Search Results for author:
Found 83 papers, 34 papers with code
Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision
Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry.
GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training
We show rigorous theoretical and convergence guarantees of the proposed algorithm and, through our extensive experiments on real-world datasets, show the effectiveness of our proposed framework.
AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning
Our central insight is that using an informative subset of the dataset for model training runs involved in hyper-parameter optimization, allows us to find the optimal hyper-parameter configuration significantly faster.
SPEAR : Semi-supervised Data Programming in Python
SPEAR facilitates weak supervision in the form of heuristics (or rules) and association of noisy labels to the training dataset.
When Do Neural Nets Outperform Boosted Trees on Tabular Data?
To this end, we conduct the largest tabular data analysis to date, comparing 19 algorithms across 176 datasets, and we find that the 'NN vs. GBDT' debate is overemphasized: for a surprisingly high number of datasets, either the performance difference between GBDTs and NNs is negligible, or light hyperparameter tuning on a GBDT is more important than choosing between NNs and GBDTs.
Submodlib: A Submodular Optimization Library
A recent work has also leveraged submodular functions to propose submodular information measures which have been found to be very useful in solving the problems of guided subset selection and guided summarization.
UDAAN: Machine Learning based Post-Editing tool for Document Translation
UDAAN has an end-to-end Machine Translation (MT) plus post-editing pipeline wherein users can upload a document to obtain raw MT output.
Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification
Such a joint learning is expected to provide a twofold advantage: i) the classifier generalizes better as it leverages the prior knowledge of existence of a hierarchy over the labels, and ii) in addition to the label co-occurrence information, the label-embedding may benefit from the manifold structure of the input datapoints, leading to embeddings that are more faithful to the label hierarchy.
Ranked #1 on
Multi-Label Text Classification
on RCV1
General Classification
Hierarchical Multi-label Classification
+1
PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection
Examples of such problems include: i)targeted learning, where the goal is to find subsets with rare classes or rare attributes on which the model is underperforming, and ii)guided summarization, where data (e. g., image collection, text, document or video) is summarized for quicker human consumption with specific additional user intent.
Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
We analyze the performance of representative crowd counting approaches across standard datasets at per strata level and in aggregate.
LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos
Analyzing the interactions between humans and objects from a video includes identification of the relationships between humans and the objects present in the video.
Human-Object Interaction Detection
Relationship Detection
+1
AutoML for Climate Change: A Call to Action
The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications.
Cross-Lingual Training for Automatic Question Generation
For a new language, such training instances are hard to obtain making the QG problem even more challenging.
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights
In this work, we propose the first large scale study of automatic speech recognition (ASR) in Sanskrit, with an emphasis on the impact of unit selection in Sanskrit ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning
Finally, we propose Glister-Active, an extension to batch active learning, and we empirically demonstrate the performance of Glister on a wide range of tasks including, (a) data selection to reduce training time, (b) robust learning under label noise and imbalance settings, and (c) batch-active learning with several deep and shallow models.
A Benchmark and Dataset for Post-OCR text correction in Sanskrit
Keeping this in mind, we release a multi-domain dataset, from areas as diverse as astronomy, medicine and mathematics, with some of them as old as 18 centuries.
Meta-Learning for Effective Multi-task and Multilingual Modelling
We present experiments on five different tasks and six different languages from the XTREME multilingual benchmark dataset.
Data Programming using Continuous and Quality-Guided Labeling Functions
Scarcity of labeled data is a bottleneck for supervised learning models.
TEXTRON: Weakly Supervised Multilingual Text Detection through Data Programming
In order to solve this problem, we propose TEXTRON, a Data Programming-based approach, where users can plug various text detection methods into a weak supervision-based learning framework.
Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering
In response, we identify a key structural idiom in OKVQA , viz., S3 (select, substitute and search), and build a new data set and challenge around it.
Training Data Subset Selection for Regression with Controlled Generalization Error
First, we represent this problem with simplified constraints using the dual of the original training problem and show that the objective of this new representation is a monotone and alpha-submodular function, for a wide variety of modeling choices.
Cross-Modal learning for Audio-Visual Video Parsing
In this paper, we present a novel approach to the audio-visual video parsing (AVVP) task that demarcates events from a video separately for audio and visual modalities.
