SOURCE-LINKED INTELLIGENCE

USPLIT-VQA: U-Shaped Split Learning for Visual Question Answering with Contribution-Aware Weighted Aggregation

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Visual Question Answering (VQA) systems, jointly interpreting images and natural language queries, hold significant promise across many domains, yet the privacy-sensitive nature of user data creates a fundamental barrier. Centralized training requires access to all data, while federated learning requires each client to host the full model. We propose USPLIT-VQA, a U-shaped split learning framework for privacy-preserving VQA in which each client retains the initial layers and the classification head while the server hosts the computationally heavy intermediate layers, keeping raw inputs and lab

Read original source ↗ Open in workspace

recordType

paper

region

Global