Continual Rare-Class Recognition with Emerging Novel Subclasses

06/28/2019
by   Hung Nguyen, et al.
5

Given a labeled dataset that contains a rare (or minority) class of of-interest instances, as well as a large class of instances that are not of interest, how can we learn to recognize future of-interest instances over a continuous stream? We introduce RaRecognize, which (i) estimates a general decision boundary between the rare and the majority class, (ii) learns to recognize individual rare subclasses that exist within the training data, as well as (iii) flags instances from previously unseen rare subclasses as newly emerging. The learner in (i) is general in the sense that by construction it is dissimilar to the specialized learners in (ii), thus distinguishes minority from the majority without overly tuning to what is seen in the training data. Thanks to this generality, RaRecognize ignores all future instances that it labels as majority and recognizes the recurrent as well as emerging rare subclasses only. This saves effort at test time as well as ensures that the model size grows moderately over time as it only maintains specialized minority learners. Through extensive experiments, we show that RaRecognize outperforms state-of-the art baselines on three real-world datasets that contain corporate-risk and disaster documents as rare classes.

READ FULL TEXT

page 25

page 26

page 27

research
01/29/2019

Rare geometries: revealing rare categories via dimension-driven statistics

In many situations, the classes of data points of primary interest also ...
research
06/17/2022

Active Data Discovery: Mining Unknown Data using Submodular Information Measures

Active Learning is a very common yet powerful framework for iteratively ...
research
03/13/2018

Target Driven Instance Detection

While state-of-the-art general object detectors are getting better and b...
research
10/17/2018

Learning to Separate Domains in Generalized Zero-Shot and Open Set Learning: a probabilistic perspective

This paper studies the problem of domain division problem which aims to ...
research
12/13/2018

Detecting rare visual relations using analogies

We seek to detect visual relations in images of the form of triplets t =...
research
07/19/2023

Towards Reliable Rare Category Analysis on Graphs via Individual Calibration

Rare categories abound in a number of real-world networks and play a piv...
research
07/04/2022

Anomaly-aware multiple instance learning for rare anemia disorder classification

Deep learning-based classification of rare anemia disorders is challenge...

Please sign up or login with your details

Forgot password? Click here to reset