Related papers: Cross-Modal Few-Shot Learning: a Generative Transf…
Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled…
Few-shot classification aims to recognize novel categories with only few labeled images in each class. Existing metric-based few-shot classification algorithms predict categories by comparing the feature embeddings of query images with…
Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn…
While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models. Furthermore, a significant…
Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems. Unsupervised Few-Shot Learning (U-FSL) seeks to bridge this…
There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel…
The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples. A central challenge is that the available training examples are normally insufficient to determine which visual…
The goal of few-shot classification is to learn a model that can classify novel classes using only a few training examples. Despite the promising results shown by existing meta-learning algorithms in solving the few-shot classification…
In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated data. The fine-tuning…
Most of the few-shot learning methods learn to transfer knowledge from datasets with abundant labeled data (i.e., the base set). From the perspective of class space on base set, existing methods either focus on utilizing all classes under a…
One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet…
Deep learning based models have excelled in many computer vision tasks and appear to surpass humans' performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large…
The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data. It is challenging mainly due to two aspects: (1) it lacks good feature representation of novel classes; (2) a few of…
Deep convolutional neural networks generally perform well in underwater object recognition tasks on both optical and sonar images. Many such methods require hundreds, if not thousands, of images per class to generalize well to unseen…
The objective of few-shot object detection (FSOD) is to detect novel objects with few training samples. The core challenge of this task is how to construct a generalized feature space for novel categories with limited data on the basis of…
Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of…
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…
The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.…
Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple…
In this work, we propose a novel meta-learning approach for few-shot classification, which learns transferable prior knowledge across tasks and directly produces network parameters for similar unseen tasks with training samples. Our…