The Hierarchical Prompt Composition Network (HPC-NET) is introduced, a parameter-efficient architecture for continual learning in open-world environments that decomposes learnable prompts into three tiers: foundational prompts that encode broad visual primitives, compositional prompts that aggregate mid-level patterns, and instance prompts that capture category-specific features.
ProCAP is proposed, a probabilistic cross-attentive prompt learning framework that improves cross-modal interaction and training stability without updating any CLIP weights: it learns both visual and textual prompt tokens and links them through stacked bidirectional multi-head cross-attention so the two branches refine...
Hiwa Azeez Abbas, Fatemeh Daneshfar, M. Abdar· 0 citations
Gated Adaptive Prompting (GAP-Prompt) is proposed, a novel method that introduces instance-level adaptability to the prompting process and achieves state-of-the-art performance on fine-grained intra-task diversity.
Trung-Anh Dang, D. Bùi, Ngoc-Son Vu et al.· 1 citation
KeyRec is a training-free framework for constructing bounded visual memory that preserves fine-grained recent observations in a visual cache and organizes historical evidence into a structured event bank and achieves the best compressed performance in 13 of 15 settings using only 10\% of the dense decoder-facing visual...
Zi-Han Chen, Xuejian Rong, Xiao-Juan Wang et al.· 0 citations
Scaling up vision-language models like CLIP for dense prediction tasks has recently gained considerable attention. DeCLIP builds upon this direction by decoupling the self-attention mechanism in the final transformer layer to separate content and context representations. However, evidence suggests that different layers...
Yinghao Shan, Yao Shi, Yun-Xu Sun· International Symposium on W...· 0 citations
Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstream tasks has largely relied on fixed prompts. Existing prompt learning methods, meanwhile, treat class labels as a flat set and do not exploit available taxonomic struc...
Andro Erdelez, Pascal Mettes, B. Bozorgtabar· 0 citations
Processing long visual token sequences from high-resolution images makes multi-step reasoning computationally expensive for multimodal Large Language Models (MLLMs). Existing one-shot pruning and aggregation methods compress visual tokens into a fixed context before decoding. However, visual evidence needs can shift as...
Yi-Cheng Xue, Han Wu, Ju-Feng Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
