# Low-shot Image Classification on iNaturalist-18 (val) Source: [Low-shot Image Classification on iNaturalist-18 (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:15.255Z Evaluation of Low-shot Image Classification performance on the validation split of the iNaturalist 2018 dataset, reporting accuracy for 1-shot, 5-shot, and 10-shot settings. 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 | Low-shot Image Classification | | Dataset (including any stated split) | iNaturalist-18 (val) | | Metric | Top-1 Accuracy (5-shot) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 (5-shot)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (1-shot)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (10-shot)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (5-shot) | Result date | Report paper | | --- | --- | --- | --- | | MAWS | 73.7 | Not recorded | 68fa71ee1e209131cea539db | | MAWS | 72.8 | Not recorded | 68fa71ee1e209131cea539db | | MAWS | 67.8 | Not recorded | 68fa71ee1e209131cea539db | | SWAG | 62.8 | Not recorded | 68fa71ee1e209131cea539db | | OpenCLIP | 55.7 | Not recorded | 68fa71ee1e209131cea539db | | OpenCLIP | 54.6 | Not recorded | 68fa71ee1e209131cea539db | | CLIP | 49 | Not recorded | 68fa71ee1e209131cea539db | | MAE | 48.5 | Not recorded | 68fa71ee1e209131cea539db | | DINO | 45.9 | Not recorded | 68fa71ee1e209131cea539db | | MSN | 38 | Not recorded | 68fa71ee1e209131cea539db | ### MAWS Top-1 Accuracy (5-shot): 73.7. Result ID: 699200363a6c3148490bf655. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"IG-3B","Architecture":"ViT-6.5B"}. This record does not assert independent reproduction. ### MAWS Top-1 Accuracy (5-shot): 72.8. Result ID: 699200363a6c3148490bf654. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"IG-3B","Architecture":"ViT-2B"}. This record does not assert independent reproduction. ### MAWS Top-1 Accuracy (5-shot): 67.8. Result ID: 699200363a6c3148490bf653. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"IG-3B","Architecture":"ViT-H"}. This record does not assert independent reproduction. ### SWAG Top-1 Accuracy (5-shot): 62.8. Result ID: 699200363a6c3148490bf652. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"IG-3.6B","Architecture":"ViT-H"}. This record does not assert independent reproduction. ### OpenCLIP Top-1 Accuracy (5-shot): 55.7. Result ID: 699200363a6c3148490bf64e. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Dataset":"LAION-2B","Architecture":"ViT-G"}. This record does not assert independent reproduction. ### OpenCLIP Top-1 Accuracy (5-shot): 54.6. Result ID: 699200363a6c3148490bf64d. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Dataset":"LAION-2B","Architecture":"ViT-H"}. This record does not assert independent reproduction. ### CLIP Top-1 Accuracy (5-shot): 49. Result ID: 699200363a6c3148490bf64c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"WIT-400M","Architecture":"ViT-L"}. This record does not assert independent reproduction. ### MAE Top-1 Accuracy (5-shot): 48.5. Result ID: 699200363a6c3148490bf651. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"IN1k","Architecture":"ViT-H"}. This record does not assert independent reproduction. ### DINO Top-1 Accuracy (5-shot): 45.9. Result ID: 699200363a6c3148490bf64f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"IN1k","Architecture":"ViT-B/8"}. This record does not assert independent reproduction. ### MSN Top-1 Accuracy (5-shot): 38. Result ID: 699200363a6c3148490bf650. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Dataset":"IN1k","Architecture":"ViT-L/7"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.