Related papers: Explanation-Guided Training for Cross-Domain Few-S…
Most of the existing deep neural nets on automatic facial expression recognition focus on a set of predefined emotion classes, where the amount of training data has the biggest impact on performance. However, in the standard setting…
Annotated images and ground truth for the diagnosis of rare and novel diseases are scarce. This is expected to prevail, considering the small number of affected patient population and limited clinical expertise to annotate images. Further,…
Few-shot learning (FSL) approaches are usually based on an assumption that the pre-trained knowledge can be obtained from base (seen) categories and can be well transferred to novel (unseen) categories. However, there is no guarantee,…
We study the problem of few-shot graph classification across domains with nonequivalent feature spaces by introducing three new cross-domain benchmarks constructed from publicly available datasets. We also propose an attention-based graph…
A recent study finds that existing few-shot learning methods, trained on the source domain, fail to generalize to the novel target domain when a domain gap is observed. This motivates the task of Cross-Domain Few-Shot Learning (CD-FSL). In…
While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming.…
Few-shot classification involves identifying new categories using a limited number of labeled samples. Current few-shot classification methods based on local descriptors primarily leverage underlying consistent features across visible and…
We propose a method that can perform one-class classification given only a small number of examples from the target class and none from the others. We formulate the learning of meaningful features for one-class classification as a…
Motivated by the success of the Segment Anything Model (SAM) in promptable segmentation, recent studies leverage SAM to develop training-free solutions for few-shot segmentation, which aims to predict object masks in the target image based…
Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train…
Graph few-shot learning has attracted increasing attention due to its ability to rapidly adapt models to new tasks with only limited labeled nodes. Despite the remarkable progress made by existing graph few-shot learning methods, several…
A two-stage training paradigm consisting of sequential pre-training and meta-training stages has been widely used in current few-shot learning (FSL) research. Many of these methods use self-supervised learning and contrastive learning to…
In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable…
The ability to incrementally learn new classes from limited samples is crucial to the development of artificial intelligence systems for real clinical application. Although existing incremental learning techniques have attempted to address…
Due to the emergence of powerful computing resources and large-scale annotated datasets, deep learning has seen wide applications in our daily life. However, most current methods require extensive data collection and retraining when dealing…
Pre-trained vision-language models have inspired much research on few-shot learning. However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant…
Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks…
Over the past few years, state-of-the-art image segmentation algorithms are based on deep convolutional neural networks. To render a deep network with the ability to understand a concept, humans need to collect a large amount of pixel-level…
Few-shot learning (FSL) is an emergent paradigm of learning that attempts to learn to reason with low sample complexity to mimic the way humans learn, generalise and extrapolate from only a few seen examples. While FSL attempts to mimic…
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…