TECHNIQUE
Computer Vision
| Name | Kind | When | Maturity |
|---|---|---|---|
| timm (PyTorch Image Models) | library | fine-tuning a proven pretrained backbone on a labeled dataset is the whole job | commodity |
| Zero-shot VLM classification (CLIP/SigLIP) | pattern | no labeled data yet; class names as text prompts deliver a working baseline | established |
| Managed vision AutoML (Vertex AI / Azure Custom Vision) | service | no ML team owns the model; labeled images in, hosted endpoint out | established |
No published applications observed using this technique yet.
Teardown coverage accrues forward — the taxonomy is the map, the count is the honest state of it.
Back to the technique map