# Image Classification on ImageNet (val) (Top-1 Accuracy and FLOPs) Source: [Image Classification on ImageNet (val) (Top-1 Accuracy and FLOPs)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:34.097Z Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting Top-1 Accuracy alongside training and testing computational complexity (FLOPs). 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 (val) | | Metric | Training FLOPs | | Unit | OTHER | | Direction | Lower is better | | Results loaded | 15 of 15 | | 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 - [Training FLOPs](): Lower is better; unit: OTHER. - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Rs](): Higher is better; unit: SCALAR. - [Test FLOPs](): Lower is better; unit: OTHER. ## Recorded results | Method | Training FLOPs | Result date | Report paper | | --- | --- | --- | --- | | SET | 0.1 | Not recorded | 68fa6a2b1e209131cea268f5 | | SET | 0.23 | Not recorded | 68fa6a2b1e209131cea268f5 | | Static | 0.24 | Not recorded | 68fa6a2b1e209131cea268f5 | | RigL | 0.25 | Not recorded | 68fa6a2b1e209131cea268f5 | | RigL-ITOP | 0.25 | Not recorded | 68fa6a2b1e209131cea268f5 | | Static | 0.42 | Not recorded | 68fa6a2b1e209131cea268f5 | | RigL | 0.42 | Not recorded | 68fa6a2b1e209131cea268f5 | | RigL-ITOP | 0.42 | Not recorded | 68fa6a2b1e209131cea268f5 | | SNFS | 0.5 | Not recorded | 68fa6a2b1e209131cea268f5 | | RigL-ITOP\_2x | 0.5 | Not recorded | 68fa6a2b1e209131cea268f5 | | GMP | 0.51 | Not recorded | 68fa6a2b1e209131cea268f5 | | GMP | 0.56 | Not recorded | 68fa6a2b1e209131cea268f5 | | SNFS | 0.61 | Not recorded | 68fa6a2b1e209131cea268f5 | | RigL-ITOP\_2x | 0.84 | Not recorded | 68fa6a2b1e209131cea268f5 | | Dense | 13200000000000000000 | Not recorded | 68fa6a2b1e209131cea268f5 | ### SET Training FLOPs: 0.1. Result ID: 698e1d1fffc3901de09ae7d6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.9"}. This record does not assert independent reproduction. ### SET Training FLOPs: 0.23. Result ID: 698e1d1fffc3901de09ae7dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.8"}. This record does not assert independent reproduction. ### Static Training FLOPs: 0.24. Result ID: 698e1d1fffc3901de09ae7d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.9"}. This record does not assert independent reproduction. ### RigL Training FLOPs: 0.25. Result ID: 698e1d1fffc3901de09ae7d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.9"}. This record does not assert independent reproduction. ### RigL-ITOP Training FLOPs: 0.25. Result ID: 698e1d1fffc3901de09ae7da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.9"}. This record does not assert independent reproduction. ### Static Training FLOPs: 0.42. Result ID: 698e1d1fffc3901de09ae7dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.8"}. This record does not assert independent reproduction. ### RigL Training FLOPs: 0.42. Result ID: 698e1d1fffc3901de09ae7df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.8"}. This record does not assert independent reproduction. ### RigL-ITOP Training FLOPs: 0.42. Result ID: 698e1d1fffc3901de09ae7e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.8"}. This record does not assert independent reproduction. ### SNFS Training FLOPs: 0.5. Result ID: 698e1d1fffc3901de09ae7d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.9"}. This record does not assert independent reproduction. ### RigL-ITOP\_2x Training FLOPs: 0.5. Result ID: 698e1d1fffc3901de09ae7db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.9","Training Time":"Extended 2x"}. This record does not assert independent reproduction. ### GMP Training FLOPs: 0.51. Result ID: 698e1d1fffc3901de09ae7e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.8"}. This record does not assert independent reproduction. ### GMP Training FLOPs: 0.56. Result ID: 698e1d1fffc3901de09ae7d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.9"}. This record does not assert independent reproduction. ### SNFS Training FLOPs: 0.61. Result ID: 698e1d1fffc3901de09ae7de. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.8"}. This record does not assert independent reproduction. ### RigL-ITOP\_2x Training FLOPs: 0.84. Result ID: 698e1d1fffc3901de09ae7e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.8","Training Time":"Extended 2x"}. This record does not assert independent reproduction. ### Dense Training FLOPs: 13200000000000000000. Result ID: 698e1d1fffc3901de09ae7d4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","sparsity":"0.0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.