Effizientes Aggregationsverfahren und System für Lernen mit mehreren Instanzen
Anmelder: Tata Consultancy Services Limited 🇮🇳
Details
- Veröffentlichungs-Nr.
- EP4718291
- Anmeldetag
- 17. September 2025
- Veröffentlichung
- 1. April 2026
- Rechtsraum
- EP
Abstract
Multiple Instance Learning (MIL) is a useful method for extracting information from Gigapixel images using weakly supervised learning. Traditionally, it was approached with the hypothesis of considering each instance as an independent and identically distributed entity. Recently, it has been suggested that correlations between different instances would yield better results for classification. The present disclosure is designed to improve classification performance significantly. The self-selective MIL of the present disclosure facilitates binary classification with enhanced insights into more aggressive tumor regions.
Anmelder
- Firma
- Tata Consultancy Services Limited
- Land
- 🇮🇳 Indien
Indisches IT-Dienstleistungs- und Beratungsunternehmen, Teil der Tata Group. Bietet Softwareentwicklung, IT-Consulting, Outsourcing und digitale Transformationslösungen für Unternehmenskunden weltweit an.
1.851 Patente in unserer Datenbank
Vertreten von
-
Goddar, Heinz J.