相关论文: GenCo: An Auxiliary Generator from Contrastive Lea…

Advances in generative modeling based on GANs has motivated the community to find their use beyond image generation and editing tasks. In particular, several recent works have shown that GAN representations can be re-purposed for…

Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data. Here, the main challenge is how to construct diverse tasks for meta-learning without label information; recent…

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…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative…

Few-shot learning aims to transfer information from one task to enable generalization on novel tasks given a few examples. This information is present both in the domain and the class labels. In this work we investigate the complementary…

Few-shot segmentation enables the model to recognize unseen classes with few annotated examples. Most existing methods adopt prototype learning architecture, where support prototype vectors are expanded and concatenated with query features…

Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success,…

Training effective Generative Adversarial Networks (GANs) requires large amounts of training data, without which the trained models are usually sub-optimal with discriminator over-fitting. Several prior studies address this issue by…

As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…

Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a…

Microscopy images often suffer from high levels of noise, which can hinder further analysis and interpretation. Content-aware image restoration (CARE) methods have been proposed to address this issue, but they often require large amounts of…

The capacity to learn incrementally from an online stream of data is an envied trait of human learners, as deep neural networks typically suffer from catastrophic forgetting and stability-plasticity dilemma. Several works have previously…

The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods.…

The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on the construction side, both handcrafted and generative…

The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem…

In this work, we address the challenging task of few-shot segmentation. Previous few-shot segmentation methods mainly employ the information of support images as guidance for query image segmentation. Although some works propose to build…

Self-supervised learning has achieved remarkable success in acquiring high-quality representations from unlabeled data. The widely adopted contrastive learning framework aims to learn invariant representations by minimizing the distance…

The application of deep neural networks to remote sensing imagery is often constrained by the lack of ground-truth annotations. Adressing this issue requires models that generalize efficiently from limited amounts of labeled data, allowing…

Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on supervised learning and thus require vast amounts of training data. Due to their scarcity and minuscule…