Few-Shot Pattern Detection via Template Matching and Regression

Eunchan Jo, Dahyun Kang, Sanghyun Kim, Yunseon Choi, Minsu Cho

Keywords: Detection, Counting, Few-Shot Counting and Detection

Abstract:

We address the problem of few-shot pattern detection, which aims to detect all instances of a given pattern, typically represented by a few exemplars, from an input image.
Although similar problems have been studied in few-shot object counting and detection (FSCD), previous methods and their benchmarks have narrowed patterns of interest to object categories and often fail to localize non-object patterns.
In this work, we propose a simple yet effective detector based on template matching and regression, dubbed TMR.
While previous FSCD methods typically represent given target exemplars as a spatially collapsed prototype, losing their spatial structure, we revisit and refine classic template matching and regression.
It effectively preserves and leverages the spatial layout of exemplars through a minimalistic structure with only a few learnable convolutional or projection layers on top of a frozen backbone.
We also introduce a new dataset, dubbed RPINE, which covers a wider range of patterns than existing object-centric datasets.
Experiments on three benchmarks, RPINE, FSCD-147, FSCD-LVIS, demonstrate that our method outperforms recent state-of-the-art methods, showing an outstanding generalization ability on cross-dataset evaluation.

Submission Number: 20