Related papers: Task Adaptive Feature Transformation for One-Shot …
We develop a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance. Our approach combines a regularized Mahalanobis-distance-based soft k-means clustering procedure with a…
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve…
In this paper, we propose an approach to improve few-shot classification performance using a composite rotation based auxiliary task. Few-shot classification methods aim to produce neural networks that perform well for classes with a large…
One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore…
Few-shot image generation aims to effectively adapt a source generative model to a target domain using very few training images. Most existing approaches introduce consistency constraints-typically through instance-level or…
Deep neural networks often fail to adapt representations to novel tasks under distribution shifts, especially when only a few examples are available. This paper identifies a core obstacle behind this failure: channel bias, where networks…
Few-shot learning (FSL) aims to enable models to recognize novel objects or classes with limited labelled data. Feature generators, which synthesize new data points to augment limited datasets, have emerged as a promising solution to this…
Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks…
In the research field of few-shot learning, the main difference between image-based and video-based is the additional temporal dimension. In recent years, some works have used the Transformer to deal with frames, then get the attention…
Overfitting is a significant challenge in Few-Shot Learning (FSL), where models trained on small, variable datasets tend to memorize rather than generalize to unseen tasks. Regularization is crucial in FSL to prevent overfitting and enhance…
Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task. In this paper, we propose to exploit an additional big dataset with different categories to improve the accuracy of few-shot…
Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…
Learning to generate a task-aware base learner proves a promising direction to deal with few-shot learning (FSL) problem. Existing methods mainly focus on generating an embedding model utilized with a fixed metric (eg, cosine distance) for…
We propose a few-shot learning method for unsupervised feature selection, which is a task to select a subset of relevant features in unlabeled data. Existing methods usually require many instances for feature selection. However, sufficient…
In this work we propose a HyperTransformer, a Transformer-based model for supervised and semi-supervised few-shot learning that generates weights of a convolutional neural network (CNN) directly from support samples. Since the dependence of…
The k-Nearest Neighbors (kNN) classifier is a fundamental non-parametric machine learning algorithm. However, it is well known that it suffers from the curse of dimensionality, which is why in practice one often applies a kNN classifier on…
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 classification aims to adapt classifiers to novel classes with a few training samples. However, the insufficiency of training data may cause a biased estimation of feature distribution in a certain class. To alleviate this problem,…
The challenge in few-shot learning is that available data is not enough to capture the underlying distribution. To mitigate this, two emerging directions are (a) using local image representations, essentially multiplying the amount of data…
Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. Such ability stems from their capacity to identify common features shared between new and previously seen images while…