paper-with-me

홈 › Papers

PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition

2025-03-21 · Ibtissam Saadi, Abdenour Hadid, Douglas W. Cunningham, Abdelmalik Taleb-Ahmed, Yassin El Hillali

Vision-Language Models (VLMs) like CLIP offer promising solutions for Dynamic Facial Expression Recognition (DFER) but face challenges such as inefficient full fine-tuning, high complexity, and poor alignment between textual and visual representations. Additionally, existing methods struggle with ineffective temporal modeling. To address these issues, we propose PE-CLIP, a parameter-efficient fine-tuning (PEFT) framework that adapts CLIP for DFER while significantly reducing trainable parameters while maintaining high accuracy. PE-CLIP introduces two specialized adapters: a Temporal Dynamic Adapter (TDA) and a Shared Adapter (ShA). The TDA is a GRU-based module with dynamic scaling that captures sequential dependencies while emphasizing informative temporal features and suppressing irrelevant variations. The ShA is a lightweight adapter that refines representations within both textual and visual encoders, ensuring consistency and efficiency. Additionally, we integrate Multi-modal Prompt Learning (MaPLe), introducing learnable prompts for visual and action unit-based textual inputs, enhancing semantic alignment between modalities and enabling efficient CLIP adaptation for dynamic tasks. We evaluate PE-CLIP on two benchmark datasets, DFEW and FERV39K, achieving competitive performance compared to state-of-the-art methods while requiring fewer trainable parameters. By balancing efficiency and accuracy, PE-CLIP sets a new benchmark in resource-efficient DFER. The source code of the proposed PE-CLIP will be publicly available at https://github.com/Ibtissam-SAADI/PE-CLIP .

📄 PDF Abstract BibTeX arXiv:2503.16945

Code (0)

등록된 구현이 없습니다.

Tasks

Dynamic Facial Expression RecognitionFacial Expression Recognitionparameter-efficient fine-tuningPrompt Learning

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
Adapter 설명 없음

Similar Papers 제목 키워드 기반

Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification

2024-09-25 · Ming Li, Jike Zhong, Chenxin Li, Liuzhuozheng Li 외

Recent advances in fine-tuning Vision-Language Models (VLMs) have witnessed the success of prompt tuning and adapter tuning, while the classic model fine-tuning on inherent parameters seems to be overlooked. It is believ…

Language ModelingLanguage Modelling

Adaptive Parameter Selection for Tuning Vision-Language Models

2025-01-01 · CVPR 2025 1 · Yi Zhang, Yi-Xuan Deng, Meng-Hao Guo, Shi-Min Hu

Vision-language models (VLMs) like CLIP have been widely used in various specific tasks.Parameter-efficient fine-tuning (PEFT) methods, such as prompt and adapter tuning,have become key techniques for adapting these …

Few-Shot Learning

CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values

2025-09-03 · Taha Koleilat, Hassan Rivaz, Yiming Xiao arxiv

Vision-language models (VLMs) like CLIP have shown impressive zero-shot and few-shot learning capabilities across diverse applications. However, adapting these models to new fine-grained domains remains difficult due to …

Prompt EngineeringFew-Shot LearningDomain Adaptation

CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition

2025-04-02 · Sarah Alyami, Hamzah Luqman

Continuous sign language recognition (CSLR) focuses on interpreting and transcribing sequences of sign language gestures in videos. In this work, we propose CLIP sign language adaptation (CLIP-SLA), a novel CSLR framewor…

parameter-efficient fine-tuningSign Language Recognition

CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models

2024-03-28 · Saurav Jha, Dong Gong, Lina Yao

Continual learning (CL) aims to help deep neural networks learn new knowledge while retaining what has been learned. Owing to their powerful generalizability, pre-trained vision-language models such as Contrastive Langua…

Continual Learning