# Learning to Find Common Objects Across Few Image Collections

## TL;DR

This paper introduces a data-driven approach to identify common objects across multiple image collections by learning potential functions and employing a fast greedy inference algorithm, significantly improving efficiency and accuracy.

## Contribution

It proposes a novel method to learn unary and pairwise potentials for common object detection, along with a fast greedy inference algorithm, advancing few-shot recognition and co-localization tasks.

## Key findings

- Learning potential functions improves performance over existing methods.
- The greedy algorithm is ~10 times faster than traditional structured inference.
- Achieved competitive results on few-shot recognition and co-localization benchmarks.

## Abstract

Given a collection of bags where each bag is a set of images, our goal is to select one image from each bag such that the selected images are from the same object class. We model the selection as an energy minimization problem with unary and pairwise potential functions. Inspired by recent few-shot learning algorithms, we propose an approach to learn the potential functions directly from the data. Furthermore, we propose a fast greedy inference algorithm for energy minimization. We evaluate our approach on few-shot common object recognition as well as object co-localization tasks. Our experiments show that learning the pairwise and unary terms greatly improves the performance of the model over several well-known methods for these tasks. The proposed greedy optimization algorithm achieves performance comparable to state-of-the-art structured inference algorithms while being ~10 times faster. The code is publicly available on https://github.com/haamoon/finding_common_object.