1 code implementation • 1 May 2024 • Hanyang Chi, Jian Pang, Bingfeng Zhang, Weifeng Liu
Consistency learning is a central strategy to tackle unlabeled data in semi-supervised medical image segmentation (SSMIS), which enforces the model to produce consistent predictions under the perturbation.
no code implementations • Pattern Recognition 2023 • Xinqiao Zhao, Jimin Xiao, Siyue Yu, Hui Li, Bingfeng Zhang
In this paper, we propose a Weight-Guided Class Complementing framework to address this issue.
Ranked #11 on Long-tail Learning on CIFAR-10-LT (ρ=100)
1 code implementation • CVPR 2023 • Xiaoyang Wang, Bingfeng Zhang, Limin Yu, Jimin Xiao
Inspired by density-based unsupervised clustering, we propose to leverage feature density to locate sparse regions within feature clusters defined by label and pseudo labels.
1 code implementation • CVPR 2022 • Siyue Yu, Jimin Xiao, Bingfeng Zhang, Eng Gee Lim
To achieve this, we design a democratic prototype generation module to generate democratic response maps, covering sufficient co-salient regions and thereby involving more shared attributes of co-salient objects.
Ranked #3 on Co-Salient Object Detection on CoCA
no code implementations • 3 Aug 2021 • Bingfeng Zhang, Jimin Xiao, Yao Zhao
In this paper, we propose a new regularized loss which utilizes both shallow and deep features that are dynamically updated in order to aggregate sufficient information to represent the relationship of different pixels.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • 9 Jul 2021 • Siyue Yu, Jimin Xiao, Bingfeng Zhang, Eng Gee Lim
Most mask-propagation based models are faster but with relatively low performance due to failure to adapt to object appearance variation.
1 code implementation • 8 Jun 2021 • Bingfeng Zhang, Jimin Xiao, Jianbo Jiao, Yunchao Wei, Yao Zhao
More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset.
1 code implementation • CVPR 2021 • Bingfeng Zhang, Jimin Xiao, Terry Qin
Specifically, through making an initial prediction for the annotated support image, the covered and uncovered foreground regions are encoded to the primary and auxiliary support vectors using masked GAP, respectively.
Ranked #62 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
1 code implementation • 8 Dec 2020 • Siyue Yu, Bingfeng Zhang, Jimin Xiao, Eng Gee Lim
Since scribble labels fail to offer detailed salient regions, we propose a local coherence loss to propagate the labels to unlabeled regions based on image features and pixel distance, so as to predict integral salient regions with complete object structures.
1 code implementation • CVPR 2020 • Mingjie Sun, Jimin Xiao, Eng Gee Lim, Bingfeng Zhang, Yao Zhao
Specifically, the reinforcement learning agent learns to decide whether to update the target template according to the quality of the predicted result.
1 code implementation • 19 Nov 2019 • Bingfeng Zhang, Jimin Xiao, Yunchao Wei, Ming-Jie Sun, Kai-Zhu Huang
Such reliable regions are then directly served as ground-truth labels for the parallel segmentation branch, where a newly designed dense energy loss function is adopted for optimization.
Ranked #22 on Semantic Segmentation on PASCAL VOC 2012 val