Ranked #1 on
Event Detection
on Audio Set
Rule Augmented Unsupervised Constituency Parsing
We introduce a novel formulation that takes advantage of the syntactic grammar rules and is independent of the base system.
Semi-Supervised Data Programming with Subset Selection
The first contribution of this work is an introduction of a framework, \model which is a semi-supervised data programming paradigm that learns a \emph{joint model} that effectively uses the rules/labelling functions along with semi-supervised loss functions on the feature space.
Gradient Coreset for Federated Learning
We conduct experiments using four real-world datasets and show that GCFL is (1) more compute and energy efficient than FL, (2) robust to various kinds of noise in both the feature space and labels, (3) preserves the privacy of the validation dataset, and (4) introduces a small communication overhead but achieves significant gains in performance, particularly in cases when the clients' data is noisy.
SMART: Submodular Data Mixture Strategy for Instruction Tuning
Instruction Tuning involves finetuning a language model on a collection of instruction-formatted datasets in order to enhance the generalizability of the model to unseen tasks.
Rudder: A Cross Lingual Video and Text Retrieval Dataset
Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input.
Ranked #1 on
Video Retrieval
on Charades-STA
Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming
These LFs, in turn, have been used to generate a large amount of additional noisy labeled data, in a paradigm that is now commonly referred to as data programming.
EIGEN: Expert-Informed Joint Learning Aggregation for High-Fidelity Information Extraction from Document Images
We empirically show that our EIGEN framework can significantly improve the performance of state-of-the-art deep models with the availability of very few labeled data instances.
Unsupervised Learning of Explainable Parse Trees for Improved Generalisation
In this work, we propose an attention mechanism over Tree-LSTMs to learn more meaningful and explainable parse tree structures.
Adaptive Mixing of Auxiliary Losses in Supervised Learning
In several supervised learning scenarios, auxiliary losses are used in order to introduce additional information or constraints into the supervised learning objective.
Sāmayik: A Benchmark and Dataset for English-Sanskrit Translation
Translation models trained on our dataset demonstrate statistically significant improvements when translating out-of-domain contemporary corpora, outperforming models trained on older classical-era poetry datasets.
Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks
Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts.
Automating Reading Comprehension by Generating Question and Answer Pairs
Neural network-based methods represent the state-of-the-art in question generation from text.
Learning Discriminative Relational Features for Sequence Labeling
For learning features derived from inputs at a particular sequence position, we propose a Hierarchical Kernels-based approach (referred to as Hierarchical Kernel Learning for Structured Output Spaces - StructHKL).
A Unified Multi-Faceted Video Summarization System
Most importantly, we also show that we can summarize hours of video data in a few seconds, and our system allows the user to generate summaries of various lengths and types interactively on the fly.
Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text
The {\it generator} is a sequence-to-sequence model that incorporates the {\it structure} and {\it semantics} of the question being generated.
A Framework towards Domain Specific Video Summarization
We propose a novel framework for domain specific video summarization.
Entity Resolution and Location Disambiguation in the Ancient Hindu Temples Domain using Web Data
We present a system for resolving entities and disambiguating locations based on publicly available web data in the domain of ancient Hindu Temples.
Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importance
This paper addresses automatic summarization of videos in a unified manner.
Efficient Reuse of Structured and Unstructured Resources for Ontology Population
A domain ontology for an organization, often consists of classes whose instances are either specific to, or independent of the organization.
Tale of tails using rule augmented sequence labeling for event extraction
The problem of event extraction is a relatively difficult task for low resource languages due to the non-availability of sufficient annotated data.
ParaQG: A System for Generating Questions and Answers from Paragraphs
Generating syntactically and semantically valid and relevant questions from paragraphs is useful with many applications.
Multi-Person 3D Human Pose Estimation from Monocular Images
Multi-person 3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data.
Ranked #8 on
3D Multi-Person Pose Estimation
on MuPoTS-3D
3D Human Pose Estimation
3D Multi-Person Human Pose Estimation
Putting the Horse before the Cart: A Generator-Evaluator Framework for Question Generation from Text
The \textit{generator} is a sequence-to-sequence model that incorporates the \textit{structure} and \textit{semantics} of the question being generated.
