all AI news
Boosting Model Resilience via Implicit Adversarial Data Augmentation
April 26, 2024, 4:41 a.m. | Xiaoling Zhou, Wei Ye, Zhemg Lee, Rui Xie, Shikun Zhang
cs.LG updates on arXiv.org arxiv.org
Abstract: Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To address this, we propose to augment the deep features of samples by incorporating their adversarial and anti-adversarial perturbation distributions, enabling adaptive adjustment in the learning difficulty tailored to each sample's specific characteristics. We then theoretically reveal that our augmentation process approximates the optimization of a …
abstract adversarial arxiv augment augmentation biases boosting cs.cv cs.lg data features improving performance pivotal resilience role samples training training data type via
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote