Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation
Semantic segmentation is a challenging task in the absence of densely labelled data. Only
relying on class activation maps (CAM) with image-level labels provides deficient …
relying on class activation maps (CAM) with image-level labels provides deficient …
Complementary patch for weakly supervised semantic segmentation
Abstract Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels
has been greatly advanced by exploiting the outputs of Class Activation Map (CAM) to …
has been greatly advanced by exploiting the outputs of Class Activation Map (CAM) to …
Self-guided and cross-guided learning for few-shot segmentation
Few-shot segmentation has been attracting a lot of attention due to its effectiveness to
segment unseen object classes with a few annotated samples. Most existing approaches …
segment unseen object classes with a few annotated samples. Most existing approaches …
Unlocking the potential of ordinary classifier: Class-specific adversarial erasing framework for weakly supervised semantic segmentation
Weakly supervised semantic segmentation (WSSS) using image-level classification labels
usually utilizes the Class Activation Maps (CAMs) to localize objects of interest in images …
usually utilizes the Class Activation Maps (CAMs) to localize objects of interest in images …
Activation modulation and recalibration scheme for weakly supervised semantic segmentation
Image-level weakly supervised semantic segmentation (WSSS) is a fundamental yet
challenging computer vision task facilitating scene understanding and automatic driving …
challenging computer vision task facilitating scene understanding and automatic driving …
Boundary-enhanced co-training for weakly supervised semantic segmentation
The existing weakly supervised semantic segmentation (WSSS) methods pay much
attention to generating accurate and complete class activation maps (CAMs) as pseudo …
attention to generating accurate and complete class activation maps (CAMs) as pseudo …
Adaptive early-learning correction for segmentation from noisy annotations
Deep learning in the presence of noisy annotations has been studied extensively in
classification, but much less in segmentation tasks. In this work, we study the learning …
classification, but much less in segmentation tasks. In this work, we study the learning …
Ecs-net: Improving weakly supervised semantic segmentation by using connections between class activation maps
Image-level weakly supervised semantic segmentation is a challenging task. As
classification networks tend to capture notable object features and are insensitive to …
classification networks tend to capture notable object features and are insensitive to …
Expansion and shrinkage of localization for weakly-supervised semantic segmentation
Generating precise class-aware pseudo ground-truths, aka, class activation maps (CAMs), is
essential for Weakly-Supervised Semantic Segmentation. The original CAM method usually …
essential for Weakly-Supervised Semantic Segmentation. The original CAM method usually …
Threshold matters in wsss: Manipulating the activation for the robust and accurate segmentation model against thresholds
Weakly-supervised semantic segmentation (WSSS) has recently gained much attention for
its promise to train segmentation models only with image-level labels. Existing WSSS …
its promise to train segmentation models only with image-level labels. Existing WSSS …