Question Generation from Paragraphs: A Tale of Two Hierarchical Models
Specifically, we propose (a) a novel hierarchical BiLSTM model with selective attention and (b) a novel hierarchical Transformer architecture, both of which learn hierarchical representations of paragraphs.
Realistic Video Summarization through VISIOCITY: A New Benchmark and Evaluation Framework
Thirdly, we demonstrate that in the presence of multiple ground truth summaries (due to the highly subjective nature of the task), learning from a single combined ground truth summary using a single loss function is not a good idea.
A Unified Framework for Generic, Query-Focused, Privacy Preserving and Update Summarization using Submodular Information Measures
We study submodular information measures as a rich framework for generic, query-focused, privacy sensitive, and update summarization tasks.
How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization
For long videos, human reference summaries necessary for supervised video summarization techniques are difficult to obtain.
WARM: A Weakly (+Semi) Supervised Model for Solving Math word Problems
We approach this problem by first learning to generate the equation using the problem description and the final answer, which we subsequently use to train a supervised MWP solver.
Submodular Mutual Information for Targeted Data Subset Selection
With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data.
Vocabulary Matters: A Simple yet Effective Approach to Paragraph-level Question Generation
Question generation (QG) has recently attracted considerable attention.
Effective Evaluation of Deep Active Learning on Image Classification Tasks
Issues in the current literature include sometimes contradictory observations on the performance of different AL algorithms, unintended exclusion of important generalization approaches such as data augmentation and SGD for optimization, a lack of study of evaluation facets like the labeling efficiency of AL, and little or no clarity on the scenarios in which AL outperforms random sampling (RS).
DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation
To address this problem, we propose DITTO (Data-efficient and faIr Targeted subseT selectiOn) that uses Submodular Mutual Information (SMI) functions as acquisition functions to find the most informative set of utterances matching a target accent within a fixed budget.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Error Correction in ASR using Sequence-to-Sequence Models
Post-editing in Automatic Speech Recognition (ASR) entails automatically correcting common and systematic errors produced by the ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets
This issue is further pronounced in SSL methods, as they would use this biased model to obtain psuedo-labels (on the unlabeled data) during training.
Investigating Modality Bias in Audio Visual Video Parsing
We focus on the audio-visual video parsing (AVVP) problem that involves detecting audio and visual event labels with temporal boundaries.
Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches
This skew affects all stages within the pipelines of deep crowd counting approaches.
DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures
Avoiding out-of-distribution (OOD) data is critical for training supervised machine learning models in the medical imaging domain.
CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification
It is often the case that a suboptimal performance is obtained on some classes due to the natural class imbalance issue that comes with medical data.
WARM: A Weakly (+Semi) Supervised Math Word Problem Solver
In order to address this challenge of equation annotation, we propose a weakly supervised model for solving MWPs by requiring only the final answer as supervision.
DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
In this work we present \dictdis, a lexically constrained NMT system that disambiguates between multiple candidate translations derived from dictionaries.
Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training
Training state-of-the-art ASR systems such as RNN-T often has a high associated financial and environmental cost.
Speeding up NAS with Adaptive Subset Selection
A majority of recent developments in neural architecture search (NAS) have been aimed at decreasing the computational cost of various techniques without affecting their final performance.
INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models
A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size.
Temporally Aligning Long Audio Interviews with Questions: A Case Study in Multimodal Data Integration
The problem of audio-to-text alignment has seen significant amount of research using complete supervision during training.
Using Early Readouts to Mediate Featural Bias in Distillation
Deep networks tend to learn spurious feature-label correlations in real-world supervised learning tasks.
INSITE: labelling medical images using submodular functions and semi-supervised data programming
We demonstrate that informed subset selection followed by semi-supervised data programming methods using these images as exemplars perform better than other state-of-the-art semi-supervised methods.
FAIR: Filtering of Automatically Induced Rules
The availability of large annotated data can be a critical bottleneck in training machine learning algorithms successfully, especially when applied to diverse domains.
Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering
In this paper, we propose a modified version of the MedQA-USMLE dataset, which is subjective, to mimic real-life clinical scenarios.
