# Image Classification on ICinW Source: [Image Classification on ICinW]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:12.724Z Evaluation of Image Classification performance across the 20 constituent datasets comprising the ICinW suite. 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) | ICinW | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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. - [Caltech-101 Accuracy](): Higher is better; unit: PERCENT. - [CIFAR-10 Accuracy](): Higher is better; unit: PERCENT. - [CIFAR-100 Accuracy](): Higher is better; unit: PERCENT. - [Country211 Accuracy](): Higher is better; unit: PERCENT. - [DTD Accuracy](): Higher is better; unit: PERCENT. - [EuroSAT Accuracy](): Higher is better; unit: PERCENT. - [FER-2013 Accuracy](): Higher is better; unit: PERCENT. - [Aircraft Accuracy](): Higher is better; unit: PERCENT. - [Food-101 Accuracy](): Higher is better; unit: PERCENT. - [GTSRB Accuracy](): Higher is better; unit: PERCENT. - [Memes Accuracy](): Higher is better; unit: PERCENT. - [KittiDis Accuracy](): Higher is better; unit: PERCENT. - [MNIST Accuracy](): Higher is better; unit: PERCENT. - [Flowers Accuracy](): Higher is better; unit: PERCENT. - [Pets Accuracy](): Higher is better; unit: PERCENT. - [PatchCam Accuracy](): Higher is better; unit: PERCENT. - [SST2 Accuracy](): Higher is better; unit: PERCENT. - [RESISC45 Accuracy](): Higher is better; unit: PERCENT. - [Cars Accuracy](): Higher is better; unit: PERCENT. - [Voc2007 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MaskCLIP | 48.9 | Not recorded | 68fa6f0a1e209131cea437fe | | KLITE | 45.5 | Not recorded | 68fa6f0a1e209131cea437fe | | YT-CLIP | 44.5 | Not recorded | 68fa6f0a1e209131cea437fe | | UniCL | 44 | Not recorded | 68fa6f0a1e209131cea437fe | | Gramer | 43.2 | Not recorded | 68fa6f0a1e209131cea437fe | | MaskCLIP | 40.1 | Not recorded | 68fa6f0a1e209131cea437fe | | SLIP | 37.8 | Not recorded | 68fa6f0a1e209131cea437fe | | CLIP | 34 | Not recorded | 68fa6f0a1e209131cea437fe | ### MaskCLIP Average Accuracy: 48.9. Result ID: 69907f0f3a6c31484900fc26. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training dataset":"ICinW Academic Track","Evaluation protocol":"Zero-shot","Backbone":"ViT-B"}. This record does not assert independent reproduction. ### KLITE Average Accuracy: 45.5. Result ID: 69907f0f3a6c31484900fc27. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training dataset":"ICinW Academic Track","Evaluation protocol":"Zero-shot","Backbone":"Swin-B"}. This record does not assert independent reproduction. ### YT-CLIP Average Accuracy: 44.5. Result ID: 69907f0f3a6c31484900fc28. [Reporting paper]() Recorded evaluation configuration: {"Pre-training dataset":"ICinW Academic Track","Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction. ### UniCL Average Accuracy: 44. Result ID: 69907f0f3a6c31484900fc29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training dataset":"ICinW Academic Track","Evaluation protocol":"Zero-shot","Backbone":"Focal-B"}. This record does not assert independent reproduction. ### Gramer Average Accuracy: 43.2. Result ID: 69907f0f3a6c31484900fc2a. [Reporting paper]() Recorded evaluation configuration: {"Pre-training dataset":"ICinW Academic Track","Evaluation protocol":"Zero-shot","Backbone":"Swin-B"}. This record does not assert independent reproduction. ### MaskCLIP Average Accuracy: 40.1. Result ID: 69907f0f3a6c31484900fc25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training dataset":"YFCC-15M","Evaluation protocol":"Zero-shot","Backbone":"ViT-B"}. This record does not assert independent reproduction. ### SLIP Average Accuracy: 37.8. Result ID: 69907f0f3a6c31484900fc24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training dataset":"YFCC-15M","Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction. ### CLIP Average Accuracy: 34. Result ID: 69907f0f3a6c31484900fc23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training dataset":"YFCC-15M","Evaluation protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.