Accelerated Rotation-Invariant Convolution for UAV Image Segmentation

• URL: http://arxiv.org/abs/2512.08888v2
• Date: Mon, 15 Dec 2025 15:14:24 GMT
• Title: Accelerated Rotation-Invariant Convolution for UAV Image Segmentation
• Authors: Manduhu Manduhu, Alexander Dow, Gerard Dooly, James Riordan,
• Abstract summary: In this paper, we introduce a GPU-optimized rotation-invariant convolution framework.<n>By exploiting structured data sharing among symmetrically rotated filters, our method achieves multi-orientation convolution with greatly reduced memory traffic and computational redundancy.<n>Across extensive benchmarks, the proposed convolution achieves 20--55% faster training and 15--45% lower energy consumption than CUDNN.
• Score: 36.23556720064733
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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\(\times\)256 inputs, and 32% speedup and 23% lower energy usage on 1024\(\times\)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.

Related papers

• Computing a Characteristic Orientation for Rotation-Independent Image Analysis [0.0]
  General Intensity Direction (GID) is a preprocessing method that improves rotation robustness without modifying the network architecture.<n>It transforms the image while preserving spatial structure, making it compatible with convolutional networks.<n> Experimental evaluation on the rotated MNIST dataset shows that the proposed method achieves higher accuracy than state-of-the-art rotation-invariant architectures.
  arXiv  Detail & Related papers  (2026-02-24T14:08:12Z)
• Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers [35.57122848273358]
  We introduce Eff-GRot, an approach for efficient and generalizable rotation estimation from RGB images.<n>Given a query image and a set of reference images with known orientations, our method directly predicts the object's rotation in a single forward pass.
  arXiv  Detail & Related papers  (2025-12-21T15:57:13Z)
• Rotated Mean-Field Variational Inference and Iterative Gaussianization [11.954133194037858]
  We propose to perform mean-field variational inference (MFVI) in a rotated coordinate system.<n>MFVI in a rotated coordinate system defines a rotation and a coordinatewise map that together move the target closer to Gaussian.<n>Iterating this procedure yields a sequence of transformations that progressively transforms the target toward Gaussian.
  arXiv  Detail & Related papers  (2025-10-09T03:13:44Z)
• GMR-Conv: An Efficient Rotation and Reflection Equivariant Convolution Kernel Using Gaussian Mixture Rings [4.365790707793824]
  We introduce an efficient convolution kernel that smooths radial symmetry using a mixture of Gaussian-weighted rings.<n>Experiments on eight classification and one segmentation datasets demonstrate that GMR-Conv not only matches conventional CNNs' performance but can also surpass it in applications with orientation-less data.
  arXiv  Detail & Related papers  (2025-04-03T17:58:18Z)
• Speedy MASt3R [68.47052557089631]
  MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching scheme.<n>Fast MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy.<n>This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.
  arXiv  Detail & Related papers  (2025-03-13T03:56:22Z)
• Improved Vessel Segmentation with Symmetric Rotation-Equivariant U-Net [4.365790707793824]
  We propose an efficient symmetric rotation-equivariant (SRE) convolutional kernel implementation to the U-Net architecture.<n>We validate the effectiveness of our method through improved segmentation performance on retina vessel fundus imaging.<n>Our proposed SRE U-Net not only significantly surpasses standard U-Net in handling rotated images, but also outperforms existing equivariant learning methods.
  arXiv  Detail & Related papers  (2025-01-24T15:54:51Z)
• Irrational Complex Rotations Empower Low-bit Optimizers [102.56966165088963]
  We propose a novel state compression algorithm, namely $pi$-Quant, for memory-efficient training.<n>We show that it can reduce the bit-width of parameters to 3.32-bit, achieving a 75% reduction in parameter scale and a 40% decrease in GPU memory usage.
  arXiv  Detail & Related papers  (2025-01-22T14:17:57Z)
• SRE-Conv: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification [4.2790694771618725]
  Convolutional neural networks (CNNs) are essential tools for computer vision tasks, but they lack desired properties.<n>SRE-Conv kernel is designed to learn rotation-invariant features while simultaneously compressing the model size.<n>SRE-Conv-CNN demonstrated improved rotated image classification performance accuracy on all 16 test datasets in both 2D and 3D images.
  arXiv  Detail & Related papers  (2025-01-16T18:59:02Z)
• Variable-size Symmetry-based Graph Fourier Transforms for image compression [65.7352685872625]
  We propose a new family of Symmetry-based Graph Fourier Transforms of variable sizes into a coding framework. Our proposed algorithm generates symmetric graphs on the grid by adding specific symmetrical connections between nodes. Experiments show that SBGFTs outperform the primary transforms integrated in the explicit Multiple Transform Selection.
  arXiv  Detail & Related papers  (2024-11-24T13:00:44Z)
• Gaussian Primitives for Deformable Image Registration [9.184092856125067]
  Experimental results on brain MRI, lung CT, and cardiac MRI datasets demonstrate that GaussianDIR outperforms existing DIR methods in both accuracy and efficiency. As a training-free approach, it challenges the stereotype that iterative methods are inherently slow and transcend the limitations of poor generalization.
  arXiv  Detail & Related papers  (2024-06-05T15:44:54Z)
• RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging [62.315673415889314]
  This paper proposes a deep recurrent Rotation Averaging Graph (RAGO) for Multiple Rotation Averaging (MRA) Our framework is a real-time learning-to-optimize rotation averaging graph with a tiny size deployed for real-world applications.
  arXiv  Detail & Related papers  (2022-12-14T13:19:40Z)
• Dynamic Region-Aware Convolution [85.20099799084026]
  We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions. On ImageNet classification, DRConv-based ShuffleNetV2-0.5x achieves state-of-the-art performance of 67.1% at 46M multiply-adds level with 6.3% relative improvement.
  arXiv  Detail & Related papers  (2020-03-27T05:49:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.