# Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network

arXiv: https://arxiv.org/abs/1904.00197 · HTML: https://mlsanity.com/paper/1904.00197/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2019.

## Built on by (most cited first, 2 of 2)

- [SO(2) and O(2) Equivariance in Image Recognition with Bessel-Convolutional Neural Networks](https://mlsanity.com/paper/2304.09214/) (2023)
- [On the effectiveness of Rotation-Equivariance in U-Net: A Benchmark for Image Segmentation](https://mlsanity.com/paper/2412.09182/) (2024)

## Abstract (arXiv)

This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer. Max-pooling layer discards the pose, i.e., translational and rotational relationship between the low-level features, and hence unable to capture the spatial hierarchies between low and high level features. The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer. The proposed SIFT Descriptor CNN therefore combines the feature extraction capabilities of CNN model and rotation invariance of SIFT descriptor. Experimental results on the MNIST and fashionMNIST datasets indicates reasonable improvements over conventional methods available in literature.