paper-with-me

Papers

Sample-specific and Context-aware Augmentation for Long Tail Image Classification

2021-09-29 · Jiahao Chen, Bing Su

Recent long-tail classification methods generally adopt the two-stage pipeline and focus on learning the classifier to tackle the imbalanced data in the second stage via re-sampling or re-weighting, but the classifier is easily prone to overconfidence in head classes. Data augmentation is a natural way to tackle this issue. Existing augmentation methods either perform low-level transformations or apply the same semantic transformation for all samples. However, meaningful augmentations for different samples should be different. In this paper, we propose a novel sample-specific and context-aware augmentation learning method for long-tail image classification. We model the semantic within-class transformation range for each sample by a specific Gaussian distribution and design a semantic transformation generator (STG) to predict the distribution from the sample itself. To encode the context information accurately, STG is equipped with a memory-based structure. We train STG by constructing ground-truth distributions for samples of head classes in the feature space. We apply STG to samples of tail classes for augmentation in the classifier-tuning stage. Extensive experiments on four imbalanced datasets show the effectiveness of our method.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation

2025-10-01 · Suorong Yang, Jie Zong, Lihang Wang, Ziheng Qin 외 arxiv

Data augmentation has been widely employed to improve the generalization of deep neural networks. Most existing methods apply fixed or random transformations. However, we find that sample difficulty evolves along with th…

Data Augmentation

CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation

2026-04-21 · Nassim Sadallah, Mohand Saïd Allili arxiv

Reliable crack detection and segmentation are vital for structural health monitoring, yet the scarcity of well-annotated data constitutes a major challenge. To address this limitation, we propose a novel context-aware ge…

Crack SegmentationData Augmentation

Context-Aware Data Augmentation for LIDAR 3D Object Detection

2022-11-20 · Xuzhong Hu, Zaipeng Duan, Jie Ma

For 3D object detection, labeling lidar point cloud is difficult, so data augmentation is an important module to make full use of precious annotated data. As a widely used data augmentation method, GT-sample effectively …

3D Object DetectionData AugmentationObjectobject-detection+1

Trajectory-aware Principal Manifold Framework for Data Augmentation and Image Generation

2023-07-30 · Elvis Han Cui, Bingbin Li, Yanan Li, Weng Kee Wong 외

Data augmentation for deep learning benefits model training, image transformation, medical imaging analysis and many other fields. Many existing methods generate new samples from a parametric distribution, like the Gauss…

Data AugmentationImage Generation

LaPA$^2$: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation

2025-08-06 · Jiabing Yang, Yixiang Chen, Zichen Wen, Chenhang Cui 외 arxiv

Prefix-based methods have emerged as a promising paradigm for Controllable Text Generation (CTG) due to their parameter efficiency. However, while effective in short sequences, their controllability tends to diminish as …

Text Generation