One-Shot Segmentation
17 papers with code • 1 benchmarks • 3 datasets
( Image credit: One-Shot Learning for Semantic Segmentation )
Benchmarks
These leaderboards are used to track progress in One-Shot Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Omniglot
UMD-i Affrodance Dataset
Most implemented papers
One-Shot Transfer of Affordance Regions? AffCorrs!
In this work, we tackle one-shot visual search of object parts.
One-Shot Synthesis of Images and Segmentation Masks
boschresearch/one-shot-synthesis
•
•
To this end, inspired by the recent architectural developments of single-image GANs, we introduce our OSMIS model which enables the synthesis of segmentation masks that are precisely aligned to the generated images in the one-shot regime.
Robust One-shot Segmentation of Brain Tissues via Image-aligned Style Transformation
jinxlv/one-shot-segmentation-via-ist
•
•
In this paper, we propose a novel image-aligned style transformation to reinforce the dual-model iterative learning for robust one-shot segmentation of brain tissues.
One-Shot Segmentation of Novel White Matter Tracts via Extensive Data Augmentation
liuwan0208/one-shot-extensive-data-augmentation
•
•
However, accurate segmentation of novel WM tracts can still be challenging in the one-shot setting, where only one scan is annotated for the novel WM tracts.
One-shot and Partially-Supervised Cell Image Segmentation Using Small Visual Prompt
usagisukisuki/oneshot-part-cellsegmentation
•
•
Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training.
AdLER: Adversarial Training with Label Error Rectification for One-Shot Medical Image Segmentation
To address these issues, we propose a novel one-shot medical image segmentation method with adversarial training and label error rectification (AdLER), with the aim of improving the diversity of generated data and correcting label errors to enhance segmentation performance.
SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation
In-context segmentation aims at segmenting novel images using a few labeled example images, termed as "in-context examples", exploring content similarities between examples and the target.
