Mitigating Shortcut Learning: Texture-Penalized Prototype Networks

• URL: http://arxiv.org/abs/2609.07504v1
• Date: Mon, 07 Sep 2026 13:51:49 GMT
• Title: Mitigating Shortcut Learning: Texture-Penalized Prototype Networks
• Abstract summary: CNNs exhibit severe performance degradation due to a strong inductive texture bias.<n>To address this flaw, this study introduces the Texture-Penalized Prototype Network (TPPN)<n>TPPN shifts this inherent bias without depending on resource-intensive augmented datasets.
• Score: 0.7816377212023298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Standard Convolutional Neural Networks (CNNs) exhibit severe performance degradation due to a strong inductive texture bias that prioritizes local, high-frequency patterns over global structural shapes. This dependency causes confident misclassifications during textural changes or environmental effects. To address this flaw, this study introduces the Texture-Penalized Prototype Network (TPPN), a novel architectural framework that shifts this inherent bias without depending on resource-intensive augmented datasets. Specifically, a Texture-Penalization Branch (TPB) imposes a penalty to suppress the extraction of local texture proxies, forcing the network backbone to discard high-frequency cues and extract purified, shape-biased representations. By evaluating similarities within a prototype-based hypersphere derived from the final convolutional features, the approach enforces strict geometric constraints, treating objects as compositions of essential parts to achieve robust classification. Evaluations on texture-shape cue-conflict datasets and synthetic noise benchmarks demonstrate the stronger shape bias of this structural disentanglement. The proposed framework reduces the inherent texture bias of a baseline ResNet-50 from 55.11% to 29.73%, surpassing the texture-suppression capabilities of an off-the-shelf Vision Transformer (ViT-B/16). Furthermore, the approach demonstrates robust generalization under cue-conflict conditions, resisting textural shortcut learning when encountering Out-of-Distribution (OOD) shapes. The model maintains stronger shape accuracy against elevated perturbations. On clean validation data, the architecture incurs a minimal drop in accuracy of 0.90 percentage points. This provides a structural, efficient solution to CNN texture bias.

Related papers

• Chaotic Contrastive Learning for Robust Texture Classification [0.0]
  This paper introduces a novel framework that synergizes Self-Supervised Learning with deterministic chaotic dynamics.<n>We propose a chaotic contrastive pre-training strategy, where pixel-wise chaotic maps act as non-linear data augmentation techniques.<n> Experimental results on six texture benchmarks demonstrate the superiority of the proposed method.
  arXiv  Detail & Related papers  (2026-05-06T15:11:28Z)
• Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework [14.897323487173587]
  Generative diffusion priors have recently achieved state-of-the-art performance in natural image super-resolution.<n>Their direct application to remote sensing image super-resolution reveals significant shortcomings.<n>We propose TexADiff, a novel framework that begins by estimating a Relative Texture Map (RTDM) to represent the texture distribution.
  arXiv  Detail & Related papers  (2026-04-15T15:36:49Z)
• Alternating Gradient Flow Utility: A Unified Metric for Structural Pruning and Dynamic Routing in Deep Networks [52.153950303594684]
  We propose a decoupled kinetic paradigm inspired by Alternating Gradient Flow (AGF)<n>AGF accurately captures the network's structural "kinetic utility"<n>We design a hybrid routing framework that decouples AGF-guided offline structural search from online execution via zero-cost physical priors.
  arXiv  Detail & Related papers  (2026-03-12T18:19:21Z)
• 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)
• Quantifying and Inducing Shape Bias in CNNs via Max-Pool Dilation [0.9176056742068813]
  Convolutional Neural Networks (CNNs) are known to exhibit a strong texture bias, favoring local patterns over global shape information.<n>We propose a data-driven metric that quantifies the shape-texture balance of a dataset by computing the Structural Similarity Index (SSIM)<n>We introduce a computationally efficient adaptation method that promotes shape bias by modifying the dilation of max-pooling operations while keeping convolutional weights frozen.
  arXiv  Detail & Related papers  (2026-01-09T07:36:29Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• TopoFR: A Closer Look at Topology Alignment on Face Recognition [58.45515807380505]
  We propose TopoFR, a novel FR model that leverages a topological structure alignment strategy called PTSA and a hard sample mining strategy named SDE.<n> PTSA uses persistent homology to align the topological structures of the input and latent spaces, effectively preserving the structure information and improving the generalization performance of FR model.<n> Experimental results on popular face benchmarks demonstrate the superiority of our TopoFR over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-14T14:58:30Z)
• 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)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)

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.