Label Hallucination for Few-Shot Classification

by   Yiren Jian, et al.

Few-shot classification requires adapting knowledge learned from a large annotated base dataset to recognize novel unseen classes, each represented by few labeled examples. In such a scenario, pretraining a network with high capacity on the large dataset and then finetuning it on the few examples causes severe overfitting. At the same time, training a simple linear classifier on top of "frozen" features learned from the large labeled dataset fails to adapt the model to the properties of the novel classes, effectively inducing underfitting. In this paper we propose an alternative approach to both of these two popular strategies. First, our method pseudo-labels the entire large dataset using the linear classifier trained on the novel classes. This effectively "hallucinates" the novel classes in the large dataset, despite the novel categories not being present in the base database (novel and base classes are disjoint). Then, it finetunes the entire model with a distillation loss on the pseudo-labeled base examples, in addition to the standard cross-entropy loss on the novel dataset. This step effectively trains the network to recognize contextual and appearance cues that are useful for the novel-category recognition but using the entire large-scale base dataset and thus overcoming the inherent data-scarcity problem of few-shot learning. Despite the simplicity of the approach, we show that that our method outperforms the state-of-the-art on four well-established few-shot classification benchmarks.


page 1

page 2

page 3

page 4


Cooperative Bi-path Metric for Few-shot Learning

Given base classes with sufficient labeled samples, the target of few-sh...

Incremental Few-Shot Learning with Attention Attractor Networks

Machine learning classifiers are often trained to recognize a set of pre...

Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification

Rare diseases are characterized by low prevalence and are often chronica...

Generative Low-Shot Network Expansion

Conventional deep learning classifiers are static in the sense that they...

Impact of base dataset design on few-shot image classification

The quality and generality of deep image features is crucially determine...

Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes

Few-shot classification (FSC), the task of adapting a classifier to unse...

Pseudo Shots: Few-Shot Learning with Auxiliary Data

In many practical few-shot learning problems, even though labeled exampl...

Please sign up or login with your details

Forgot password? Click here to reset