Related papers: A Relational Model for One-Shot Classification
This paper introduces the DeepATLAS foundational model for localization tasks in the domain of high-dimensional biomedical data. Upon convergence of the proposed self-supervised objective, a pretrained model maps an input to an…
In this paper, we introduce the new ideas of augmenting Convolutional Neural Networks (CNNs) with Memory and learning to learn the network parameters for the unlabelled images on the fly in one-shot learning. Specifically, we present Memory…
We demonstrate a deep learning-based offline autofocusing method, termed Deep-R, that is trained to rapidly and blindly autofocus a single-shot microscopy image of a specimen that is acquired at an arbitrary out-of-focus plane. We…
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…
We present a new approach, called meta-meta classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of learners, where each learner has high bias and low variance…
Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. Although previous approaches pre-define the type of dataset bias to prevent the…
Few-shot image classification aims to accurately classify unlabeled images using only a few labeled samples. The state-of-the-art solutions are built by deep learning, which focuses on designing increasingly complex deep backbones.…
Few-shot learning or meta-learning leverages the data scarcity problem in machine learning. Traditionally, training data requires a multitude of samples and labeling for supervised learning. To address this issue, we propose a one-shot…
We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we propose and evaluate several novel models consisting of (1) an…
Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called…
This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples. The new…
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…
Object recognition has become a crucial part of machine learning and computer vision recently. The current approach to object recognition involves Deep Learning and uses Convolutional Neural Networks to learn the pixel patterns of the…
Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class. One way to alleviate this problem is to acquire a strong inductive bias via meta-learning on similar tasks. In this paper, we show…
This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a…
Estimating the pose of an unseen object is the goal of the challenging one-shot pose estimation task. Previous methods have heavily relied on feature matching with great success. However, these methods are often inefficient and limited by…
We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn…
Few-shot learning presents a challenging paradigm for training discriminative models on a few training samples representing the target classes to discriminate. However, classification methods based on deep learning are ill-suited for such…
Zero-shot learning (ZSL) models rely on learning a joint embedding space where both textual/semantic description of object classes and visual representation of object images can be projected to for nearest neighbour search. Despite the…
When data is unlabelled and the target task is not known a priori, divergent search offers a strategy for learning a wide range of skills. Having such a repertoire allows a system to adapt to new, unforeseen tasks. Unlabelled image data is…