Large-Scale Few-Shot Classification with Semi-supervised Hierarchical k-Probabilistic PCAs
This paper introduces a hierarchical semi-supervised framework for few-shot classification on large-scale datasets. The method leverages the development of self-learning-based representation learning and proposes a hierarchical semi-supervised classifier called Hierarchical k-Probabilistic Principal Component Analyzers (Hk-PPCAs), on a pretrained generic self-learned feature extractor. The classifier models the feature space using a two-level hierarchical structure. The first-level image classes and second-level super-classes are modeled as Probabilistic Principal Component Analyzers (PPCA) Gaussian distributions, which makes the framework scalable for adding new classes without retraining the whole model. The proposed PPCA-based Gaussian prototypes ensure the stability of classification under the few-shot setting and the hierarchical structure reduces the classification time from O(K) to O(K−−√) for K image classes. This makes the approach computationally efficient and practicable in large-scale classification. Experiments on ImageNet-1k and ImageNet-10k show the effectiveness of the proposed approach.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationRepresentation LearningSelf-LearningSimilar Papers 제목 키워드 기반
Learning to Self-Train for Semi-Supervised Few-Shot Classification
Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a cla…
ClassificationGeneral ClassificationMeta-LearningEmpirical Perspectives on One-Shot Semi-supervised Learning
One of the greatest obstacles in the adoption of deep neural networks for new applications is that training the network typically requires a large number of manually labeled training samples. We empirically investigate t…
image-classificationImage ClassificationVariadic Learning by Bayesian Nonparametric Deep Embedding
Learning at small or large scales of data is addressed by two strong but divided frontiers: few-shot learning and standard supervised learning. Few-shot learning focuses on sample efficiency at small scale, while supervi…
ClusteringFew-Shot LearningMeta-LearningMetric LearningScaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
The high cost of obtaining high-quality annotated data for in-context learning (ICL) has motivated the development of methods that use self-generated annotations in place of ground-truth labels. While these approaches ha…
In-Context LearningSelf-Adaptive Label Augmentation for Semi-supervised Few-shot Classification
Few-shot classification aims to learn a model that can generalize well to new tasks when only a few labeled samples are available. To make use of unlabeled data that are more abundantly available in real applications, Re…
Classification