Summary of Robust Influence-based Training Methods For Noisy Brain Mri, by Minh-hao Van et al.
Robust Influence-based Training Methods for Noisy Brain MRI
by Minh-Hao Van, Alycia N. Carey, Xintao Wu
First submitted to arxiv on: 15 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed research aims to develop a deep learning-based approach for accurately classifying brain tumors in MRI images, while addressing the realistic scenario of noisy training data. Two novel training methods, Influence-based Sample Reweighing (ISR) and Influence-based Sample Perturbation (ISP), are introduced, which leverage influence functions from robust statistics to reweight or perturb training examples according to their influence on the training process. These methods aim to harden the classification model against noisy training data without compromising its generalization ability on test data. The proposed approach is evaluated over a common brain tumor dataset and compared to three baselines, demonstrating improved performance in classifying brain tumors. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers has developed a new way to help doctors correctly diagnose brain tumors using MRI scans. Most current methods assume that the training data is perfect, but this isn’t always true. The proposed approach takes into account noisy or imperfect training data and uses two new techniques to improve classification accuracy. These techniques, ISR and ISP, work by adjusting the importance of each piece of training data based on how well it helps or hurts the learning process. The results show that these methods can accurately classify brain tumors even when the training data is noisy. |
Keywords
» Artificial intelligence » Classification » Deep learning » Generalization
