Decoupling foreground and background with Siamese ViT networks for weakly-supervised semantic segmentation

M Lin, G Li, S Xu, Y Hao, S Zhang - Neurocomputing, 2024 - Elsevier
Due to the coarse granularity of information extraction in image-level annotation-based
weakly supervised semantic segmentation algorithms, there exists a significant gap between …

Superpixel Guided Network for Weakly Supervised Semantic Segmentation

Z Xie, W Jiang, Y Yang, H Lu - IEEE Signal Processing Letters, 2024 - ieeexplore.ieee.org
Image-level weakly supervised semantic segmentation faces challenges in accurately
capturing boundaries and representing intricate details due to the absence of pixel-level …

Hierarchical Activation Dual Backbone Network for Weakly Supervised Semantic Segmentation

C Zhang, L Zhang - IEEE Sensors Journal, 2024 - ieeexplore.ieee.org
Weakly supervised semantic segmentation (WSSS) aims to achieve segmentation using
weak labels, thereby reducing annotation costs. Current mainstream WSSS methods utilize …

Knowledge Distillation in Fourier Frequency Domain for Dense Prediction

M Shi, C Zheng, Q Yi, J Weng… - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
Knowledge distillation has been widely used to enhance student network performance for
dense prediction tasks. Most previous knowledge distillation methods focus on valuable …