# Image Classification on SVHN (Absolute, Normalized, and Average Accuracy) Source: [Image Classification on SVHN (Absolute, Normalized, and Average Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-03-30T07:32:50.878Z Evaluation of standard Image Classification performance on the SVHN dataset, reporting Absolute, Normalized, and Average 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 | Image Classification | | Dataset (including any stated split) | SVHN | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Average Accuracy](): Higher is better; unit: PERCENT. - [Absolute Accuracy](): Higher is better; unit: PERCENT. - [Normalized Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Finetuned | 84.1 | Not recorded | 69ca036c0636e5bf4afc9280 | | TARA-Variant B | 76.3 | Not recorded | 69ca036c0636e5bf4afc9280 | | TARA-Variant A | 74 | Not recorded | 69ca036c0636e5bf4afc9280 | | Iso-C | 73.6 | Not recorded | 69ca036c0636e5bf4afc9280 | | Iso-CTS | 73.5 | Not recorded | 69ca036c0636e5bf4afc9280 | | AdaMerging | 70 | Not recorded | 69ca036c0636e5bf4afc9280 | | KnOTS-TIES | 68 | Not recorded | 69ca036c0636e5bf4afc9280 | | TIES | 64.9 | Not recorded | 69ca036c0636e5bf4afc9280 | | EMR-Merging | 64 | Not recorded | 69ca036c0636e5bf4afc9280 | | KnOTS-DARE-TIES | 63.9 | Not recorded | 69ca036c0636e5bf4afc9280 | | TA | 63.8 | Not recorded | 69ca036c0636e5bf4afc9280 | | Linear | 63.7 | Not recorded | 69ca036c0636e5bf4afc9280 | | RobustMerge | 63.3 | Not recorded | 69ca036c0636e5bf4afc9280 | | DARE-TIES | 63.1 | Not recorded | 69ca036c0636e5bf4afc9280 | | LoRA-LEGO | 62.9 | Not recorded | 69ca036c0636e5bf4afc9280 | | SVD | 62.6 | Not recorded | 69ca036c0636e5bf4afc9280 | | RegMean | 60.9 | Not recorded | 69ca036c0636e5bf4afc9280 | | FR-Merging | 57.6 | Not recorded | 69ca036c0636e5bf4afc9280 | ### Finetuned Average Accuracy: 84.1. Result ID: 69ca271147f34ce924b274c6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Baseline"}. This record does not assert independent reproduction. ### TARA-Variant B Average Accuracy: 76.3. Result ID: 69ca271147f34ce924b274d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### TARA-Variant A Average Accuracy: 74. Result ID: 69ca271147f34ce924b274d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### Iso-C Average Accuracy: 73.6. Result ID: 69ca271147f34ce924b274cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### Iso-CTS Average Accuracy: 73.5. Result ID: 69ca271147f34ce924b274ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### AdaMerging Average Accuracy: 70. Result ID: 69ca271147f34ce924b274cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### KnOTS-TIES Average Accuracy: 68. Result ID: 69ca271147f34ce924b274d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### TIES Average Accuracy: 64.9. Result ID: 69ca271147f34ce924b274c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### EMR-Merging Average Accuracy: 64. Result ID: 69ca271147f34ce924b274cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### KnOTS-DARE-TIES Average Accuracy: 63.9. Result ID: 69ca271147f34ce924b274d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### TA Average Accuracy: 63.8. Result ID: 69ca271147f34ce924b274c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### Linear Average Accuracy: 63.7. Result ID: 69ca271147f34ce924b274d1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### RobustMerge Average Accuracy: 63.3. Result ID: 69ca271147f34ce924b274d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### DARE-TIES Average Accuracy: 63.1. Result ID: 69ca271147f34ce924b274ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### LoRA-LEGO Average Accuracy: 62.9. Result ID: 69ca271147f34ce924b274d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### SVD Average Accuracy: 62.6. Result ID: 69ca271147f34ce924b274d0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"LoRA-aware Merging"}. This record does not assert independent reproduction. ### RegMean Average Accuracy: 60.9. Result ID: 69ca271147f34ce924b274c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. ### FR-Merging Average Accuracy: 57.6. Result ID: 69ca271147f34ce924b274cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-trained":"ImageNet-21k","Fine-tuning Protocol":"rank-16 LoRA","Merging Category":"Vanilla Merging"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.