# Image Classification on ImageNet 1K (val) (kNN and Linear Evaluation Metrics) Source: [Image Classification on ImageNet 1K (val) (kNN and Linear Evaluation Metrics)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:09:19.004Z Evaluation of Image Classification performance on the validation split of ImageNet 1K, reporting metrics derived from k-Nearest Neighbors (kNN) and linear probing evaluations (Lin. \[C\], Lin. \[D\]). 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 (val) | | Metric | kNN Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [kNN Accuracy](): Higher is better; unit: PERCENT. - [Linear Probe Acc \[C\]](): Higher is better; unit: PERCENT. - [Linear Probe Acc \[D\]](): Higher is better; unit: PERCENT. - [Linear Probe Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | kNN Accuracy | Result date | Report paper | | --- | --- | --- | --- | | iBOT-vMF | 78.66 | Not recorded | 68fa733f1e209131cea5b3cc | | DINO-vMF | 77.4 | Not recorded | 68fa733f1e209131cea5b3cc | | STELLAR | 77.31 | Not recorded | 69818197a8b01e76cc8e269f | | iBOT | 77.1 | Not recorded | 68fa733f1e209131cea5b3cc | | DINO | 76.11 | Not recorded | 68fa733f1e209131cea5b3cc | | DINO | 74.69 | Not recorded | 69818197a8b01e76cc8e269f | | MSN | 73.33 | Not recorded | 68fa733f1e209131cea5b3cc | | STELLAR | 67.25 | Not recorded | 69818197a8b01e76cc8e269f | | STELLAR | 64.71 | Not recorded | 69818197a8b01e76cc8e269f | | DINO | 54.41 | Not recorded | 69818197a8b01e76cc8e269f | | MAE | 25.82 | Not recorded | 69818197a8b01e76cc8e269f | | TiTok | 7.3 | Not recorded | 69818197a8b01e76cc8e269f | | TiTok | 7.29 | Not recorded | 69818197a8b01e76cc8e269f | ### iBOT-vMF kNN Accuracy: 78.66. Result ID: 6992b18e3a6c31484910c811. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-Base/16"}. This record does not assert independent reproduction. ### DINO-vMF kNN Accuracy: 77.4. Result ID: 6992b18e3a6c31484910c813. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-Base/16"}. This record does not assert independent reproduction. ### STELLAR kNN Accuracy: 77.31. Result ID: 69975b0f5698665ec4ad6f1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# TKS":"16","Backbone":"ViT-H"}. This record does not assert independent reproduction. ### iBOT kNN Accuracy: 77.1. Result ID: 6992b18e3a6c31484910c810. [Reporting paper]() Recorded evaluation configuration: {"Architecture":"ViT-Base/16"}. This record does not assert independent reproduction. ### DINO kNN Accuracy: 76.11. Result ID: 6992b18e3a6c31484910c812. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-Base/16"}. This record does not assert independent reproduction. ### DINO kNN Accuracy: 74.69. Result ID: 69975b0f5698665ec4ad6f17. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# TKS":"1","Backbone":"ViT-B","Token":"CLS"}. This record does not assert independent reproduction. ### MSN kNN Accuracy: 73.33. Result ID: 6992b18e3a6c31484910c815. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-Base/16"}. This record does not assert independent reproduction. ### STELLAR kNN Accuracy: 67.25. Result ID: 69975b0f5698665ec4ad6f1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# TKS":"16","Backbone":"ViT-B"}. This record does not assert independent reproduction. ### STELLAR kNN Accuracy: 64.71. Result ID: 69975b0f5698665ec4ad6f1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# TKS":"196","Backbone":"ViT-B"}. This record does not assert independent reproduction. ### DINO kNN Accuracy: 54.41. Result ID: 69975b0f5698665ec4ad6f18. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# TKS":"196","Backbone":"ViT-B"}. This record does not assert independent reproduction. ### MAE kNN Accuracy: 25.82. Result ID: 69975b0f5698665ec4ad6f19. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# TKS":"196","Backbone":"ViT-B"}. This record does not assert independent reproduction. ### TiTok kNN Accuracy: 7.3. Result ID: 69975b0f5698665ec4ad6f1a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# TKS":"32","Backbone":"ViT-B","Decoder":"Native ViT decoder of larger size"}. This record does not assert independent reproduction. ### TiTok kNN Accuracy: 7.29. Result ID: 69975b0f5698665ec4ad6f1b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# TKS":"64","Backbone":"ViT-B","Decoder":"Native ViT decoder of larger size"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.