Search Results for author:
Found 30 papers, 21 papers with code
Equity through Access: A Case for Small-scale Deep Learning
The recent advances in deep learning (DL) have been accelerated by access to large-scale data and compute.
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency
We present experiments on two benchmark datasets showing that adversarial fine-tuning of compressed models can achieve robustness performance comparable to adversarially trained models, while also improving computational efficiency.
CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning
We invite the graph ML community to address these open challenges by presenting two new chemically-informed large-scale inorganic (CHILI) nanomaterials datasets: A medium-scale dataset (with overall >6M nodes, >49M edges) of mono-metallic oxide nanomaterials generated from 12 selected crystal types (CHILI-3K) and a large-scale dataset (with overall >183M nodes, >1. 2B edges) of nanomaterials generated from experimentally determined crystal structures (CHILI-100K).
Ranked #1 on
X-ray PDF regression
on CHILI-100K
Is Adversarial Training with Compressed Datasets Effective?
This synthetic dataset retains the essential information of the original dataset, enabling models trained on it to achieve performance levels comparable to those trained on the full dataset.
Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization
Further, we present a correction to the assumptions on the distribution of intermediate activation maps in EXACT (assumed to be uniform) and show improved variance estimations of the quantization and dequantization steps.
Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI
The solution lionized by both industry and the ML community to improve the environmental sustainability of ML is to increase the efficiency with which ML systems operate in terms of both compute and energy consumption.
Operating critical machine learning models in resource constrained regimes
The resource consumption of deep learning models in terms of amount of training data, compute and energy costs are known to be massive.
Explicit Temporal Embedding in Deep Generative Latent Models for Longitudinal Medical Image Synthesis
This, in contrast to previous methods, allows us to synthesize continuous, smooth, and high-quality longitudinal volumetric data with limited supervision.
EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search
We advocate for including energy efficiency as an additional performance criterion in NAS.
Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation
Contrastive self-supervised learning provides a framework to learn meaningful representations using learned notions of similarity measures from simple pretext tasks.
Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised Methods
The results show that unsupervised methods to discover interpretable directions in GANs generalize to VAEs and can be applied to medical images.
Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis
In this study, we present and compare the features of four tools from literature to quantify the carbon footprint of DL.
Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks
The performance of the proposed tensor network segmentation model is compared with relevant baseline methods.
Identifying partial mouse brain microscopy images from Allen reference atlas using a contrastively learned semantic space
The correspondence between the partial mouse brain image and reference atlas plate is determined based on the distance between low dimensional embeddings of brain slices and atlas plates that are obtained from Siamese networks using contrastive learning.
Segmenting two-dimensional structures with strided tensor networks
We use the matrix product state (MPS) tensor network on non-overlapping patches of a given input image to predict the segmentation mask by learning a pixel-wise linear classification rule in a high dimensional space.
Dynamic $β$-VAEs for quantifying biodiversity by clustering optically recorded insect signals
While insects are the largest and most diverse group of terrestrial animals, constituting ca.
Multi-layered tensor networks for image classification
The recently introduced locally orderless tensor network (LoTeNet) for supervised image classification uses matrix product state (MPS) operations on grids of transformed image patches.
Locally orderless tensor networks for classifying two- and three-dimensional medical images
The proposed locally orderless tensor network (LoTeNet) is compared with relevant methods on three datasets.
Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models
In this work, we present Carbontracker, a tool for tracking and predicting the energy and carbon footprint of training DL models.
Uncertainty quantification in medical image segmentation with normalizing flows
In this work, we propose a novel conditional generative model that is based on conditional Normalizing Flow (cFlow).
Lung Segmentation from Chest X-rays using Variational Data Imputation
Pulmonary opacification is the inflammation in the lungs caused by many respiratory ailments, including the novel corona virus disease 2019 (COVID-19).
Tensor Networks for Medical Image Classification
With the increasing adoption of machine learning tools like neural networks across several domains, interesting connections and comparisons to concepts from other domains are coming to light.
A joint 3D UNet-Graph Neural Network-based method for Airway Segmentation from chest CTs
In this approach, the convolutional layers at the deepest level of the UNet are replaced by a GNN-based module with a series of graph convolutions.
Segmentation of Roots in Soil with U-Net
We evaluate our system using 867 images for which we have obtained line-intersect counts, attaining a Spearman rank correlation of 0. 9748 and an $r^2$ of 0. 9217.
Graph Refinement based Airway Extraction using Mean-Field Networks and Graph Neural Networks
Graph refinement, or the task of obtaining subgraphs of interest from over-complete graphs, can have many varied applications.
Extracting Tree-structures in CT data by Tracking Multiple Statistically Ranked Hypotheses
We propose to use statistical ranking of local hypotheses in constructing the MHT tree, which yields a probabilistic interpretation of scores across scales and helps alleviate the scale-dependence of MHT parameters.
Extraction of Airways using Graph Neural Networks
We present extraction of tree structures, such as airways, from image data as a graph refinement task.
Mean Field Network based Graph Refinement with application to Airway Tree Extraction
Performance of the method is compared with two methods: the first uses probability images from a trained voxel classifier with region growing, which is similar to one of the best performing methods at EXACT'09 airway challenge, and the second method is based on Bayesian smoothing on these probability images.
Extraction of Airways with Probabilistic State-space Models and Bayesian Smoothing
The evolution of individual branches is modelled using a process model and the observed data is incorporated into the update step of the Bayesian smoother using a measurement model that is based on a multi-scale blob detector.
Extraction of airway trees using multiple hypothesis tracking and template matching
The results show improvements in performance when compared to the original method and region growing on intensity images.
