Delving into multimodal prompting for fine-grained visual classification

• المؤلفون الرئيسيون: JIANG, Xin, TANG, Hao, GAO, Junyao, DU, Xiaoyu, HE, Shengfeng, LI, Zechao
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2024
• الموضوعات: Fine-grained visual classification; Categorization; Multimodal prompts; Optimization strategy; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces; Software Engineering
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8741; https://ink.library.smu.edu.sg/context/sis_research/article/9744/viewcontent/28034_Article_Text_32088_1_2_20240324.pdf
• المؤسسة: Singapore Management University

Fine-grained visual classification (FGVC) involves categorizing fine subdivisions within a broader category, which poses challenges due to subtle inter-class discrepancies and large intra-class variations. However, prevailing approaches primarily focus on uni-modal visual concepts. Recent advancements in pre-trained vision-language models have demonstrated remarkable performance in various high-level vision tasks, yet the applicability of such models to FGVC tasks remains uncertain. In this paper, we aim to fully exploit the capabilities of cross-modal description to tackle FGVC tasks and propose a novel multimodal prompting solution, denoted as MP-FGVC, based on the contrastive language-image pertaining (CLIP) model. Our MP-FGVC comprises a multimodal prompts scheme and a multimodal adaptation scheme. The former includes Subcategory-specific Vision Prompt (SsVP) and Discrepancy-aware Text Prompt (DaTP), which explicitly highlights the subcategory-specific discrepancies from the perspectives of both vision and language. The latter aligns the vision and text prompting elements in a common semantic space, facilitating cross-modal collaborative reasoning through a Vision-Language Fusion Module (VLFM) for further improvement on FGVC. Moreover, we tailor a two-stage optimization strategy for MP-FGVC to fully leverage the pre-trained CLIP model and expedite efficient adaptation for FGVC. Extensive experiments conducted on four FGVC datasets demonstrate the effectiveness of our MP-FGVC.