# Image Classification on ImageNet 1k Depth (KNN & Linear Probing) Source: [Image Classification on ImageNet 1k Depth (KNN & Linear Probing)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:15.789Z Evaluation of Image Classification performance on the ImageNet 1k Depth dataset, reporting accuracy via Top-1/Top-5 KNN evaluation and Linear Probing accuracy. 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 Depth | | Metric | Top-1 Accuracy (KNN) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 (KNN)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (KNN)](): Higher is better; unit: PERCENT. - [Linear Probing Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (KNN) | Result date | Report paper | | --- | --- | --- | --- | | DINOv3 | 64.07 | Not recorded | 69799834a2b28e761d87ccbd | | DINOv3 | 64.07 | Not recorded | 69799834a2b28e761d87ccbd | | DeFM | 63.46 | Not recorded | 69799834a2b28e761d87ccbd | | DeFM | 63.46 | Not recorded | 69799834a2b28e761d87ccbd | | DINOv2 | 61.93 | Not recorded | 69799834a2b28e761d87ccbd | | DINOv2 | 61.93 | Not recorded | 69799834a2b28e761d87ccbd | | C-RADIOv3 | 55.9 | Not recorded | 69799834a2b28e761d87ccbd | | C-RADIOv3 | 55.9 | Not recorded | 69799834a2b28e761d87ccbd | | DeFM | 55.27 | Not recorded | 69799834a2b28e761d87ccbd | | DeFM | 55.27 | Not recorded | 69799834a2b28e761d87ccbd | | DINOv3 | 49.5 | Not recorded | 69799834a2b28e761d87ccbd | | DINOv3 | 49.5 | Not recorded | 69799834a2b28e761d87ccbd | | DINOv2 | 47.66 | Not recorded | 69799834a2b28e761d87ccbd | | DINOv2 | 47.66 | Not recorded | 69799834a2b28e761d87ccbd | | Theia | 28.17 | Not recorded | 69799834a2b28e761d87ccbd | | Theia | 28.17 | Not recorded | 69799834a2b28e761d87ccbd | ### DINOv3 Top-1 Accuracy (KNN): 64.07. Result ID: 6999d14a5698665ec44fbec2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-L/16"}. This record does not assert independent reproduction. ### DINOv3 Top-1 Accuracy (KNN): 64.07. Result ID: 6999d14a5698665ec44fbf01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-L/16"}. This record does not assert independent reproduction. ### DeFM Top-1 Accuracy (KNN): 63.46. Result ID: 6999d14a5698665ec44fbec3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-L/14"}. This record does not assert independent reproduction. ### DeFM Top-1 Accuracy (KNN): 63.46. Result ID: 6999d14a5698665ec44fbf02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-L/14"}. This record does not assert independent reproduction. ### DINOv2 Top-1 Accuracy (KNN): 61.93. Result ID: 6999d14a5698665ec44fbec0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-L/14"}. This record does not assert independent reproduction. ### DINOv2 Top-1 Accuracy (KNN): 61.93. Result ID: 6999d14a5698665ec44fbeff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-L/14"}. This record does not assert independent reproduction. ### C-RADIOv3 Top-1 Accuracy (KNN): 55.9. Result ID: 6999d14a5698665ec44fbec1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-L/16 (CPE)"}. This record does not assert independent reproduction. ### C-RADIOv3 Top-1 Accuracy (KNN): 55.9. Result ID: 6999d14a5698665ec44fbf00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-L/16 (CPE)"}. This record does not assert independent reproduction. ### DeFM Top-1 Accuracy (KNN): 55.27. Result ID: 6999d14a5698665ec44fbec7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-S/14"}. This record does not assert independent reproduction. ### DeFM Top-1 Accuracy (KNN): 55.27. Result ID: 6999d14a5698665ec44fbf06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-S/14"}. This record does not assert independent reproduction. ### DINOv3 Top-1 Accuracy (KNN): 49.5. Result ID: 6999d14a5698665ec44fbec6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-S/16"}. This record does not assert independent reproduction. ### DINOv3 Top-1 Accuracy (KNN): 49.5. Result ID: 6999d14a5698665ec44fbf05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-S/16"}. This record does not assert independent reproduction. ### DINOv2 Top-1 Accuracy (KNN): 47.66. Result ID: 6999d14a5698665ec44fbec5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-S/14"}. This record does not assert independent reproduction. ### DINOv2 Top-1 Accuracy (KNN): 47.66. Result ID: 6999d14a5698665ec44fbf04. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-S/14"}. This record does not assert independent reproduction. ### Theia Top-1 Accuracy (KNN): 28.17. Result ID: 6999d14a5698665ec44fbec4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"DeiT-S/16"}. This record does not assert independent reproduction. ### Theia Top-1 Accuracy (KNN): 28.17. Result ID: 6999d14a5698665ec44fbf03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"DeiT-S/16"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.