… Here, we propose a Confidence Refining Vein Network (CoRE-Net) for the leaf vein
segmentation, which utilizes the continuity and branching of veins and converges by self-supervised …

… Taking a detour from this prevalent practice, we approach the self-supervision problem by
letting the neural network itself determine whether two pixels (actually two local patches due to …

… Leaf Vein Segmentation (HALVS). To acquire high-resolution and high-contrast leaf venation
images from the raw leaf … work, we propose the first PSL solution to leaf vein segmentation. …

… To address the aforementioned issues, inspired by the great successes of transformer model
[9] in computer vision (CV), we introduce the transformer to the leaf vein segmentation task. …

… extracting features based on leaf shape, texture or vein patterns [3]… segmentation. Examples
2 and 3 demonstrate the separation … Additionally, self-supervision is particularly useful when …

… that completes the leaf segmentation task and accurately depicts the leaf edge. Phadikar et
… In our system, we propose pixel-level self-supervision and fast CRF supervision to solve this …

… In our system, we propose pixel-level self-supervision and fast CRF supervision to solve this
… (5) The existence of leaf veins makes the texture information of leaf surfaces complicated. …

… Leaf vein segmentation is of great importance for increasing … To further improve the
performance of vein image segmentation, … Leaf vein segmentation with self-supervision. …

… Image segmentation plays a crucial role in the analysis of leaf vein phenotypes as it enables
the extraction of a wealth of phenotype information, including, among others, color, shape, …

… Experimental results show that very significant accuracy increments are obtained by the
proposed pipeline, leading to the conclusion that the self-supervision mechanism introduced in …