Checkpoints for DINO-QPM, from the paper DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification (CVPR Workshops 2026, paper, arXiv:2604.07166). Code: github.com/RobertZimm/DINO-QPM. Archived on Zenodo: doi:10.5281/zenodo.24194857.
DINO-QPM is a lightweight interpretability adapter on top of a frozen DINOv2 backbone. An MLP maps each patch embedding to 512 features, which are average-pooled, and a sparse, binary QPM layer selects 50 of them and assigns 5 to each class. Every class is thus explained by 5 features that can be localised in the image.
The checkpoints behind the paper's tables were not kept. These models were retrained with the same architecture, losses and hyperparameters as in the paper, with three differences:
They were trained with our internal training code, a successor of the public repository. Their accuracy was re-computed with the public repository and matches the values logged at training time exactly.
Top-1 test accuracy (%), mean ± standard deviation over 5 seeds:
| Model | CUB-200-2011 | Stanford Cars |
|---|---|---|
| DINO-QPM (fine-tuned), released | 88.4 ± 0.3 | 93.7 ± 0.1 |
| DINO-QPM (fine-tuned), paper | 88.3 ± 0.3 | 94.0 ± 0.2 |
| Dense model, released | 80.7 ± 0.3 | 91.7 ± 0.2 |
| Dense model, paper | 78.1 ± 0.3 | 92.9 ± 0.1 |
Per seed:
| Seed | CUB dense | CUB fine-tuned | Cars dense | Cars fine-tuned |
|---|---|---|---|---|
| 2847391 | 81.0 | 88.3 | 91.8 | 93.7 |
| 3748291 | 80.9 | 88.9 | 91.4 | 93.7 |
| 5647382 | 80.2 | 88.1 | 91.6 | 93.8 |
| 6190452 | 80.6 | 88.4 | 91.9 | 93.6 |
| 9182736 | 80.6 | 88.1 | 91.6 | 93.4 |
Interpretability metrics (%) of the fine-tuned models, computed with this repository (--eval-mode cub_segmentation_overlap class_independence contrastiveness diversity; Plausibility is CUBSegmentationOverlap_gradcam_dilated, CUB only), mean ± standard deviation over 5 seeds:
| Model | Plausibility CUB | SID@5 CUB | SID@5 Cars | Class-Indep. CUB | Class-Indep. Cars | Contrast. CUB | Contrast. Cars |
|---|---|---|---|---|---|---|---|
| DINO-QPM, released | 97.1 ± 0.2 | 92.0 ± 0.3 | 94.0 ± 0.1 | 93.9 ± 0.1 | 93.7 ± 0.1 | 99.8 ± 0.0 | 99.8 ± 0.0 |
| DINO-QPM, paper | 95.0 ± 0.6 | 90.1 ± 0.0 | 91.7 ± 0.2 | 93.7 ± 0.1 | 93.7 ± 0.1 | 100.0 ± 0.0 | 100.0 ± 0.0 |
20 checkpoints: 2 datasets × 5 seeds × 2 stages.
cub/ CUB-200-2011 (200 classes)
cars/ Stanford Cars (196 classes)
└── seed_<seed>/
├── dense/ dense model (512 features, all used by every class)
│ ├── model.safetensors
│ └── config.yaml
└── finetune/ DINO-QPM (50 selected features, 5 per class)
├── model.safetensors
└── config.yaml
backbone/dinov2_vitb14_reg4_pretrain.pth copy of Meta's DINOv2 weights (Hugging Face only)
model.safetensors holds the adapter only (~44 MB); the frozen DINOv2 ViT-B/14 backbone with registers is loaded separately. The fine-tuned files also hold the QPM feature selection (linear.selection). The header metadata records dataset, seed and stage.config.yaml is the configuration the model was trained with (machine-specific settings removed).<dataset>/SHA256SUMS lists the checksums of all files of a dataset.backbone/ is an unmodified copy of dinov2_vitb14_reg4_pretrain.pth from facebookresearch/dinov2 (Apache-2.0). The code uses it only if the download from Meta fails.Install the code (pip install -e . in the repository), then:
python main.py evaluate --pretrained cub/2847391/finetune --eval-mode accuracy
python main.py inference --pretrained cars/2847391 --image-path my_car.jpg
from dino_qpm.hub import load_pretrained
model, config = load_pretrained("cub", seed=2847391, stage="finetune")
The datasets are needed for evaluation only; see the repository README for the setup. A downloaded file can also be passed directly: python main.py evaluate --model-path cub/seed_2847391/finetune/model.safetensors.
| Dense | Fine-tuning | |
|---|---|---|
| Epochs | 10 | 25 |
| Batch size | 32 | 16 |
| Optimiser | AdamW (schedule-free) | AdamW (schedule-free) |
| Learning rate | 1e-3 | 5e-3 |
| Weight decay | 7e-4 | 8e-4 |
| Dropout (final layer) | 0.2 | 0 |
| Feature diversity loss λ_div | 0.5 | 1 |
| L1 on feature maps / feature vector | 0 / 0 | 5 / 1 |
Backbone: DINOv2 ViT-B/14 with 4 registers, frozen, 224 × 224 input. MLP adapter: 4 layers, hidden size 2048, batch norm, ReLU, 512 output features, applied per patch token, average pooling. QPM: 50 features, 5 per class, solved with Gurobi (MIP gap 0.5 %, time limit 3 h). Seeds: 2847391, 3748291, 5647382, 6190452, 9182736. Hardware: one NVIDIA GPU per run.
Apache License 2.0; copyright notice in NOTICE. The models build on DINOv2 (Apache-2.0) and were trained on CUB-200-2011 and Stanford Cars, which have their own terms of use for research.
@inproceedings{zimmermann2026dino-qpm,
title = {{DINO-QPM}: Adapting Visual Foundation Models for Globally Interpretable Image Classification},
author = {Zimmermann, Robert and Norrenbrock, Thomas and Rosenhahn, Bodo},
booktitle = {2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
year = {2026}
}
backbone/dinov2_vitb14_reg4_pretrain.pth 346 MBcub/seed_2847391/dense/model.safetensors 45 MBcub/seed_3748291/dense/model.safetensors 45 MBcub/seed_5647382/dense/model.safetensors 45 MBcub/seed_6190452/dense/model.safetensors 45 MBcub/seed_9182736/dense/model.safetensors 45 MBcars/seed_2847391/dense/model.safetensors 45 MBcars/seed_3748291/dense/model.safetensors 45 MBcars/seed_5647382/dense/model.safetensors 45 MBcars/seed_6190452/dense/model.safetensors 45 MBcars/seed_9182736/dense/model.safetensors 45 MBcub/seed_2847391/finetune/model.safetensors 44 MBcub/seed_3748291/finetune/model.safetensors 44 MBcub/seed_5647382/finetune/model.safetensors 44 MBcub/seed_6190452/finetune/model.safetensors 44 MBcub/seed_9182736/finetune/model.safetensors 44 MBcars/seed_2847391/finetune/model.safetensors 44 MBcars/seed_3748291/finetune/model.safetensors 44 MBcars/seed_5647382/finetune/model.safetensors 44 MBcars/seed_6190452/finetune/model.safetensors 44 MBcars/seed_9182736/finetune/model.safetensors 44 MB