# Fine-grained Image Classification on FGVC (CUB-200, Stanford Dogs, Stanford Cars, NABirds) (test) Source: [Fine-grained Image Classification on FGVC (CUB-200, Stanford Dogs, Stanford Cars, NABirds) (test)]() Collection index: [llms.txt]() Data updated: 2026-07-09T07:00:52.059Z Evaluation of Fine-grained Image Classification performance on a specific subset of the FGVC benchmark suite, comprising CUB-200, Stanford Dogs, Stanford Cars, and NABirds on the test split. 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) | FGVC (CUB-200, Stanford Dogs, Stanford Cars, NABirds) (test) | | Metric | Average Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LoCA (r16) | 90.06 | Not recorded | 6a4f2b1e32fb937314875c53 | | CA | 89.28 | Not recorded | 6a4f2b1e32fb937314875c53 | | LoRA | 88.18 | Not recorded | 6a4f2b1e32fb937314875c53 | | FSF | 88.04 | Not recorded | 6a4f2b1e32fb937314875c53 | | CoLoRA | 86.11 | Not recorded | 6a4f2b1e32fb937314875c53 | | LoCA (r16) | 83.67 | Not recorded | 6a4f2b1e32fb937314875c53 | | CA | 83.48 | Not recorded | 6a4f2b1e32fb937314875c53 | | FSF | 81.07 | Not recorded | 6a4f2b1e32fb937314875c53 | | LoRA | 80.96 | Not recorded | 6a4f2b1e32fb937314875c53 | | FFT | 79.73 | Not recorded | 6a4f2b1e32fb937314875c53 | | LP | 77.55 | Not recorded | 6a4f2b1e32fb937314875c53 | | CoLoRA | 76.44 | Not recorded | 6a4f2b1e32fb937314875c53 | | FFT | 75.73 | Not recorded | 6a4f2b1e32fb937314875c53 | | Bias | 64.98 | Not recorded | 6a4f2b1e32fb937314875c53 | | Bias | 48.85 | Not recorded | 6a4f2b1e32fb937314875c53 | | LP | 45.39 | Not recorded | 6a4f2b1e32fb937314875c53 | ### LoCA (r16) Average Top-1 Accuracy: 90.06. Result ID: 6a4f471760b88bb339e472a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"3.70"}. This record does not assert independent reproduction. ### CA Average Top-1 Accuracy: 89.28. Result ID: 6a4f471760b88bb339e472a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"6.13"}. This record does not assert independent reproduction. ### LoRA Average Top-1 Accuracy: 88.18. Result ID: 6a4f471760b88bb339e472a1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"17.58"}. This record does not assert independent reproduction. ### FSF Average Top-1 Accuracy: 88.04. Result ID: 6a4f471760b88bb339e472a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"1.11"}. This record does not assert independent reproduction. ### CoLoRA Average Top-1 Accuracy: 86.11. Result ID: 6a4f471760b88bb339e472a5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"4.57"}. This record does not assert independent reproduction. ### LoCA (r16) Average Top-1 Accuracy: 83.67. Result ID: 6a4f471760b88bb339e472aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"1.94"}. This record does not assert independent reproduction. ### CA Average Top-1 Accuracy: 83.48. Result ID: 6a4f471760b88bb339e472a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"2.23"}. This record does not assert independent reproduction. ### FSF Average Top-1 Accuracy: 81.07. Result ID: 6a4f471760b88bb339e472a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"2.52"}. This record does not assert independent reproduction. ### LoRA Average Top-1 Accuracy: 80.96. Result ID: 6a4f471760b88bb339e472a2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"2.43"}. This record does not assert independent reproduction. ### FFT Average Top-1 Accuracy: 79.73. Result ID: 6a4f471760b88bb339e4729b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"87.87"}. This record does not assert independent reproduction. ### LP Average Top-1 Accuracy: 77.55. Result ID: 6a4f471760b88bb339e4729d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"0.31"}. This record does not assert independent reproduction. ### CoLoRA Average Top-1 Accuracy: 76.44. Result ID: 6a4f471760b88bb339e472a6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"0.99"}. This record does not assert independent reproduction. ### FFT Average Top-1 Accuracy: 75.73. Result ID: 6a4f471760b88bb339e4729c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"24.14"}. This record does not assert independent reproduction. ### Bias Average Top-1 Accuracy: 64.98. Result ID: 6a4f471760b88bb339e4729f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ConvNeXt-B","Number of Trainable Parameters (M)":"0.44"}. This record does not assert independent reproduction. ### Bias Average Top-1 Accuracy: 48.85. Result ID: 6a4f471760b88bb339e472a0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"0.67"}. This record does not assert independent reproduction. ### LP Average Top-1 Accuracy: 45.39. Result ID: 6a4f471760b88bb339e4729e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Trainable Parameters (M)":"0.62"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.