More Like this

1. GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs

   https://doi.org/10.1109/CVPR52733.2024.00585  

   Munir, Mustafa; Avery, William; Rahman, Md Mostafijur; Marculescu, Radu (June 2024, IEEE)

   Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made within an image. Additionally, we propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification, object detection, instance segmentation, and semantic segmentation tasks. Our smallest model, GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with less GMACs and a similar number of parameters. Our largest model, GreedyViG-B obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6% decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3% decrease in GMACs. Our work shows that hybrid CNNGNN architectures not only provide a new avenue for designing efficient models, but that they can also exceed the performance of current state-of-the-art models. 

   more » « less
2. A Real-time Machine Learning-based GPS Spoofing Solution for Location-dependent UAV Applications

   https://doi.org/10.1109/eIT57321.2023.10187344  

   M. Nayfeh; J. Price; M. Alkhatib; K. Al Shamaileh; N. Kaabouch; V. Devabhaktuni (July 2023, IEEE International Conference on Electro Information Technology)

   In this paper, a three-class machine learning (ML) model is implemented on an unmanned aerial vehicle (UAV) with a Raspberry Pi processor for classifying two global positioning system (GPS) spoofing attacks (i.e., static, dynamic) in real-time. First, several models are developed and tested utilizing a dataset collected in a previous work. This dataset conveys GPS-specific features, including location information. Models evaluations are carried out using the detection rate, F-score, false alarm rate, and misdetection rate, which all showed an acceptable performance. Then, the optimum model is loaded to the processor and tested for real-time detection and classification. Location-dependent applications, such as fixed-route public transportations are expected to benefit from the methodology presented herein as the longitude, latitude, and altitude features are characterized in the developed model. 

   more » « less
3. Privately Publishable Per-instance Privacy

   Redberg, Rachel; Wang, Yu-Xiang (December 2021, Advances in neural information processing systems)

   We consider how to privately share the personalized privacy losses incurred by objective perturbation, using per-instance differential privacy (pDP). Standard differential privacy (DP) gives us a worst-case bound that might be orders of magnitude larger than the privacy loss to a particular individual relative to a fixed dataset. The pDP framework provides a more fine-grained analysis of the privacy guarantee to a target individual, but the per-instance privacy loss itself might be a function of sensitive data. In this paper, we analyze the per-instance privacy loss of releasing a private empirical risk minimizer learned via objective perturbation, and propose a group of methods to privately and accurately publish the pDP losses at little to no additional privacy cost. 

   more » « less
4. Forward Index Compression for Instance Retrieval in an Augmented Reality Application

   https://doi.org/10.1109/BigData47090.2019.9006023  

   Wang, Qi; Siedlaczek, Michal; Chen, Yen-Yu; Gormish, Michael; Suel, Torsten (December 2019, 2019 IEEE International Conference on Big Data)

   Instance retrieval systems are widely used in applications such as robot navigation, medical diagnosis, and augmented reality. Blippar is a company that creates compelling augmented reality experiences or provides you with the tools to build your own. In this paper we focus on one of the company's augmented-reality applications, with which users are able to point their phone cameras at different objects in order to receive information about the objects in real time. In this paper, we provide what we believe to be the first study of forward index compression techniques for such instance retrieval systems. First, we perform an analysis of real-world data from a large-scale commercial instance retrieval system, run by Blippar focusing on augmented reality. Then we propose an entropy-based lossless compression strategy. Experiments show that our proposed Huffman-based approach outperforms a variety of other compression techniques, while also increasing overall system efficiency slightly. 

   more » « less
5. Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs

   Munir, Mustafa; Zhang, Alex; Marculescu, Radu (December 2025, PMLR)

   Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs); however, common graph construction methods, such as k-nearest neighbor (KNN), can be expensive on larger images. While methods such as Sparse Vision Graph Attention (SVGA) have shown promise, SVGA’s fixed step scale can lead to over-squashing and missing multiple connections to gain the same information that could be gained from a long-range link. Through this observation, we propose a new graph construction method, Logarithmic Scalable Graph Construction (LSGC) to enhance performance by limiting the number of long-range links. To this end, we propose LogViG, a novel hybrid CNN-GNN model that utilizes LSGC. Furthermore, inspired by the successes of multiscale and high-resolution architectures, we introduce and apply a high-resolution branch and fuse features between our high-resolution and low-resolution branches for a multi-scale high-resolution Vision GNN network. Extensive experiments show that LogViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification and semantic segmentation tasks. Our smallest model, Ti-LogViG, achieves an average top-1 accuracy on ImageNet-1K of 79.9% with a standard deviation of ± 0.2%, 1.7% higher average accuracy than Vision GNN with a 24.3% reduction in parameters and 35.3% reduction in GMACs. Our work shows that leveraging long-range links in graph construction for ViGs through our proposed LSGC can exceed the performance of current state-of-the-art ViGs. 

   more » « less