COMPAS: Representation Learning with Compositional Part Sharing for Few-Shot Classification

01/28/2021
by   Ju He, et al.
0

Few-shot image classification consists of two consecutive learning processes: 1) In the meta-learning stage, the model acquires a knowledge base from a set of training classes. 2) During meta-testing, the acquired knowledge is used to recognize unseen classes from very few examples. Inspired by the compositional representation of objects in humans, we train a neural network architecture that explicitly represents objects as a set of parts and their spatial composition. In particular, during meta-learning, we train a knowledge base that consists of a dictionary of part representations and a dictionary of part activation maps that encode frequent spatial activation patterns of parts. The elements of both dictionaries are shared among the training classes. During meta-testing, the representation of unseen classes is learned using the part representations and the part activation maps from the knowledge base. Finally, an attention mechanism is used to strengthen those parts that are most important for each category. We demonstrate the value of our compositional learning framework for a few-shot classification using miniImageNet, tieredImageNet, CIFAR-FS, and FC100, where we achieve state-of-the-art performance.

READ FULL TEXT

page 1

page 4

page 5

research
02/08/2021

Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning

The goal of few-shot learning is to learn a classifier that can recogniz...
research
10/01/2020

Few-Shot Classification By Few-Iteration Meta-Learning

Learning in a low-data regime from only a few labeled examples is an imp...
research
01/16/2013

Complexity of Representation and Inference in Compositional Models with Part Sharing

This paper describes serial and parallel compositional models of multipl...
research
09/11/2019

Few-Shot Classification on Unseen Domains by Learning Disparate Modulators

Although few-shot learning studies have advanced rapidly with the help o...
research
02/18/2020

Few-Shot Few-Shot Learning and the role of Spatial Attention

Few-shot learning is often motivated by the ability of humans to learn n...
research
05/12/2020

Compositional Few-Shot Recognition with Primitive Discovery and Enhancing

Few-shot learning (FSL) aims at recognizing novel classes given only few...
research
05/26/2023

Im-Promptu: In-Context Composition from Image Prompts

Large language models are few-shot learners that can solve diverse tasks...

Please sign up or login with your details

Forgot password? Click here to reset