Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation
Recent attention has been devoted to the pursuit of learning semantic segmentation models
exclusively from image tags, a paradigm known as image-level Weakly Supervised …
exclusively from image tags, a paradigm known as image-level Weakly Supervised …
Tuning-free Universally-Supervised Semantic Segmentation
X Yang, X Gong - arXiv preprint arXiv:2405.14294, 2024 - arxiv.org
This work presents a tuning-free semantic segmentation framework based on classifying
SAM masks by CLIP, which is universally applicable to various types of supervision. Initially …
SAM masks by CLIP, which is universally applicable to various types of supervision. Initially …
Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS) with image-level labels intends to
achieve dense tasks without laborious annotations. However, due to the ambiguous …
achieve dense tasks without laborious annotations. However, due to the ambiguous …
Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video
Weakly supervised video object segmentation (WSVOS) enables the identification of
segmentation maps without requiring an extensive training dataset of object masks, relying …
segmentation maps without requiring an extensive training dataset of object masks, relying …
Size Constraints in Segmentation and Size Predictions
X Fan - 2024 - uwspace.uwaterloo.ca
Segment size, which one may equivalently refer to as volume, area, or cardinality, is
uniquely defined by segmentation, eg by aggregating pixel-level predictions. On the other …
uniquely defined by segmentation, eg by aggregating pixel-level predictions. On the other …