Semantic-Rearrangement-Based Multi-Level Alignment for Domain Generalized Segmentation

no code implementations • 21 Apr 2024 • Guanlong Jiao, Chenyangguang Zhang, Haonan Yin, Yu Mo, Biqing Huang, Hui Pan, Yi Luo, Jingxian Liu

SRMA first incorporates a Semantic Rearrangement Module (SRM), which conducts semantic region randomization to enhance the diversity of the source domain sufficiently.

Semantic Segmentation

MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision

no code implementations • 18 Oct 2023 • Chenyangguang Zhang, Guanlong Jiao, Yan Di, Gu Wang, Ziqin Huang, Ruida Zhang, Fabian Manhardt, Bowen Fu, Federico Tombari, Xiangyang Ji

Previous works concerning single-view hand-held object reconstruction typically rely on supervision from 3D ground-truth models, which are hard to collect in real world.

Object Object Reconstruction

LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection

no code implementations • 16 Jul 2023 • Haonan Yin, Guanlong Jiao, Qianhui Wu, Borje F. Karlsson, Biqing Huang, Chin Yew Lin

Moreover, we are the first who pose the problem of hyperparameter selection in unsupervised anomaly detection, and propose a solution of synthesizing anomaly data for a pseudo validation set to address this problem.

Unsupervised Anomaly Detection