Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is inefficient as it relies on high computational costs (e.g., training GPU memory) and massive storage space. In this paper, we aim to study parameter-efficient transfer learning for point cloud analysis with an ideal trade-off between task performance and parameter efficiency. To achieve this goal, we freeze the parameters of the default pre-trained models and then propose the Dynamic Adapter, which generates a dynamic scale for each token, considering the token significance to the downstream task. We further seamlessly integrate Dynamic Adapter with Prompt Tuning (DAPT) by constructing Internal Prompts, capturing the instance-specific features for interaction. Extensive experiments conducted on five challenging datasets demonstrate that the proposed DAPT achieves superior performance compared to the full fine-tuning counterparts while significantly reducing the trainable parameters and training GPU memory by 95% and 35%, respectively. Code is available at https://github.com/LMD0311/DAPT.
Code (1)
Tasks
3D Parameter-Efficient Fine-Tuning for ClassificationGPUTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
UniPET-SPK: A Unified Framework for Parameter-Efficient Tuning of Pre-trained Speech Models for Robust Speaker Verification
With excellent generalization ability, SSL speech models have shown impressive performance on various downstream tasks in the pre-training and fine-tuning paradigm. However, as the size of pre-trained models grows, fine-…
Speaker VerificationPrompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model
Prompting and adapter tuning have emerged as efficient alternatives to fine-tuning (FT) methods. However, existing studies on speech prompting focused on classification tasks and failed on more complex sequence generatio…
Cross-Lingual ASRDecoderslot-fillingSlot FillingPE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition
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 tex…
Dynamic Facial Expression RecognitionFacial Expression Recognitionparameter-efficient fine-tuningPrompt LearningAdapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision
Parameter-efficient fine-tuning (PEFT) has become increasingly important as foundation models continue to grow in both popularity and size. Adapter has been particularly well-received due to their potential for parameter…
3D Classificationparameter-efficient fine-tuningPrompt Tuning based Adapter for Vision-Language Model Adaption
Large pre-trained vision-language (VL) models have shown significant promise in adapting to various downstream tasks. However, fine-tuning the entire network is challenging due to the massive number of model parameters. …
Few-Shot Image Classificationimage-classificationImage ClassificationLanguage Modeling+1