Dataset Augmentation with Synthetic Images Improves Semantic Segmentation
Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock for further improvements. We show that augmentation of the weakly annotated training dataset with synthetic images minimizes both the annotation efforts and also the cost of capturing images with sufficient variety. Evaluation on the PASCAL 2012 validation dataset shows an increase in mean IOU from 52.80% to 55.47% by adding just 100 synthetic images per object class. Our approach is thus a promising solution to the problems of annotation and dataset collection.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic SegmentationSimilar Papers 제목 키워드 기반
ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation
Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception task…
Data Augmentationimage-classificationImage Classificationobject-detection+3Generative Synthetic Augmentation using Label-to-Image Translation for Nuclei Image Segmentation
In medical image diagnosis, pathology image analysis using semantic segmentation becomes important for efficient screening as a field of digital pathology. The spatial augmentation is ordinary used for semantic segmentat…
Image SegmentationSegmentationSemantic SegmentationTranslationEnhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance
Data augmentation is crucial for pixel-wise annotation tasks like semantic segmentation, where labeling requires significant effort and intensive labor. Traditional methods, involving simple transformations such as rotat…
Data AugmentationSegmentationSemantic SegmentationFew-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks
Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a light…
Synthetic Data GenerationData AugmentationR&D: Balancing Reliability and Diversity in Synthetic Data Augmentation for Semantic Segmentation
Collecting and annotating datasets for pixel-level semantic segmentation tasks are highly labor-intensive. Data augmentation provides a viable solution by enhancing model generalization without additional real-world data…
Semantic SegmentationData Augmentation