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

2026-03-03 · Maoyuan Shao, Yutong Gao, Xinyang Huang, Chuang Zhu, Lijuan Sun, Guoshun Nan arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.02557

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning

2026-06-08 · Trapoom Ukarapol, Pakhapoom Sarapat, Nut Chukamphaeng arxiv

Large language models (LLMs) sometimes exhibit language confusion when generating non-English text. Existing approaches typically rely on fine-tuning to mitigate this issue. In contrast, we propose a tuning-free paradigm…

When Safety Blocks Sense: Measuring Semantic Confusion in LLM Refusals

2025-11-30 · Riad Ahmed Anonto, Md Labid Al Nahiyan, Md Tanvir Hassan arxiv

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local in…

BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming

2026-06-23 · Jiaxiang Liu, Tianxiang Hu, Juwei Guan, Yujie Wu 외 arxiv

Recent advances in vision-language models (VLMs) such as CLIP have demonstrated strong generalization across natural-image domains. However, adapting these models to biomedical imaging is non-trivial: full-model fine-tun…

Visual Instance-aware Prompt Tuning

2025-07-10 · Xi Xiao, Yunbei Zhang, Xingjian Li, Tianyang Wang 외 arxiv

Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. …

parameter-efficient fine-tuning Visual Prompt Tuning

JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling

2025-05-20 · Jinwang Song, Hongying Zan, Kunli Zhang, Lingling Mu 외

Text-to-SQL, which maps natural language to SQL queries, has benefited greatly from recent advances in Large Language Models (LLMs). While LLMs offer various paradigms for this task, including prompting and supervised fi…

Text to SQL Text-To-SQL