Just Noticeable Difference Modeling for Deep Visual Features

• URL: http://arxiv.org/abs/2601.21933v1
• Date: Thu, 29 Jan 2026 16:22:31 GMT
• Title: Just Noticeable Difference Modeling for Deep Visual Features
• Authors: Rui Zhao, Wenrui Li, Lin Zhu, Yajing Zheng, Weisi Lin,
• Abstract summary: Just noticeable difference (JND) characterizes the maximum imperceptible distortion for images under human or machine vision.<n>We propose FeatJND, a task-aligned JND formulation that predicts the maximum per-feature perturbation map.<n>We show that FeatJND-guided step-size allocation yields clear gains over random step-size permutation and global uniform step size under the same noise budget.
• Score: 59.93185561462793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep visual features are increasingly used as the interface in vision systems, motivating the need to describe feature characteristics and control feature quality for machine perception. Just noticeable difference (JND) characterizes the maximum imperceptible distortion for images under human or machine vision. Extending it to deep visual features naturally meets the above demand by providing a task-aligned tolerance boundary in feature space, offering a practical reference for controlling feature quality under constrained resources. We propose FeatJND, a task-aligned JND formulation that predicts the maximum tolerable per-feature perturbation map while preserving downstream task performance. We propose a FeatJND estimator at standardized split points and validate it across image classification, detection, and instance segmentation. Under matched distortion strength, FeatJND-based distortions consistently preserve higher task performance than unstructured Gaussian perturbations, and attribution visualizations suggest FeatJND can suppress non-critical feature regions. As an application, we further apply FeatJND to token-wise dynamic quantization and show that FeatJND-guided step-size allocation yields clear gains over random step-size permutation and global uniform step size under the same noise budget. Our code will be released after publication.

Related papers

• Towards Robust DeepFake Detection under Unstable Face Sequences: Adaptive Sparse Graph Embedding with Order-Free Representation and Explicit Laplacian Spectral Prior [12.202765237400143]
  We propose a Laplacian-Regularized Graph Convolutional Network (LR-GCN) that robustly detects DeepFakes from noisy or unordered face sequences.<n>LR-GCN achieves state-of-the-art performance and significantly improved robustness under severe global and local disruptions.
  arXiv  Detail & Related papers  (2025-12-08T12:31:07Z)
• Saccadic Vision for Fine-Grained Visual Classification [10.681604440788854]
  Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features.<n>Existing part-based methods rely on complex localization networks that learn mappings from pixel to sample space.<n>We propose a two-stage process that first extracts peripheral features and generates a sample map.<n>We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations.
  arXiv  Detail & Related papers  (2025-09-19T07:03:37Z)
• JAFAR: Jack up Any Feature at Any Resolution [53.343826346140624]
  JAFAR is a lightweight and flexible feature upsampler for Foundation Visions.<n>It enhances the spatial resolution of visual features from any Foundation Vision to an arbitrary target resolution.<n>It generalizes remarkably well to significantly higher output scales.
  arXiv  Detail & Related papers  (2025-06-10T20:53:12Z)
• SG-JND: Semantic-Guided Just Noticeable Distortion Predictor For Image Compression [50.2496399381438]
  Just noticeable distortion (JND) represents the threshold of distortion in an image that is minimally perceptible to the human visual system. Traditional JND prediction methods only rely on pixel-level or sub-band level features. We propose a Semantic-Guided JND network to leverage semantic information for JND prediction.
  arXiv  Detail & Related papers  (2024-08-08T07:14:57Z)
• Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection [1.0358639819750703]
  In unsupervised anomaly detection (UAD) research, it is necessary to develop a computationally efficient and scalable solution. We revisit the reconstruction-by-inpainting approach and rethink to improve it by analyzing strengths and weaknesses. We propose Feature Attenuation of Defective Representation (FADeR) that only employs two layers which attenuates feature information of anomaly reconstruction.
  arXiv  Detail & Related papers  (2024-07-05T15:44:53Z)
• Boosting Visual Recognition in Real-world Degradations via Unsupervised Feature Enhancement Module with Deep Channel Prior [22.323789227447755]
  Fog, low-light, and motion blur degrade image quality and pose threats to the safety of autonomous driving. This work proposes a novel Deep Channel Prior (DCP) for degraded visual recognition. Based on this, a novel plug-and-play Unsupervised Feature Enhancement Module (UFEM) is proposed to achieve unsupervised feature correction.
  arXiv  Detail & Related papers  (2024-04-02T07:16:56Z)
• Towards Top-Down Just Noticeable Difference Estimation of Natural Images [65.14746063298415]
  Just noticeable difference (JND) estimation mainly dedicates to modeling the visibility masking effects of different factors in spatial and frequency domains. In this work, we turn to a dramatically different way to address these problems with a top-down design philosophy. Our proposed JND model can achieve better performance than several latest JND models.
  arXiv  Detail & Related papers  (2021-08-11T06:51:50Z)
• Fine-Grained Dynamic Head for Object Detection [68.70628757217939]
  We propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance. Experiments demonstrate the effectiveness and efficiency of the proposed method on several state-of-the-art detection benchmarks.
  arXiv  Detail & Related papers  (2020-12-07T08:16:32Z)
• Generative Hierarchical Features from Synthesizing Images [65.66756821069124]
  We show that learning to synthesize images can bring remarkable hierarchical visual features that are generalizable across a wide range of applications. The visual feature produced by our encoder, termed as Generative Hierarchical Feature (GH-Feat), has strong transferability to both generative and discriminative tasks.
  arXiv  Detail & Related papers  (2020-07-20T18:04:14Z)

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.