all AI news
DeNetDM: Debiasing by Network Depth Modulation
April 1, 2024, 4:41 a.m. | Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, Anjan Dutta
cs.LG updates on arXiv.org arxiv.org
Abstract: When neural networks are trained on biased datasets, they tend to inadvertently learn spurious correlations, leading to challenges in achieving strong generalization and robustness. Current approaches to address such biases typically involve utilizing bias annotations, reweighting based on pseudo-bias labels, or enhancing diversity within bias-conflicting data points through augmentation techniques. We introduce DeNetDM, a novel debiasing method based on the observation that shallow neural networks prioritize learning core attributes, while deeper ones emphasize biases when …
abstract annotations arxiv augmentation bias biases challenges correlations cs.cv cs.lg current data datasets diversity labels learn network networks neural networks robustness through type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
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