activity
20192026
most citedAffinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation

153 citations · 217 across the 11 of their papers we have counts for

collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2026

TALENT: Target-aware Efficient Tuning for Referring Image Segmentation

Shuo Jin, Siyue Yu, Bingfeng Zhang +3

Referring image segmentation aims to segment specific targets based on a natural text expression. Recently, parameter-efficient tuning (PET) has emerged as a promising paradigm. Ho…

cs.CV2026

TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection

Zhijin He, Shuo Jin, Siyue Yu +4

Co-salient Object Detection (CoSOD) aims to segment salient objects that consistently appear across a group of related images. Despite the notable progress achieved by recent train…

cs.CV20241 cited

Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation

Bingfeng Zhang, Siyue Yu, Yunchao Wei +2

Weakly supervised semantic segmentation has witnessed great achievements with image-level labels. Several recent approaches use the CLIP model to generate pseudo labels for trainin…

cs.CV2022

Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection

Siyue Yu, Jimin Xiao, Bingfeng Zhang +1

Co-salient object detection, with the target of detecting co-existed salient objects among a group of images, is gaining popularity. Recent works use the attention mechanism or ext…

cs.CV202112 cited

Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation

Bingfeng Zhang, Jimin Xiao, Yao Zhao

We focus on tackling weakly supervised semantic segmentation with scribble-level annotation. The regularized loss has been proven to be an effective solution for this task. However…

cs.CV2021

Fast Pixel-Matching for Video Object Segmentation

Siyue Yu, Jimin Xiao, BingFeng Zhang +1

Video object segmentation, aiming to segment the foreground objects given the annotation of the first frame, has been attracting increasing attentions. Many state-of-the-art approa…