# Image Classification on CUB-200 1.0 (test) Source: [Image Classification on CUB-200 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-04-16T06:49:21.650Z Evaluation of Image Classification performance on the test split of the CUB-200 1.0 dataset, reporting metrics derived from various pre-trained feature extractors (e.g., CLIP, DINO-v2). 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) | CUB-200 1.0 (test) | | Metric | Average 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 Accuracy](): Higher is better; unit: PERCENT. - [CLIP Accuracy](): Higher is better; unit: PERCENT. - [DINO-v2 Accuracy](): Higher is better; unit: PERCENT. - [EVA-02 Accuracy](): Higher is better; unit: PERCENT. - [MoCo-v3 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Full Dataset | 73.8 | Not recorded | 69857586c97a0b3e3b5d5c3c | | Ours (SFM+CI) | 69.9 | Not recorded | 69857586c97a0b3e3b5d5c3c | | Ours (SFM) | 66.8 | Not recorded | 69857586c97a0b3e3b5d5c3c | | LGM | 66.2 | Not recorded | 69857586c97a0b3e3b5d5c3c | | Centroids | 55.7 | Not recorded | 69857586c97a0b3e3b5d5c3c | | Diff-TPT | 52.8 | Not recorded | 68fa79001e209131cea7b953 | | Neighbors (SFM) | 52.7 | Not recorded | 69857586c97a0b3e3b5d5c3c | | VS2 | 52.69 | Not recorded | 68fa79001e209131cea7b953 | | C-TPT | 52.54 | Not recorded | 68fa79001e209131cea7b953 | | VS2 | 52.47 | Not recorded | 68fa79001e209131cea7b953 | | TPT | 51.83 | Not recorded | 68fa79001e209131cea7b953 | | CLIP | 51.76 | Not recorded | 68fa79001e209131cea7b953 | | CLIP | 51.54 | Not recorded | 68fa79001e209131cea7b953 | | VS2 | 51.54 | Not recorded | 68fa79001e209131cea7b953 | | Neighbors (LGM) | 49.2 | Not recorded | 69857586c97a0b3e3b5d5c3c | | Random | 41.3 | Not recorded | 69857586c97a0b3e3b5d5c3c | ### Full Dataset Average Accuracy: 73.8. Result ID: 69973e865698665ec48f1dfe. [Reporting paper]() Recorded evaluation configuration: {"Train Set":"Full"}. This record does not assert independent reproduction. ### Ours (SFM+CI) Average Accuracy: 69.9. Result ID: 69973e865698665ec48f1dfd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction. ### Ours (SFM) Average Accuracy: 66.8. Result ID: 69973e865698665ec48f1dfc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction. ### LGM Average Accuracy: 66.2. Result ID: 69973e865698665ec48f1dfb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction. ### Centroids Average Accuracy: 55.7. Result ID: 69973e865698665ec48f1df8. [Reporting paper]() Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction. ### Diff-TPT Average Accuracy: 52.8. Result ID: 69e0865947f34ce924c939cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Test-time Prompt Tuning":"true"}. This record does not assert independent reproduction. ### Neighbors (SFM) Average Accuracy: 52.7. Result ID: 69973e865698665ec48f1dfa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction. ### VS2 Average Accuracy: 52.69. Result ID: 69e0865947f34ce924c939d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32"}. This record does not assert independent reproduction. ### C-TPT Average Accuracy: 52.54. Result ID: 69e0865947f34ce924c939ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Test-time Prompt Tuning":"true"}. This record does not assert independent reproduction. ### VS2 Average Accuracy: 52.47. Result ID: 69e0865947f34ce924c939d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Ensemble":"true"}. This record does not assert independent reproduction. ### TPT Average Accuracy: 51.83. Result ID: 69e0865947f34ce924c939cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Test-time Prompt Tuning":"true"}. This record does not assert independent reproduction. ### CLIP Average Accuracy: 51.76. Result ID: 69e0865947f34ce924c939cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### CLIP Average Accuracy: 51.54. Result ID: 69e0865947f34ce924c939cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Ensemble":"true"}. This record does not assert independent reproduction. ### VS2 Average Accuracy: 51.54. Result ID: 69e0865947f34ce924c939d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Ensemble":"true","Test-time Augmentation":"true"}. This record does not assert independent reproduction. ### Neighbors (LGM) Average Accuracy: 49.2. Result ID: 69973e865698665ec48f1df9. [Reporting paper]() Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction. ### Random Average Accuracy: 41.3. Result ID: 69973e865698665ec48f1df7. [Reporting paper]() Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.