OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning

by   Mamshad Nayeem Rizve, et al.

Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while relying on a small set of labeled data. One common assumption in most SSL methods is that the labeled and unlabeled data are from the same underlying data distribution. However, this is hardly the case in many real-world scenarios, which limits their applicability. In this work, instead, we attempt to solve the recently proposed challenging open-world SSL problem that does not make such an assumption. In the open-world SSL problem, the objective is to recognize samples of known classes, and simultaneously detect and cluster samples belonging to novel classes present in unlabeled data. This work introduces OpenLDN that utilizes a pairwise similarity loss to discover novel classes. Using a bi-level optimization rule this pairwise similarity loss exploits the information available in the labeled set to implicitly cluster novel class samples, while simultaneously recognizing samples from known classes. After discovering novel classes, OpenLDN transforms the open-world SSL problem into a standard SSL problem to achieve additional performance gains using existing SSL methods. Our extensive experiments demonstrate that OpenLDN outperforms the current state-of-the-art methods on multiple popular classification benchmarks while providing a better accuracy/training time trade-off.


page 1

page 2

page 3

page 4


Semi-Supervised Learning in the Few-Shot Zero-Shot Scenario

Semi-Supervised Learning (SSL) leverages both labeled and unlabeled data...

Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning

Semi-supervised learning (SSL) has been proposed to leverage unlabeled d...

Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

In open-world semi-supervised learning, a machine learning model is task...

Open-World Learning Without Labels

Open-world learning is a problem where an autonomous agent detects thing...

Towards Semi-supervised Universal Graph Classification

Graph neural networks have pushed state-of-the-arts in graph classificat...

Spacing Loss for Discovering Novel Categories

Novel Class Discovery (NCD) is a learning paradigm, where a machine lear...

Towards Realistic Semi-Supervised Learning

Deep learning is pushing the state-of-the-art in many computer vision ap...

Please sign up or login with your details

Forgot password? Click here to reset