mlsanityData to 7 Oct 2026

Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks

arXiv 2409.18235 ↗First posted 26 Sep 2024cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs), while increasingly deployed in many applications, struggle with robustness against anomalous and out-of-distribution (OOD) data. Current OOD benchmarks often oversimplify, focusing on single-object tasks and not fully representing complex real-world anomalies. This paper introduces a new, straightforward method employing graph structures and topological features to effectively detect both far-OOD and near-OOD data. We convert images into networks of interconnected human understandable features or visual concepts. Through extensive testing on two novel tasks, including ablation studies with large vocabularies and diverse tasks, we demonstrate the method's effectiveness. This approach enhances DNN resilience to OOD data and promises improved performance in various applications.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

31 of 56 references.

References · 31

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  7. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
19 more
  1. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  3. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  4. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  5. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  6. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  7. 2015A note on the evaluation of generative modelscited by 291
  8. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  9. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  10. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  11. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  12. 2020Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Modelscited by 116
  13. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  14. 2018NetLSD: Hearing the Shape of a Graphcited by 51
  15. 2016Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenescited by 50
  16. 2020CSKG: The CommonSense Knowledge Graphcited by 45
  17. 2021A Survey on Open Set Recognitioncited by 25
  18. 2018A Simple Baseline Algorithm for Graph Classificationcited by 15
  19. 2021Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterizationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 3.

4 papers.

  1. 2024Forte : Finding Outliers with Representation Typicality Estimationcited by 9
  2. 2026Trust The Typicalcited by 3
  3. 2026Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separationcited by 3
  4. 2026Context Determines Optimal Architecture in Materials Segmentationcited by 1