MoE-RelationNet++: Adaptive Keypoint Selection via Conditional Experts

Modeling contextual relationships among key features is crucial for improving object detection, yet existing relation-based methods rely on fixed feature selection and shared transformations, limiting their ability to capture diverse feature interactions in complex scenes. To address this, we propos...

Cijeli opis

Bibliografski detalji

Glavni autori:	Yuhan Peng, Gaofeng Zhang
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2026-05-01
Serija:	Applied Sciences
Teme:	object detection Mixture-of-Experts MoE-RelationNet++ contextual relationships
Online pristup:	https://www.mdpi.com/2076-3417/16/11/5192
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!