1 code implementation • 6 Apr 2024 • Pengxiao Han, Changkun Ye, Jieming Zhou, Jing Zhang, Jie Hong, Xuesong Li
We propose a new approach, the Latent-based Diffusion Model for Long-tailed Recognition (LDMLR), as a feature augmentation method to tackle the issue.
1 code implementation • ICCV 2023 • Jiawei Liu, Changkun Ye, Shan Wang, Ruikai Cui, Jing Zhang, Kaihao Zhang, Nick Barnes
To improve model calibration, we propose Adaptive Stochastic Label Perturbation (ASLP) which learns a unique label perturbation level for each training image.
no code implementations • 11 Oct 2022 • Changkun Ye, Nick Barnes, Lars Petersson, Russell Tsuchida
Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process.