Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery

Dadsetan, Saba; Pichler, David; Wilson, David L.; Hovakimyan, Naira; Hobbs, Jennifer

doi:10.1109/cvprw53098.2021.00330

Cited by 5 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relational GCNs [41] add to this framework by also considering multiple edge types, namely, relations (such as temporal and spatial relations), and the aggregating information from each relation via separate weights in a single layer. Recently, GCNs have been adopted for tasks involving audio [12,61] and images [33,11,5]. Following the success of graph models to efficiently perform image-based tasks, we are eager to demonstrate our extension of the image-graph representation to videos.…”

Section: Graph Convolutional Neural Networkmentioning

confidence: 99%

“…For example, optical-flow dramatically improved the accuracy in the two-stream methodology that was proposed in [43]. Additionally, over-segmentation using superpixels has been found useful as input features for machine learning models due to the limited loss of important details, accompanied by a dramatic reduction in the expended time by means of reducing the number of elements of the input [21,11,5].…”

Section: Benefits Of Graphvidmentioning

confidence: 99%

“…One can clearly discern a person playing a guitar in both images. A different way of depicting the relations between superpixels is a graph with nodes representing superpixels [33,11,5]. Such a representation has the advantage of being invariant to rotations and flips, which obviates the need for further augmentations.…”

Section: Introductionmentioning

confidence: 99%

“…Recent years have seen a surge in the utilization of Graph Neural Networks (GNNs) [26] in tasks that involve images [33,11,5], audio [12,61] and other data forms [54,55,1]. In this paper, we propose GraphVid, a concise graph representation of videos that enables video processing via GNNs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

GraphVid: It Only Takes a Few Nodes to Understand a Video

Kosman¹,

Castro²

2022

Preprint

View full text Add to dashboard Cite

We propose a concise representation of videos that encode perceptually meaningful features into graphs. With this representation, we aim to leverage the large amount of redundancies in videos and save computations. First, we construct superpixel-based graph representations of videos by considering superpixels as graph nodes and create spatial and temporal connections between adjacent superpixels. Then, we leverage Graph Convolutional Networks to process this representation and predict the desired output. As a result, we are able to train models with much fewer parameters, which translates into short training periods and a reduction in computation resource requirements. A comprehensive experimental study on the publicly available datasets Kinetics-400 and Charades shows that the proposed method is highly cost-effective and uses limited commodity hardware during training and inference. It reduces the computational requirements 10-fold while achieving results that are comparable to state-ofthe-art methods. We believe that the proposed approach is a promising direction that could open the door to solving video understanding more efficiently and enable more resource limited users to thrive in this research field.

show abstract