MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
MobileCLIP was introduced in MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training (CVPR 2024), by Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel.
This repository contains the MobileCLIP-B (LT) checkpoint for timm.
Highlights
- Our smallest variant
MobileCLIP-S0obtains similar zero-shot performance as OpenAI's ViT-B/16 model while being 4.8x faster and 2.8x smaller. MobileCLIP-S2obtains better avg zero-shot performance than SigLIP's ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples.MobileCLIP-B(LT) attains zero-shot ImageNet performance of 77.2% which is significantly better than recent works like DFN and SigLIP with similar architectures or even OpenAI's ViT-L/14@336.
Checkpoints
| Model | # Seen Samples (B) | # Params (M) (img + txt) | Latency (ms) (img + txt) | IN-1k Zero-Shot Top-1 Acc. (%) | Avg. Perf. (%) on 38 datasets |
|---|---|---|---|---|---|
| MobileCLIP-S0 | 13 | 11.4 + 42.4 | 1.5 + 1.6 | 67.8 | 58.1 |
| MobileCLIP-S1 | 13 | 21.5 + 63.4 | 2.5 + 3.3 | 72.6 | 61.3 |
| MobileCLIP-S2 | 13 | 35.7 + 63.4 | 3.6 + 3.3 | 74.4 | 63.7 |
| MobileCLIP-B | 13 | 86.3 + 63.4 | 10.4 + 3.3 | 76.8 | 65.2 |
| MobileCLIP-B (LT) | 36 | 86.3 + 63.4 | 10.4 + 3.3 | 77.2 | 65.8 |