Multi-Prompt with Depth Partitioned Cross-Modal Learning
This work addresses the limitation of single-prompt methods in vision-language tasks for improved generalization in image recognition, though it is incremental as it builds on existing prompting techniques.
The paper tackles the problem of soft prompt learning in vision-language models by introducing a multi-modal prompting technique that uses multiple prompts to capture diverse attributes of categories, achieving a 79.28 harmonic mean averaged over 11 datasets, which is a 7.62 improvement over CoOp.
In recent years, soft prompt learning methods have been proposed to fine-tune large-scale vision-language pre-trained models for various downstream tasks. These methods typically combine learnable textual tokens with class tokens as input for models with frozen parameters. However, they often employ a single prompt to describe class contexts, failing to capture categories' diverse attributes adequately. This study introduces the Partitioned Multi-modal Prompt (PMPO), a multi-modal prompting technique that extends the soft prompt from a single learnable prompt to multiple prompts. Our method divides the visual encoder depths and connects learnable prompts to the separated visual depths, enabling different prompts to capture the hierarchical contextual depths of visual representations. Furthermore, to maximize the advantages of multi-prompt learning, we incorporate prior information from manually designed templates and learnable multi-prompts, thus improving the generalization capabilities of our approach. We evaluate the effectiveness of our approach on three challenging tasks: new class generalization, cross-dataset evaluation, and domain generalization. For instance, our method achieves a $79.28$ harmonic mean, averaged over 11 diverse image recognition datasets ($+7.62$ compared to CoOp), demonstrating significant competitiveness compared to state-of-the-art prompting methods.