Does deep machine vision have just noticeable difference (JND)?

• URL: http://arxiv.org/abs/2102.08168v1
• Date: Tue, 16 Feb 2021 14:19:35 GMT
• Title: Does deep machine vision have just noticeable difference (JND)?
• Authors: Jian Jin, Xingxing Zhang, Xin Fu, Huan Zhang, Weisi Lin, Jian Lou, Yao Zhao
• Abstract summary: There is little exploration on the existence of Just Noticeable Difference (JND) for AI, like Deep Machine Vision (DMV) In this paper, we take an initial attempt, and demonstrate that DMV does have the JND, termed as DMVJND. It has been discovered that DMV can tolerate distorted images with average PSNR of only 9.56dB (the lower the better), by generating JND via unsupervised learning with our DMVJND-NET.
• Score: 74.68805484753442
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As an important perceptual characteristic of the Human Visual System (HVS), the Just Noticeable Difference (JND) has been studied for decades with image/video processing (e.g., perceptual image/video coding). However, there is little exploration on the existence of JND for AI, like 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 DMV does have the JND, termed as DMVJND. Besides, we propose a JND model for the classification task in DMV. It has been discovered that DMV can tolerate distorted images with average PSNR of only 9.56dB (the lower the better), by generating JND via unsupervised learning with our DMVJND-NET. In particular, a semantic-guided redundancy assessment strategy is designed to constrain the magnitude and spatial distribution of the JND. Experimental results on classification tasks demonstrate that we successfully find and model the JND for deep machine vision. Meanwhile, our DMV-JND paves a possible direction for DMV oriented image/video compression, watermarking, quality assessment, deep neural network security, and so on.

Related papers

• DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines [48.07705666485972]
  Just Recognizable Difference (JRD) represents the minimum visual difference that is detectable by machine vision. We propose a Deep Transformer based JRD (DT-JRD) prediction model for Video Coding for Machines (VCM) The accurately predicted JRD can be used reduce the coding bit rate while maintaining the accuracy of machine tasks.
  arXiv  Detail & Related papers  (2024-11-14T09:34:36Z)
• The First Comprehensive Dataset with Multiple Distortion Types for Visual Just-Noticeable Differences [40.50003266570956]
  This work establishes a generalized JND dataset with a coarse-to-fine JND selection, which contains 106 source images and 1,642 JND maps, covering 25 distortion types. A fine JND selection is carried out on the JND candidates with a crowdsourced subjective assessment.
  arXiv  Detail & Related papers  (2023-03-05T03:12:57Z)
• HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimation [69.49393407465456]
  We propose an HVS-inspired signal degradation network for JND estimation. We analyze the HVS perceptual process in JND subjective viewing to obtain relevant insights. We show that the proposed method achieves the SOTA performance for accurately estimating the redundancy of the HVS.
  arXiv  Detail & Related papers  (2022-08-16T07:53:45Z)
• JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes [75.20435924081585]
  JPerceiver can simultaneously estimate scale-aware depth and VO as well as BEV layout from a monocular video sequence. It exploits the cross-view geometric transformation (CGT) to propagate the absolute scale from the road layout to depth and VO. Experiments on Argoverse, Nuscenes and KITTI show the superiority of JPerceiver over existing methods on all the above three tasks.
  arXiv  Detail & Related papers  (2022-07-16T10:33:59Z)
• Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision [0.0]
  We perform monocular depth estimation by virtual-world supervision (MonoDEVS) and real-world SfM self-supervision. Our MonoDEVSNet outperforms previous MDE CNNs trained on monocular and even stereo sequences.
  arXiv  Detail & Related papers  (2021-03-22T22:33:49Z)
• DMD: A Large-Scale Multi-Modal Driver Monitoring Dataset for Attention and Alertness Analysis [54.198237164152786]
  Vision is the richest and most cost-effective technology for Driver Monitoring Systems (DMS) The lack of sufficiently large and comprehensive datasets is currently a bottleneck for the progress of DMS development. In this paper, we introduce the Driver Monitoring dataset (DMD), an extensive dataset which includes real and simulated driving scenarios.
  arXiv  Detail & Related papers  (2020-08-27T12:33:54Z)
• MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views [60.538802124885414]
  We present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for multi-class object detection and drivable space segmentation. MVLidarNet is able to detect and classify objects while simultaneously determining the drivable space using a single LiDAR scan as input. We show results on both KITTI and a much larger internal dataset, thus demonstrating the method's ability to scale by an order of magnitude.
  arXiv  Detail & Related papers  (2020-06-09T21:28:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.