paper-with-me

홈 › Papers

Continual Improvement of Threshold-Based Novelty Detection

2023-09-05 · Abe Ejilemele, Jorge Mendez-Mendez

When evaluated in dynamic, open-world situations, neural networks struggle to detect unseen classes. This issue complicates the deployment of continual learners in realistic environments where agents are not explicitly informed when novel categories are encountered. A common family of techniques for detecting novelty relies on thresholds of similarity between observed data points and the data used for training. However, these methods often require manually specifying (ahead of time) the value of these thresholds, and are therefore incapable of adapting to the nature of the data. We propose a new method for automatically selecting these thresholds utilizing a linear search and leave-one-out cross-validation on the ID classes. We demonstrate that this novel method for selecting thresholds results in improved total accuracy on MNIST, Fashion MNIST, and CIFAR-10.

📄 PDF Abstract BibTeX arXiv:2309.02551

Code (0)

등록된 구현이 없습니다.

Tasks

Novelty Detection

Similar Papers 제목 키워드 기반

Continual Novelty Detection

2021-06-24 · Rahaf Aljundi, Daniel Olmeda Reino, Nikolay Chumerin, Richard E. Turner

Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, re…

Continual LearningNovelty Detection

CND-IDS: Continual Novelty Detection for Intrusion Detection Systems

2025-02-19 · Sean Fuhrman, Onat Gungor, Tajana Rosing

Intrusion detection systems (IDS) play a crucial role in IoT and network security by monitoring system data and alerting to suspicious activities. Machine learning (ML) has emerged as a promising solution for IDS, offeri…

Continual LearningIntrusion DetectionNovelty Detection

SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries

2022-06-28 · Meghna Gummadi, David Kent, Jorge A. Mendez, Eric Eaton

While deep neural networks (DNNs) have achieved impressive classification performance in closed-world learning scenarios, they typically fail to generalize to unseen categories in dynamic open-world environments, in whic…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+2

Open-World Continual Learning: Unifying Novelty Detection and Continual Learning

2023-04-20 · Gyuhak Kim, Changnan Xiao, Tatsuya Konishi, Zixuan Ke 외

As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or lea…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+2

Deep Transfer Learning for Multiple Class Novelty Detection

2019-03-06 · CVPR 2019 6 · Pramuditha Perera, Vishal M. Patel

We propose a transfer learning-based solution for the problem of multiple class novelty detection. In particular, we propose an end-to-end deep-learning based approach in which we investigate how the knowledge contained …

Novelty DetectionTransfer Learning