Federated learning aims to facilitate collaborative training among multiple clients with data
heterogeneity in a privacy-preserving manner, which either generates the generalized …

The prevalence of long-tailed distributions in real-world data often results in classification
models favoring the dominant classes, neglecting the less frequent ones. Current …

Out-of-distribution issues lead to different optimization directions between clients, which
weakens collaborative modeling in federated learning. Existing methods aims to decouple …

Classifying videos differs from that of images in the need to capture the information on what
has happened, instead of what is in the frames. Conventional methods typically follow the …

Image classification models often demonstrate unstable performance in real-world
applications due to variations in image information, driven by differing visual perspectives of …

Image classification algorithms are commonly based on the Independent and Identically
Distribution (iid) assumption, but in practice, the Out‐Of‐Distribution (OOD) problem widely …

Abstract 3D scene understanding and reconstruction aims to obtain a concise scene
representation from images and reconstruct the complete scene, including the scene layout …

Data imbalance across clients in federated learning often leads to different local feature
space partitions, harming the global model's generalization ability. Existing methods either …