Search Results for author:
Found 24 papers, 6 papers with code
PuzzleTuning: Explicitly Bridge Pathological and Natural Image with Puzzles
Pathological image analysis is a crucial field in computer vision.
Finding Meaningful Distributions of ML Black-boxes under Forensic Investigation
Our goal is to select a set of samples from the corpus for the given model.
A Deep Learning Network for the Classification of Intracardiac Electrograms in Atrial Tachycardia
From our findings, the CNN-LSTM model achieved an accuracy of 81% for the balanced dataset.
PaRT: Parallel Learning Towards Robust and Transparent AI
Each subset consists of network segments, that can be combined and shared across specific tasks.
Use of small auxiliary networks and scarce data to improve the adversarial robustness of deep learning models
Experiments on the CIFAR10 dataset showed that using only $10\%$ of the full training set, the proposed method was able to adequately defend the model against the AutoPGD attack while maintaining a classification accuracy on clean images outperforming the model with adversarial training by $7\%$.
An End-to-End Breast Tumour Classification Model Using Context-Based Patch Modelling- A BiLSTM Approach for Image Classification
However, due to patch-based analysis, most of the current methods fail to exploit the underlying spatial relationship among the patches.
Explaining Adversarial Vulnerability with a Data Sparsity Hypothesis
We found that models trained using our framework, as well as other regularization methods and adversarial training support our hypothesis of data sparsity and that models trained with these methods learn to have decision boundaries more similar to the aforementioned ideal decision boundary.
Automated Deep Learning Analysis of Angiography Video Sequences for Coronary Artery Disease
The evaluation of obstructions (stenosis) in coronary arteries is currently done by a physician's visual assessment of coronary angiography video sequences.
Distribution Based MIL Pooling Filters are Superior to Point Estimate Based Counterparts
We showed that the performance of different pooling filters are different for different MIL tasks.
Machine-Learning Study using Improved Correlation Configuration and Application to Quantum Monte Carlo Simulation
We classify the BKT phase and the paramagnetic phase of the quantum XY model using the machine-learning approach.
Studying The Effect of MIL Pooling Filters on MIL Tasks
In this paper, we study the effect of different MIL pooling filters on the performance of MIL models in real world MIL tasks.
Enhancing Transformation-Based Defenses Against Adversarial Attacks with a Distribution Classifier
Furthermore, on the adversarial counterparts, with the image transformation, the resulting shapes of the distribution of softmax are similar to the distributions from the clean images.
Confusing and Detecting ML Adversarial Attacks with Injected Attractors
Many machine learning adversarial attacks find adversarial samples of a victim model ${\mathcal M}$ by following the gradient of some attack objective functions, either explicitly or implicitly.
Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts
Motivation: High resolution 2D whole slide imaging provides rich information about the tissue structure.
Machine-Learning Studies on Spin Models
As an alternative to investigating the thermal average of macroscopic physical quantities, they have used the spin configurations for the classification of the disordered and ordered phases of a phase transition through machine learning.
Statistical Mechanics
Cribriform pattern detection in prostate histopathological images using deep learning models
In this paper, we present an annotated cribriform dataset along with analysis of deep learning models and hand-crafted features for cribriform pattern detection in prostate histopathological images.
Weakly Supervised Clustering by Exploiting Unique Class Count
We have constructed a neural network based $ucc$ classifier and experimentally shown that the clustering performance of our framework with our weakly supervised $ucc$ classifier is comparable to that of fully supervised learning models where labels for all instances are known.
Enhancing Transformation-based Defenses using a Distribution Classifier
Furthermore, on the adversarial counterparts, with the image transformation, the resulting shapes of the distribution of softmax are similar to the distributions from the clean images.
Fence GAN: Towards Better Anomaly Detection
However, the traditional GAN loss is not directly aligned with the anomaly detection objective: it encourages the distribution of the generated samples to overlap with the real data and so the resulting discriminator has been found to be ineffective as an anomaly detector.
Gated-Dilated Networks for Lung Nodule Classification in CT scans
Different types of Convolutional Neural Networks (CNNs) have been applied to detect cancerous lung nodules from computed tomography (CT) scans.
Ranked #3 on
Lung Nodule Classification
on LIDC-IDRI
Theoretical and Experimental Analysis on the Generalizability of Distribution Regression Network
However, in Kou et al. (2018) and some other works on distribution regression, there is a lack of comprehensive comparative study on both theoretical basis and generalization abilities of the methods.
A Compact Network Learning Model for Distribution Regression
Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces.
Flipped-Adversarial AutoEncoders
We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously trains a generative model G that maps an arbitrary latent code distribution to a data distribution and an encoder E that embodies an "inverse mapping" that encodes a data sample into a latent code vector.
Distribution Regression Network
We introduce our Distribution Regression Network (DRN) which performs regression from input probability distributions to output probability distributions.
