Learning to Find Common Objects Across Few Image Collections
This addresses the problem of few-shot common object recognition and object co-localization for computer vision researchers, presenting an incremental improvement with a faster inference method.
The paper tackles the problem of selecting one image from each bag in a collection such that all selected images belong to the same object class, modeling it as an energy minimization problem. The results show that learning the potential functions improves performance over existing methods, and the proposed greedy algorithm achieves comparable accuracy to state-of-the-art structured inference while being about 10 times faster.
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.