mlsanityData to 7 Oct 2026

Just Noticeable Difference for Deep Machine Vision

arXiv 2102.08168 ↗First posted 16 Feb 2021cs.CV eess.IVcited by 19

Not on the map. Why?

Abstract (arXiv)

As an important perceptual characteristic of the Human Visual System (HVS), the Just Noticeable Difference (JND) has been studied for decades with image and video processing (e.g., perceptual visual signal compression). However, there is little exploration on the existence of JND for the Deep Machine Vision (DMV), although the DMV has made great strides in many machine vision tasks. In this paper, we take an initial attempt, and demonstrate that the DMV has the JND, termed as the DMV-JND. We then propose a JND model for the image classification task in the DMV. It has been discovered that the DMV can tolerate distorted images with average PSNR of only 9.56dB (the lower the better), by generating JND via unsupervised learning with the proposed DMV-JND-NET. In particular, a semantic-guided redundancy assessment strategy is designed to restrain the magnitude and spatial distribution of the DMV-JND. Experimental results on image classification demonstrate that we successfully find the JND for deep machine vision. Our DMV-JND facilitates a possible direction for DMV-oriented image and video compression, watermarking, quality assessment, deep neural network security, and so on.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 26 of its 50 references that are in the map. First posted on arXiv 16 Feb 2021.

Builds on

26 of 50 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2016Adversarial Machine Learning at Scalecited by 934
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  10. 2016Universal adversarial perturbationscited by 774
  11. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  12. 2018Video-to-Video Synthesiscited by 388
14 more
  1. 2017Residual Attention Network for Image Classificationcited by 385
  2. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  3. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
  4. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  5. 2018Adversarial Complementary Learning for Weakly Supervised Object Localizationcited by 166
  6. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  7. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  8. 2018Self-produced Guidance for Weakly-supervised Object Localizationcited by 72
  9. 2019Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attackscited by 35
  10. 2017VideoSet: A Large-Scale Compressed Video Quality Dataset Based on JND Measurementcited by 33
  11. 2016Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connectionscited by 30
  12. 2018Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compressioncited by 6
  13. 2020Hybrid-Attention Guided Network with Multiple Resolution Features for Person Re-Identificationcited by 2
  14. 2018DeepQoE: A unified Framework for Learning to Predict Video QoEcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 2; 2024: 2; 2025: 4; 2026: 5.

19 papers.

Sort:

By area:

  1. 2023Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Frameworkcited by 11
  2. 2025Just Noticeable Difference for Large Multimodal Modelscited by 9
  3. 2022Perceptual Video Coding for Machines via Satisfied Machine Ratio Modelingcited by 7
  4. 2022Full RGB Just Noticeable Difference (JND) Modellingcited by 4
  5. 2025MUGSQA: Novel Multi-Uncertainty-Based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarkscited by 4
  6. 2021A New Image Codec Paradigm for Human and Machine Usescited by 3
  7. 2022Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generationcited by 3
  8. 2023JND-Based Perceptual Optimization For Learned Image Compressioncited by 3
  9. 2025Customizable ROI-Based Deep Image Compressioncited by 3
  10. 2026Just Noticeable Difference Modeling for Deep Visual Featurescited by 3
  11. 2024DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machinescited by 2
  12. 2026Scaling Audio-Visual Quality Assessment Dataset via Crowdsourcingcited by 2
7 more
  1. 2022HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimationcited by 1
  2. 2024Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approachcited by 1
  3. 2022Just Noticeable Difference Modeling for Face Recognition Systemcited by 0
  4. 2025Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Modelscited by 0
  5. 2026CI-ICM: Channel Importance-driven Learned Image Coding for Machinescited by 0
  6. 2026Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Applicationcited by 0
  7. 2026Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Modelscited by 0