Search Results for author:
Found 18 papers, 3 papers with code
XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification
Detecting out-of-distribution (OOD) data at inference time is crucial for many applications of machine learning.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Numerical Evaluation of a muon tomography system for imaging defects in concrete structures
The images of the test cases with and without the defect have been simulated for a month-long exposure of cosmic muons on the basis of their scattering from the composite concrete structures.
High Energy Physics - Experiment Image and Video Processing Instrumentation and Detectors
Fast simulation of avalanche and streamer in GEM detector using hydrodynamic approach
A fast, hydrodynamic numerical model has been developed on the COMSOL Multi-physics platform to simulate the evolution and dynamics of charged particles in gaseous ionization detectors based on the Gaseous Electron Multipliers (GEM).
Instrumentation and Detectors High Energy Physics - Experiment
A One-Shot Learning Framework for Assessment of Fibrillar Collagen from Second Harmonic Generation Images of an Infarcted Myocardium
Myocardial infarction (MI) is a scientific term that refers to heart attack.
Context-Aware Design of Cyber-Physical Human Systems (CPHS)
The impacts of context factors driving human system interaction are challenging and are difficult to capture and replicate in existing design models.
DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image Classification
Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning.
Ranked #1 on
Satellite Image Classification
on SAT-4
PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters
We show that by learning the features at each resolution independently a trained model is able to accurately classify characters even in the presence of noise.
Ranked #1 on
Image Classification
on Noisy MNIST (AWGN)
Improving Prediction Accuracy in Building Performance Models Using Generative Adversarial Networks (GANs)
To potentially reduce the discrepancies and improve the prediction accuracy of BPMs, this paper proposes a computational framework for learning mixture models by using Generative Adversarial Networks (GANs) that appropriately combining existing BPMs with knowledge on occupant behaviors to contextual factors in new designs.
Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation
High fidelity route choice models are required to predict traffic levels with higher accuracy.
Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images
Machine learning has proven to be useful in classification and segmentation of images.
Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters
Classification techniques for images of handwritten characters are susceptible to noise.
Ranked #1 on
Document Image Classification
on n-MNIST
Unsupervised Learning using Pretrained CNN and Associative Memory Bank
In this paper, we present a new architecture and an approach for unsupervised object recognition that addresses the above mentioned problem with fine tuning associated with pretrained CNN-based supervised deep learning approaches while allowing automated feature extraction.
Ranked #1 on
Fine-Grained Image Classification
on Caltech-101
(Accuracy metric)
Few-Shot Image Classification
Fine-Grained Image Classification
+2
CactusNets: Layer Applicability as a Metric for Transfer Learning
Deep neural networks trained over large datasets learn features that are both generic to the whole dataset, and specific to individual classes in the dataset.
Core Sampling Framework for Pixel Classification
The intermediate map responses of a Convolutional Neural Network (CNN) contain information about an image that can be used to extract contextual knowledge about it.
A Theoretical Analysis of Deep Neural Networks for Texture Classification
To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate.
Automatic Synthesis of Geometry Problems for an Intelligent Tutoring System
This paper presents an intelligent tutoring system, GeoTutor, for Euclidean Geometry that is automatically able to synthesize proof problems and their respective solutions given a geometric figure together with a set of properties true of it.
Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets
Learning sparse feature representations is a useful instrument for solving an unsupervised learning problem.
DeepSat - A Learning framework for Satellite Imagery
Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning.
Ranked #2 on
Satellite Image Classification
on SAT-6
