Search Results for author:
Found 17 papers, 5 papers with code
Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging
Although Vision Transformers (ViTs) have recently demonstrated superior performance in medical imaging problems, they face explainability issues similar to previous architectures such as convolutional neural networks.
Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification
Through large-scale experiments on various patient sizes in the training set, we show that medical institutions do not need a decade's worth of MRI images to train an AI model that performs competitively with the state-of-the-art, provided the model leverages foundation models.
Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals
Using both supervised and self-supervised convolutional neural networks, as well as vision transformers in large-scale experiments, we demonstrate that deep learning with color FIM images consistently outperforms monochrome images, thus highlighting the potential of color FIM in stress source classification compared to its monochrome counterparts.
Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
To avoid the "benchmark lottery" on ImageNet and to ensure a fair benchmarking process, we investigate the usage of a unified metric that takes into account the performance of models on other ImageNet variant datasets.
Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models
With the advancements in self-supervised learning (SSL), transformer-based computer vision models have recently demonstrated superior results compared to convolutional neural networks (CNNs) and are poised to dominate the field of artificial intelligence (AI)-based medical imaging in the upcoming years.
BRCA Gene Mutations in dbSNP: A Visual Exploration of Genetic Variants
BRCA genes, comprising BRCA1 and BRCA2 play indispensable roles in preserving genomic stability and facilitating DNA repair mechanisms.
Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training
In this survey, we review a plethora of research efforts conducted on image-oriented SSL, providing a historic view and paying attention to best practices as well as useful software packages.
Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
Even though deep neural networks (DNNs) achieve state-of-the-art results for a number of problems involving genomic data, getting DNNs to explain their decision-making process has been a major challenge due to their black-box nature.
Exact Feature Collisions in Neural Networks
Predictions made by deep neural networks were shown to be highly sensitive to small changes made in the input space where such maliciously crafted data points containing small perturbations are being referred to as adversarial examples.
Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
We find that $71\%$ of the adversarial examples that achieve model-to-model adversarial transferability are misclassified into one of the top-5 classes predicted for the underlying source images.
Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
Although the adoption rate of deep neural networks (DNNs) has tremendously increased in recent years, a solution for their vulnerability against adversarial examples has not yet been found.
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems
Another concern that is often cited when designing smart home applications is the resilience of these applications against cyberattacks.
Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability
Regional adversarial attacks often rely on complicated methods for generating adversarial perturbations, making it hard to compare their efficacy against well-known attacks.
Perturbation Analysis of Gradient-based Adversarial Attacks
Our experiments reveal that the Iterative Fast Gradient Sign attack, which is thought to be fast for generating adversarial examples, is the worst attack in terms of the number of iterations required to create adversarial examples in the setting of equal perturbation.
Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning.
Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation
Given that a large portion of medical imaging problems are effectively segmentation problems, we analyze the impact of adversarial examples on deep learning-based image segmentation models.
How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples
Nowadays, the output of the softmax function is also commonly used to assess the strength of adversarial examples: malicious data points designed to fail machine learning models during the testing phase.
