# Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images

arXiv: https://arxiv.org/abs/2004.03037 · HTML: https://mlsanity.com/paper/2004.03037/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 30 of 33)

- [MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging](https://mlsanity.com/paper/2410.06542/) (2024)
- [Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images](https://mlsanity.com/paper/2202.07001/) (2022)
- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [Multi-Class Cell Detection Using Spatial Context Representation](https://mlsanity.com/paper/2110.04886/) (2021)
- [Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures](https://mlsanity.com/paper/2407.09468/) (2024)
- [Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions](https://mlsanity.com/paper/2303.12484/) (2023)
- [Resolution-Based Distillation for Efficient Histology Image Classification](https://mlsanity.com/paper/2101.04170/) (2021)
- [From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology](https://mlsanity.com/paper/2204.05044/) (2022)
- [Topology-Guided Multi-Class Cell Context Generation for Digital Pathology](https://mlsanity.com/paper/2304.02255/) (2023)
- [Rotation Invariance and Extensive Data Augmentation: a strategy for the Mitosis Domain Generalization (MIDOG) Challenge](https://mlsanity.com/paper/2109.00823/) (2021)
- [GradMix for nuclei segmentation and classification in imbalanced pathology image datasets](https://mlsanity.com/paper/2210.12938/) (2022)
- [Geometrical aspects of lattice gauge equivariant convolutional neural networks](https://mlsanity.com/paper/2303.11448/) (2023)
- [Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images](https://mlsanity.com/paper/2309.07394/) (2023)
- [Explicit Discovery of Nonlinear Symmetries from Dynamic Data](https://mlsanity.com/paper/2510.01855/) (2025)
- [A QuadTree Image Representation for Computational Pathology](https://mlsanity.com/paper/2108.10873/) (2021)
- [Incorporating Arbitrary Matrix Group Equivariance into KANs](https://mlsanity.com/paper/2410.00435/) (2024)
- [Grassmann Manifold Flows for Stable Shape Generation](https://mlsanity.com/paper/2211.02900/) (2022)
- [Fine-Grained Hard Negative Mining: Generalizing Mitosis Detection with a Fifth of the MIDOG 2022 Dataset](https://mlsanity.com/paper/2301.01079/) (2023)
- [Rotation-Scale Equivariant Steerable Filters](https://mlsanity.com/paper/2304.04600/) (2023)
- [Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology](https://mlsanity.com/paper/2312.09792/) (2023)
- [SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging](https://mlsanity.com/paper/2409.08537/) (2024)
- [Category Prompt Mamba Network for Nuclei Segmentation and Classification](https://mlsanity.com/paper/2503.10422/) (2025)
- [Learning to Transform for Generalizable Instance-wise Invariance](https://mlsanity.com/paper/2309.16672/) (2023)
- [Current Symmetry Group Equivariant Convolution Frameworks for Representation Learning](https://mlsanity.com/paper/2409.07327/) (2024)
- [MRL: Learning to Mix with Attention and Convolutions](https://mlsanity.com/paper/2208.13975/) (2022)
- [SO(2) and O(2) Equivariance in Image Recognition with Bessel-Convolutional Neural Networks](https://mlsanity.com/paper/2304.09214/) (2023)
- [Harmformer: Harmonic Networks Meet Transformers for Continuous Roto-Translation Equivariance](https://mlsanity.com/paper/2411.03794/) (2024)
- [Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction](https://mlsanity.com/paper/2605.08276/) (2026)
- [Transformation Invariant Cancerous Tissue Classification Using Spatially Transformed DenseNet](https://mlsanity.com/paper/2204.11066/) (2022)
- [Learning Nuclei Representations with Masked Image Modelling](https://mlsanity.com/paper/2306.17116/) (2023)

## Abstract (arXiv)

Histology images are inherently symmetric under rotation, where each orientation is equally as likely to appear. However, this rotational symmetry is not widely utilised as prior knowledge in modern Convolutional Neural Networks (CNNs), resulting in data hungry models that learn independent features at each orientation. Allowing CNNs to be rotation-equivariant removes the necessity to learn this set of transformations from the data and instead frees up model capacity, allowing more discriminative features to be learned. This reduction in the number of required parameters also reduces the risk of overfitting. In this paper, we propose Dense Steerable Filter CNNs (DSF-CNNs) that use group convolutions with multiple rotated copies of each filter in a densely connected framework. Each filter is defined as a linear combination of steerable basis filters, enabling exact rotation and decreasing the number of trainable parameters compared to standard filters. We also provide the first in-depth comparison of different rotation-equivariant CNNs for histology image analysis and demonstrate the advantage of encoding rotational symmetry into modern architectures. We show that DSF-CNNs achieve state-of-the-art performance, with significantly fewer parameters, when applied to three different tasks in the area of computational pathology: breast tumour classification, colon gland segmentation and multi-tissue nuclear segmentation.