activity
20222026
most citedL2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation

10 citations · 10 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion

Yuqi Yang, Dongliang Chang, Yijia Ling +2

Colour is one of the most perceptually salient yet least controllable attributes in image generation. Although recent diffusion models can modify object colours from user instructi…

cs.CV2025

Controllable-Continuous Color Editing in Diffusion Model via Color Mapping

Yuqi Yang, Dongliang Chang, Yuanchen Fang +3

In recent years, text-driven image editing has made significant progress. However, due to the inherent ambiguity and discreteness of natural language, color editing still faces cha…

cs.CV2024

Empowering Segmentation Ability to Multi-modal Large Language Models

Yuqi Yang, Peng-Tao Jiang, Jing Wang +4

Multi-modal large language models (MLLMs) can understand image-language prompts and demonstrate impressive reasoning ability. In this paper, we extend MLLMs' output by empowering M…

cs.CV2024

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

Yuqi Yang, Peng-Tao Jiang, Qibin Hou +3

Previous multi-task dense prediction methods based on the Mixture of Experts (MoE) have received great performance but they neglect the importance of explicitly modeling the global…

cs.CV2023

CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation

Boyuan Sun, Yuqi Yang, Le Zhang +2

This paper presents a simple but performant semi-supervised semantic segmentation approach, called CorrMatch. Previous approaches mostly employ complicated training strategies to l…

cs.CV202318 cited

Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation

Peng-Tao Jiang, Yuqi Yang

Weakly supervised semantic segmentation with weak labels is a long-lived ill-posed problem. Mainstream methods mainly focus on improving the quality of pseudo labels. In this repor…