Fine-Grained Image Classification on FGVC Suite (Zero-Shot)
81Avg AccuracyViT-L/14 Sparse
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| ViT-L/14 SparseSparsity=0.66%, Evaluation=Zero-shot2026.01 | 81 | 94 | 79 | 93.1 | 92 | 53.7 | 74 | — | — | |
| ViT-L/14 baselineSparsity=100%, Evaluation=Zero-shot2026.01 | 80.4 | 93.4 | 79.2 | 93.1 | 92 | 50.8 | 74.2 | — | — | |
| ViT-L/14 Sparse+Sparsity=0.47%, Evaluation=Zero-shot2026.01 | 79.9 | 94 | 78.1 | 92.9 | 91.8 | 48.5 | 73.9 | — | — | |
| OpenAI ViT-B/32Sparsity=100%, Evaluation=Zero-shot2026.01 | 71.1 | 85.5 | 73.3 | 89.6 | 86.1 | 24.6 | 67.8 | — | — | |
| Prisma ViT-B/32 cls@11Sparsity=2.8%, Evaluation=Zero-shot2026.01 | 69.5 | 84.5 | 69.5 | 89.1 | 85 | 22.9 | 66 | — | — |