Enhancing Visualization and Explainability of Computer Vision Models with Local Interpretable Model-Agnostic Explanations (LIME)

Hamilton, Nicholas A.; Webb, Adam; Wilder, Matt; Hendrickson, Ben; Blanck, Matt; Nelson, Erin; Roemer, Wiley; Havens, Timothy C.

doi:10.1109/ssci51031.2022.10022096

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To do this we used Surrogate Object Detection Explainer (SODEx) in combination with SubLIME to explain which regions of an image affected detections. 17,21 This consists of a few steps. The first is to split an image into small regions called superpixels.…”

Section: Methodsmentioning

confidence: 99%

“…[13][14][15] We also use a modification of Local Interpretable Model-Agnostic Explanations (LIME) we previously described named Sub-model Stabilized and Sub-grid Superimposed LIME (SubLIME) in order to explain precisely how the data augmentations affect the training process. 16,17 The remainder of this paper is organized as follows: Section 2 describes the data used in our experiments, Section 3 details the two augmentation techniques, Section 4 describes our experiments, Section 5 explains the results of our experiment, and in Section 6 we give our final thoughts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Synthetic augmentation methods for object detection in infrared overhead imagery

Hamilton,

Webb,

Wilder

et al. 2024

Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II

View full text Add to dashboard Cite

Geospatial intelligence is a subject with many opportunities for machine automation. Object detection is one desirable application. However, a lack of high-volume relevant datasets can make this task difficult. To combat this issue, we introduced a spin-set augmentation technique to generate synthetic training data. We used these synthetic datasets to augment the training of an object detection deep network, focusing on visible band imagery. We have continued our efforts by further testing this method on long-wave infrared imagery, including results from YOLO, SSD, and Faster R-CNN algorithms. We also introduce another synthetic augmentation technique which involves generating physics-based fully-rendered images of 3D synthetic scenery and targets and compared the rendered image performance to that of spin-sets. This paper analyzes both the spin-set and rendered image augmentation techniques in terms of object detection performance, complexity, generalizability, and explainability.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Synthetic augmentation methods for object detection in infrared overhead imagery

Hamilton,

Webb,

Wilder

et al. 2024

Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II

View full text Add to dashboard Cite

show abstract

Sequential Model Using Explainable AI Method to Detect Eye Diseases

Aaron Samuel,

Muhammad Fadil,

Beaulah Jeyavathana

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Classification of SARS-CoV-2 sequences as recombinants via a pre-trained CNN and identification of a mathematical signature relative to recombinant feature at Spike, via interpretability

Guerrero-Tamayo,

Sanz Urquijo,

Olivares

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The global impact of the SARS-CoV-2 pandemic has underscored the need for a deeper understanding of viral evolution to anticipate new viruses or variants. Genetic recombination is a fundamental mechanism in viral evolution, yet it remains poorly understood. In this study, we conducted a comprehensive research on the genetic regions associated with genetic recombination features in SARS-CoV-2. With this aim, we implemented a two-phase transfer learning approach using genomic spectrograms of complete SARS-CoV-2 sequences. In the first phase, we utilized a pre-trained VGG-16 model with genomic spectrograms of HIV-1, and in the second phase, we applied HIV-1 VGG-16 model to SARS-CoV-2 spectrograms. The identification of key recombination hot zones was achieved using the Grad-CAM interpretability tool, and the results were analyzed by mathematical and image processing techniques. Our findings unequivocally identify the SARS-CoV-2 Spike protein (S protein) as the pivotal region in the genetic recombination feature. For non-recombinant sequences, the relevant frequencies clustered around 1/6 and 1/12. In recombinant sequences, the sharp prominence of the main hot zone in the Spike protein prominently indicated a frequency of 1/6. These findings suggest that in the arithmetic series, every 6 nucleotides (two triplets) in S may encode crucial information, potentially concealing essential details about viral characteristics, in this case, recombinant feature of a SARS-CoV-2 genetic sequence. This insight further underscores the potential presence of multifaceted information within the genome, including mathematical signatures that define an organism’s unique attributes.

show abstract

Enhancing Visualization and Explainability of Computer Vision Models with Local Interpretable Model-Agnostic Explanations (LIME)

Cited by 4 publications

References 15 publications

Synthetic augmentation methods for object detection in infrared overhead imagery

Synthetic augmentation methods for object detection in infrared overhead imagery

Sequential Model Using Explainable AI Method to Detect Eye Diseases

Classification of SARS-CoV-2 sequences as recombinants via a pre-trained CNN and identification of a mathematical signature relative to recombinant feature at Spike, via interpretability

Contact Info

Product

Resources

About