Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/EVA-CLIP-18B

EVA-CLIP-18B

Reported on 8 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

Zero-Shot Transfer Image ClassificationonSUN
Accuracy· 2024-02-06
77.7
SOTA
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252
Zero-Shot Transfer Image ClassificationonImageNet V2
Accuracy (Private)· 2024-02-06
77.9
best: 81.2 (BASIC (Lion))
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252
Zero-Shot Transfer Image ClassificationonImageNet-A
Accuracy (Private)· 2024-02-06
87.3
best: 90.2 (CoCa)
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252
Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· 2024-02-06
83.8
best: 88.5 (M2-Encoder)
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252
Zero-Shot Transfer Image ClassificationonImageNet-R
Accuracy· 2024-02-06
95.7
best: 96.8 (BASIC (Lion))
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252
Zero-Shot Transfer Image ClassificationonFood-101
Top 1 Accuracy· 2024-02-06
95.8
best: 96.2 (MAWS (ViT-2B))
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252
Zero-Shot Transfer Image ClassificationonObjectNet
Accuracy (Private)· 2024-02-06
82.2
best: 87.6 (LiT-22B)
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252
Zero-Shot Transfer Image ClassificationonImageNet-Sketch
Accuracy (Private)· 2024-02-06
74.7
best: 77.6 (CoCa)
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters arXiv:2402.04252