Closed-loop correction reprogramming for fine-grained visual prompting.

Abstract

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.².