Image-Scale Robustness and Visual Recognition Performance: A Cross-Architecture Analysis

• URL: http://arxiv.org/abs/2609.06051v1
• Date: Sat, 05 Sep 2026 12:12:00 GMT
• Title: Image-Scale Robustness and Visual Recognition Performance: A Cross-Architecture Analysis
• Abstract summary: We examine whether scale robustness exhibits a common quantitative structure across modern vision models.<n>We evaluate 20 pretrained ImageNet-1K classifiers spanning seven architectural families.
• Score: 2.2505457850833284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The sensitivity of visual recognition models to changes in image scale is well established, yet the factors governing this sensitivity across heterogeneous architectures remain unclear. In this work, we investigate whether scale robustness exhibits a common quantitative structure across modern vision models. We evaluate 20 pretrained ImageNet-1K classifiers spanning seven architectural families, including convolutional, mobile, efficient, and Transformer-based architectures. By systematically reducing input image scale, we construct scale-accuracy response curves and define a characteristic scale as a compact measure of the onset of substantial recognition degradation. We then examine the relationship between characteristic scale and baseline recognition accuracy, model parameter count, architectural family, and representation stability. A strong inverse association is observed between baseline accuracy and characteristic scale (Pearson r = -0.890, R^2= 0.792, p < 10^-6). This relationship remains stable under bootstrap resampling, leave-one-architecture-out analysis, and leave-one-family-out analysis. In contrast, parameter count provides negligible additional explanatory power after controlling for baseline accuracy (p = 0.80), while architectural family does not provide significant incremental explanatory power. Furthermore, characteristic scale shows essentially no association with representation stability (r = -0.003, p = 0.991). These results indicate that, across the studied models, scale robustness is strongly organized by baseline recognition performance rather than simply by model size, architectural family, or representation stability. The study provides an empirical framework for characterizing scale robustness across vision architectures and identifies a reproducible accuracy-scale regularity that warrants further theoretical investigation.

Related papers

• Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations [0.431493144418712]
  Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices.<n>This study presents a systematic evaluation on how static PTQ affects the interpretability / explainability of five widely used CNN architectures.
  arXiv  Detail & Related papers  (2026-07-24T19:26:47Z)
• SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation [4.096797783087454]
  SaliencyDecor is a training framework that enforces feature decorrelation to improve attribution fidelity without modifying saliency methods or model architectures.<n>We show that our method produces substantially sharper and more object-focused saliency maps while simultaneously improving predictive performance.
  arXiv  Detail & Related papers  (2026-04-28T07:25:07Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• Leveraging Persistence Image to Enhance Robustness and Performance in Curvilinear Structure Segmentation [17.808385571339624]
  PIs-Regressor learns persistence image (PI) - finite, differentiable representations of topological features - directly from data.<n>Unlike existing methods that depend heavily on handcrafted loss functions, our approach directly incorporates topological information into the network structure.<n>Our approach on three curvilinear benchmarks demonstrate state-of-the-art performance in both pixel-level accuracy and topological fidelity.
  arXiv  Detail & Related papers  (2026-01-25T23:51:45Z)
• Systematic Characterization of Minimal Deep Learning Architectures: A Unified Analysis of Convergence, Pruning, and Quantization [6.49583548940407]
  Deep learning networks excel at classification, yet identifying minimal architectures that reliably solve a task remains challenging.<n>We present a computational methodology for exploring and analyzing the relationships among convergence, pruning, and quantization.<n>Our initial results show that, despite architectural diversity, performance is largely invariant and learning dynamics consistently exhibit three regimes: unstable, learning, and overfitting.
  arXiv  Detail & Related papers  (2026-01-25T20:31:10Z)
• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark [71.3555284685426]
  We introduce RealUnify, a benchmark designed to evaluate bidirectional capability synergy.<n>RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks.<n>We find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient.
  arXiv  Detail & Related papers  (2025-09-29T15:07:28Z)
• Scale-Invariance Drives Convergence in AI and Brain Representations [7.318297580732467]
  Recent studies indicate that large-scale AI models often converge toward similar internal representations that also align with neural activity.<n>We quantify two core aspects of scale-invariance in AI representations: dimensional stability and structural similarity across scales.<n>Our analysis reveals that embeddings with more consistent dimension and higher structural similarity across scales align better with fMRI data.
  arXiv  Detail & Related papers  (2025-06-13T15:36:04Z)
• Isomorphic Pruning for Vision Models [56.286064975443026]
  Structured pruning reduces the computational overhead of deep neural networks by removing redundant sub-structures. We present Isomorphic Pruning, a simple approach that demonstrates effectiveness across a range of network architectures.
  arXiv  Detail & Related papers  (2024-07-05T16:14:53Z)
• Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression [53.15502562048627]
  Recent work has built the connection between self-supervised learning and the approximation of the top eigenspace of a graph Laplacian operator. This work delves into a statistical analysis of augmentation-based pretraining.
  arXiv  Detail & Related papers  (2023-06-01T15:18:55Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.