Papers › Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion

Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion

14 Feb 2024arXiv:2402.09530archive 2025-07-28

Edgar Heinert, Matthias Rottmann, Kira Maag, Karsten Kahl

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.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

eheinert/reducing-texture-bias-of-dnns-via-eed officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial Robustness Domain Generalization Image Classification Image Compression Semantic Segmentation image-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Attention CARLA Dense Connections Diffusion Entropy Regularization Focus Layer Normalization Linear Layer Multi-Head Attention PPO Residual Connection Softmax Vision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections