# Imagenet Zoom Classification Eval

> Evaluates image classification models' accuracy on standard and out-of-distribution datasets. It specifically probes the impact of spatial zooming and foreground/background signal separation on model performance, revealing how much background cues contribute to classification accuracy. Use when the user wants to benchmark on ImageNet, ImageNet-A, ObjectNet, or asks about evaluating this task. Reports top-1 accuracy.

- Skill: `qhjqhj00/imagenet-zoom-classification-eval` (Agent Skill)
- Install (CLI): `npx skillmds add qhjqhj00/imagenet-zoom-classification-eval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qhjqhj00/imagenet-zoom-classification-eval/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: qhjqhj00 (https://skillmd.com/u/qhjqhj00)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/qhjqhj00/imagenet-zoom-classification-eval

---


# imagenet-zoom-classification-eval

> ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification — Taesiri et al. (2023) (arXiv:2304.05538, 2023)

## What this evaluates

Evaluates image classification models' accuracy on standard and out-of-distribution datasets. It specifically probes the impact of spatial zooming and foreground/background signal separation on model performance, revealing how much background cues contribute to classification accuracy.

## Datasets

- **ImageNet** — total ?; splits: test (-1)
- **ImageNet-A** — total ?; splits: test (-1)
- **ObjectNet** — total ?; splits: test (-1)

## Metrics

- `top-1 accuracy` **(primary)** — range: percent
  - Percentage of correctly predicted class labels out of the total number of test instances.
- `Mann-Whitney U test p-value` — range: [0, 1]
  - Non-parametric statistical test used to determine if there is a significant difference in the distribution of object counts between two datasets.

## Input / output format

**Input**: RGB images (original resolution or resized) fed into a pretrained vision classifier.

**Output**: Class label predictions (top-1) or aggregated accuracy scores across multiple zoom crops.

## Scoring recipe

```python
def compute_top1_accuracy(predictions, gold_labels):
    correct = sum(1 for p, g in zip(predictions, gold_labels) if p == g)
    return (correct / len(gold_labels)) * 100
```

## Common pitfalls

- Models heavily rely on background cues; masking background (BGSet) drastically drops accuracy, so standard ImageNet evaluation can overestimate robustness to spatial bias.
- Zoom-based test-time augmentation requires searching over multiple crop scales/positions; using a single 1-crop baseline significantly underestimates the model's potential accuracy.

## Evidence (verbatim from paper)

> Table A8: ImageNet classification from object-only and background-only signals. Numbers show the maximum possible top-1 accuracy (%) using zoom-based transforms for minimum set covers in Appendix B.4. We discover that background signals potentially hold significance for image classification.

## Citation

```bibtex
@misc{taesiri2023imagenethard,
  title={ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification},
  author={Taesiri et al. (2023)},
  year={2023},
  note={arXiv:2304.05538}
}
```

- arXiv: 2304.05538