相关论文: MA 3 : Model Agnostic Adversarial Augmentation for…

We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data…

Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a lightweight synthetic…

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…

Generative models excel in creating realistic images, yet their dependency on extensive datasets for training presents significant challenges, especially in domains where data collection is costly or challenging. Current data-efficient…

Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common…

Few-shot recognition learns a recognition model with very few (e.g., 1 or 5) images per category, and current few-shot learning methods focus on improving the average accuracy over many episodes. We argue that in real-world applications we…

This paper presents FusionShot, a focal diversity optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot models. The paper makes three original contributions. First,…

Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings. As such data augmentation is…

Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. A na\"ive solution here is to train a separate model for each domain using few-shot domain…

Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We…

Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state-of-the-art approaches are largely unsuitable in scarce data regimes.…

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the…

In computer vision, it is standard practice to draw a single sample from the data augmentation procedure for each unique image in the mini-batch. However recent work has suggested drawing multiple samples can achieve higher test accuracies.…

Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples. While literature has demonstrated great successes via representation learning, in this work, we show that substantial…

In this paper, we look at cross-domain few-shot classification which presents the challenging task of learning new classes in previously unseen domains with few labelled examples. Existing methods, though somewhat effective, encounter…

Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples. Given the inherent diversity of tasks arising in existing benchmarks, recent methods use…

Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods.…

Few-shot learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labelled samples of the new classes (support set) as reference. So far, plenty of algorithms…

Few-shot learning is an important research field of machine learning in which a classifier must be trained in such a way that it can adapt to new classes which are not included in the training set. However, only small amounts of examples of…

We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…