Active Learning (AL) is a human-in-the-loop framework to interactively a...
Deep neural networks have consistently shown great performance in severa...
A salient characteristic of large pre-trained language models (PTLMs) is...
Training deep networks and tuning hyperparameters on large datasets is
c...
Training state-of-the-art ASR systems such as RNN-T often has a high
ass...
Avoiding out-of-distribution (OOD) data is critical for training supervi...
Training deep learning models on medical datasets that perform well for ...
Active Learning is a very common yet powerful framework for iteratively ...
Deep neural networks have seen great success in recent years; however,
t...
Current semi-supervised learning (SSL) methods assume a balance between ...
Submodular functions are a special class of set functions which naturall...
Few-shot classification (FSC) requires training models using a few (typi...
Deep neural networks based object detectors have shown great success in ...
Continual learning (CL) aims to develop techniques by which a single mod...
We study the task of personalizing ASR models to a target non-native
spe...
A critical bottleneck in supervised machine learning is the need for lar...
Recently a class of generalized information measures was defined on sets...
We present SPEAR, an open-source python library for data programming wit...
Active learning has proven to be useful for minimizing labeling costs by...
Data subset selection from a large number of training instances has been...
Semi-supervised learning (SSL) algorithms have had great success in rece...
Prior studies have shown that, training machine learning models via empi...
Recently, unsupervised parsing of syntactic trees has gained considerabl...
With the rapid growth of data, it is becoming increasingly difficult to ...
With increasing data, techniques for finding smaller, yet effective subs...
Automatic video summarization is still an unsolved problem due to severa...
Large scale machine learning and deep models are extremely data-hungry.
...
Model-Agnostic Meta-Learning (MAML) is a popular gradient-based meta-lea...
Deep Models are increasingly becoming prevalent in summarization problem...
Federated Learning (FL) is a decentralized machine learning protocol tha...
We study submodular information measures as a rich framework for generic...
Semi-supervised learning (SSL) based on deep neural networks (DNNs) has
...
The paradigm of data programming <cit.> has shown a lot of
promise in us...
Automatic video summarization is still an unsolved problem due to severa...
Information-theoretic quantities like entropy and mutual information hav...
Submodular Functions are a special class of set functions, which general...
Robust Optimization is becoming increasingly important in machine learni...
In this paper, we shall study a unified framework of robust submodular
o...
We are motivated by large scale submodular optimization problems, where
...
In this paper, we investigate a class of submodular problems which in ge...
Supervised machine learning based state-of-the-art computer vision techn...
This paper addresses automatic summarization of videos in a unified mann...
In the light of exponentially increasing video content, video summarizat...
With increasing amounts of visual data being created in the form of vide...
We present a unified framework for Batch Online Learning (OL) for Click
...
This paper introduces Jensen, an easily extensible and scalable toolkit ...
Supervised machine learning based state-of-the-art computer vision techn...
This paper demonstrates the effectiveness of our customized deep learnin...
In real world systems, the predictions of deployed Machine Learned model...
This paper addresses automatic summarization and search in visual data
c...