Monocular depth estimation method based on multi-objective federated evolutionary neural architecture search

By employing a multi-objective federated evolutionary neural architecture search method, a lightweight encoder supernet is constructed and combined with a Mamba iterative CRF decoder. This solves the problem of optimizing the accuracy and latency of monocular depth estimation models under federated learning, achieving efficient, accurate, and privacy-preserving monocular depth estimation on edge devices.

CN122244121APending Publication Date: 2026-06-19HANGZHOU NORMAL UNIVERSITY
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU NORMAL UNIVERSITY
Filing Date
2026-05-21
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

Existing technologies struggle to automate the design of high-performance monocular depth estimation models within a federated learning framework, especially when balancing model accuracy, inference latency, and privacy protection. Traditional methods suffer from high communication overhead and poor model generalization ability.

⚗Method used

A multi-objective federated evolutionary neural architecture search method is adopted. By constructing a searchable lightweight encoder supernet, optimizing the encoder architecture using the NSGA-II algorithm, and combining the Mamba iterative CRF decoder and federated weight inheritance adaptation module, the dual objectives of accuracy and latency are optimized, and collaborative training is carried out in a federated learning environment.

🎯Benefits of technology

It achieves efficient and accurate monocular depth estimation on edge devices, reduces communication overhead, adapts to heterogeneous data distribution, improves model generalization ability, protects user privacy, and provides flexible hardware adaptation in different scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention belongs to the field of computer vision and federated learning technology, and relates to a monocular depth estimation method based on multi-objective federated evolutionary neural architecture search. First, a searchable lightweight encoder supernet is constructed based on a federated learning framework, and each candidate architecture of the encoder architecture population is generated by sampling from the supernet. Second, the NSGA-II multi-objective evolutionary algorithm is used to iteratively search the encoder architecture population to obtain a Pareto-optimal set of encoder architectures that satisfies the dual objectives of depth prediction accuracy and edge inference latency. Next, a monocular depth estimation network is constructed. Then, the monocular depth estimation network is co-trained under a federated learning framework until the network converges. Finally, the monocular image to be tested is input into the trained monocular depth estimation network to obtain a pixel-level depth map corresponding to the input image. This invention solves the problems of low model efficiency, high communication overhead, and difficulty in achieving a balance between accuracy and latency faced by existing models.
Need to check novelty before this filing date? Find Prior Art