activity
20172022
most citedA Unified Model for Multi-class Anomaly Detection

87 citations · 136 across the 7 of their papers we have counts for

collaborators
Showing 2022 · cs.CVShow all

5 papers · 2 filters

cs.CV2022★ 2 cited

ADTR: Anomaly Detection Transformer with Feature Reconstruction

Zhiyuan You, Kai Yang, Wenhan Luo +3

Anomaly detection with only prior knowledge from normal samples attracts more attention because of the lack of anomaly samples. Existing CNN-based pixel reconstruction approaches s…

cs.CV2022★ 87 cited

A Unified Model for Multi-class Anomaly Detection

Zhiyuan You, Lei Cui, Yujun Shen +4

Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplish…

cs.CV2022★ 1 cited

The Z-axis, X-axis, Weight and Disambiguation Methods for Constructing Local Reference Frame in 3D Registration: An Evaluation

Bao Zhao, Xianyong Fang, Jiahui Yue +3

The local reference frame (LRF), as an independent coordinate system generated on a local 3D surface, is widely used in 3D local feature descriptor construction and 3D transformati…

cs.CV2022★ 5 cited

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Yuchao Wang, Haochen Wang, Yujun Shen +6

The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predict…

cs.CV2022

Few-shot Object Counting with Similarity-Aware Feature Enhancement

Zhiyuan You, Kai Yang, Wenhan Luo +3

This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i.e., described by one or several support images) occurring in the query ima…