Learning to Learn Image Classifiers with Informative Visual Analogy

10/17/2017
by   Linjun Zhou, et al.
0

In recent years, we witnessed a huge success of Convolutional Neural Networks on the task of the image classification. However, these models are notoriously data hungry and require tons of training images to learn the parameters. In contrast, people are far better learner who can learn a new concept very fast with only a few samples. The plausible mysteries making the difference are two fundamental learning mechanisms: learning to learn and learning by analogy. In this paper, we attempt to investigate a new human-like learning method by organically combining these two mechanisms. In particular, we study how to generalize the classification parameters of previously learned concepts to a new concept. we first propose a novel Visual Analogy Network Embedded Regression (VANER) model to jointly learn a low-dimensional embedding space and a linear mapping function from the embedding space to classification parameters for base classes. We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes. By inputting the learned embedding into VANER, we can derive the classification parameters for the new class.These classification parameters are purely generalized from base classes (i.e. transferred classification parameters), while the samples in the new class, although only a few, can also be exploited to generate a set of classification parameters (i.e. model classification parameters). Therefore, we further investigate the fusion strategy of the two kinds of parameters so that the prior knowledge and data knowledge can be fully leveraged. We also conduct extensive experiments on ImageNet and the results show that our method can consistently and significantly outperform state-of-the-art baselines.

READ FULL TEXT
research
11/22/2022

Adaptive Prototypical Networks

Prototypical network for Few shot learning tries to learn an embedding f...
research
11/08/2021

SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning

Teaching machines to recognize a new category based on few training samp...
research
11/05/2022

Prototypical quadruplet for few-shot class incremental learning

Many modern computer vision algorithms suffer from two major bottlenecks...
research
05/31/2019

Subspace Networks for Few-shot Classification

We propose subspace networks for the problem of few-shot classification,...
research
03/01/2020

Novelty-Prepared Few-Shot Classification

Few-shot classification algorithms can alleviate the data scarceness iss...
research
09/15/2022

Visual Recognition with Deep Nearest Centroids

We devise deep nearest centroids (DNC), a conceptually elegant yet surpr...
research
01/17/2013

Affinity Weighted Embedding

Supervised (linear) embedding models like Wsabie and PSI have proven suc...

Please sign up or login with your details

Forgot password? Click here to reset