# Image Classification on CIFAR-100 (Acc. (%) and Acc./#ReLU) Source: [Image Classification on CIFAR-100 (Acc. (%) and Acc./#ReLU)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:33:57.546Z Evaluation of Image Classification performance on CIFAR-100, reporting standard accuracy alongside the accuracy normalized by the count of ReLU activations. 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) | CIFAR-100 | | Metric | Accuracy (%) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [Accuracy (%)](): Higher is better; unit: PERCENT. - [Accuracy / #ReLU](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy (%) | Result date | Report paper | | --- | --- | --- | --- | | Baseline | 78.23 | Not recorded | 6948d060423ea42265729dc1 | | DeepShare | 77.98 | Not recorded | 6948d060423ea42265729dc1 | | DeepShare | 77.29 | Not recorded | 6948d060423ea42265729dc1 | | HybReNet | 77.14 | Not recorded | 6948d060423ea42265729dc1 | | DeepShare | 76.13 | Not recorded | 6948d060423ea42265729dc1 | | Seesaw | 75.89 | Not recorded | 6948d060423ea42265729dc1 | | Spatial sharing | 75.51 | Not recorded | 6948d060423ea42265729dc1 | | AutoRep | 75.48 | Not recorded | 6948d060423ea42265729dc1 | | SENet | 75.28 | Not recorded | 6948d060423ea42265729dc1 | | AutoRep | 74.92 | Not recorded | 6948d060423ea42265729dc1 | | AutoRep | 73.79 | Not recorded | 6948d060423ea42265729dc1 | | SNL | 73.75 | Not recorded | 6948d060423ea42265729dc1 | | Spatial sharing | 73.03 | Not recorded | 6948d060423ea42265729dc1 | | HybReNet | 72.65 | Not recorded | 6948d060423ea42265729dc1 | | Seesaw | 72.32 | Not recorded | 6948d060423ea42265729dc1 | | SENet | 70.59 | Not recorded | 6948d060423ea42265729dc1 | | Sphynx | 69.57 | Not recorded | 6948d060423ea42265729dc1 | | CryptoNAS | 68.5 | Not recorded | 6948d060423ea42265729dc1 | | SNL | 66.53 | Not recorded | 6948d060423ea42265729dc1 | ### Baseline Accuracy (%): 78.23. Result ID: 69994f845698665ec4b9eef5. [Reporting paper]() Recorded evaluation configuration: {"#ReLUs (K)":"491.52","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DeepShare Accuracy (%): 77.98. Result ID: 69994f845698665ec4b9eefe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"49.9","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DeepShare Accuracy (%): 77.29. Result ID: 69994f845698665ec4b9ef05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"12.9","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### HybReNet Accuracy (%): 77.14. Result ID: 69994f845698665ec4b9eefd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"52","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DeepShare Accuracy (%): 76.13. Result ID: 69994f845698665ec4b9ef07. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"6","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Seesaw Accuracy (%): 75.89. Result ID: 69994f845698665ec4b9eef7. [Reporting paper]() Recorded evaluation configuration: {"#ReLUs (K)":"78","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Spatial sharing Accuracy (%): 75.51. Result ID: 69994f845698665ec4b9eefa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"50","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### AutoRep Accuracy (%): 75.48. Result ID: 69994f845698665ec4b9eefc. [Reporting paper]() Recorded evaluation configuration: {"#ReLUs (K)":"50","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SENet Accuracy (%): 75.28. Result ID: 69994f845698665ec4b9eefb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"49.6","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### AutoRep Accuracy (%): 74.92. Result ID: 69994f845698665ec4b9ef04. [Reporting paper]() Recorded evaluation configuration: {"#ReLUs (K)":"12.9","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### AutoRep Accuracy (%): 73.79. Result ID: 69994f845698665ec4b9ef06. [Reporting paper]() Recorded evaluation configuration: {"#ReLUs (K)":"6","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SNL Accuracy (%): 73.75. Result ID: 69994f845698665ec4b9eef9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"49.9","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Spatial sharing Accuracy (%): 73.03. Result ID: 69994f845698665ec4b9ef00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"30","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### HybReNet Accuracy (%): 72.65. Result ID: 69994f845698665ec4b9ef01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"26","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Seesaw Accuracy (%): 72.32. Result ID: 69994f845698665ec4b9eeff. [Reporting paper]() Recorded evaluation configuration: {"#ReLUs (K)":"36","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SENet Accuracy (%): 70.59. Result ID: 69994f845698665ec4b9ef02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"24.6","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Sphynx Accuracy (%): 69.57. Result ID: 69994f845698665ec4b9eef8. [Reporting paper]() Recorded evaluation configuration: {"#ReLUs (K)":"51.2","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### CryptoNAS Accuracy (%): 68.5. Result ID: 69994f845698665ec4b9eef6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"100","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### SNL Accuracy (%): 66.53. Result ID: 69994f845698665ec4b9ef03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#ReLUs (K)":"12.9","Backbone":"ResNet-18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.