# Image Classification on CIFAR-100 (test) (Accuracy vs FLOPs Budget) Source: [Image Classification on CIFAR-100 (test) (Accuracy vs FLOPs Budget)]() Collection index: [llms.txt]() Data updated: 2026-05-08T07:27:02.616Z Evaluation of Image Classification performance on the CIFAR-100 test set, reporting Top-1 accuracy measured at specific computational budgets defined by FLOPs percentages (25%, 50%, 75%, 100%). 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 (test) | | Metric | Top-1 Accuracy (25% FLOPs) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 (25% FLOPs)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (50% FLOPs)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (75% FLOPs)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (100% FLOPs)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (25% FLOPs) | Result date | Report paper | | --- | --- | --- | --- | | LwF | 0.7071 | Not recorded | 69fd6de45497b3b670c89276 | | EWC | 0.705 | Not recorded | 69fd6de45497b3b670c89276 | | LwF | 0.665 | Not recorded | 69fd6de45497b3b670c89276 | | Separate | 0.6625 | Not recorded | 69fd6de45497b3b670c89276 | | Joint | 0.6593 | Not recorded | 69fd6de45497b3b670c89276 | | EWC | 0.651 | Not recorded | 69fd6de45497b3b670c89276 | | Separate | 0.649 | Not recorded | 69fd6de45497b3b670c89276 | | Branch-wise | 0.6419 | Not recorded | 69fd6de45497b3b670c89276 | | Joint | 0.6284 | Not recorded | 69fd6de45497b3b670c89276 | | Branch-wise | 0.5824 | Not recorded | 69fd6de45497b3b670c89276 | | Disjoint | 0.5674 | Not recorded | 69fd6de45497b3b670c89276 | | Disjoint | 0.5257 | Not recorded | 69fd6de45497b3b670c89276 | ### LwF Top-1 Accuracy (25% FLOPs): 0.7071. Result ID: 69fd8fe547f34ce924e02df7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-34","lambda":"100","rho":"0.7"}. This record does not assert independent reproduction. ### EWC Top-1 Accuracy (25% FLOPs): 0.705. Result ID: 69fd8fe547f34ce924e02df6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-34","lambda":"100","rho":"0.7"}. This record does not assert independent reproduction. ### LwF Top-1 Accuracy (25% FLOPs): 0.665. Result ID: 69fd8fe547f34ce924e02dfd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MSDNet","lambda":"1000","rho":"0.2"}. This record does not assert independent reproduction. ### Separate Top-1 Accuracy (25% FLOPs): 0.6625. Result ID: 69fd8fe547f34ce924e02df4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-34"}. This record does not assert independent reproduction. ### Joint Top-1 Accuracy (25% FLOPs): 0.6593. Result ID: 69fd8fe547f34ce924e02dfb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MSDNet"}. This record does not assert independent reproduction. ### EWC Top-1 Accuracy (25% FLOPs): 0.651. Result ID: 69fd8fe547f34ce924e02dfc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MSDNet","lambda":"1000","rho":"0.2"}. This record does not assert independent reproduction. ### Separate Top-1 Accuracy (25% FLOPs): 0.649. Result ID: 69fd8fe547f34ce924e02dfa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MSDNet"}. This record does not assert independent reproduction. ### Branch-wise Top-1 Accuracy (25% FLOPs): 0.6419. Result ID: 69fd8fe547f34ce924e02df3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-34"}. This record does not assert independent reproduction. ### Joint Top-1 Accuracy (25% FLOPs): 0.6284. Result ID: 69fd8fe547f34ce924e02df5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-34"}. This record does not assert independent reproduction. ### Branch-wise Top-1 Accuracy (25% FLOPs): 0.5824. Result ID: 69fd8fe547f34ce924e02df9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MSDNet"}. This record does not assert independent reproduction. ### Disjoint Top-1 Accuracy (25% FLOPs): 0.5674. Result ID: 69fd8fe547f34ce924e02df8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MSDNet"}. This record does not assert independent reproduction. ### Disjoint Top-1 Accuracy (25% FLOPs): 0.5257. Result ID: 69fd8fe547f34ce924e02df2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-34"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.