Alignment Based Matching Networks for One-Shot Classification and Open-Set Recognition

03/11/2019
by   Paresh Malalur, et al.
0

Deep learning for object classification relies heavily on convolutional models. While effective, CNNs are rarely interpretable after the fact. An attention mechanism can be used to highlight the area of the image that the model focuses on thus offering a narrow view into the mechanism of classification. We expand on this idea by forcing the method to explicitly align images to be classified to reference images representing the classes. The mechanism of alignment is learned and therefore does not require that the reference objects are anything like those being classified. Beyond explanation, our exemplar based cross-alignment method enables classification with only a single example per category (one-shot). Our model cuts the 5-way, 1-shot error rate in Omniglot from 2.1 while simultaneously providing point-wise alignment information providing some understanding on what the network is capturing. This method of alignment also enables the recognition of an unsupported class (open-set) in the one-shot setting while maintaining an F1-score of above 0.5 for Omniglot even with 19 other distracting classes while baselines completely fail to separate the open-set class in the one-shot setting.

READ FULL TEXT

page 7

page 9

research
06/28/2022

Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting

Keyword spotting is the task of detecting a keyword in streaming audio. ...
research
07/31/2021

Learning Few-shot Open-set Classifiers using Exemplar Reconstruction

We study the problem of how to identify samples from unseen categories (...
research
03/25/2021

Learning Dynamic Alignment via Meta-filter for Few-shot Learning

Few-shot learning (FSL), which aims to recognise new classes by adapting...
research
10/20/2022

Visual-Semantic Contrastive Alignment for Few-Shot Image Classification

Few-Shot learning aims to train and optimize a model that can adapt to u...
research
06/27/2019

Few-Shot Video Classification via Temporal Alignment

There is a growing interest in learning a model which could recognize no...
research
04/22/2022

iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition

Image classification, which classifies images by pre-defined categories,...
research
07/08/2014

Regression-Based Image Alignment for General Object Categories

Gradient-descent methods have exhibited fast and reliable performance fo...

Please sign up or login with your details

Forgot password? Click here to reset