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 …

[HTML][HTML] Managing the unknown in machine learning: Definitions, related areas, recent advances, and prospects

M Barcina-Blanco, JL Lobo, P Garcia-Bringas… - Neurocomputing, 2024‏ - Elsevier
In the rapidly evolving domain of machine learning, the ability to adapt to unforeseen
circumstances and novel data types is of paramount importance. The deployment of Artificial …

Entropic open-set active learning

B Safaei, VS Vibashan, CM de Melo… - Proceedings of the AAAI …, 2024‏ - ojs.aaai.org
Active Learning (AL) aims to enhance the performance of deep models by selecting the most
informative samples for annotation from a pool of unlabeled data. Despite impressive …

Revisiting confidence estimation: Towards reliable failure prediction

F Zhu, XY Zhang, Z Cheng… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Reliable confidence estimation is a challenging yet fundamental requirement in many risk-
sensitive applications. However, modern deep neural networks are often overconfident for …

Rcl: Reliable continual learning for unified failure detection

F Zhu, Z Cheng, XY Zhang, CL Liu… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Deep neural networks are known to be overconfident for what they don't know in the wild
which is undesirable for decision-making in high-stakes applications. Despite quantities of …

Pilora: Prototype guided incremental lora for federated class-incremental learning

H Guo, F Zhu, W Liu, XY Zhang, CL Liu - European Conference on …, 2024‏ - Springer
Existing federated learning methods have effectively dealt with decentralized learning in
scenarios involving data privacy and non-IID data. However, in real-world situations, each …

Enhancing Outlier Knowledge for Few-Shot Out-of-Distribution Detection with Extensible Local Prompts

F Zeng, Z Cheng, F Zhu, XY Zhang - arxiv preprint arxiv:2409.04796, 2024‏ - arxiv.org
Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories,
has gained prominence in practical scenarios. Recently, the advent of vision-language …

Overcoming common flaws in the evaluation of selective classification systems

J Traub, TJ Bungert, CT Lüth, M Baumgartner… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Selective Classification, wherein models can reject low-confidence predictions, promises
reliable translation of machine-learning based classification systems to real-world scenarios …

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

F Zeng, Z Cheng, F Zhu, H Wei, XY Zhang - The Thirteenth International …‏ - openreview.net
Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories,
has gained prominence in practical scenarios. Recently, the advent of vision-language …