arXiv subjects

Zhiguang Hu

Publications and source records attributed to Zhiguang Hu.

4 recordsLinked to original sources

arXiv2024

MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects

We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: Declarative Knowledge, including 875 words that describe common anomalies across various domains and specific categories, with detailed explanations for < what, why, how>, including causes and visual characteristics; and Constructivist Learning, providing 2K multiple-choice questions with varying levels of difficulty, each paired with images and corresponded answer explanations. We also propose a baseline for visual-text tasks and conduct extensive benchmarking experiments to evaluate advanced methods across different settings, highlighting the challenges and efficacy of our dataset.

cs.CV↗

arXiv2024

ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection

Current unsupervised anomaly detection approaches perform well on public datasets but struggle with specific anomaly types due to the domain gap between pre-trained feature extractors and target-specific domains. To tackle this issue, this paper presents a two-stage training strategy, called \textbf{ToCoAD}. In the first stage, a discriminative network is trained by using synthetic anomalies in a self-supervised learning manner. This network is then utilized in the second stage to provide a negative feature guide, aiding in the training of the feature extractor through bootstrap contrastive learning. This approach enables the model to progressively learn the distribution of anomalies specific to industrial datasets, effectively enhancing its generalizability to various types of anomalies. Extensive experiments are conducted to demonstrate the effectiveness of our proposed two-stage training strategy, and our model produces competitive performance, achieving pixel-level AUROC scores of 98.21\%, 98.43\% and 97.70\% on MVTec AD, VisA and BTAD respectively.

cs.CV↗

arXiv2015

Even dimensional homogeneous Finsler spaces with positive flag curvature

In this paper, we use the technique of Finslerian submersion to deduce a flag curvature formula for homogeneous Finsler spaces. Based on this formula, we give a complete classification of even-dimensional smooth coset spaces $G/H$ admitting $G$-invariant Finsler metrics with positive flag curvature. It turns out that the classification list coincides with that of the even dimensional homogeneous Riemannian manifolds with positive sectional curvature obtained by N.R. Wallach. We also find out all the coset spaces admitting invariant non-Riemannian Finsler metrics with positive flag curvature.

math.DG↗

arXiv2012

Ricci-quadratic homogeneous Randers spaces

A Finsler space is called Ricci-quadratic if its Ricci curvature $Ric(x,y)$ is quadratic in $y$. It is called a Berwald space if its Chern connection defines a linear connection directly on the underlying manifold $M$. In this article, we prove that a homogeneous Randers space is Ricci-quadratic if and only if it is of Berwald type.

math.DG↗