# Image Classification on ImageNet All unseen Source: [Image Classification on ImageNet All unseen]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:45:20.649Z Evaluation of standard Image Classification performance on the 'ImageNet All unseen' dataset split, utilizing Flat Hit@K and Hierarchical precision 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) | ImageNet All unseen | | Metric | Flat Hit@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Flat Hit@1](): Higher is better; unit: PERCENT. - [Flat Hit@2](): Higher is better; unit: PERCENT. - [Flat Hit@5](): Higher is better; unit: PERCENT. - [Flat Hit@10](): Higher is better; unit: PERCENT. - [Flat Hit@20](): Higher is better; unit: PERCENT. - [Hierarchical Precision@2](): Higher is better; unit: PERCENT. - [Hierarchical Precision@5](): Higher is better; unit: PERCENT. - [Hierarchical Precision@10](): Higher is better; unit: PERCENT. - [Hierarchical Precision@20](): Higher is better; unit: PERCENT. ## Recorded results | Method | Flat Hit@1 | Result date | Report paper | | --- | --- | --- | --- | | ConSE(10) | 1.5 | Not recorded | 68fa62861e209131ce9f9e6e | | ConSE(1000) | 1.5 | Not recorded | 68fa62861e209131ce9f9e6e | | Oursstruct | 1.5 | Not recorded | 68fa62861e209131ce9f9e6e | | ConSE(1) | 1.4 | Not recorded | 68fa62861e209131ce9f9e6e | | ConSE(10) \[33\] | 1.4 | Not recorded | 68fa62861e209131ce9f9e6e | | Ourso-vs-o | 1.4 | Not recorded | 68fa62861e209131ce9f9e6e | | ConSE(CV) | 1.3 | Not recorded | 68fa62861e209131ce9f9e6e | ### ConSE(10) Flat Hit@1: 1.5. Result ID: 698bdaedecace47ef5592aaa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T":"10","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### ConSE(1000) Flat Hit@1: 1.5. Result ID: 698bdaedecace47ef5592aac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T":"1000","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### Oursstruct Flat Hit@1: 1.5. Result ID: 698bdaedecace47ef5592aaf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"struct","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### ConSE(1) Flat Hit@1: 1.4. Result ID: 698bdaedecace47ef5592aa9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T":"1","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### ConSE(10) \[33\] Flat Hit@1: 1.4. Result ID: 698bdaedecace47ef5592aab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T":"10","Evaluation":"Zero-shot","Source":"Published Results"}. This record does not assert independent reproduction. ### Ourso-vs-o Flat Hit@1: 1.4. Result ID: 698bdaedecace47ef5592aae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"o-vs-o","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### ConSE(CV) Flat Hit@1: 1.3. Result ID: 698bdaedecace47ef5592aad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T":"Class-wise CV","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.