Great progress has been witnessed for weakly supervised semantic segmentation, which aims to segment objects without dense pixel annotations. Most approaches concentrate on …
Abstract Class Activation Mapping (CAM) methods have recently gained much attention for weakly-supervised object localization (WSOL) tasks. They allow for CNN visualization and …
H Chen, Y Jin, G Jin, C Zhu… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Most of the recent image segmentation methods have tried to achieve the utmost segmentation results using large-scale pixel-level annotated data sets. However, obtaining …
Weakly supervised semantic segmentation task aims to learn a segmentation model with only image-level annotations. Existing methods generally refine the initial seeds to obtain …
M Lee, S Lee, J Lee, H Shim - IEEE transactions on pattern …, 2023 - ieeexplore.ieee.org
Existing studies on semantic segmentation using image-level weak supervision have several limitations, including sparse object coverage, inaccurate object boundaries, and co …
Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class predictions with only image-level labels for training. To this end, previous methods adopt the …
X Zhang, W Zhao, W Zhang, J Peng… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The existing publicly available datasets with pixel-level labels contain limited categories, and it is difficult to generalize to the real world containing thousands of categories. In this …
J Feng, X Wang, W Liu - Science China Information Sciences, 2021 - Springer
The scarcity of fully-annotated data becomes the biggest obstacle that prevents many deep learning approaches from widely applied. Weakly-supervised visual learning which can …
M Zhang, Y Zhou, B Liu, J Zhao, R Yao… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Few shot semantic segmentation has been proposed to enhance the generalization ability of traditional models with limited data. Previous works mainly focus on the supervised tasks …