# Zero-shot Classification on ELEVATER ImageNet 21 datasets Source: [Zero-shot Classification on ELEVATER ImageNet 21 datasets]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:13.321Z Evaluation of Zero-shot Classification performance on the ELEVATER ImageNet 21 datasets collection, measured by the average metric. 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 | Zero-shot Classification | | Dataset (including any stated split) | ELEVATER ImageNet 21 datasets | | Metric | Average Accuracy | | 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 - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CLIP-FT | 56.9 | Not recorded | 68fa70f11e209131cea4e388 | | CLIP | 56.4 | Not recorded | 68fa70f11e209131cea4e388 | | MosaiCLIP WiSE-FT | 55.9 | Not recorded | 68fa70f11e209131cea4e388 | | Syn-CLIP | 55.3 | Not recorded | 68fa70f11e209131cea4e388 | | MosaiCLIP NoCurric | 54.9 | Not recorded | 68fa70f11e209131cea4e388 | | Teaching SVLC | 54.8 | Not recorded | 68fa70f11e209131cea4e388 | | MosaiCLIP | 53.5 | Not recorded | 68fa70f11e209131cea4e388 | ### CLIP-FT Average Accuracy: 56.9. Result ID: 699166c83a6c31484907e5cf. [Reporting paper]() Recorded evaluation configuration: {"mode":"Fine-tuned"}. This record does not assert independent reproduction. ### CLIP Average Accuracy: 56.4. Result ID: 699166c83a6c31484907e5ce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MosaiCLIP WiSE-FT Average Accuracy: 55.9. Result ID: 699166c83a6c31484907e5d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"fine\_tuning":"WiSE-FT"}. This record does not assert independent reproduction. ### Syn-CLIP Average Accuracy: 55.3. Result ID: 699166c83a6c31484907e5d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_data":"Million-scale synthetic data"}. This record does not assert independent reproduction. ### MosaiCLIP NoCurric Average Accuracy: 54.9. Result ID: 699166c83a6c31484907e5d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"curriculum\_learning":"false"}. This record does not assert independent reproduction. ### Teaching SVLC Average Accuracy: 54.8. Result ID: 699166c83a6c31484907e5d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"augmentation":"External LLM text augmentation"}. This record does not assert independent reproduction. ### MosaiCLIP Average Accuracy: 53.5. Result ID: 699166c83a6c31484907e5d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.