Search Results for author: Songmin Dai

Found 3 papers, 1 papers with code

Unsupervised Learning of Multi-level Structures for Anomaly Detection

no code implementations25 Apr 2021 Songmin Dai, Jide Li, Lu Wang, Congcong Zhu, Yifan Wu, Xiaoqiang Li

This paper first introduces a novel method to generate anomalous data by breaking up global structures while preserving local structures of normal data at multiple levels.

Anomaly Detection

Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks

1 code implementation ICCV 2021 Congcong Zhu, Xiaoqiang Li, Jide Li, Songmin Dai

We argue that exploring the weaknesses of the detector so as to remedy them is a promising method of robust facial landmark detection.

Face Alignment Facial Landmark Detection

Learning Segmentation Masks with the Independence Prior

no code implementations12 Nov 2018 Songmin Dai, Xiaoqiang Li, Lu Wang, Pin Wu, Weiqin Tong, Yimin Chen

We get appealing results in both tasks, which shows the independence prior is useful for instance segmentation and it is possible to unsupervisedly learn instance masks with only one image.

Instance Segmentation Weakly-Supervised Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.