---
license: apache-2.0
tags:
- pytorch
- image-classification
- robust-representation
- modular-ai
- dynamic-masking
- dinov2
- ifam
arxiv: 2506.08915
library_name: generic
---

# iFAM (imagenet-k1) Model Checkpoint

This is the official pre-trained checkpoint of the **iFAM (Inherently Faithful Attention Maps for Vision Transformers)** framework, proposed in the paper **"Two-stage Vision Transformers and Hard Masking offer Robust Object Representations"** (accepted as an oral presentation at ICPR 2026).

- **Paper:** [Two-stage Vision Transformers and Hard Masking offer Robust Object Representations](https://arxiv.org/abs/2506.08915)
- **Repository:** [GitHub - ananthu-aniraj/ifam](https://github.com/ananthu-aniraj/ifam)

## Model Description
iFAM model trained on the ImageNet-1K dataset with 1 part (K=1).

The iFAM framework is a two-stage approach:
1. **Stage 1 (Selector):** Processes the full image to discover object parts and identify task-relevant regions.
2. **Stage 2 (Predictor):** Restricts its receptive field to the selected regions using input attention masking, preventing spurious background details from affecting the classification.

## Usage

To use this model, ensure you have the `ifam` repository cloned and the dependencies installed. You can load this model directly from the Hugging Face Hub:

```python
import torch
import sys
# Append the path to the ifam repository
sys.path.append("/path/to/ifam")

from models import FullTwoStageModelDoubleClassify

# Load the model directly from Hugging Face Hub
model = FullTwoStageModelDoubleClassify.from_pretrained("ananthu-aniraj/ifam-imagenet-k1")
model.eval()

# Example: Run inference
# x = torch.rand(1, 3, 224, 224)
# with torch.no_grad():
#     outputs = model(x)
```

## Citation
If you use this model in your research, please cite:
```bibtex
@inproceedings{aniraj2026ifam,
  title={Two-stage Vision Transformers and Hard Masking offer Robust Object Representations},
  author={Aniraj, Ananthu and Dantas, Cassio F. and Ienco, Dino and Marcos, Diego},
  booktitle={International Conference on Pattern Recognition (ICPR)},
  year={2026}
}
```