Projects per year
Abstract
AI-enabled systems in security, autonomous systems, safety, and healthcare do not only need to effectively detect Outof- Distribution (OoD) samples, but also to recognize Objects of Concern (OoC), e.g. multiple thorax diseases, efficiently with fewshots. Detecting OoD samples is crucial, because reporting an out-of-domain input as abnormal is better than falsely classifying it. Data samples, during inference, are not confined to a finite labelled set, and thus closed-set approaches are limiting, as they misclassify OoD inputs, and they may assign them high prediction confidence. Furthermore, although anomaly detection is possible, recognizing new OoC fast using only few-shot samples remains challenging. There is a lack of methodologies for joint anomaly detection and few-shot OoC classification. Our contribution is the development of a framework for joint few-shot OoC detection and classification and anomaly detection in the unknown previouslyunseen, in the wild, environment, which is known as Open-World Recognition (OWR). We propose a novel methodology, the data distribution boundary Contrastive Training Recognition (CTR) classifier for few-shot OWR. CTR takes advantage of labels and classes to learn the normal (and few-shot abnormal) data better, to more accurately detect OoD. The proposed model: (i) reduces failures to detect anomalies in health- and safety-critical applications for avoiding unfavourable consequences, (ii) decreases false alarms, and (iii) improves performance overall. Our framework differs from existing approaches because: (a) anomaly and OoC detection are combined, which has several benefits, including improved OoD performance, (b) the performance, accuracy, and robustness of OoD and few-shot OoC detection are improved by strengthening the estimation of the normal class distribution at the boundary of its support, self-generating samples and setting them as abnormal, and (c) the knowledge base of models is also augmented by learning class-incrementally, alleviating forgetting. CTR outperforms baselines in several settings, including on the SVHN, CIFAR-FS, and BSCD-FS ChestX and ISIC datasets.
Original language | English |
---|---|
Title of host publication | 2022 26th International Conference on Pattern Recognition (ICPR) |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 1792-1799 |
Number of pages | 8 |
ISBN (Electronic) | 978-1-6654-9062-7 |
ISBN (Print) | 978-1-6654-9063-4 |
DOIs | |
Publication status | E-pub ahead of print - 29 Nov 2022 |
Event | 26TH International Conference on Pattern Recognition - Palais des congrès de Montréal, Montréal Québec, Canada Duration: 21 Aug 2022 → 25 Aug 2022 https://www.icpr2022.com/ |
Conference
Conference | 26TH International Conference on Pattern Recognition |
---|---|
Abbreviated title | ICPR 2022 |
Country/Territory | Canada |
City | Montréal Québec |
Period | 21/08/22 → 25/08/22 |
Internet address |
Fingerprint
Dive into the research topics of 'CTR: Contrastive Training Recognition Classifier for Few-Shot Open-World Recognition'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Signal Processing in the Information Age
Davies, M. (Principal Investigator), Hopgood, J. (Co-investigator), Hospedales, T. (Co-investigator), Mulgrew, B. (Co-investigator), Thompson, J. (Co-investigator), Tsaftaris, S. (Co-investigator) & Yaghoobi Vaighan, M. (Co-investigator)
1/07/18 → 31/03/24
Project: Research