On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “WSI”

Iterative annotation to ease neural network training: Specialized machine learning in medical image analysiseess.IV

A tool simplifies neural network training for medical image analysis.

problem Difficulties in training neural networks for medical image analysis.

method Intuitive interface for WSI annotation and display, human-in-the-loop strategy.

result Improved network performance through iterative annotation.

neural networks medical image analysis WSI annotation machine learning

2018-12-18abs ↗pdf ↗

How Effective Can Dropout Be in Multiple Instance Learning ?cs.CV

Dropout improves MIL performance on noisy WSI classification.

problem Noisy feature embeddings and weak supervision in MIL for WSI classification.

method Empirical exploration of dropout in MIL, proposing MIL-Dropout.

result MIL-Dropout boosts MIL performance with minimal computational cost.

dropout multiple instance learning weakly supervised learning histological whole slide image noisy feature embeddings

2025-04-21abs ↗pdf ↗

Learning Permutation Invariant Representations using Memory Networkscs.LG

MEM learns set functions from permutation-invariant data.

problem Learning from sets of instances with labels only on sets, not instances.

method Memory-based Exchangeable Model (MEM) with self-attention mechanism.

result Achieved 84.84% accuracy on lung cancer classification.

Memory Networks Set Functions Permutation Invariance Neural Networks Lung Cancer Classification

2019-11-18abs ↗pdf ↗

Automated Prostate Cancer Diagnosis Based on Gleason Grading Using Convolutional Neural Networkeess.IV

CNN-based prostate cancer grading improves accuracy and efficiency.

problem Manual Gleason grading by pathologists is time-consuming and prone to errors.

method Patch-Based Image Reconstruction (PBIR), Distribution Correction (DC), Quadratic Weighted Mean Square Error (QWMSE).

result Achieved superior expert-level performance (0.8885 quadratic-weighted kappa coefficient).

prostate cancer CNN Gleason grading deep learning histopathology

2020-11-29abs ↗pdf ↗