20 results for “data augmentation”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper investigates the effects of synthetic data augmentation on score-based classification metrics.
Paul Koch, Paul Hofmann, Ferdinand Waßelewsky, Adem Karakurt +2 more
This paper reviews and explores recent advancements in GenAI-based data generation and augmentation methods for improving the initial active data ramp-up phase in industrial computer vision applicatio…
This paper proposes an uncertainty-guided synthetic context augmentation strategy for semantic segmentation models to improve performance on complex datasets with data sparsity and rare or visually di…
This paper explores the impact of poisoning attacks on data augmentation techniques, specifically on 3D point cloud datasets using GANs, and demonstrates that poisoning can evade augmentation and prop…
Xiaojing Chen, Jingqi Cheng, Xu Zhao, Wan Jiang +1 more
The paper introduces Score-Guided Classification (SGC), a novel framework that uses an unsupervised anomaly score as a 'Pathological Prior' to guide EEG-based depression detection, overcoming the limi…
Cheng Ji, Yu Zhao, Xiaochong Jiang, Wenting Yang +1 more
The paper proposes a new framework for data augmentation that prioritizes regions with strong texture responses for style replacement.
Eight voice cloning models are benchmarked on five paralinguistic tasks, showing most preserve signal with modest degradation. Cloning English clinical speech into Japanese outperforms raw cross-lingu…
This paper explores data augmentation techniques to improve dysarthric speech recognition using a pre-trained Wav2Vec2 model.
Xiuwei Xu, Haowen Sun, Angyuan Ma, Yiwei Zhang +6 more
The paper proposes a real-to-real demonstration augmentation framework, R2RDreamer, to improve spatial generalization in imitation-learned manipulation policies.
Ni Li, Nuohao Liu, Ryan Jacobs, Ajay Annamareddy +4 more
The paper proposes using a mask-conditioned latent diffusion model to generate synthetic, labeled TEM images for data augmentation, achieving small but measurable performance improvements in defect de…
This paper investigates the use of synthetic facial images to supplement training data for recognizing genetic syndromes.
Contrastive learning outperforms classification-based approach to authorship verification
This paper evaluates multiple LLMs (DeepSeek-R1, OpenBioLLM-Llama3, Qwen 3.5) for generating privacy-safe, high-quality synthetic mental health reports, demonstrating their effectiveness in expanding…
The paper proposes a Reference-Augmented Training (RAT) strategy to improve deepfake detection performance.
This paper explores the use of Large Language Models (LLMs) in data fusion tasks for tabular data and shows their superiority over traditional methods.
This paper introduces AutoBackSwap, a method to reduce reliance of classifiers on spurious backgrounds in image classification tasks using a secondary network and infilling.
The paper aims to ensure AI-generated outputs align with user-specified target distributions.