Search Results for author:
Found 62 papers, 21 papers with code
CABINET: Content Relevance based Noise Reduction for Table Question Answering
Typically, only a small part of the whole table is relevant to derive the answer for a given question.
Ranked #1 on
Semantic Parsing
on WikiSQL
(Denotation accuracy (test) metric)
Behavior Optimized Image Generation
We show that BoigLLM outperforms 13x larger models such as GPT-3. 5 and GPT-4 in this task, demonstrating that while these state-of-the-art models can understand images, they lack information on how these images perform in the real world.
All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation
Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks.
Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
We call these models Large Content and Behavior Models (LCBMs).
Long-Term Ad Memorability: Understanding and Generating Memorable Ads
Finally, with the intent of memorable ad generation, we present a scalable method to build a high-quality memorable ad generation model by leveraging automatically annotated data.
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training
We demonstrate the effectiveness of our approach, named LOCATE, on multiple standard video object segmentation, image saliency detection, and object segmentation benchmarks, achieving results on par with and, in many cases surpassing state-of-the-art methods.
FODVid: Flow-guided Object Discovery in Videos
Segmentation of objects in a video is challenging due to the nuances such as motion blurring, parallax, occlusions, changes in illumination, etc.
SARC: Soft Actor Retrospective Critic
The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures eventual consistency between the two.
A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot
Multimedia content, such as advertisements and story videos, exhibit a rich blend of creativity and multiple modalities.
HyHTM: Hyperbolic Geometry based Hierarchical Topic Models
We present HyHTM - a Hyperbolic geometry based Hierarchical Topic Models - that addresses these limitations by incorporating hierarchical information from hyperbolic geometry to explicitly model hierarchies in topic models.
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.
Explaining RL Decisions with Trajectories
To do so, we encode trajectories in offline training data individually as well as collectively (encoding a set of trajectories).
Parameter Efficient Local Implicit Image Function Network for Face Segmentation
Face parsing is defined as the per-pixel labeling of images containing human faces.
Synthesizing Human Gaze Feedback for Improved NLP Performance
Feedback can be either explicit (e. g. ranking used in training language models) or implicit (e. g. using human cognitive signals in the form of eyetracking).
Towards Estimating Transferability using Hard Subsets
As transfer learning techniques are increasingly used to transfer knowledge from the source model to the target task, it becomes important to quantify which source models are suitable for a given target task without performing computationally expensive fine tuning.
UMFuse: Unified Multi View Fusion for Human Editing applications
Numerous pose-guided human editing methods have been explored by the vision community due to their extensive practical applications.
VGFlow: Visibility guided Flow Network for Human Reposing
The task of human reposing involves generating a realistic image of a person standing in an arbitrary conceivable pose.
Distilling the Undistillable: Learning from a Nasty Teacher
The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature.
One-Shot Doc Snippet Detection: Powering Search in Document Beyond Text
MONOMER fuses context from visual, textual, and spatial modalities of snippets and documents to find query snippet in target documents.
Persuasion Strategies in Advertisements
Motivated by persuasion literature in social psychology and marketing, we introduce an extensive vocabulary of persuasion strategies and build the first ad image corpus annotated with persuasion strategies.
LM-CORE: Language Models with Contextually Relevant External Knowledge
Large transformer-based pre-trained language models have achieved impressive performance on a variety of knowledge-intensive tasks and can capture factual knowledge in their parameters.
Differentiable Agent-based Epidemiology
Mechanistic simulators are an indispensable tool for epidemiology to explore the behavior of complex, dynamic infections under varying conditions and navigate uncertain environments.
INDIGO: Intrinsic Multimodality for Domain Generalization
To this end, we propose IntriNsic multimodality for DomaIn GeneralizatiOn (INDIGO), a simple and elegant way of leveraging the intrinsic modality present in these pre-trained multimodal networks along with the visual modality to enhance generalization to unseen domains at test-time.
CoSe-Co: Text Conditioned Generative CommonSense Contextualizer
To train CoSe-Co, we propose a novel dataset comprising of sentence and commonsense knowledge pairs.
On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models
Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation.
DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks
We introduce DeepABM, a framework for agent-based modeling that leverages geometric message passing of graph neural networks for simulating action and interactions over large agent populations.
MINIMAL: Mining Models for Data Free Universal Adversarial Triggers
It is well known that natural language models are vulnerable to adversarial attacks, which are mostly input-specific in nature.
ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors
Image-based virtual try-on involves synthesizing perceptually convincing images of a model wearing a particular garment and has garnered significant research interest due to its immense practical applicability.
Video2Skill: Adapting Events in Demonstration Videos to Skills in an Environment using Cyclic MDP Homomorphisms
Humans excel at learning long-horizon tasks from demonstrations augmented with textual commentary, as evidenced by the burgeoning popularity of tutorial videos online.
No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge
This allows the training of the language model to be de-coupled from the external knowledge source and the latter can be updated without affecting the parameters of the language model.
CoSe-Co: Sentence Conditioned Generative CommonSense Contextualizer for Language Models
Pre-trained Language Models (PTLMs) have been shown to perform well on natural language reasoning tasks requiring commonsense.
Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring
In our technique, we take advantage of the fact that oral proficiency tests rate multiple responses for a candidate.
