Decoupled Prototype Matching with Vision Foundation Models for Few-Shot Industrial Object Detection

2026-04-29

AI Summary

This work addresses the challenge of few-shot object detection in industrial settings, where new objects are frequently introduced and labeled data are scarce. The authors propose a training-free detection method that leverages a vision foundation model to construct category prototypes from only a few reference images and integrates a segmentation model to generate region proposals. Detection is achieved through a decoupled prototype matching mechanism that enables efficient feature alignment. The approach allows rapid deployment for novel categories using just a handful of reference images, without requiring CAD models or large-scale annotations. Experiments on three industrial datasets demonstrate a 6.9% average precision (AP) improvement over the current best training-free methods, highlighting its strong practical potential.

Abstract

Industrial object detection systems typically rely on large annotated datasets, which are expensive to collect and challenging to maintain in industrial scenarios where the inventory of objects changes frequently. This work addresses the challenge of few-shot object detection in such industrial scenarios, where only a limited number of labeled samples are available for newly introduced objects. We present a detection framework that leverages vision foundation models to recognize objects with minimal supervision. The method constructs class prototypes from a small set of reference samples by extracting feature representations. For a given query scene during inference, object regions are generated using a segmentation model, and feature embeddings are extracted and matched with class prototypes using similarity matching. We evaluate the detection method on three established industrial datasets from the Benchmark for 6D Object Pose Estimation benchmark following the official 2D object detection evaluation protocol. We demonstrate competitive detection performance, improving AP by 6.9% compared to the state-of-the-art training-free detection methods. Furthermore, the presented method is able to onboard new objects using only a few reference images, without requiring any CAD models or large annotated datasets. These properties make the approach well-suited for real-world industrial applications.

Problem

• few-shot object detection
• industrial object detection
• limited labeled data
• new object onboarding

Innovation

• few-shot object detection
• vision foundation models
• prototype matching
• industrial object detection
• training-free detection