README.md

---
language:
- en
base_model:
- openai/clip-vit-large-patch14
tags:
- memorability
- computer_vision
- perceptual_tasks
- CLIP
- LaMem
- THINGS
---
# Don’t Judge Before You CLIP: Memorability Prediction Model

PreceptCLIP-Memorability is a model designed to predict image memorability (the likelihood of an image to be remembered). This is the official model from the paper ["Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks"](https://arxiv.org/abs/2503.13260). Our model applies LoRA adaptation on the CLIP visual encoder with an additional MLP head to achieve state-of-the-art results.

## Training Details

- *Dataset*: [LaMem](http://memorability.csail.mit.edu/download.html) (Large-Scale Image Memorability)
- *Architecture*: CLIP Vision Encoder (ViT-L/14) with *LoRA adaptation*
- *Loss Function*: Mean Squared Error (MSE) Loss for memorability prediction
- *Optimizer*: AdamW
- *Learning Rate*: 5e-05
- *Batch Size*: 32

## Usage

To use the model for inference:

```python
from torchvision import transforms
import torch
from PIL import Image
from huggingface_hub import hf_hub_download
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Load model
model_path = hf_hub_download(repo_id="PerceptCLIP/PerceptCLIP_Memorability", filename="perceptCLIP_Memorability.pth")
model = torch.load(model_path).to(device).eval()

# Load an image
image = Image.open("image_path.jpg").convert("RGB")

# Preprocess and predict
def Mem_preprocess():
    transform = transforms.Compose([
        transforms.Resize(224),
        transforms.CenterCrop(size=(224, 224)),  
        transforms.ToTensor(),
        transforms.Normalize(mean=(0.48145466, 0.4578275, 0.40821073), 
                             std=(0.26862954, 0.26130258, 0.27577711))
    ])
    return transform

image = Mem_preprocess()(image).unsqueeze(0).to(device)

with torch.no_grad():
    mem_score = model(image).item()

print(f"Predicted Memorability Score: {mem_score:.4f}")