877 - On the Texture Bias for Few-Shot CNN Segmentation

Learning What Not To Segment: A New Perspective on Few Shot Segmentation | CVPR 2022Подробнее

Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?Подробнее

FGN: Fully Guided Network for Few-Shot Instance SegmentationПодробнее

Few-shot Medical Image Segmentation with Cycle-resemblance AttentionПодробнее

CVPR 2021: Incremental Few-Shot Instance SegmentationПодробнее

Exploring the Origins and Prevalence of Texture Bias in Convolutional Neural NetworksПодробнее

Learning Few-shot Segmentation from Bounding Box AnnotationsПодробнее

Frustratingly Simple Few-Shot Object DetectionПодробнее

Few-Shot Learning of Part-Specific Probability Space for 3D Shape SegmentationПодробнее

Few-shot learning methodsПодробнее

[WACV 2022] MaskSplit: Self-supervised Meta-learning for Few-shot Semantic SegmentationПодробнее

Few-shot Segmentation Using pre-trained GANПодробнее

A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic SegmentationПодробнее

Unsupervised Meta-Learning for Few-Shot Image ClassificationПодробнее

173 - Variational Prototype Inference for Few-Shot Semantic SegmentationПодробнее

CRNet: Cross-Reference Networks for Few-Shot SegmentationПодробнее

FSS-1000: A 1000-Class Dataset for Few-Shot SegmentationПодробнее

Robert Geirhos: ImageNet-trained CNNs are biased towards texture (ICLR 2019 talk)Подробнее