# flexgrid2vec: Learning Efficient Visual Representations Vectors

arXiv: https://arxiv.org/abs/2007.15444 · HTML: https://mlsanity.com/paper/2007.15444/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Spatiotemporal Data Mining: A Survey on Challenges and Open Problems](https://mlsanity.com/paper/2103.17128/) (2021)
- [Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks](https://mlsanity.com/paper/2106.00717/) (2021)
- [MARL: Multimodal Attentional Representation Learning for Disease Prediction](https://mlsanity.com/paper/2105.00310/) (2021)
- [Signature-Graph Networks](https://mlsanity.com/paper/2110.11551/) (2021)
- [GCCN: Global Context Convolutional Network](https://mlsanity.com/paper/2110.11664/) (2021)

## Abstract (arXiv)

We propose flexgrid2vec, a novel approach for image representation learning. Existing visual representation methods suffer from several issues, including the need for highly intensive computation, the risk of losing in-depth structural information and the specificity of the method to certain shapes or objects. flexgrid2vec converts an image to a low-dimensional feature vector. We represent each image with a graph of flexible, unique node locations and edge distances. flexgrid2vec is a multi-channel GCN that learns features of the most representative image patches. We have investigated both spectral and non-spectral implementations of the GCN node-embedding. Specifically, we have implemented flexgrid2vec based on different node-aggregation methods, such as vector summation, concatenation and normalisation with eigenvector centrality. We compare the performance of flexgrid2vec with a set of state-of-the-art visual representation learning models on binary and multi-class image classification tasks. Although we utilise imbalanced, low-size and low-resolution datasets, flexgrid2vec shows stable and outstanding results against well-known base classifiers. flexgrid2vec achieves 96.23% on CIFAR-10, 83.05% on CIFAR-100, 94.50% on STL-10, 98.8% on ASIRRA and 89.69% on the COCO dataset.