Just Noticeable Difference for Deep Machine Vision

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