Active generalized category discovery

S Ma, F Zhu, Z Zhong, XY Zhang… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Abstract Generalized Category Discovery (GCD) is a pragmatic and challenging open-world
task which endeavors to cluster unlabeled samples from both novel and old classes …

[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 …

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 …

Dual mean-teacher: An unbiased semi-supervised framework for audio-visual source localization

Y Guo, S Ma, H Su, Z Wang, Y Zhao… - Advances in …, 2023‏ - proceedings.neurips.cc
Abstract Audio-Visual Source Localization (AVSL) aims to locate sounding objects within
video frames given the paired audio clips. Existing methods predominantly rely on self …

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 …

Review on machine learning application in tissue engineering: What has been done so far? Application areas, challenges, and perspectives

O Jeznach, S Tabakoglu, A Zaszczyńska… - Journal of Materials …, 2024‏ - Springer
Artificial intelligence and machine learning (ML) approaches have recently been getting
much of researchers' attention. The growing interest in these methods results from the fast …

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 …

Towards extracting ethical concerns-related software requirements from app reviews

A Sorathiya, G Ginde - Proceedings of the 39th IEEE/ACM International …, 2024‏ - dl.acm.org
As mobile applications become increasingly integral to our daily lives, concerns about ethics
have grown drastically. Users share their experiences, report bugs, and request new …

SelEx: Self-expertise in Fine-Grained Generalized Category Discovery

S Rastegar, M Salehi, YM Asano, H Doughty… - … on Computer Vision, 2024‏ - Springer
In this paper, we address Generalized Category Discovery, aiming to simultaneously
uncover novel categories and accurately classify known ones. Traditional methods, which …

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 …