# Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion

arXiv: https://arxiv.org/abs/2402.09530 · HTML: https://mlsanity.com/paper/2402.09530/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 14 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2003.00867/) (2020)
- [On the Robustness of Semantic Segmentation Models to Adversarial Attacks](https://mlsanity.com/paper/1711.09856/) (2017)
- [Are Convolutional Neural Networks or Transformers more like human vision?](https://mlsanity.com/paper/2105.07197/) (2021)
- [Delving Deep into the Generalization of Vision Transformers under Distribution Shifts](https://mlsanity.com/paper/2106.07617/) (2021)
- [Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities](https://mlsanity.com/paper/1811.00648/) (2018)
- [Robust Contrastive Learning Using Negative Samples with Diminished Semantics](https://mlsanity.com/paper/2110.14189/) (2021)
- [Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation](https://mlsanity.com/paper/1810.05162/) (2018)
- [Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation](https://mlsanity.com/paper/2003.06555/) (2020)
- [Proximal Splitting Adversarial Attacks for Semantic Segmentation](https://mlsanity.com/paper/2206.07179/) (2022)
- [The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing](https://mlsanity.com/paper/2101.03924/) (2021)
- [Learning Visual Representations for Transfer Learning by Suppressing Texture](https://mlsanity.com/paper/2011.01901/) (2020)
- [Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation](https://mlsanity.com/paper/2310.17436/) (2023)
- [Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation](https://mlsanity.com/paper/2305.12825/) (2023)

## Built on by (most cited first, 11 of 11)

- [Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP](https://mlsanity.com/paper/2409.15035/) (2024)
- [Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation](https://mlsanity.com/paper/2503.12453/) (2025)
- [Decomposing and Revising What Language Models Generate](https://mlsanity.com/paper/2509.00765/) (2025)
- [Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?](https://mlsanity.com/paper/2410.10160/) (2024)
- [Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks](https://mlsanity.com/paper/2507.10239/) (2025)
- [Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks](https://mlsanity.com/paper/2409.11373/) (2024)
- [On the Influence of Shape, Texture and Color for Learning Semantic Segmentation](https://mlsanity.com/paper/2410.14878/) (2024)
- [Contrast All the Time: Learning Time Series Representation from Temporal Consistency](https://mlsanity.com/paper/2410.15416/) (2024)
- [Fast Preemptive Robustification: High-Frequency Response Anti-Aligns Shared Vulnerability](https://mlsanity.com/paper/2603.25244/) (2026)
- [Texture-Shape Bias Balancing for Robust Synthetic-to-Real Semantic Segmentation in Automotive NIR Imagery](https://mlsanity.com/paper/2606.15072/) (2026)
- [Investigating the Visual Cues of CNNs for Vascular Segmentation: A Case Study in Microscopy and Fundus Imaging](https://mlsanity.com/paper/2607.23371/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) for image processing tend to focus on localized texture patterns, commonly referred to as texture bias. While most of the previous works in the literature focus on the task of image classification, we go beyond this and study the texture bias of CNNs in semantic segmentation. In this work, we propose to train CNNs on pre-processed images with less texture to reduce the texture bias. Therein, the challenge is to suppress image texture while preserving shape information. To this end, we utilize edge enhancing diffusion (EED), an anisotropic image diffusion method initially introduced for image compression, to create texture reduced duplicates of existing datasets. Extensive numerical studies are performed with both CNNs and vision transformer models trained on original data and EED-processed data from the Cityscapes dataset and the CARLA driving simulator. We observe strong texture-dependence of CNNs and moderate texture-dependence of transformers. Training CNNs on EED-processed images enables the models to become completely ignorant with respect to texture, demonstrating resilience with respect to texture re-introduction to any degree. Additionally we analyze the performance reduction in depth on a level of connected components in the semantic segmentation and study the influence of EED pre-processing on domain generalization as well as adversarial robustness.