Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916703324078080 |
|---|---|
| author | Brouwer, Eric van Woerden, Jan Erik Burghouts, Gertjan Valdenegro-Toro, Matias Zullich, Marco |
| author_facet | Brouwer, Eric van Woerden, Jan Erik Burghouts, Gertjan Valdenegro-Toro, Matias Zullich, Marco |
| contents | Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive Language-Image Pre-Training (CLIP) model through adaptive prompt tuning, guided by real-time visual inputs. Unlike existing techniques such as Context Optimization (CoOp) and Visual Prompt Tuning (VPT), which are constrained by static prompts or visual token reliance, the proposed approach leverages a cross-attention mechanism to dynamically refine text prompts for the image at hand. This enables an image-specific alignment of textual features with image patches extracted from the Vision Transformer, making the model more effective for datasets with high intra-class variance and low inter-class differences. The method is evaluated on several datasets, including CUBirds, Oxford Flowers, and FGVC Aircraft, showing significant performance gains over static prompt tuning approaches. To ensure these performance gains translate into trustworthy predictions, we integrate Monte-Carlo Dropout in our approach to improve the reliability of the model predictions and uncertainty estimates. This integration provides valuable insights into the model's predictive confidence, helping to identify when predictions can be trusted and when additional verification is necessary. This dynamic approach offers a robust solution, advancing the state-of-the-art for few-shot fine-grained classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14640 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning Brouwer, Eric van Woerden, Jan Erik Burghouts, Gertjan Valdenegro-Toro, Matias Zullich, Marco Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive Language-Image Pre-Training (CLIP) model through adaptive prompt tuning, guided by real-time visual inputs. Unlike existing techniques such as Context Optimization (CoOp) and Visual Prompt Tuning (VPT), which are constrained by static prompts or visual token reliance, the proposed approach leverages a cross-attention mechanism to dynamically refine text prompts for the image at hand. This enables an image-specific alignment of textual features with image patches extracted from the Vision Transformer, making the model more effective for datasets with high intra-class variance and low inter-class differences. The method is evaluated on several datasets, including CUBirds, Oxford Flowers, and FGVC Aircraft, showing significant performance gains over static prompt tuning approaches. To ensure these performance gains translate into trustworthy predictions, we integrate Monte-Carlo Dropout in our approach to improve the reliability of the model predictions and uncertainty estimates. This integration provides valuable insights into the model's predictive confidence, helping to identify when predictions can be trusted and when additional verification is necessary. This dynamic approach offers a robust solution, advancing the state-of-the-art for few-shot fine-grained classification. |
| title | Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.14640 |