README.md

---
title: ProgResViT
emoji: 🪜
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.26.0
app_file: app.py
short_description: Adaptive-compute ViT that classifies in progressive rounds
python_version: "3.12"
startup_duration_timeout: 30m
license: mit
---

# ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers

Interactive ImageNet-1K demo of [ProgResViT](https://huggingface.co/papers/2609.03216)
(arXiv:2609.03216, Kiel University).

ProgResViT performs inference **progressively**. Round 1 processes a low-resolution
image with a narrow subnetwork (3 of 6 attention heads). If the round-1 prediction is
confident enough — measured by the entropy of its top-10 softmax — inference stops
there. Otherwise the model recycles the round-1 tokens and refines the prediction at a
higher input resolution with the full-width subnetwork. All rounds share a single
backbone, conditioned by **Progress-Conditioned Soft Gating (PSG)**.

The demo exposes that mechanism directly: it runs both rounds, shows each round's top-5
prediction, and reports which round the routing threshold would have stopped at, along
with the GMACs saved.

## Checkpoints

All four released DeiT-S checkpoints are available in the dropdown:

| Resolution schedule | Training | Top-1 | GMACs (full path) |
|---|---|---:|---:|
| 160 → 384 | KD | 84.90% | 16.152 |
| 160 → 384 | standard | 83.70% | 16.152 |
| 192 → 240 | KD | 83.80% | 6.267 |
| 192 → 240 | standard | 82.21% | 6.267 |

Weights: [NCPS on the Hub](https://huggingface.co/NCPS). Default routing thresholds are
the authors' reported operating points (≤0.03 pp top-1 drop).

## Implementation notes

- The ProgResViT model code is the authors' vendored `timm` fork, copied verbatim from
  [ds-kiel/ProgResViT](https://github.com/ds-kiel/ProgResViT) (MIT; `NOTICE` and
  `LICENSE-timm.txt` retained).
- Preprocessing matches `validate.py` upstream: bicubic resize with `crop_pct=0.9`,
  center crop to the checkpoint's eval resolution, ImageNet mean/std.
- Rounds are run with `model._forward_stage(...)` exactly as the upstream evaluator
  does, so both rounds are always computed and the routing decision is reported rather
  than short-circuited — that is what makes the trade-off visible.
- GMACs figures are the authors' measured values from `results/RESULTS.md`.

## Credits

Example photographs come from
[linoyts/repo-to-space-example-inputs](https://huggingface.co/datasets/linoyts/repo-to-space-example-inputs).

## Citation

```bibtex
@article{progresvit2026,
  title  = {ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers},
  year   = {2026},
  eprint = {2609.03216}
}
```