# Fine-grained Image Classification on Oxford-IIIT Pets (Acc, ECE, SCE) Source: [Fine-grained Image Classification on Oxford-IIIT Pets (Acc, ECE, SCE)]() Collection index: [llms.txt]() Data updated: 2026-05-01T08:26:32.139Z Evaluation of Fine-grained Image Classification performance on the Oxford-IIIT Pets dataset, reporting Accuracy, Expected Calibration Error (ECE), and Sorted Calibration Error (SCE). 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) | Oxford-IIIT Pets | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [ECE](): Lower is better; unit: PERCENT. - [SCE](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DynaPrompt+C-TPT | 88.61 | Not recorded | 69f433c455a3c32af89fd373 | | DynaPrompt+O-TPT | 88.55 | Not recorded | 69f433c455a3c32af89fd373 | | DynaPrompt+FPP | 88.36 | Not recorded | 69f433c455a3c32af89fd373 | | DynaPrompt (Paper) | 88.28 | Not recorded | 69f433c455a3c32af89fd373 | | C-TPT | 88.2 | Not recorded | 69f433c455a3c32af89fd373 | | CLIP | 88 | Not recorded | 69f433c455a3c32af89fd373 | | O-TPT | 87.95 | Not recorded | 69f433c455a3c32af89fd373 | | DynaPrompt (Replication) | 87.71 | Not recorded | 69f433c455a3c32af89fd373 | | FPP | 87.3 | Not recorded | 69f433c455a3c32af89fd373 | | TPT | 87.1 | Not recorded | 69f433c455a3c32af89fd373 | ### DynaPrompt+C-TPT Accuracy: 88.61. Result ID: 69f463ac47f34ce924da5190. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"CLIP-ViT/B16","Framework":"DynaPrompt","Hard Prompt":"a photo of a"}. This record does not assert independent reproduction. ### DynaPrompt+O-TPT Accuracy: 88.55. Result ID: 69f463ac47f34ce924da5191. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"CLIP-ViT/B16","Framework":"DynaPrompt","Hard Prompt":"a photo of a"}. This record does not assert independent reproduction. ### DynaPrompt+FPP Accuracy: 88.36. Result ID: 69f463ac47f34ce924da5192. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"CLIP-ViT/B16","Framework":"DynaPrompt","Hard Prompt":"a photo of a"}. This record does not assert independent reproduction. ### DynaPrompt (Paper) Accuracy: 88.28. Result ID: 69f463ac47f34ce924da518e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"CLIP-ViT/B16","Framework":"DynaPrompt","Hard Prompt":"a photo of a"}. This record does not assert independent reproduction. ### C-TPT Accuracy: 88.2. Result ID: 69f463ac47f34ce924da51f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Venue":"ICLR 2024","Backbone":"CLIP-ViT/B16","Framework":"TPT","Prompt Template":"a photo of a"}. This record does not assert independent reproduction. ### CLIP Accuracy: 88. Result ID: 69f463ac47f34ce924da51ee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Venue":"ICML 2021","Backbone":"CLIP-ViT/B16","Framework":"TPT","Prompt Template":"a photo of a"}. This record does not assert independent reproduction. ### O-TPT Accuracy: 87.95. Result ID: 69f463ac47f34ce924da51f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Venue":"CVPR 2025","Backbone":"CLIP-ViT/B16","Framework":"TPT","Prompt Template":"a photo of a"}. This record does not assert independent reproduction. ### DynaPrompt (Replication) Accuracy: 87.71. Result ID: 69f463ac47f34ce924da518f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"CLIP-ViT/B16","Framework":"DynaPrompt","Hard Prompt":"a photo of a"}. This record does not assert independent reproduction. ### FPP Accuracy: 87.3. Result ID: 69f463ac47f34ce924da51f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Venue":"CVPR 2026","Backbone":"CLIP-ViT/B16","Framework":"TPT","Prompt Template":"a photo of a"}. This record does not assert independent reproduction. ### TPT Accuracy: 87.1. Result ID: 69f463ac47f34ce924da51ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Venue":"NeurIPS 2022","Backbone":"CLIP-ViT/B16","Framework":"TPT","Prompt Template":"a photo of a"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.