3 papers
cs.CV2026
Accelerating Rectified Flow Models via Trajectory-Aware Caching
Xiao Liu, Kai Liu, Naiyang Guan +5
Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching me…
cs.CV2023
MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification
Junjie Zhu, Yiying Li, Chunping Qiu +3
Vision Transformer (ViT) models have recently emerged as powerful and versatile models for various visual tasks. Recently, a work called PMF has achieved promising results in few-s…
cs.CV2023
LPN: Language-guided Prototypical Network for few-shot classification
Kaihui Cheng, Chule Yang, Xiao Liu +2
Few-shot classification aims to adapt to new tasks with limited labeled examples. To fully use the accessible data, recent methods explore suitable measures for the similarity betw…