Multi-Modal Association based Grouping for Form Structure Extraction
Experimental results show the effectiveness of our approach achieving a recall of 90. 29%, 73. 80%, 83. 12%, and 52. 72% for the above structures, respectively, outperforming semantic segmentation baselines significantly.
Form2Seq : A Framework for Higher-Order Form Structure Extraction
To mitigate this, we propose Form2Seq, a novel sequence-to-sequence (Seq2Seq) inspired framework for structure extraction using text, with a specific focus on forms, which leverages relative spatial arrangement of structures.
Information-theoretic Evolution of Model Agnostic Global Explanations
Our approach builds on top of existing local model explanation methods to extract conditions important for explaining model behavior for specific instances followed by an evolutionary algorithm that optimizes an information theory based fitness function to construct rules that explain global model behavior.
Data InStance Prior (DISP) in Generative Adversarial Networks
Previous works have addressed training in low data setting by leveraging transfer learning and data augmentation techniques.
TAN-NTM: Topic Attention Networks for Neural Topic Modeling
Topic models have been widely used to learn text representations and gain insight into document corpora.
LT-GAN: Self-Supervised GAN with Latent Transformation Detection
We propose a self-supervised approach (LT-GAN) to improve the generation quality and diversity of images by estimating the GAN-induced transformation (i. e. transformation induced in the generated images by perturbing the latent space of generator).
Ranked #4 on
Image Generation
on CelebA-HQ 128x128
SHERLock: Self-Supervised Hierarchical Event Representation Learning
Also, they are believed to be arranged hierarchically, allowing for an efficient representation of complex long-horizon experiences.
Data Instance Prior for Transfer Learning in GANs
Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images.
SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval
The ability to efficiently search for images is essential for improving the user experiences across various products.
Retrospective Loss: Looking Back to Improve Training of Deep Neural Networks
Deep neural networks (DNNs) are powerful learning machines that have enabled breakthroughs in several domains.
Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency
We show through illustrative examples (Chess, Atari, Go), human studies (Chess), and automated evaluation methods (Chess) that our approach generates saliency maps that are more interpretable for humans than existing approaches.
SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation
Few-shot segmentation (FSS) methods perform image segmentation for a particular object class in a target (query) image, using a small set of (support) image-mask pairs.
Exploring Neural Models for Parsing Natural Language into First-Order Logic
We model FOL parsing as a sequence to sequence mapping task where given a natural language sentence, it is encoded into an intermediate representation using an LSTM followed by a decoder which sequentially generates the predicates in the corresponding FOL formula.
SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On
An efficient framework for this is composed of two stages: (1) warping (transforming) the try-on cloth to align with the pose and shape of the target model, and (2) a texture transfer module to seamlessly integrate the warped try-on cloth onto the target model image.
ShapeVis: High-dimensional Data Visualization at Scale
This graph captures the structural characteristics of the point cloud, and its weights are determined using a Finite Markov Chain.
Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo Loss
We show how agents trained with SQLoss evolve cooperative behavior in several social dilemma matrix games.
Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution
We show through illustrative examples (Chess, Atari, Go), human studies (Chess), and automated evaluation methods (Chess) that SARFA generates saliency maps that are more interpretable for humans than existing approaches.
A Method for Computing Class-wise Universal Adversarial Perturbations
We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks.
Attributional Robustness Training using Input-Gradient Spatial Alignment
Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust.
Ranked #1 on
Weakly-Supervised Object Localization
on CUB-200-2011
(Top-1 Error Rate metric)
BIG-bench Machine Learning
Weakly-Supervised Object Localization
Document Structure Extraction using Prior based High Resolution Hierarchical Semantic Segmentation
We introduce our new human-annotated forms dataset and show that our method significantly outperforms different segmentation baselines on this dataset in extracting hierarchical structures.
Retrospection: Leveraging the Past for Efficient Training of Deep Neural Networks
Deep neural networks are powerful learning machines that have enabled breakthroughs in several domains.
Charting the Right Manifold: Manifold Mixup for Few-shot Learning
A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution.
Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models
We analyze the adversarially trained robust models to study their vulnerability against adversarial attacks at the level of the latent layers.
ReDecode Framework for Iterative Improvement in Paraphrase Generation
Generating paraphrases, that is, different variations of a sentence conveying the same meaning, is an important yet challenging task in NLP.
Attention Based Natural Language Grounding by Navigating Virtual Environment
We develop an attention mechanism for multi-modal fusion of visual and textual modalities that allows the agent to learn to complete the task and achieve language grounding.
Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space
Recently, Neural networks have seen a huge surge in its adoption due to their ability to provide high accuracy on various tasks.
Learning to navigate by distilling visual information and natural language instructions
In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in a 2D grid environment.
Improving Search through A3C Reinforcement Learning based Conversational Agent
We develop a reinforcement learning based search assistant which can assist users through a set of actions and sequence of interactions to enable them realize their intent.
MAGIX: Model Agnostic Globally Interpretable Explanations
Explaining the behavior of a black box machine learning model at the instance level is useful for building trust.
Introspection: Accelerating Neural Network Training By Learning Weight Evolution
In this paper, we explore the idea of learning weight evolution pattern from a simple network for accelerating training of novel neural networks.
