. Result ID: 698ef6653a6c314849f41114. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attention used complete image":"No","Classification used complete image":"No","Evaluation Criterion":"Equivalent accuracy to PatchDrop","Time steps (t)":13}. This record does not assert independent reproduction. ### PatchDrop Top-1 Accuracy: 76. Result ID: 698ef6653a6c314849f41112. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attention used complete image":"Yes","Classification used complete image":"Yes"}. This record does not assert independent reproduction. ### GFNet Top-1 Accuracy: 75.93. Result ID: 698ef6653a6c314849f4110e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attention used complete image":"Yes","Classification used complete image":"Yes"}. This record does not assert independent reproduction. ### TNet Top-1 Accuracy: 74.62. Result ID: 698ef6653a6c314849f41110. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attention used complete image":"Yes","Classification used complete image":"Yes"}. This record does not assert independent reproduction. ### STN Top-1 Accuracy: 71.4. Result ID: 698ef6653a6c314849f41111. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attention used complete image":"Yes","Classification used complete image":"Yes","Development":"developed in \[46\] based on \[32\]"}. This record does not assert independent reproduction. ### Saccader Top-1 Accuracy: 70.31. Result ID: 698ef6653a6c314849f4110f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attention used complete image":"Yes","Classification used complete image":"No","Source":"results from \[27\]"}. This record does not assert independent reproduction. ### DRAM Top-1 Accuracy: 67.5. Result ID: 698ef6653a6c314849f4110d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attention used complete image":"Yes","Classification used complete image":"No","Source":"results from \[27\]"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.