# Just Noticeable Difference for Deep Machine Vision

arXiv: https://arxiv.org/abs/2102.08168 · HTML: https://mlsanity.com/paper/2102.08168/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 16 Feb 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Video-to-Video Synthesis](https://mlsanity.com/paper/1808.06601/) (2018)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [DualGAN: Unsupervised Dual Learning for Image-to-Image Translation](https://mlsanity.com/paper/1704.02510/) (2017)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors](https://mlsanity.com/paper/1807.07978/) (2018)
- [Improving Black-box Adversarial Attacks with a Transfer-based Prior](https://mlsanity.com/paper/1906.06919/) (2019)
- [Self-produced Guidance for Weakly-supervised Object Localization](https://mlsanity.com/paper/1807.08902/) (2018)
- [Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks](https://mlsanity.com/paper/1906.04392/) (2019)
- [VideoSet: A Large-Scale Compressed Video Quality Dataset Based on JND Measurement](https://mlsanity.com/paper/1701.01500/) (2017)
- [Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections](https://mlsanity.com/paper/1606.08921/) (2016)
- [Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compression](https://mlsanity.com/paper/1807.00270/) (2018)
- [Hybrid-Attention Guided Network with Multiple Resolution Features for Person Re-Identification](https://mlsanity.com/paper/2009.07536/) (2020)
- [DeepQoE: A unified Framework for Learning to Predict Video QoE](https://mlsanity.com/paper/1804.03481/) (2018)

## Built on by (most cited first, 19 of 19)

- [Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework](https://mlsanity.com/paper/2307.12626/) (2023)
- [Just Noticeable Difference for Large Multimodal Models](https://mlsanity.com/paper/2507.00490/) (2025)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [Full RGB Just Noticeable Difference (JND) Modelling](https://mlsanity.com/paper/2203.00629/) (2022)
- [MUGSQA: Novel Multi-Uncertainty-Based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarks](https://mlsanity.com/paper/2511.06830/) (2025)
- [A New Image Codec Paradigm for Human and Machine Uses](https://mlsanity.com/paper/2112.10071/) (2021)
- [Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation](https://mlsanity.com/paper/2206.08638/) (2022)
- [JND-Based Perceptual Optimization For Learned Image Compression](https://mlsanity.com/paper/2302.13092/) (2023)
- [Customizable ROI-Based Deep Image Compression](https://mlsanity.com/paper/2507.00373/) (2025)
- [Just Noticeable Difference Modeling for Deep Visual Features](https://mlsanity.com/paper/2601.21933/) (2026)
- [DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines](https://mlsanity.com/paper/2411.09308/) (2024)
- [Scaling Audio-Visual Quality Assessment Dataset via Crowdsourcing](https://mlsanity.com/paper/2602.22659/) (2026)
- [HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimation](https://mlsanity.com/paper/2208.07583/) (2022)
- [Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach](https://mlsanity.com/paper/2412.17477/) (2024)
- [Just Noticeable Difference Modeling for Face Recognition System](https://mlsanity.com/paper/2209.05856/) (2022)
- [Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models](https://mlsanity.com/paper/2508.19850/) (2025)
- [CI-ICM: Channel Importance-driven Learned Image Coding for Machines](https://mlsanity.com/paper/2604.05347/) (2026)
- [Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application](https://mlsanity.com/paper/2604.09421/) (2026)
- [Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models](https://mlsanity.com/paper/2608.21247/) (2026)

## 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.