Open-world machine learning: A review and new outlooks

F Zhu, S Ma, Z Cheng, XY Zhang, Z Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Machine learning has achieved remarkable success in many applications. However,
existing studies are largely based on the closed-world assumption, which assumes that the …

Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning

M Xu, H Kim, J Yang, A Fuentes, Y Meng… - Frontiers in Plant …, 2023 - frontiersin.org
Recent advancements in deep learning have brought significant improvements to plant
disease recognition. However, achieving satisfactory performance often requires high …

Lmc: Large model collaboration with cross-assessment for training-free open-set object recognition

H Qu, X Hui, Y Cai, J Liu - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Open-set object recognition aims to identify if an object is from a class that has been
encountered during training or not. To perform open-set object recognition accurately, a key …

Feature selection for classification with Spearman's rank correlation coefficient-based self-information in divergence-based fuzzy rough sets

J Jiang, X Zhang, Z Yuan - Expert Systems with Applications, 2024 - Elsevier
Feature selection facilitates uncertainty disposal and information mining, and it has received
widespread research interests. Divergence-based fuzzy rough sets (Div-FRSs), a new kind …

Towards trustworthy dataset distillation

S Ma, F Zhu, Z Cheng, XY Zhang - Pattern Recognition, 2025 - Elsevier
Efficiency and trustworthiness are two eternal pursuits when applying deep learning in
practical scenarios. Considering efficiency, dataset distillation (DD) endeavors to reduce …

Openmix+: Revisiting data augmentation for open set recognition

G Jiang, P Zhu, Y Wang, Q Hu - IEEE Transactions on Circuits …, 2023 - ieeexplore.ieee.org
Open set recognition requires models to recognize samples of known classes learned in the
training set while reject unknowns not learned. Compared with the structural risk …

Unified classification and rejection: A one-versus-all framework

Z Cheng, XY Zhang, CL Liu - Machine Intelligence Research, 2024 - Springer
Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-
of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural …

Open set classification of gan-based image manipulations via a vit-based hybrid architecture

J Wang, O Alamayreh, B Tondi… - Proceedings of the …, 2023 - openaccess.thecvf.com
Classification of AI-manipulated content is receiving great attention, for distinguishing
different types of manipulations. Most of the methods developed so far fail in the open-set …

Orientational clustering learning for open-set hyperspectral image classification

H Xu, W Chen, C Tan, H Ning, H Sun… - IEEE Geoscience and …, 2024 - ieeexplore.ieee.org
Recently, some literature has begun to pay attention to the open-set problem in remote
sensing application scenarios and studied various open-set hyperspectral image …

Improving open set recognition via visual prompts distilled from common-sense knowledge

S Kim, HI Kim, YM Ro - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
Open Set Recognition (OSR) poses significant challenges in distinguishing known from
unknown classes. In OSR, the overconfidence problem has become a persistent obstacle …