# Object Classification on ImageNet (val) (Top-1 & Top-5 Acc) Source: [Object Classification on ImageNet (val) (Top-1 & Top-5 Acc)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:02.080Z Evaluation of Object Classification performance on the validation split of the ImageNet dataset, reporting standard Top-1 and Top-5 Accuracy metrics. 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 | Object Classification | | Dataset (including any stated split) | ImageNet (val) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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. - [Top-5 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | NeuTRENO DeiT + FeatScale | 73.23 | Not recorded | 68fa715f1e209131cea50ee9 | | NeuTRENO-DeiT | 73.01 | Not recorded | 68fa715f1e209131cea50ee9 | | NeuTRENO Adaptation | 72.63 | Not recorded | 68fa715f1e209131cea50ee9 | | DeiT + FeatScale | 72.346 | Not recorded | 68fa715f1e209131cea50ee9 | | Softmax DeiT | 72.17 | Not recorded | 68fa715f1e209131cea50ee9 | ### NeuTRENO DeiT + FeatScale Top-1 Accuracy: 73.23. Result ID: 6991ca373a6c3148490a9b66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeiT","Mechanism":"FeatScale","Attention":"NeuTRENO"}. This record does not assert independent reproduction. ### NeuTRENO-DeiT Top-1 Accuracy: 73.01. Result ID: 6991ca373a6c3148490a9b63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeiT","Attention":"NeuTRENO"}. This record does not assert independent reproduction. ### NeuTRENO Adaptation Top-1 Accuracy: 72.63. Result ID: 6991ca373a6c3148490a9b64. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeiT","Mode":"Adaptation"}. This record does not assert independent reproduction. ### DeiT + FeatScale Top-1 Accuracy: 72.346. Result ID: 6991ca373a6c3148490a9b65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeiT","Mechanism":"FeatScale"}. This record does not assert independent reproduction. ### Softmax DeiT Top-1 Accuracy: 72.17. Result ID: 6991ca373a6c3148490a9b62. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeiT","Attention":"Softmax"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.