paper-with-me

홈 › Papers

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

2026-02-24 · Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani arxiv

Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple transformer layers significantly boosts performance, it dramatically increases the number of trainable parameters, with state-of-the-art methods requiring millions of parameters and abandoning the parameter efficiency that makes prompt tuning attractive. In this work, we propose MMLoP (Multi-Modal Low-Rank Prompting), a framework that achieves deep multi-modal prompting with only 11.5K trainable parameters, comparable to early text-only methods like CoOp. MMLoP parameterizes vision and text prompts at each transformer layer through a low-rank factorization that constrains prompts to a compact subspace, providing parameter efficiency while motivating the need for our complementary regularization components. To further close the accuracy gap with state-of-the-art methods, we introduce three complementary components: a self-regulating consistency loss that anchors prompted representations to frozen zero-shot CLIP features at both the feature and logit levels, a uniform drift correction that removes the global embedding shift induced by prompt tuning to preserve class-discriminative structure, and a shared up-projection that couples vision and text prompts through a common low-rank factor to enforce cross-modal alignment. Extensive experiments across three benchmarks and 11 diverse datasets demonstrate that MMLoP achieves a highly favorable accuracy-efficiency tradeoff, outperforming the majority of existing methods including those with orders of magnitude more parameters, while achieving a harmonic mean of 79.70\% on base-to-novel generalization. Code is available at https://github.com/sajjad-ucsb/MMLoP.

📄 PDF Abstract BibTeX arXiv:2602.21397

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Progressive Multi-modal Conditional Prompt Tuning

2024-04-18 · Xiaoyu Qiu, Hao Feng, Yuechen Wang, Wengang Zhou 외

Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial for downstream tasks. However, existing…

Multimodal Emotion Recognition with Vision-language Prompting and Modality Dropout

2024-09-11 · Anbin QI, Zhongliang Liu, Xinyong Zhou, Jinba Xiao 외

In this paper, we present our solution for the Second Multimodal Emotion Recognition Challenge Track 1(MER2024-SEMI). To enhance the accuracy and generalization performance of emotion recognition, we propose several meth…

Emotion RecognitionMultimodal Emotion RecognitionPrompt Learning

Vision Graph Prompting via Semantic Low-Rank Decomposition

2025-05-07 · Zixiang Ai, Zichen Liu, Jiahuan Zhou

Vision GNN (ViG) demonstrates superior performance by representing images as graph structures, providing a more natural way to capture irregular semantic patterns beyond traditional grid or sequence-based representations…

parameter-efficient fine-tuningVisual Prompting

Delving into Multimodal Prompting for Fine-grained Visual Classification

2023-09-16 · Xin Jiang, Hao Tang, Junyao Gao, Xiaoyu Du 외

Fine-grained visual classification (FGVC) involves categorizing fine subdivisions within a broader category, which poses challenges due to subtle inter-class discrepancies and large intra-class variations. However, preva…

ClassificationFine-Grained Image Classification

Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models

2024-02-19 · Xuanyu Lei, Zonghan Yang, Xinrui Chen, Peng Li 외

State-of-the-art Large Multi-Modal Models (LMMs) have demonstrated exceptional capabilities in vision-language tasks. Despite their advanced functionalities, the performances of LMMs are still limited in challenging scen…

Visual Prompting