Advancing Prompt Learning through an External Layer
- URL: http://arxiv.org/abs/2407.19674v6
- Date: Fri, 15 Nov 2024 09:48:05 GMT
- Title: Advancing Prompt Learning through an External Layer
- Authors: Fangming Cui, Xun Yang, Chao Wu, Liang Xiao, Xinmei Tian,
- Abstract summary: We propose a paradigm called EnPrompt with a novel External Layer (EnLa)
The learnable external layer is built upon valid embeddings of pre-trained CLIP.
Four experiments demonstrate that our method outperforms the existing prompt learning method.
- Score: 24.77977865016954
- License:
- Abstract: Prompt learning represents a promising method for adapting pre-trained vision-language models (VLMs) to various downstream tasks by learning a set of text embeddings. One challenge inherent to these methods is the poor generalization performance due to the invalidity of the learned text embeddings for unseen tasks. A straightforward approach to bridge this gap is to freeze the text embeddings in prompts, which results in a lack of capacity to adapt VLMs for downstream tasks. To address this dilemma, we propose a paradigm called EnPrompt with a novel External Layer (EnLa). Specifically, we propose a textual external layer and learnable visual embeddings for adapting VLMs to downstream tasks. The learnable external layer is built upon valid embeddings of pre-trained CLIP. This design considers the balance of learning capabilities between the two branches. To align the textual and visual features, we propose a novel two-pronged approach: i) we introduce the optimal transport as the discrepancy metric to align the vision and text modalities, and ii) we introduce a novel strengthening feature to enhance the interaction between these two modalities. Four representative experiments (i.e., base-to-novel generalization, few-shot learning, cross-dataset generalization, domain shifts generalization) across 15 datasets demonstrate that our method outperforms the existing prompt learning method.
Related papers
- Instructing Prompt-to-Prompt Generation for Zero-Shot Learning [116.33775552866476]
We propose a textbfPrompt-to-textbfPrompt generation methodology (textbfP2P) to distill instructive visual prompts for transferable knowledge discovery.
The core of P2P is to mine semantic-related instruction from prompt-conditioned visual features and text instruction on modal-sharing semantic concepts.
arXiv Detail & Related papers (2024-06-05T07:59:48Z) - Exploring the Transferability of Visual Prompting for Multimodal Large Language Models [47.162575147632396]
Transferable Visual Prompting (TVP) is a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model.
We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts.
arXiv Detail & Related papers (2024-04-17T09:39:07Z) - Concept-Guided Prompt Learning for Generalization in Vision-Language
Models [33.361744437967126]
We propose Concept-Guided Prompt Learning for vision-language models.
We leverage the well-learned knowledge of Contrastive Language-Image Pretraining to create a visual concept cache.
In order to refine the text features, we develop a projector that transforms multi-level visual features into text features.
arXiv Detail & Related papers (2024-01-15T04:04:47Z) - APLe: Token-Wise Adaptive for Multi-Modal Prompt Learning [15.844451999840588]
We propose Token-wise Adaptive for Multi-modal Prompt Learning (APLe) for tuning both modalities prompts, vision and language, as tokens in a sequential manner.
APLe shows robustness and favourable performance in prompt-length experiments with an absolute advantage in adopting the V-L models.
arXiv Detail & Related papers (2024-01-12T04:54:01Z) - Prompt Highlighter: Interactive Control for Multi-Modal LLMs [50.830448437285355]
This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation.
We introduce a novel inference method, Prompt Highlighter, which enables users to highlight specific prompt spans to interactively control the focus during generation.
We find that, during inference, guiding the models with highlighted tokens through the attention weights leads to more desired outputs.
arXiv Detail & Related papers (2023-12-07T13:53:29Z) - Improving In-Context Learning in Diffusion Models with Visual
Context-Modulated Prompts [83.03471704115786]
We introduce improved Prompt Diffusion (iPromptDiff) in this study.
iPromptDiff integrates an end-to-end trained vision encoder that converts visual context into an embedding vector.
We show that a diffusion-based vision foundation model, when equipped with this visual context-modulated text guidance and a standard ControlNet structure, exhibits versatility and robustness across a variety of training tasks.
arXiv Detail & Related papers (2023-12-03T14:15:52Z) - DPL: Decoupled Prompt Learning for Vision-Language Models [41.90997623029582]
We propose a new method, Decoupled Prompt Learning, which reformulates the attention in prompt learning to alleviate this problem.
Our approach is flexible for both visual and textual modalities, making it easily extendable to multi-modal prompt learning.
arXiv Detail & Related papers (2023-08-19T15:48:38Z) - Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary
Object Detection [87.39089806069707]
We propose a fine-grained Visual-Text Prompt-driven self-training paradigm for Open-Vocabulary Detection (VTP-OVD)
During the adapting stage, we enable VLM to obtain fine-grained alignment by using learnable text prompts to resolve an auxiliary dense pixel-wise prediction task.
Experiments show that our method achieves the state-of-the-art performance for open-vocabulary object detection, e.g., 31.5% mAP on unseen classes of COCO.
arXiv Detail & Related papers (2022-11-02T03:38:02Z) - MaPLe: Multi-modal Prompt Learning [54.96069171726668]
We propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations.
Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes.
arXiv Detail & Related papers (2022-10-06T17:59:56Z) - LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of
Vision & Language Models [67.19124099815645]
We propose a novel Language-Aware Soft Prompting (LASP) learning method to alleviate base class overfitting.
LASP is inherently amenable to including, during training, virtual classes, i.e. class names for which no visual samples are available.
LASP matches and surpasses, for the first time, the accuracy on novel classes obtained by hand-crafted prompts and CLIP for 8 out of 11 test datasets.
arXiv Detail & Related papers (2022-10-03T17:56:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.