# Accelerated Rotation-Invariant Convolution for UAV Image Segmentation

arXiv: https://arxiv.org/abs/2512.08888 · HTML: https://mlsanity.com/paper/2512.08888/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 79 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Builds on (most cited first, 30 of 41)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Harmonic Networks: Deep Translation and Rotation Equivariance](https://mlsanity.com/paper/1612.04642/) (2016)
- [Gauge Equivariant Convolutional Networks and the Icosahedral CNN](https://mlsanity.com/paper/1902.04615/) (2019)
- [cuDNN: Efficient Primitives for Deep Learning](https://mlsanity.com/paper/1410.0759/) (2014)
- [A General Theory of Equivariant CNNs on Homogeneous Spaces](https://mlsanity.com/paper/1811.02017/) (2018)
- [Learning Steerable Filters for Rotation Equivariant CNNs](https://mlsanity.com/paper/1711.07289/) (2017)
- [Equivariance Through Parameter-Sharing](https://mlsanity.com/paper/1702.08389/) (2017)
- [Fast Algorithms for Convolutional Neural Networks](https://mlsanity.com/paper/1509.09308/) (2015)
- [Exploiting Cyclic Symmetry in Convolutional Neural Networks](https://mlsanity.com/paper/1602.02660/) (2016)
- [Fast Training of Convolutional Networks through FFTs](https://mlsanity.com/paper/1312.5851/) (2013)
- [Oriented Response Networks](https://mlsanity.com/paper/1701.01833/) (2017)
- [CubeNet: Equivariance to 3D Rotation and Translation](https://mlsanity.com/paper/1804.04458/) (2018)
- [Gabor Convolutional Networks](https://mlsanity.com/paper/1705.01450/) (2017)
- [VDD: Varied Drone Dataset for Semantic Segmentation](https://mlsanity.com/paper/2305.13608/) (2023)
- [3D G-CNNs for Pulmonary Nodule Detection](https://mlsanity.com/paper/1804.04656/) (2018)
- [TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs](https://mlsanity.com/paper/2311.12862/) (2023)
- [Fast Convolutional Nets With fbfft: A GPU Performance Evaluation](https://mlsanity.com/paper/1412.7580/) (2014)
- [HexaConv](https://mlsanity.com/paper/1803.02108/) (2018)
- [Learning rotation invariant convolutional filters for texture classification](https://mlsanity.com/paper/1604.06720/) (2016)
- [RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network](https://mlsanity.com/paper/2211.11812/) (2022)
- [RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks](https://mlsanity.com/paper/1805.06846/) (2018)

## Abstract (arXiv)

Rotation invariance is essential for precise, object-level segmentation in UAV aerial imagery, where targets can have arbitrary orientations and exhibit fine-scale details. Conventional segmentation architectures like U-Net rely on convolution operators that are not rotation-invariant, leading to degraded segmentation accuracy across varying viewpoints. Rotation invariance can be achieved by expanding the filter bank across multiple orientations; however, this will significantly increase computational cost and memory traffic. In this paper, we introduce a GPU-optimized rotation-invariant convolution framework that eliminates the traditional data-lowering (im2col) step required for matrix-multiplication-based convolution. By exploiting structured data sharing among symmetrically rotated filters, our method achieves multi-orientation convolution with greatly reduced memory traffic and computational redundancy. We further generalize the approach to accelerate convolution with arbitrary (non-symmetric) rotation angles. Across extensive benchmarks, the proposed convolution achieves 20--55% faster training and 15--45% lower energy consumption than CUDNN, while maintaining accuracy comparable to state-of-the-art rotation-invariant methods. In the eight-orientation setting, our approach achieves up to 45% speedup and 41% energy savings on 256(×)256 inputs, and 32% speedup and 23% lower energy usage on 1024(×)1024 inputs. Integrated into a U-Net segmentation model, the framework yields up to 6% improvement in accuracy over the non-rotation-aware baseline. These results demonstrate that the proposed method provides an effective and highly efficient alternative to existing rotation-invariant CNN frameworks.