DeepAI AI Chat
Log In Sign Up

Dense Classification and Implanting for Few-Shot Learning

by   Yann Lifchitz, et al.

Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available examples. We propose two simple and effective solutions: (i) dense classification over feature maps, which for the first time studies local activations in the domain of few-shot learning, and (ii) implanting, that is, attaching new neurons to a previously trained network to learn new, task-specific features. On miniImageNet, we improve the prior state-of-the-art on few-shot classification, i.e., we achieve 62.5 1-shot, 5-shot and 10-shot settings respectively.


Extensively Matching for Few-shot Learning Event Detection

Current event detection models under super-vised learning settings fail ...

Fine-Grain Few-Shot Vision via Domain Knowledge as Hyperspherical Priors

Prototypical networks have been shown to perform well at few-shot learni...

Few-Shot Learning via Saliency-guided Hallucination of Samples

Learning new concepts from a few of samples is a standard challenge in c...

Deep Reinforcement One-Shot Learning for Artificially Intelligent Classification Systems

In recent years there has been a sharp rise in networking applications, ...

On the Importance of Distractors for Few-Shot Classification

Few-shot classification aims at classifying categories of a novel task b...

Improved Few-Shot Visual Classification

Few-shot learning is a fundamental task in computer vision that carries ...

Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching

Dense prediction tasks are a fundamental class of problems in computer v...