Search Results for author:
Found 41 papers, 17 papers with code
Building an AI Support Tool for Real-time Ulcerative Colitis Diagnosis
We propose using a machine-learning based MES classification system to support the endoscopic process and to mitigate the observer-variability.
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.
Tree Counting by Bridging 3D Point Clouds with Imagery
We leverage the fusion of three-dimensional LiDAR measurements and 2D imagery to facilitate the accurate counting of trees.
Predicting urban tree cover from incomplete point labels and limited background information
This paper studies how to combine accurate point labels of urban trees along streets with crowd-sourced annotations from an open geographic database to delineate city trees in remote sensing images, a task which is challenging even for humans.
Benchmarking Individual Tree Mapping with Sub-meter Imagery
There is a rising interest in mapping trees using satellite or aerial imagery, but there is no standardized evaluation protocol for comparing and enhancing methods.
Familiarity-Based Open-Set Recognition Under Adversarial Attacks
Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications.
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.
Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints
We investigate the properties of the mined images, and find that images trained on a small number of image captions generalize to a much larger number of semantically related captions.
Smooth Monotonic Networks
The resulting smooth min-max (SMM) network module inherits the asymptotic approximation properties from the MM architecture.
BuildSeg: A General Framework for the Segmentation of Buildings
Building segmentation from aerial images and 3D laser scanning (LiDAR) is a challenging task due to the diversity of backgrounds, building textures, and image quality.
LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensing
In this work, we propose a DUN called low-rank CS network (LR-CSNet) for natural image CS.
EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search
We advocate for including energy efficiency as an additional performance criterion in NAS.
Self-Supervised Speech Representation Learning: A Review
Although self-supervised speech representation is still a nascent research area, it is closely related to acoustic word embedding and learning with zero lexical resources, both of which have seen active research for many years.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Remember to correct the bias when using deep learning for regression!
We suggest to adjust the bias of the machine learning model after training as a default postprocessing step, which efficiently solves the problem.
A Brief Overview of Unsupervised Neural Speech Representation Learning
Unsupervised representation learning for speech processing has matured greatly in the last few years.
Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass
Quantification of forest biomass stocks and their dynamics is important for implementing effective climate change mitigation measures.
Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?
We compare learned speech features from wav2vec 2. 0, state-of-the-art ASR transcripts, and the ground truth text as input for a novel speech-based named entity recognition task, a cardiac arrest detection task on real-world emergency calls and two existing SLU benchmarks.
Ranked #7 on
Spoken Language Understanding
on Fluent Speech Commands
(using extra training data)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+8
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
The bound is based on a novel parametric form of the Chebyshev- Cantelli inequality (a. k. a.
Information Bottleneck: Exact Analysis of (Quantized) Neural Networks
In this setting, we observed a fitting phase for all layers and a compression phase for the output layer in all experiments; the compression in the hidden layers was dependent on the type of activation function.
Do End-to-End Speech Recognition Models Care About Context?
We test this hypothesis by measuring temporal context sensitivity and evaluate how the models perform when we constrain the amount of contextual information in the audio input.
On Scaling Contrastive Representations for Low-Resource Speech Recognition
We explore the performance of such systems without fine-tuning by training a state-of-the-art speech recognizer on the fixed representations from the computationally demanding wav2vec 2. 0 framework.
Multimodal Variational Autoencoders for Semi-Supervised Learning: In Defense of Product-of-Experts
Multimodal generative models should be able to learn a meaningful latent representation that enables a coherent joint generation of all modalities (e. g., images and text).
A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model
To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity.
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
We present a novel analysis of the expected risk of weighted majority vote in multiclass classification.
On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions
We propose a modified Metropolis transition operator that behaves almost always identically to the standard Metropolis operator and prove that it ensures irreducibility and convergence to the limiting distribution in the multivariate binary case with fixed-order updates.
A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity.
The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset
Purpose: To organize a knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic segmentation methods relevant for monitoring osteoarthritis progression.
Label-similarity Curriculum Learning
We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label representation.
One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation
The system relies on multi-planar data augmentation which facilitates the application of a single 2D architecture based on the familiar U-Net.
U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging
We propose U-Time, a fully feed-forward deep learning approach to physiological time series segmentation developed for the analysis of sleep data.
Knowledge distillation for semi-supervised domain adaptation
As a result, their performance is significantly lower on data from unseen sources compared to the performance on data from the same source as the training data.
The Liver Tumor Segmentation Benchmark (LiTS)
In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018.
On PAC-Bayesian Bounds for Random Forests
This effect provides a significant boost in performance when the errors are independent or negatively correlated, but when the correlations are strong the advantage from taking the majority vote is small.
PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation
For proper generalization performance of convolutional neural networks (CNNs) in medical image segmentation, the learnt features should be invariant under particular non-linear shape variations of the input.
Training Big Random Forests with Little Resources
Without access to large compute clusters, building random forests on large datasets is still a challenging problem.
Big Universe, Big Data: Machine Learning and Image Analysis for Astronomy
Astrophysics and cosmology are rich with data.
CMA-ES with Optimal Covariance Update and Storage Complexity
The covariance matrix adaptation evolution strategy (CMA-ES) is arguably one of the most powerful real-valued derivative-free optimization algorithms, finding many applications in machine learning.
A Strongly Quasiconvex PAC-Bayesian Bound
We propose a new PAC-Bayesian bound and a way of constructing a hypothesis space, so that the bound is convex in the posterior distribution and also convex in a trade-off parameter between empirical performance of the posterior distribution and its complexity.
Bigger Buffer k-d Trees on Multi-Many-Core Systems
A buffer k-d tree is a k-d tree variant for massively-parallel nearest neighbor search.
Sacrificing information for the greater good: how to select photometric bands for optimal accuracy
This study promotes a feature selection algorithm, which selects the most informative magnitudes and colours for a given task of estimating physical quantities from photometric data alone.
Population-Contrastive-Divergence: Does Consistency help with RBM training?
Compared to CD, it leads to a consistent estimate and may have a significantly lower bias.
