> For the complete documentation index, see [llms.txt](https://docs.unitlab.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.unitlab.ai/documentation/auto-labeling/find-similar.md).

# Find Similar

Use one verified box, polygon, mask, or cuboid to find and review similar objects in the current image or frame.

Find Similar turns one verified object into a reviewed set of visually related proposals. It is designed for dense, repetitive scenes such as products, crops, cells, components, people, or vehicles.

![Magic Touch selects one object and Find Similar proposes matching instances](https://292810646-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FGjVLUz4wthGkGlRKM6rM%2Fuploads%2FrCcVkvXnwXbKswXGmGDP%2Fauto-labeling-detect-and-similar.avif?alt=media)

### What Find Similar does

Find Similar is a contextual Workbench action. It appears after you select a compatible object and searches the **current image or current video frame**. It does not search an entire dataset.

| Seed geometry     | Proposal geometry | Supported |
| ----------------- | ----------------- | --------- |
| Bounding box      | Bounding box      | Yes       |
| Polygon           | Polygon           | Yes       |
| Segmentation mask | Segmentation mask | Yes       |
| Cuboid / 3D box   | Cuboid / 3D box   | Yes       |

The current experience exposes a confidence threshold, removes strong overlaps with committed annotations, and holds new results as pending proposals. Use **Clear** to discard the proposal set or **Accept all** after review.

{% hint style="info" %}
Find Similar is example-driven. [Prompt Labeling](/documentation/auto-labeling/prompt-labeling.md) is text-driven. Both produce proposals, but they solve different discovery problems.
{% endhint %}

### Before you start

* Choose a seed that is correctly classified and tightly annotated.
* Prefer a clear, representative instance rather than a heavily occluded edge case.
* Confirm repeated objects are visually similar enough for example-based retrieval.
* Zoom so the seed boundary can be inspected before search.
* Read the project policy for duplicates, partial objects, and minimum visible area.

### Find repeated objects

{% stepper %}
{% step %}

#### Create or select the seed

Draw a box, polygon, mask, or cuboid around one representative instance. Select the finished object in the canvas or Objects panel.
{% endstep %}

{% step %}

#### Start Find Similar

Choose **Find Similar** from the contextual header action. If it is missing, verify the seed geometry is supported and the object is selected.
{% endstep %}

{% step %}

#### Tune confidence

Start with a conservative threshold. Lower it when recall is too low; raise it when unrelated candidates dominate.
{% endstep %}

{% step %}

#### Inspect pending proposals

Review the complete canvas, not only the area around the seed. Compare each proposal with the class definition and check overlap with existing annotations.
{% endstep %}

{% step %}

#### Accept or clear

Choose **Accept all** only when the set is appropriate. Otherwise clear the set, improve the seed or threshold, and run again.
{% endstep %}

{% step %}

#### Finish annotation QA

Correct boundaries, complete required properties, and submit through the configured workflow.
{% endstep %}
{% endstepper %}

### Current auto-labeling demo

{% embed url="<https://homepage-files.s3.us-east-2.amazonaws.com/hero-videos/hero/auto-labeling-2.mp4>" %}

*Live Unitlab demo used on the Video Annotation product page. The result remains editable and reviewable in the Workbench.*

### Threshold strategy

| Result pattern                          | Adjustment                                                          |
| --------------------------------------- | ------------------------------------------------------------------- |
| Many false positives                    | Raise confidence or choose a more distinctive seed                  |
| Similar objects are missed              | Lower confidence gradually and inspect the complete set             |
| One object receives duplicate proposals | Confirm the seed is committed and inspect overlap suppression       |
| Different states are mixed              | Use a more specific class or split the work by state/property       |
| Scale changes reduce recall             | Seed a second representative scale and review it as a separate pass |

### Review controls

For each proposal, verify:

* class and instance identity;
* geometry tightness or boundary precision;
* truncation and occlusion policy;
* duplicates and overlap with existing objects;
* required class properties;
* relations to other objects;
* consistency with nearby manually labeled examples.

{% hint style="warning" %}
Similarity is not semantic proof. A visually close result can still violate the ontology, and a valid instance can be visually different from the seed.
{% endhint %}

### When to use another tool

| Need                                                 | Better choice                                                                                     |
| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |
| Find objects from a natural-language concept         | [Prompt Labeling](/documentation/auto-labeling/prompt-labeling.md)                                |
| Detect all visible instances of the active class     | [Detect Anything](/documentation/auto-labeling/detect-anything-sam-1-sam-3.md)                    |
| Propagate the same instance through frames or slices | [Bidirectional Auto-Tracking](/documentation/auto-labeling/bidirectional-auto-tracking.md)        |
| Search across many assets                            | [Embeddings, similarity, and outliers](/documentation/data/embeddings-similarity-and-outliers.md) |
| Process a project population before human review     | [Batch Auto-Labeling](/documentation/auto-labeling/batch-auto-labeling.md)                        |

### Operational guidance

Find Similar does not consume the standard AI-inference quota in the current implementation. Treat that as an execution detail, not a reason to skip review. Measure accepted proposals and correction rate on a representative cohort before using it as a standard labeling step.