---
language:
  - en
license: cc-by-sa-4.0
library_name: transformers
tags:
  - image-similarity
  - image-retrieval
  - computer-vision
  - e-commerce
  - dinov2
  - gem-pooling
  - pytorch
  - safetensors
datasets:
  - e-commerce-product-images
pipeline_tag: feature-extraction
base_model: Trendyol/trendyol-dino-v2-ecommerce-256d
---

# Trendyol DinoV2.1 Image Similarity Model

Fine-tuned DinoV2 (ViT-B/14) with **[GeM pooling](https://arxiv.org/abs/1711.02512)** for e-commerce product image retrieval.
This is the successor to [`Trendyol/trendyol-dino-v2-ecommerce-256d`](https://huggingface.co/Trendyol/trendyol-dino-v2-ecommerce-256d).

**Paper:** TBD — *"Visual Search at Trendyol"* (in review)

## Model Details

- **Model Type**: Image Similarity / Retrieval
- **Architecture**: DinoV2 ViT-B/14 + [GeM pooling](https://arxiv.org/abs/1711.02512) + linear projection (ArcFace-trained)
- **Embedding Dimension**: 256
- **Input Size**: 224×224
- **Checkpoint**: `ray-dinov2-full_catalog_1000_20-pfc-gem-mlp-run_12` epoch **09**
- **Framework**: PyTorch / SafeTensors

## What's new vs v2

| | v2 | **v2.1** |
|---|---|---|
| Pooling / head | Flatten spatial tokens → Linear(196608→256) | **[GeM](https://arxiv.org/abs/1711.02512)** → Linear(768→256) |
| Training data | 300 distinct products per ~3400 categories | 1000 distinct products per ~3400 categories |
| Preprocess | Lanczos/JPEG/332 pad pipeline | Scale+pad to 224 (training inference preprocess) |

## Quick Start

```python
import torch
from PIL import Image
from transformers import AutoModel, AutoImageProcessor

device = "cuda" if torch.cuda.is_available() else "cpu"
repo = "Trendyol/trendyol-dino-v2.1-ecommerce-256d"

processor = AutoImageProcessor.from_pretrained(repo, trust_remote_code=True)
model = AutoModel.from_pretrained(repo, trust_remote_code=True).to(device).eval()

image = Image.open("your_image.jpg").convert("RGB")
inputs = processor(images=image, return_tensors="pt")
inputs = {k: v.to(device) for k, v in inputs.items()}

with torch.no_grad():
    embeddings = model(**inputs).last_hidden_state  # [1, 256]

print(embeddings.shape)
```

## Preprocessing Pipeline

1. **ScaleImage**: resize so max side = 224 (keep aspect ratio)
2. **PadToSquare**: pad with color 255
3. **Resize**: 224×224
4. **ToTensor** + **ImageNet Normalize** (mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

## Installation

```bash
pip install transformers torch torchvision safetensors pillow numpy
```

## Intended Use

- Product image similarity search
- Visual recommendations / duplicate detection
- Content-based retrieval in e-commerce

## Limitations

- Optimized for product / e-commerce images
- Requires `trust_remote_code=True`
- Classification heads from training are **not** included in this Hub export (embeddings only)

## License

See [LICENSE](LICENSE). Same terms as the v2 release: source-available; commercial use requires attribution and prior notification to Trendyol (`scr.datascience@trendyol.com`).

## Citation

```
@misc{trendyol-dinov2-ecommerce-v21,
  title={Trendyol DinoV2.1 E-commerce Image Similarity Model},
  author={Trendyol Data Science Team},
  year={2026},
  url={https://huggingface.co/Trendyol/trendyol-dino-v2.1-ecommerce-256d}
}

@article{radenovic2018gem,
  title={Fine-tuning CNN Image Retrieval with No Human Annotation},
  author={Radenovi{\'c}, Filip and Tolias, Giorgos and Chum, Ond{\v{r}}ej},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={41},
  number={7},
  pages={1655--1668},
  year={2018},
  doi={10.1109/TPAMI.2018.2846566},
  note={GeM pooling; also arXiv:1711.02512}
}

@misc{trendyol-visual-search-tbd,
  title={Visual Search at Trendyol},
  author={Trendyol Data Science Team},
  year={2026},
  note={Paper TBD (in review)}
}
```