Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning

TL;DR

This paper introduces an adaptive prompt tuning method guided by visual inputs using cross-attention, significantly improving few-shot fine-grained classification performance by dynamically aligning textual and visual features.

Contribution

It proposes a novel adaptive prompt tuning approach with cross-attention for dynamic text prompt refinement, surpassing static prompt methods in fine-grained visual tasks.

Findings

Significant accuracy improvements on CUBirds, Oxford Flowers, FGVC Aircraft datasets.

Enhanced model reliability through Monte-Carlo Dropout for uncertainty estimation.

Outperforms existing static prompt tuning techniques in few-shot scenarios.

Abstract

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.