Add to ORKGDespite impressive progress in deep learning, generalizing far beyond the training distribution is an important open challenge. In this work, we consider few-shot classification, and aim to shed light on what makes some novel classes easier to learn than others, and what types of learned representations generalize better. To this end, we define a new paradigm in terms of attributes -- simple building blocks of which concepts are formed -- as a means of quantifying the degree of relatedness of different concepts. Our empirical analysis reveals that supervised learning generalizes poorly to new attributes, but a combination of self-supervised pretraining with supervised finetuning leads to stronger generalization. The benefit of self-supervis...
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing ...
Deep learning models have consistently produced state-of-the-art results on large, labelled datasets...
Different from deep learning with large scale supervision, few-shot learning aims to learn the sampl...
Deep learning has recently driven remarkable progress in several applications, including image class...
A two-stage training paradigm consisting of sequential pre-training and meta-training stages has bee...
A few-shot generative model should be able to generate data from a novel distribution by only observ...
Single image-level annotations only correctly describe an often small subset of an image's content, ...
Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which preven...
This paper introduces a generalized few-shot segmentation framework with a straightforward training ...
Current few-shot learning models capture visual object relations in the so-called meta-learning sett...
Few-shot classification requires deep neural networks to learn generalized representations only from...
Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes wit...
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal ...
Doctor of PhilosophyDepartment of Computer ScienceWilliam H HsuHumans are capable of learning a spec...
Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot c...
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing ...
Deep learning models have consistently produced state-of-the-art results on large, labelled datasets...
Different from deep learning with large scale supervision, few-shot learning aims to learn the sampl...
Deep learning has recently driven remarkable progress in several applications, including image class...
A two-stage training paradigm consisting of sequential pre-training and meta-training stages has bee...
A few-shot generative model should be able to generate data from a novel distribution by only observ...
Single image-level annotations only correctly describe an often small subset of an image's content, ...
Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which preven...
This paper introduces a generalized few-shot segmentation framework with a straightforward training ...
Current few-shot learning models capture visual object relations in the so-called meta-learning sett...
Few-shot classification requires deep neural networks to learn generalized representations only from...
Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes wit...
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal ...
Doctor of PhilosophyDepartment of Computer ScienceWilliam H HsuHumans are capable of learning a spec...
Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot c...
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing ...
Deep learning models have consistently produced state-of-the-art results on large, labelled datasets...
Different from deep learning with large scale supervision, few-shot learning aims to learn the sampl...