Han, PengxiaoYe, ChangkunZhou, JiemingZhang, JingHong, JieLi, Xuesong2025-05-232025-05-2397983503654742160-7508http://www.scopus.com/inward/record.url?scp=85206447690&partnerID=8YFLogxKhttps://hdl.handle.net/1885/733752819Long-tailed imbalance distribution is a common issue in practical computer vision applications. Previous works proposed methods to address this problem, which can be categorized into several classes: re-sampling, re-weighting, transfer learning, and feature augmentation. In recent years, diffusion models have shown an impressive generation ability in many sub-problems of deep computer vision. However, its powerful generation has not been explored in long-tailed problems. We propose a new approach, the Latent-based Diffusion Model for Long-tailed Recognition (LDMLR), as a feature augmentation method to tackle the issue. First, we encode the imbalanced dataset into features using the baseline model. Then, we train a Denoising Diffusion Implicit Model (DDIM) using these encoded features to generate pseudo-features. Finally, we train the classifier using the encoded and pseudo-features from the previous two steps. The model's accuracy shows an improvement on the CIFAR-LT and ImageNet-LT datasets by using the proposed method.10enPublisher Copyright: © 2024 IEEE.diffusion modelimbalance distributionlong-tailed recognition202410.1109/CVPRW63382.2024.0027085206447690