Coreset Selection For Object Detection

Hojun Lee, Suyoung Kim, Jaeyoung Yoo, Nojun Kwak

Keywords: Coreset Selection, Object Detection, Submodular Function

TL;DR: a new method for selecting a most informative subset in an entire data for object detection

Abstract: Coreset selection is a method for selecting a small, representative subset of an entire dataset. It has been primarily researched in image classification, assuming there is only one object per image. However, coreset selection for object detection is more challenging as an image can contain multiple objects. As a result, much research has yet to be done on this topic. Therefore, we introduce a new approach, $\textit{\textbf{C}oreset \textbf{S}election for \textbf{O}bject \textbf{D}etection}$ (CSOD). CSOD generates imagewise and classwise representative feature vectors for multiple objects of the same class within each image. Subsequently, we adopt submodular optimization for considering both representativeness and diversity and utilize the representative vectors in the submodular optimization process to select a subset. When we evaluated our method on the Pascal VOC dataset, our method outperformed random selection by +6.8\%p in AP$_{50}$ when selecting only 200 images.

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4748