Closed-loop correction reprogramming for fine-grained visual prompting

Visual Reprogramming (VR) adapts pre-trained models to new tasks through pixel-level attention modulation without parameter modification. While existing methods achieve competent performance on basic classification, they dispersed attention in critical discriminative regions for fine-grained tasks.Inspired by the closed-loop correction principle in PID control theory, we propose Closed-loop Correction Reprogramming (CCR), which incorporates proportional feedback for iterative refinement. Concretely, the framework comprises dual streams: a Foundation Flow for initial attention patterns and a Correction Flow that iteratively refines them with residual feedback, alternating between both. A Proportional Adjustment Controller (PAC) dynamically calibrates perturbation intensity via learnable error mapping–enhancing the correction flow’s contribution in response to increased foundational stream errors, otherwise maintaining the foundation’s dependable attributes. Experiments on 11 datasets demonstrate CCR achieves up to 10.8% accuracy gain with only 0.64% parameter increase, attaining 8.62% average improvement on five challenging fine-grained datasets (GTSRB, FLOWERS102, DTD, UCF101, FOOD101). The framework offers enhanced visual cues that improve discrimination in fine-grained classification.22Code is available at https://github.com/SafetyAI-Lab/Visual-Reprogramming.