# Fine-Grained Image Classification on FGVC Suite (Zero-Shot) Source: [Fine-Grained Image Classification on FGVC Suite (Zero-Shot)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:36:05.496Z Evaluation suite for Zero-Shot Fine-Grained Image Classification performance across multiple specialized datasets, including Foods-101, Flowers-Oxford, Pets-Oxford, Cars-Stanford, Aircrafts-FGVC, and SUN397. 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) | Fine-Grained Classification Suite zero-shot | | Metric | Avg Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Avg Accuracy](): Higher is better; unit: PERCENT. - [Accuracy (Foods-101)](): Higher is better; unit: PERCENT. - [Accuracy (Flowers-Oxford)](): Higher is better; unit: PERCENT. - [Accuracy (Pets-Oxford)](): Higher is better; unit: PERCENT. - [Accuracy (Cars-Stanford)](): Higher is better; unit: PERCENT. - [Accuracy (Aircrafts-FGVC)](): Higher is better; unit: PERCENT. - [Accuracy (SUN397)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (PGD)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (AutoAttack)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ViT-L/14 Sparse | 81 | Not recorded | 697ae972a2b28e761d87cf4a | | ViT-L/14 baseline | 80.4 | Not recorded | 697ae972a2b28e761d87cf4a | | ViT-L/14 Sparse+ | 79.9 | Not recorded | 697ae972a2b28e761d87cf4a | | OpenAI ViT-B/32 | 71.1 | Not recorded | 697ae972a2b28e761d87cf4a | | Prisma ViT-B/32 cls@11 | 69.5 | Not recorded | 697ae972a2b28e761d87cf4a | ### ViT-L/14 Sparse Avg Accuracy: 81. Result ID: 699784855698665ec4d975b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sparsity":"0.66%","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### ViT-L/14 baseline Avg Accuracy: 80.4. Result ID: 699784855698665ec4d975b0. [Reporting paper]() Recorded evaluation configuration: {"Sparsity":"100%","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### ViT-L/14 Sparse+ Avg Accuracy: 79.9. Result ID: 699784855698665ec4d975b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sparsity":"0.47%","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### OpenAI ViT-B/32 Avg Accuracy: 71.1. Result ID: 699784855698665ec4d975ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sparsity":"100%","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### Prisma ViT-B/32 cls@11 Avg Accuracy: 69.5. Result ID: 699784855698665ec4d975af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sparsity":"2.8%","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.