Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Parallel Quantum Feature Augmentation (PQFA), a novel hybrid quantum-classical framework that enhances multimodal classification by applying shallow variational quantum circuits to fused features from text and image representations. The method leverages bidirectional cross-attention and adaptive gated fusion to process inputs from frozen RoBERTa and ViT encoders, resulting in a more robust predictive performance, especially under missing-modality conditions. PQFA outperforms traditional augmentation methods while using significantly fewer parameters, demonstrating its efficiency and effectiveness in multimodal learning tasks.
PQFA achieves superior multimodal classification performance with a fraction of the parameters compared to traditional methods, showcasing the power of quantum-classical integration.
Most multimodal learning methods improve how heterogeneous representations are aligned and fused, while post-fusion enhancement remains less explored. We propose Parallel Quantum Feature Augmentation (PQFA), a hybrid quantum-classical framework that applies multiple shallow variational quantum circuits to fused multimodal features. Text and image representations extracted by frozen RoBERTa and ViT encoders are processed through bidirectional cross-attention, attentive pooling, and adaptive gated fusion. The fused feature is then amplitude-encoded into parallel quantum circuits, whose measurement readouts are concatenated with the classical representation for prediction. We evaluate PQFA on MM-IMDb and N24News through controlled comparisons using the same encoders, fusion backbone, data splits, projection dimension, and augmentation output width. PQFA consistently outperforms both the fusion backbone without quantum augmentation and a width-matched MLP augmentation baseline, while using approximately 2.2K augmentation parameters compared with 24.0K for the MLP branch. Missing-modality experiments further show improved robustness when textual or visual inputs are incomplete, with particularly clear gains when the more informative textual modality is severely degraded. Controlled ablations and feature-space analyses indicate that the improvement cannot be reproduced by random feature mappings, increased classical width, or untrained quantum transformations. Quantum-state diagnostics additionally show stable predictive performance across the tested simulated noise levels and distinct branch-specific transformations of the encoded states. These results establish PQFA as an effective and parameter-efficient strategy for post-fusion augmentation in hybrid quantum-classical multimodal learning.