paper-with-me

홈 › Papers

S2P-Net: A Spectral-Spatial Polar Network for Rotation-Invariant Object Recognition in Low-Data Regimes

2026-05-10 · Albert Heruth arxiv

We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural network architectures (CNN`s). Have a look at the results and feel free to contact me for any questions. This is my first paper:) Made by Hackbert

📄 PDF Abstract BibTeX arXiv:2605.09667

Code (0)

등록된 구현이 없습니다.

Tasks

Object RecognitionData Augmentation

Similar Papers 제목 키워드 기반

Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification

2019-12-18 · Danfeng Hong, Xin Wu, Pedram Ghamisi, Jocelyn Chanussot 외

Up to the present, an enormous number of advanced techniques have been developed to enhance and extract the spatially semantic information in hyperspectral image processing and analysis. However, locally semantic change,…

AttributeGeneral ClassificationHyperspectral Image Classificationimage-classification+1

Fourier-based Rotation-invariant Feature Boosting: An Efficient Framework for Geospatial Object Detection

2019-05-27 · Xin Wu, Danfeng Hong, Jocelyn Chanussot, Yang Xu 외

Geospatial object detection of remote sensing imagery has been attracting an increasing interest in recent years, due to the rapid development in spaceborne imaging. Most of previously proposed object detectors are very …

Objectobject-detectionObject Detection

Polar Transformer Networks

2017-09-06 · ICLR 2018 1 · Carlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou, Kostas Daniilidis

Convolutional neural networks (CNNs) are inherently equivariant to translation. Efforts to embed other forms of equivariance have concentrated solely on rotation. We expand the notion of equivariance in CNNs through the …

Rotated MNISTTranslation

Identification of Metallic Objects using Spectral MPT Signatures: Object Characterisation and Invariants

2020-12-18 · P. D. Ledger, B. A. Wilson, A. A. S. Amad, W. R. B. Lionheart

The early detection of terrorist threats, such as guns and knives, through improved metal detection, has the potential to reduce the number of attacks and improve public safety and security. To achieve this, there is con…

Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection

2026-07-06 · Peng Zhang, Tingfa Xu, Shuaihao Han, Jianan Li arxiv

Existing multispectral detectors are limited by discrete spectral processing, a scale-dependent shift in the relative reliability of spectral and spatial cues across pyramid levels, and the lack of explicit rotation-equi…

Multispectral Object Detection