# Image Classification on NICO++ Feature+label non-IID (average across domains) Source: [Image Classification on NICO++ Feature+label non-IID (average across domains)]() Collection index: [llms.txt]() Data updated: 2026-06-05T09:35:03.229Z Evaluation of Image Classification performance on the NICO++ dataset under feature and label non-IID conditions, reporting the average accuracy across domains. 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) | NICO++ Feature+label non-IID (average across domains) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Centralized | 91.51 | Not recorded | 6a22587e86173ad9c1468a6d | | HyperLoRA | 91.19 | Not recorded | 6a22587e86173ad9c1468a6d | | LoRA-FAIR | 90.04 | Not recorded | 6a22587e86173ad9c1468a6d | | FlexLoRA | 89.65 | Not recorded | 6a22587e86173ad9c1468a6d | | FLoRA | 89.6 | Not recorded | 6a22587e86173ad9c1468a6d | | FedIT | 89.48 | Not recorded | 6a22587e86173ad9c1468a6d | | FFA-LoRA | 89.45 | Not recorded | 6a22587e86173ad9c1468a6d | | Centralized | 84.5 | Not recorded | 6a22587e86173ad9c1468a6d | | HyperLoRA | 81.15 | Not recorded | 6a22587e86173ad9c1468a6d | | LoRA-FAIR | 79.53 | Not recorded | 6a22587e86173ad9c1468a6d | | FlexLoRA | 78.73 | Not recorded | 6a22587e86173ad9c1468a6d | | FedIT | 78.53 | Not recorded | 6a22587e86173ad9c1468a6d | | FLoRA | 78.41 | Not recorded | 6a22587e86173ad9c1468a6d | | FFA-LoRA | 76.78 | Not recorded | 6a22587e86173ad9c1468a6d | ### Centralized Top-1 Accuracy: 91.51. Result ID: 6a229845fbc373592c2118ea. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### HyperLoRA Top-1 Accuracy: 91.19. Result ID: 6a229845fbc373592c2118f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### LoRA-FAIR Top-1 Accuracy: 90.04. Result ID: 6a229845fbc373592c2118ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### FlexLoRA Top-1 Accuracy: 89.65. Result ID: 6a229845fbc373592c2118ee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### FLoRA Top-1 Accuracy: 89.6. Result ID: 6a229845fbc373592c2118ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### FedIT Top-1 Accuracy: 89.48. Result ID: 6a229845fbc373592c2118ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### FFA-LoRA Top-1 Accuracy: 89.45. Result ID: 6a229845fbc373592c2118eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT"}. This record does not assert independent reproduction. ### Centralized Top-1 Accuracy: 84.5. Result ID: 6a229845fbc373592c2118f1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"MLP-Mixer"}. This record does not assert independent reproduction. ### HyperLoRA Top-1 Accuracy: 81.15. Result ID: 6a229845fbc373592c2118f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP-Mixer"}. This record does not assert independent reproduction. ### LoRA-FAIR Top-1 Accuracy: 79.53. Result ID: 6a229845fbc373592c2118f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP-Mixer"}. This record does not assert independent reproduction. ### FlexLoRA Top-1 Accuracy: 78.73. Result ID: 6a229845fbc373592c2118f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"MLP-Mixer"}. This record does not assert independent reproduction. ### FedIT Top-1 Accuracy: 78.53. Result ID: 6a229845fbc373592c2118f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP-Mixer"}. This record does not assert independent reproduction. ### FLoRA Top-1 Accuracy: 78.41. Result ID: 6a229845fbc373592c2118f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"MLP-Mixer"}. This record does not assert independent reproduction. ### FFA-LoRA Top-1 Accuracy: 76.78. Result ID: 6a229845fbc373592c2118f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP-Mixer"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.