L2g: A simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation

PT Jiang, Y Yang, Q Hou, Y Wei - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Mining precise class-aware attention maps, aka, class activation maps, is essential for
weakly supervised semantic segmentation. In this paper, we present L2G, a simple online …

Multi-granularity denoising and bidirectional alignment for weakly supervised semantic segmentation

T Chen, Y Yao, J Tang - IEEE Transactions on Image …, 2023 - ieeexplore.ieee.org
Weakly supervised semantic segmentation (WSSS) models relying on class activation maps
(CAMs) have achieved desirable performance comparing to the non-CAMs-based …

Weaksam: Segment anything meets weakly-supervised instance-level recognition

L Zhu, J Zhou, Y Liu, X Hao, W Liu… - Proceedings of the 32nd …, 2024 - dl.acm.org
Weakly-supervised visual recognition using inexact supervision is a critical yet challenging
learning problem. It significantly reduces human labeling costs and traditionally relies on …

Subclassified loss: Rethinking data imbalance from subclass perspective for semantic segmentation

S Qiu, X Cheng, H Lu, H Zhang, R Wan… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Semantic segmentation plays a crucial role in enabling intelligent vehicles to perceive and
understand their surroundings. However, datasets used for semantic segmentation often …

Learning cross-channel representations for semantic segmentation

L Ma, H ** augmentation method for weakly supervised building extraction from high-resolution remote sensing imagery
X Zhang, Q Su, P **ao, W Wang, Z Li… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
It is time-consuming to collect a huge number of pixel-level annotations for accurately
extracting buildings by deep neural networks. Supported by class activation map (CAM) …

Boosting Weakly-Supervised Image Segmentation via Representation, Transform, and Compensator

C Wang, D Zhang, R Yan - … on Circuits and Systems for Video …, 2024 - ieeexplore.ieee.org
Weakly-supervised image segmentation (WSIS) is a fundamental task in the domain of
computer vision that relies on image-level class labels. While multi-stage training …