3 papers
cs.CV2026
OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance
Haoxi Zeng, Qiankun Liu, Yi Bin +5
Open-Vocabulary Segmentation (OVS) aims to segment image regions beyond predefined category sets by leveraging semantic descriptions. While CLIP based approaches excel in semantic…
cs.CV2026
Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
Muquan Li, Hang Gou, Dongyang Zhang +4
The growing demand for efficient deep learning has positioned dataset distillation as a pivotal technique for compressing training dataset while preserving model performance. Howev…
cs.CL2024
Label-template based Few-Shot Text Classification with Contrastive Learning
Guanghua Hou, Shuhui Cao, Deqiang Ouyang +1
As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough…