REVIEW 3 cited by
Prompt Tuning based Adapter for Vision-Language Model Adaption
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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. To address this issue, efficient adaptation methods such as prompt tuning have been proposed. We explore the idea of prompt tuning with multi-task pre-trained initialization and find it can significantly improve model performance. Based on our findings, we introduce a new model, termed Prompt-Adapter, that combines pre-trained prompt tunning with an efficient adaptation network. Our approach beat the state-of-the-art methods in few-shot image classification on the public 11 datasets, especially in settings with limited data instances such as 1 shot, 2 shots, 4 shots, and 8 shots images. Our proposed method demonstrates the promise of combining prompt tuning and parameter-efficient networks for efficient vision-language model adaptation. The code is publicly available at: https://github.com/Jingchensun/prompt_adapter.
Forward citations
Cited by 3 Pith papers
-
PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models
PLPP regularizes learnable prompts with a top-k, mutual KL self-distillation loss computed through a no-training LM head, yielding small but consistent gains over PromptSRC.
-
Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
SPIDER updates only parameters whose fine-tuning gradient importance exceeds their pre-trained weight importance, reducing catastrophic forgetting and improving downstream performance in multimodal LLM fine-tuning.
-
CLAP-S: Support Set Based Adaptation for Downstream Fiber-optic Acoustic Recognition
CLAP-S and CLAP-S+ adapt CLAP models to fiber-optic acoustic recognition by combining support-set retrieval with a fine-tuned adapter, reporting improved few-shot classification accuracy over existing methods.
Discussion (0). Continue with ORCID to comment.