paper-with-me

홈 › Papers

Adjusting for Bias with Procedural Data

2022-04-03 · Shesh Narayan Gupta, Nicholas Bear Brown

3D softwares are now capable of producing highly realistic images that look nearly indistinguishable from the real images. This raises the question: can real datasets be enhanced with 3D rendered data? We investigate this question. In this paper we demonstrate the use of 3D rendered data, procedural, data for the adjustment of bias in image datasets. We perform error analysis of images of animals which shows that the misclassification of some animal breeds is largely a data issue. We then create procedural images of the poorly classified breeds and that model further trained on procedural data can better classify poorly performing breeds on real data. We believe that this approach can be used for the enhancement of visual data for any underrepresented group, including rare diseases, or any data bias potentially improving the accuracy and fairness of models. We find that the resulting representations rival or even out-perform those learned directly from real data, but that good performance requires care in the 3D rendered procedural data generation. 3D image dataset can be viewed as a compressed and organized copy of a real dataset, and we envision a future where more and more procedural data proliferate while datasets become increasingly unwieldy, missing, or private. This paper suggests several techniques for dealing with visual representation learning in such a future.

📄 PDF Abstract BibTeX arXiv:2204.01108

Code (1)

aiskunks/ai_research 공식 구현

Tasks

FairnessRepresentation Learning

Similar Papers 제목 키워드 기반

Meta-Learning Neural Procedural Biases

2024-06-12 · Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhan

The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-based meta-learning attempts to address …

Few-Shot LearningMeta-Learning

Procedural Fairness and Its Relationship with Distributive Fairness in Machine Learning

2025-01-12 · ZiMing Wang, Changwu Huang, Ke Tang, Xin Yao

Fairness in machine learning (ML) has garnered significant attention in recent years. While existing research has predominantly focused on the distributive fairness of ML models, there has been limited exploration of pro…

Decision MakingFairness

Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space

2020-07-17 · Xinwei Sun, Wenjing Han, Lingjing Hu, Yuan YAO 외

The prediction and selection of lesion features are two important tasks in voxel-based neuroimage analysis. Existing multivariate learning models take two tasks equivalently and optimize simultaneously. However, in addit…

feature selectionPrediction

Vision-Language Procedural Reasoning for Context-Aware Reward Modeling of Robotic Endovascular Guidewire Navigation

2026-06-29 · Wentong Tian, Jiyuan Zhao, Tianliang Yao, Yuxiang Fan 외 arxiv

Robotic-assisted endovascular interventions demand accurate, stable, and context-aware guidewire navigation in complex and patient-specific vascular anatomies. Despite recent advances in robotic precision and learning-ba…

Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers

2025-11-17 · Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Damien Teney 외 arxiv

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases in vision transformers (ViTs) through pre…