# Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization

arXiv: https://arxiv.org/abs/2011.05702 · HTML: https://mlsanity.com/paper/2011.05702/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 4 of 4)

- [An Empirical Study of Remote Sensing Pretraining](https://mlsanity.com/paper/2204.02825/) (2022)
- [LSKNet: A Foundation Lightweight Backbone for Remote Sensing](https://mlsanity.com/paper/2403.11735/) (2024)
- [AllSpark: A Multimodal Spatio-Temporal General Intelligence Model with Ten Modalities via Language as a Reference Framework](https://mlsanity.com/paper/2401.00546/) (2023)
- [Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network](https://mlsanity.com/paper/2106.09996/) (2021)

## Abstract (arXiv)

Learning discriminative and invariant feature representation is the key to visual image categorization. In this article, we propose a novel invariant deep compressible covariance pooling (IDCCP) to solve nuisance variations in aerial scene categorization. We consider transforming the input image according to a finite transformation group that consists of multiple confounding orthogonal matrices, such as the D4 group. Then, we adopt a Siamese-style network to transfer the group structure to the representation space, where we can derive a trivial representation that is invariant under the group action. The linear classifier trained with trivial representation will also be possessed with invariance. To further improve the discriminative power of representation, we extend the representation to the tensor space while imposing orthogonal constraints on the transformation matrix to effectively reduce feature dimensions. We conduct extensive experiments on the publicly released aerial scene image data sets and demonstrate the superiority of this method compared with state-of-the-art methods. In particular, with using ResNet architecture, our IDCCP model can reduce the dimension of the tensor representation by about 98% without sacrificing accuracy (i.e., <0.5%).