Skip to content
Open access

Inductive bias influences the spatial scale of biological features learned from images

Aug 2026 · Bioinformatics Advances · Vol 6 · 0 citations · 53 references
Medicine

TL;DR

It is demonstrated that deep learning model architecture is a choice that shapes the biological scale of extracted features, highlighting the need to align a model’s inductive bias with the scientific question.

Abstract

Abstract Motivation The inductive bias of a deep learning model influences the features it extracts from biological images, making model selection a critical scientific decision. We systematically compare representations learned from scratch without pre-training by convolutional neural networks (CNNs), vision transformers, and Fourier neural operators (FNOs)—an emerging architecture largely unexplored in biological imaging—to determine how their distinct learning mechanisms shape feature learning from spatiotemporal data. Results Using a self-supervised representation learning framework on microscopy images of 2D gastruloids, as well as a distinct synthetic tumor image dataset, we show that while CNNs and FNOs achieve comparable accuracy on biological tasks, they learn features at different scales. Visual interpretation methods reveal that CNNs prioritize local, fine-grained details, whereas FNOs capture global, low-frequency structures, in line with overall population morphology. These findings demonstrate that deep learning model architecture is a choice that shapes the biological scale of extracted features, highlighting the need to align a model’s inductive bias with the scientific question. Availability and implementation All source code for the representation learning model, the tumor simulation dataset, and the gastruloid microscopy imaging dataset are available at the corresponding DOIs: https://doi.org/10.5281/zenodo.19672838, https://doi.org/10.5281/zenodo.19361370, https://doi.org/10.5281/zenodo.19373112, respectively.

Read PDF

Similar papers

#machine learning Open access Aug 2026

Why Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image Classification

Recent advances in attention-based deep learning have motivated their adoption for remote sensing image classification; however, their benefits for cryospheric imagery, where surface states are dominated by fine-grained textures and class imbalance, remain unclear. In this work, we revisit a benchmark Greenland Ice She...

C. Kulkarni, Emam Hossain · 0 citations
Open access Sep 2026

Systematic image perturbations reveal persistent gaps between human and machine vision

Summary Deep neural networks (DNNs) are promising computational models for understanding visual object recognition. Yet, whether DNNs use similar visual cues for object recognition as humans do remains unknown. We created an image set that systematically untangles global shape, internal parts, and texture information,...

Mugihiko Kato, Bi-Yu J. He · 0 citations
#machine learning Preprint Oct 2026

HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification

DNNs exhibit robustness and generalisation issues not seen in humans. They are also far less data-efficient learners, requiring considerably more training samples to accurately classify novel exemplars. Inductive bias could help with these issues by providing in-built mechanisms to improve generalisation, and hence, re...

M. Spratling, Heiko Schutt · 0 citations
Review Open access 2026

A Review of Fine-Grained Visual Categorization with Deep Learning

: Fine-grained visual categorization (FGVC) presents a class of recognition problems in which the discriminative signal is spatially concentrated, visually subtle, and easily destroyed by the preprocessing and augmentation strategies that serve coarse recognition well. Where standard image classification requires a mod...

Richard Adusei, G. Abdul-Salaam · 0 citations
Open access Aug 2026

Adaptive Feature Integration in CNN–Transformer Networks for Efficient and Interpretable Visual Classification

A novel adaptive fusion framework that adaptively combines CNN and Transformer features through learnable gating, attention-based feature integration, and explainable-AI methods is developed, intended to improve both computational efficiency and model interpretability.

Komal Sharma, Monika Sainger · 0 citations
Preprint Sep 2026

The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation

Convolutional neural networks trained on ImageNet are known to exhibit a strong preference for local high-frequency texture, an inductive bias that translates into fragile robustness against distribution shifts in real-world environments. Event cameras, in contrast, record only changes in scene brightness and are there...

Soshun Kihara, Shunsuke Yasuki, Masato Taki · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.