Text to FigureText → Imageposter

ResAD: Class-Generalizable Anomaly Detection Poster

A conference poster presenting ResAD, a framework for anomaly detection that generalizes across classes without retraining. It details the method involving residual feature generation and hypersphere constraining, alongside experimental results on MVTecAD and other datasets.

Paper context

Paper title: ResAD: A Simple Framework for Class Generalizable Anomaly Detection Abstract: A conference poster presenting ResAD, a framework for anomaly detection that generalizes across classes without retraining. It details the method involving residual feature generation and hypersphere constraining, alongside experimental results on MVTecAD and other datasets. Paper body (method & results): <!DOCTYPE html> <html lang="en"> <head> <meta content="text/html; charset=utf-8" http-equiv="content-type"/> <title>ResAD: A Simple Framework for Class Generalizable Anomaly Detection</title>  <meta content="width=device-width, initial-scale=1, shrink-to-fit=no" name="viewport"/> <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/ar5iv.0.7.9.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/ar5iv-fonts.0.7.9.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/latexml_styles.css" rel="stylesheet" type="text/css"/> <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script> <script src="https://cdnjs.cloudflare.com/ajax/libs/html2canvas/1.3.3/html2canvas.min.js"></script> <script src="/static/browse/0.3.4/js/addons_new.js"></script> <script src="/static/browse/0.3.4/js/feedbackOverlay.js"></script> <base href="/html/2410.20047v1/"/></head> <body> <nav class="ltx_page_navbar"> <nav class="ltx_TOC"> <ol class="ltx_toclist"> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S1" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">1 Introduction</a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S2" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">2 Related Work</a></li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S3" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">3 Method</a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S3.SS1" title="In 3 Method ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">3.1 Residual Feature Generating</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S3.SS2" title="In 3 Method ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">3.2 Feature Hypersphere Constraining</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S3.SS3" title="In 3 Method ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">3.3 Feature Distribution Estimating</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S3.SS4" title="In 3 Method ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">3.4 Inference and Anomaly Scoring</a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S4" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">4 Experiments</a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S4.SS1" title="In 4 Experiments ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">4.1 Experimental Setup</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S4.SS2" title="In 4 Experiments ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">4.2 Main Results</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S4.SS3" title="In 4 Experiments ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">4.3 Ablation Studies</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S4.SS4" title="In 4 Experiments ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">4.4 Generalization to Other Anomaly Detection Frameworks</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S4.SS5" title="In 4 Experiments ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">4.5 Visualization and Qualitative Results</a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#S5" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">5 Conclusion</a></li> <li class="ltx_tocentry ltx_tocentry_appendix"> <a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A1" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">A More Discussions</a> <ol class="ltx_toclist ltx_toclist_appendix"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A1.SS1" title="In Appendix A More Discussions ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">A.1 Detailed Comparison with InCTRL</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A1.SS2" title="In Appendix A More Discussions ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">A.2 Discussion on Few-Shot Normal Sample Selection Strategy</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A1.SS3" title="In Appendix A More Discussions ‣ ResAD: A Simple Framework for Class Generalizable Anomaly Detection">A.3 Feature Constraintor and Feature Distribution Estimator</a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A2" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">B Model Architecture and Complexity</a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A3" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">C Limitations</a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A4" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">D Datasets</a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A5" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">E Sensitivity of Balancing The Loss Terms</a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2410.20047v1#A6" title="In ResAD: A Simple Framework for Class Generalizable Anomaly Detection">F Additional Results</a></li> </ol></nav> </nav> <div class="ltx_page_main"> <div class="ltx_page_content"> <article class="ltx_document ltx_authors_1line"> <h1 class="ltx_title ltx_title_document">ResAD: A Simple Framework for Class Generalizable Anomaly Detection</h1> <div class="ltx_authors"> Xincheng Yao1, Zixin Chen1, Chao Gao3, Guangtao Zhai1, Chongyang Zhang1,2 1School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University 2MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University 3China Pacific Insurance (Group) Co., Ltd. {i-Dover, CZX15724137864, zhaiguangtao, sunny_zhang}@sjtu.edu.cn1 gaochao-027@cpic.com.cn3 Corresponding Author. </div> <div class="ltx_abstract"> <h6 class="ltx_title ltx_title_abstract">Abstract</h6> This paper explores the problem of class-generalizable anomaly detection, where the objective is to train one unified AD model that can generalize to detect anomalies in diverse classes from different domains without any retraining or fine-tuning on the target data. Because normal

The prompt

Above I've shared:
(1) the full paper text,
(2) all paper figures labeled by figure number,
(3) the caption for the central poster figure I'm building.

TASK: This is a CONFERENCE POSTER. **NOT** an academic-paper figure.
Style requirements:

  - Multi-section layout with a clear poster structure: large title banner
    at the top with the paper title + author/affiliation strip, then 3-6
    distinct content panels arranged in columns or a grid.
  - Large legible fonts (text must be readable at 2 m viewing distance) —
    headings ≥ 60 pt visual size in the final image.
  - Use colour blocks / panel backgrounds to delineate sections (this is
    what makes it a poster, not a single-figure diagram).
  - Aspect ratio: portrait or landscape rectangle, NOT square.

If your output looks like a standard academic-paper figure (single panel,
no title banner, dense small text, no colour blocks), you've failed the
task. Render the COMPLETE poster, not just the central figure.

Just give me the final poster image.

Try this prompt now

Open it inside the generator with the prompt pre-filled.

Try this prompt

Related prompts

Text to Figure

ResAD: Class-Generalizable Anomaly Detection Poster

Paper context

The prompt

Try this prompt now

Related prompts

PINN Framework Pipeline for Microscopy Data

DP-FTRL Privacy Amplification Analysis — Conference Poster

NC-TTT: Noise-Contrastive Test-Time Training Poster