On account of the extreme settings, stealing the black-box model without its training data is
difficult in practice. On this topic, along the lines of data diversity, this paper substantially …

For more efficient generalization to unseen domains (classes), most Few-shot Segmentation
(FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially …

Few-shot Segmentation aims to segment the interested objects in the query image with just
a handful of labeled samples (ie, support images). Previous schemes would leverage the …

The goal of few-shot segmentation (FSS) is to segment unlabeled images belonging to
previously unseen classes using only a limited number of labeled images. The main …

Few-shot semantic segmentation aims to learn a generalized model for unseen-class
segmentation with just a few densely annotated samples. Most current metric-based …

In recent years, few-shot object detection (FSOD) in remote sensing images has attracted
increasing attention. Numerous studies address the challenges posed by both intra-class …

Few-shot segmentation is an emerging and intriguing subfield within computer vision that
tackles the challenging task of segmenting objects or regions in images when only a very …

Learning generalized representations from limited training samples is crucial for applying
deep neural networks in low-resource scenarios. Recently, methods based on contrastive …

Most existing prototype-based methods typically extract a single target class prototype from
the support image, leading to false activation or information loss. In this paper, we propose a …

Convolutional neural networks (CNNs) have shown remarkable performance in the field of
infrared small target detection. However, due to the limitation of local receptive field, existing …