Search Results for author:
Found 4 papers, 2 papers with code
Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
In this study, we propose a class-driven scribble promotion network, which utilizes both scribble annotations and pseudo-labels informed by image-level classes and global semantics for supervision.
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
Instead of perturbing the samples, Sharpness-Aware Minimization (SAM) perturbs the model weights during training to find a more flat loss landscape and improve generalization.
Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-training
Moreover, we develop a multi-level contrastive learning strategy that integrates correspondences across feature-level, image-level, and pixel-level representations to ensure the encoder and decoder capture comprehensive details from representations of varying scales and granularities during the pre-training phase.
Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
Existing methods adopt an online-trained classification branch to provide pseudo annotations for supervising the segmentation branch.
