paper-with-me

홈 › Papers

ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation

2021-01-30 · Jiawei Zhang, Yanchun Zhang, Xiaowei Xu

Semantic image segmentation aims to obtain object labels with precise boundaries, which usually suffers from overfitting. Recently, various data augmentation strategies like regional dropout and mix strategies have been proposed to address the problem. These strategies have proved to be effective for guiding the model to attend on less discriminative parts. However, current strategies operate at the image level, and objects and the background are coupled. Thus, the boundaries are not well augmented due to the fixed semantic scenario. In this paper, we propose ObjectAug to perform object-level augmentation for semantic image segmentation. ObjectAug first decouples the image into individual objects and the background using the semantic labels. Next, each object is augmented individually with commonly used augmentation methods (e.g., scaling, shifting, and rotation). Then, the black area brought by object augmentation is further restored using image inpainting. Finally, the augmented objects and background are assembled as an augmented image. In this way, the boundaries can be fully explored in the various semantic scenarios. In addition, ObjectAug can support category-aware augmentation that gives various possibilities to objects in each category, and can be easily combined with existing image-level augmentation methods to further boost performance. Comprehensive experiments are conducted on both natural image and medical image datasets. Experiment results demonstrate that our ObjectAug can evidently improve segmentation performance.

📄 PDF Abstract BibTeX arXiv:2102.00221

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationImage InpaintingImage SegmentationObjectSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Cut to the Mix: Simple Data Augmentation Outperforms Elaborate Ones in Limited Organ Segmentation Datasets

2026-02-03 · Chang Liu, Fuxin Fan, Annette Schwarz, Andreas Maier arxiv

Multi-organ segmentation is a widely applied clinical routine and automated organ segmentation tools dramatically improve the pipeline of the radiologists. Recently, deep learning (DL) based segmentation models have show…

Data Augmentation

SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation

2024-01-01 · CVPR 2024 1 · Yanjie Wang, Xu Zou, Luxin Yan, Sheng Zhong 외

Once only a few-shot annotated samples are available the performance of learning-based object detection would be heavily dropped. Many few-shot object detection (FSOD) methods have been proposed to tackle this issue …

Data AugmentationDiversityFew-Shot Object DetectionObject+5

Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation

2025-07-30 · Hongbin Lin, Yifan Jiang, Juangui Xu, Jesse Jiaxi Xu 외 arxiv

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale…

Point Cloud SegmentationScene SegmentationData AugmentationScene Generation

Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation

2021-03-02 · ICCV 2021 10 · Yukun Su, Ruizhou Sun, Guosheng Lin, Qingyao Wu

Data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challe…

Data AugmentationObjectSemantic SegmentationWeakly supervised Semantic Segmentation+1

Dataset Enhancement with Instance-Level Augmentations

2024-06-12 · Orest Kupyn, Christian Rupprecht

We present a method for expanding a dataset by incorporating knowledge from the wide distribution of pre-trained latent diffusion models. Data augmentations typically incorporate inductive biases about the image formatio…

Data AugmentationObjectobject-detectionObject Detection+2