3 papers
cs.CV2025
Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation
Yong Liu, SongLi Wu, Sule Bai +3
Open-vocabulary segmentation aims to achieve segmentation of arbitrary categories given unlimited text inputs as guidance. To achieve this, recent works have focused on developing…
cs.CV2024
Universal Segmentation at Arbitrary Granularity with Language Instruction
Yong Liu, Cairong Zhang, Yitong Wang +3
This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years, specialist segmentation approaches are limited to speci…
cs.CL2024
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast
Chufan Shi, Cheng Yang, Xinyu Zhu +6
Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activat…