# Image Classification on ImageNet 1k (k-NN and Linear Probing) Source: [Image Classification on ImageNet 1k (k-NN and Linear Probing)]() Collection index: [llms.txt]() Data updated: 2026-06-01T09:24:50.568Z Evaluation of Image Classification performance on the ImageNet-1k dataset, specifically reporting accuracy derived from k-NN and linear probing evaluation protocols. 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 1k | | Metric | Top-1 Accuracy (ImageNet-1k) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 (ImageNet-1k)](): Higher is better; unit: PERCENT. - [Accuracy (k-NN)](): Higher is better; unit: PERCENT. - [Accuracy (Linear Probing)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (ImageNet-1k) | Result date | Report paper | | --- | --- | --- | --- | | NViT | 83.3 | Not recorded | 68fa7c5d1e209131cea8dc2c | | SAViT | 82.6 | Not recorded | 68fa7c5d1e209131cea8dc2c | | SnapViT | 82.6 | Not recorded | 68fa7c5d1e209131cea8dc2c | | Unpruned | 81.8 | Not recorded | 68fa7c5d1e209131cea8dc2c | | LPViT | 80.6 | Not recorded | 68fa7c5d1e209131cea8dc2c | | SN-Net | 80 | Not recorded | 68fa7c5d1e209131cea8dc2c | ### NViT Top-1 Accuracy (ImageNet-1k): 83.3. Result ID: 6a1d4e29fbc373592c16c76e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sparsity":"50%","Fine-tuning Epochs":"300"}. This record does not assert independent reproduction. ### SAViT Top-1 Accuracy (ImageNet-1k): 82.6. Result ID: 6a1d4e29fbc373592c16c770. [Reporting paper]() Recorded evaluation configuration: {"Sparsity":"50%","Fine-tuning Epochs":"300"}. This record does not assert independent reproduction. ### SnapViT Top-1 Accuracy (ImageNet-1k): 82.6. Result ID: 6a1d4e29fbc373592c16c771. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sparsity":"50%","Fine-tuning Epochs":"300"}. This record does not assert independent reproduction. ### Unpruned Top-1 Accuracy (ImageNet-1k): 81.8. Result ID: 6a1d4e29fbc373592c16c76c. [Reporting paper]() Recorded evaluation configuration: {"Sparsity":"0%"}. This record does not assert independent reproduction. ### LPViT Top-1 Accuracy (ImageNet-1k): 80.6. Result ID: 6a1d4e29fbc373592c16c76f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sparsity":"50%","Fine-tuning Epochs":"300"}. This record does not assert independent reproduction. ### SN-Net Top-1 Accuracy (ImageNet-1k): 80. Result ID: 6a1d4e29fbc373592c16c76d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sparsity":"50%","Fine-tuning Epochs":"100"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.