Data Augmentation for Object Detection via Progressive and Selective Instance-Switching

TL;DR

This paper introduces a novel data augmentation technique called Progressive and Selective Instance-Switching (PSIS) for object detection, which improves performance by generating more balanced and contextually coherent training data without external datasets.

Contribution

The paper proposes a new instance-switching augmentation method that preserves contextual coherence and addresses class imbalance and importance, enhancing object detection models.

Findings

PSIS improves detection accuracy on MS COCO benchmark.

It outperforms several state-of-the-art detectors.

The method is effective without external datasets.

Abstract

Collection of massive well-annotated samples is effective in improving object detection performance but is extremely laborious and costly. Instead of data collection and annotation, the recently proposed Cut-Paste methods [12, 15] show the potential to augment training dataset by cutting foreground objects and pasting them on proper new backgrounds. However, existing Cut-Paste methods cannot guarantee synthetic images always precisely model visual context, and all of them require external datasets. To handle above issues, this paper proposes a simple yet effective instance-switching (IS) strategy, which generates new training data by switching instances of same class from different images. Our IS naturally preserves contextual coherence in the original images while requiring no external dataset. For guiding our IS to obtain better object performance, we explore issues of instance imbalance and class importance in datasets, which frequently occur and bring adverse effect on detection performance. To this end, we propose a novel Progressive and Selective Instance-Switching (PSIS) method to augment training data for object detection. The proposed PSIS enhances instance balance by combining selective re-sampling with a class-balanced loss, and considers class importance by progressively augmenting training dataset guided by detection performance. The experiments are conducted on the challenging MS COCO benchmark, and results demonstrate our PSIS brings clear improvement over various state-of-the-art detectors (e.g., Faster R-CNN, FPN, Mask R-CNN and SNIPER), showing the superiority and generality of our PSIS. Code and models are available at: https://github.com/Hwang64/PSIS.