Can a mixture-of-experts (MoE) routing strategy with adaptive sparsity improve both throughput (FPS) and per-c

Abstract

Abstract: This review comprehensively investigates the current state and emerging trends of autonomous vehicle terrain detection and segmentation. By systematically reviewing literature from various databases, this study outlines the evolution of detection and segmentation techniques from traditional computer vision methods to advanced machine learning and deep learning approaches. It identifies critical technological advancements, evaluates their performance, and discusses the challenges faced under various environmental conditions, data acquisition, and integration with vehicle systems. This study als

Research Question

Can a mixture-of-experts (MoE) routing strategy with adaptive sparsity improve both throughput (FPS) and per-class IoU for rare categories (vegetation, obstacles) compared to standard dense transformers on the KITTI-360 dataset?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance