CVLGMLDec 30, 2018

Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification

arXiv:1812.11560v1100 citations
Originality Synthesis-oriented
AI Analysis

This work addresses histological image classification for medical applications like breast cancer and sun exposure detection, but it appears incremental as it builds on existing sampling methods.

The paper tackled high-resolution image classification in Multiple Instance Learning by proposing a patch sampling strategy based on sequential Monte-Carlo, which achieved higher generalization performance compared to grid and uniform sampling techniques, as validated on two artificial and two histological datasets for breast cancer and sun exposure classification.

We propose a patch sampling strategy based on a sequential Monte-Carlo method for high resolution image classification in the context of Multiple Instance Learning. When compared with grid sampling and uniform sampling techniques, it achieves higher generalization performance. We validate the strategy on two artificial datasets and two histological datasets for breast cancer and sun exposure classification.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes