mlsanityData to 7 Oct 2026

PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition

arXiv 2407.10918 ↗First posted 15 Jul 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Deep learning-based object recognition systems can be easily fooled by various adversarial perturbations. One reason for the weak robustness may be that they do not have part-based inductive bias like the human recognition process. Motivated by this, several part-based recognition models have been proposed to improve the adversarial robustness of recognition. However, due to the lack of part annotations, the effectiveness of these methods is only validated on small-scale nonstandard datasets. In this work, we propose PIN++, short for PartImageNet++, a dataset providing high-quality part segmentation annotations for all categories of ImageNet-1K (IN-1K). With these annotations, we build part-based methods directly on the standard IN-1K dataset for robust recognition. Different from previous two-stage part-based models, we propose a Multi-scale Part-supervised Model (MPM), to learn a robust representation with part annotations. Experiments show that MPM yielded better adversarial robustness on the large-scale IN-1K over strong baselines across various attack settings. Furthermore, MPM achieved improved robustness on common corruptions and several out-of-distribution datasets. The dataset, together with these results, enables and encourages researchers to explore the potential of part-based models in more real applications.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 59 of its 81 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

59 of 81 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2023Segment Anythingcited by 8,158
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  8. 2017Mask R-CNNcited by 7,259
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  11. 2013Intriguing properties of neural networkscited by 5,114
  12. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
38 more
  1. 2022A ConvNet for the 2020scited by 3,545
  2. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  3. 2016Wide Residual Networkscited by 3,057
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  8. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  9. 2019Natural Adversarial Examplescited by 1,401
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  11. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  12. 2021Grounded Language-Image Pre-trainingcited by 1,147
  13. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  14. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  15. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  16. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  17. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  18. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  19. 2021Improving Robustness using Generated Datacited by 233
  20. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  21. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  22. 2021Are Transformers More Robust Than CNNs?cited by 187
  23. 2021Partial success in closing the gap between human and machine visioncited by 185
  24. 2021Instances as Queriescited by 157
  25. 2023PACO: Parts and Attributes of Common Objectscited by 146
  26. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  27. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  28. 2022Learning Object-Language Alignments for Open-Vocabulary Object Detectioncited by 95
  29. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  30. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  31. 2022A Light Recipe to Train Robust Vision Transformerscited by 64
  32. 2018Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsingcited by 60
  33. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  34. 2015Deep Human Parsing with Active Template Regressioncited by 51
  35. 2023Going Denser with Open-Vocabulary Part Segmentationcited by 51
  36. 2022How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspectivecited by 39
  37. 2014Deformable Part Models are Convolutional Neural Networkscited by 35
  38. 2018Humans can decipher adversarial imagescited by 31

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

7 papers.

  1. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purificationcited by 24
  2. 2025Enhancing Concept Localization in CLIP-based Concept Bottleneck Modelscited by 6
  3. 2025PARTONOMY: Large Multimodal Models with Part-Level Visual Understandingcited by 4
  4. 2025PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detectioncited by 3
  5. 2026Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretabilitycited by 1
  6. 2026PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotationscited by 0
  7. 2026Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLMcited by 0