[KongchangAI]
Unverified50% confidenceFactExact time

Example-driven detection takes reference examples (such as cropped images with the target region annotated, or point prompts) as query inputs, and the model uses feature matching to locate regions in the image to be detected that are semantically similar to the example.

1
Sources
50%
Confidence
Long-term
Relevance
11/11/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1158570
API
curl https://kongchang.com/api/v1/knowledge/claims/1158570
MCP
get_claim(id=1158570)