Local-Global Prompt Learning via Sparse Optimal Transport

TL;DR

The paper introduces SOT-GLP, a novel prompt learning method that partitions visual regions among class prompts using optimal transport, improving few-shot classification and out-of-distribution detection in vision-language models.

Contribution

SOT-GLP is the first approach to explicitly partition salient visual regions among class prompts with balanced optimal transport, enhancing both accuracy and robustness.

Findings

Achieves 85.1% accuracy on 11 benchmarks with 16-shot ViT-B/16.

State-of-the-art 94.2% OOD detection AUC surpassing fully adapted models.

Outperforms prior prompt-learning methods in few-shot classification.

Abstract

Few-shot adaptation of vision-language models (VLMs) like CLIP typically relies on learning textual prompts matched to global image embeddings. Recent works extend this paradigm by incorporating local image-text alignment to capture fine-grained visual cues, yet these approaches often select local regions independently for each prompt, leading to redundant local feature usage and prompt overlap. We propose SOT-GLP, which introduces a shared sparse patch support and balanced optimal transport allocation to explicitly partition salient visual regions among class-specific local prompts while preserving global alignment. Our method learns shared global prompts and class-specific local prompts. The global branch maintains standard image-text matching for robust category-level alignment. The local branch constructs a class-conditioned sparse patch set using V-V attention and aligns it to multiple class-specific prompts via balanced entropic optimal transport, yielding a soft partition of patches that prevents prompt overlap and collapse. We evaluate our method on two complementary objectives: (i) few-shot classification accuracy on 11 standard benchmarks and (ii) out-of-distribution (OOD) detection. On the standard 11-dataset benchmark with 16-shot ViT-B/16, SOT-GLP achieves 85.1% average accuracy, outperforming prior prompt-learning methods. We identify a distinct accuracy-robustness trade-off in prompt learning: while learnable projections optimize in-distribution fit, they alter the foundational feature space. We demonstrate that a projection-free local alignment preserves the native geometry of the CLIP manifold, yielding state-of-the-art OOD detection performance (94.2% AUC) that surpasses fully adapted models. Implementation available at: https://github.com/Deniz2304988/SOT-GLP