CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment

TL;DR

CAPT introduces a confusion-aware prompt tuning framework for vision-language models, explicitly modeling and reducing class confusion to improve discriminability and generalization across multiple datasets.

Contribution

The paper proposes a novel framework with a confusion bank, semantic and sample confusion miners, and a multi-granularity expert to address systematic misclassifications in vision-language models.

Findings

Significantly reduces confusion-induced errors.

Improves discriminability and generalization on 11 datasets.

Resolves over 50% of confusable sample pairs.

Abstract

Vision-language models like CLIP have achieved remarkable progress in cross-modal representation learning, yet suffer from systematic misclassifications among visually and semantically similar categories. We observe that such confusion patterns are not random but persistently occur between specific category pairs, revealing the model's intrinsic bias and limited fine-grained discriminative ability. To address this, we propose CAPT, a Confusion-Aware Prompt Tuning framework that enables models to learn from their own misalignment. Specifically, we construct a Confusion Bank to explicitly model stable confusion relationships across categories and misclassified samples. On this basis, we introduce a Semantic Confusion Miner (SEM) to capture global inter-class confusion through semantic difference and commonality prompts, and a Sample Confusion Miner (SAM) to retrieve representative misclassified instances from the bank and capture sample-level cues through a Diff-Manner Adapter that integrates global and local contexts. To further unify confusion information across different granularities, a Multi-Granularity Difference Expert (MGDE) module is designed to jointly leverage semantic- and sample-level experts for more robust confusion-aware reasoning. Extensive experiments on 11 benchmark datasets demonstrate that our method significantly reduces confusion-induced errors while enhancing the discriminability and generalization of both base and novel classes, successfully resolving 50.72 percent of confusable sample pairs. Code will be released at https://github.com/greatest-gourmet/CAPT.