The invention relates to the technical field of electrical
digital data processing, and discloses a lightweight-based multi-
modal data enhancement method, which comprises the following steps: acquiring a multi-
modal feature
tensor; extracting a vector orthogonal projection scalar and determining the novelty; updating the global
covariance matrix when the novelty is greater than a redundancy threshold, and maintaining the global
covariance matrix in a register state when the novelty is not greater than the redundancy threshold; extracting a
main diagonal variance component to determine a
differential modulation coefficient; calculating a second-order moment manifold projection operator according to the global
covariance matrix, and calibrating the operator by using a
differential modulation coefficient; the calibrated operator is used for carrying out orthogonal projection on
random noise to generate a structured disturbance vector, the structured disturbance vector is superposed to a multi-
modal feature
tensor to output enhanced features, a novelty judgment mechanism is used for restraining statistical deviation caused by steady-state redundant data, computing resource occupation is reduced, and it is ensured that
semantic alignment between modals is maintained in enhanced feature distribution.