# Fine-grained Image Classification on iNaturalist 2018 Source: [Fine-grained Image Classification on iNaturalist 2018]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:38.242Z Evaluation of Fine-grained Image Classification performance on the iNaturalist 2018 dataset, typically measured by Top-1 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 | Fine-grained Image Classification | | Dataset (including any stated split) | iNaturalist 2018 | | Metric | Top-1 Acc | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 Acc](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Acc | Result date | Report paper | | --- | --- | --- | --- | | MetaFormer | 87.5 | Not recorded | 68fa6bef1e209131cea30faf | | MetaFormer | 83.2 | Not recorded | 68fa6bef1e209131cea30faf | | MetaFormer | 81.9 | Not recorded | 68fa6bef1e209131cea30faf | | Grafit | 81.2 | Not recorded | 68fa6bef1e209131cea30faf | | DeiT-B | 80.1 | Not recorded | 68fa6bef1e209131cea30faf | | SwAV | 48.6 | Not recorded | 68fa5f141e209131ce9e75ab | | BYOL | 47.6 | Not recorded | 68fa5f141e209131ce9e75ab | | Supervised | 46.7 | Not recorded | 68fa5f141e209131ce9e75ab | | BARLOW TWINS | 46.5 | Not recorded | 68fa5f141e209131ce9e75ab | | SwAV | 39.5 | Not recorded | 68fa5f141e209131ce9e75ab | | MoCo-v2 | 38.6 | Not recorded | 68fa5f141e209131ce9e75ab | | SimCLR | 37.2 | Not recorded | 68fa5f141e209131ce9e75ab | ### MetaFormer Top-1 Acc: 87.5. Result ID: 698ea8efffc3901de09f8e56. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"MetaFormer-1","Pretrain":"iNat21"}. This record does not assert independent reproduction. ### MetaFormer Top-1 Acc: 83.2. Result ID: 698ea8efffc3901de09f8e55. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"MetaFormer-1","Pretrain":"ImageNet-21k"}. This record does not assert independent reproduction. ### MetaFormer Top-1 Acc: 81.9. Result ID: 698ea8efffc3901de09f8e54. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"MetaFormer-1","Pretrain":"ImageNet-1k"}. This record does not assert independent reproduction. ### Grafit Top-1 Acc: 81.2. Result ID: 698ea8efffc3901de09f8e53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RegNet-8GF","Pretrain":"ImageNet-1k"}. This record does not assert independent reproduction. ### DeiT-B Top-1 Acc: 80.1. Result ID: 698ea8efffc3901de09f8e52. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B-16","Pretrain":"ImageNet-21k"}. This record does not assert independent reproduction. ### SwAV Top-1 Acc: 48.6. Result ID: 698bbba67a967eddb770eff7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"linear classifier on fixed features","multi-crop":true}. This record does not assert independent reproduction. ### BYOL Top-1 Acc: 47.6. Result ID: 698bbba67a967eddb770eff8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"linear classifier on fixed features"}. This record does not assert independent reproduction. ### Supervised Top-1 Acc: 46.7. Result ID: 698bbba67a967eddb770eff3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"linear classifier on fixed features"}. This record does not assert independent reproduction. ### BARLOW TWINS Top-1 Acc: 46.5. Result ID: 698bbba67a967eddb770eff9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"linear classifier on fixed features"}. This record does not assert independent reproduction. ### SwAV Top-1 Acc: 39.5. Result ID: 698bbba67a967eddb770eff6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"linear classifier on fixed features","multi-crop":false}. This record does not assert independent reproduction. ### MoCo-v2 Top-1 Acc: 38.6. Result ID: 698bbba67a967eddb770eff5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"linear classifier on fixed features"}. This record does not assert independent reproduction. ### SimCLR Top-1 Acc: 37.2. Result ID: 698bbba67a967eddb770eff4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"linear classifier on fixed features"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.