相关论文: CAFENet: Class-Agnostic Few-Shot Edge Detection Ne…

Few-shot classifiers have been shown to exhibit promising results in use cases where user-provided labels are scarce. These models are able to learn to predict novel classes simply by training on a non-overlapping set of classes. This can…

Existing semantic segmentation models heavily rely on dense pixel-wise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segmentation, which aims to segment unseen objects with zero…

Existing few-shot segmentation (FSS) only considers learning support-query correlation and segmenting unseen categories under the precise pixel masks. However, the cost of a large number of pixel masks during training is expensive. This…

We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two…

Although few-shot learning research has advanced rapidly with the help of meta-learning, its practical usefulness is still limited because most of them assumed that all meta-training and meta-testing examples came from a single domain. We…

Meta-learning has emerged as a powerful training strategy for few-shot node classification, demonstrating its effectiveness in the transductive setting. However, the existing literature predominantly focuses on transductive few-shot node…

Few-shot segmentation (FSS) aims to segment novel classes in a query image by using only a small number of supporting images from base classes. However, in cross-domain few-shot segmentation (CD-FSS), leveraging features from label-rich…

Metric-based few-shot fine-grained classification has shown promise due to its simplicity and efficiency. However, existing methods often overlook task-level special cases and struggle with accurate category description and irrelevant…

Few-shot semantic segmentation aims at recognizing the object regions of unseen categories with only a few annotated examples as supervision. The key to few-shot segmentation is to establish a robust semantic relationship between the…

Classification of new class entities requires collecting and annotating hundreds or thousands of samples that is often prohibitively costly. Few-shot learning suggests learning to classify new classes using just a few examples. Only a small…

Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…

Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examples. In previously proposed few-shot visual classifiers, it…

Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and…

While deep learning-based architectures have been widely used for correctly detecting and classifying plant diseases, they require large-scale datasets to learn generalized features and achieve state-of-the-art performance. This poses a…

Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet. However, such models require many thousands of gradient-based weight updates and unique…

Both few-shot and continual learning have seen substantial progress in the last years due to the introduction of proper benchmarks. That being said, the field has still to frame a suite of benchmarks for the highly desirable setting of…

Few-shot node classification is tasked to provide accurate predictions for nodes from novel classes with only few representative labeled nodes. This problem has drawn tremendous attention for its projection to prevailing real-world…

Although prototypical network (ProtoNet) has proved to be an effective method for few-shot sound event detection, two problems still exist. Firstly, the small-scaled support set is insufficient so that the class prototypes may not represent…

Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer structural knowledge…

Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited visual data for category understanding. However, these methods…