Search Results for author:
Found 42 papers, 21 papers with code
Towards Learning and Explaining Indirect Causal Effects in Neural Networks
Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models.
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.
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.
Feature Generation for Long-tail Classification
Oversampling instances of the tail classes attempts to solve this imbalance.
Ranked #1 on
Long-tail Learning
on mini-ImageNet-LT
Meta-Consolidation for Continual Learning
The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of.
Data Instance Prior for Transfer Learning in GANs
Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images.
Zero Shot Domain Generalization
Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would generalize to a new unseen domain.
Assisting Scene Graph Generation with Self-Supervision
Most of these works have a pre-trained object detection model as a preliminary feature extractor.
Two-Level Adversarial Visual-Semantic Coupling for Generalized Zero-shot Learning
The performance of generative zero-shot methods mainly depends on the quality of generated features and how well the model facilitates knowledge transfer between visual and semantic domains.
Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey
In light of growing challenges in agriculture with ever growing food demand across the world, efficient crop management techniques are necessary to increase crop yield.
On Saliency Maps and Adversarial Robustness
A Very recent trend has emerged to couple the notion of interpretability and adversarial robustness, unlike earlier efforts which solely focused on good interpretations or robustness against adversaries.
Generative Adversarial Data Programming
The paucity of large curated hand-labeled training data forms a major bottleneck in the deployment of machine learning models in computer vision and other fields.
On the benefits of defining vicinal distributions in latent space
The vicinal risk minimization (VRM) principle is an empirical risk minimization (ERM) variant that replaces Dirac masses with vicinal functions.
A Little Fog for a Large Turn
Small, carefully crafted perturbations called adversarial perturbations can easily fool 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
Active Learning with Point Supervision for Cost-Effective Panicle Detection in Cereal Crops
We show promising results on two publicly available cereal crop datasets - Sorghum and Wheat.
An Adaptive Supervision Framework for Active Learning in Object Detection
Our extensive experiments show that the proposed framework can be used to train good generalizable models with much lesser annotation costs than the state of the art active learning approaches for object detection.
AdvGAN++ : Harnessing latent layers for adversary generation
Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance.
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.
Submodular Batch Selection for Training Deep Neural Networks
Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today.
Automatic estimation of heading date of paddy rice using deep learning
Accurate estimation of heading date of paddy rice greatly helps the breeders to understand the adaptability of different crop varieties in a given location.
Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
Can we improve detection in the thermal domain by borrowing features from rich domains like visual RGB?
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.
Teaching GANs to Sketch in Vector Format
In this paper, we propose a standalone GAN architecture SkeGAN and a VAE-GAN architecture VASkeGAN, for sketch generation in vector format.
Zero-Shot Task Transfer
Our proposed methodology out-performs state-of-the-art models (which use ground truth)on each of our zero-shot tasks, showing promise on zero-shot task transfer.
Neural Network Attributions: A Causal Perspective
We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such).
DANTE: Deep AlterNations for Training nEural networks
We present DANTE, a novel method for training neural networks using the alternating minimization principle.
Low-Cost Transfer Learning of Face Tasks
Do we know what the different filters of a face network represent?
MASON: A Model AgnoStic ObjectNess Framework
This paper proposes a simple, yet very effective method to localize dominant foreground objects in an image, to pixel-level precision.
RefocusGAN: Scene Refocusing using a Single Image
Post-capture control of the focus position of an image is a useful photographic tool.
On the Analysis of Trajectories of Gradient Descent in the Optimization of Deep Neural Networks
Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years.
Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data
In this work, we present Adversarial Data Programming (ADP), which presents an adversarial methodology to generate data as well as a curated aggregated label has given a set of weak labeling functions.
Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification
A well-known approach for aggregation is the Dawid-Skene (DS) algorithm, which is based on the principle of Expectation-Maximization (EM).
ADINE: An Adaptive Momentum Method for Stochastic Gradient Descent
Using this motivation, we propose our method $\textit{ADINE}$ that helps weigh the previous updates more (by setting the momentum parameter $> 1$), evaluate our proposed algorithm on deep neural networks and show that $\textit{ADINE}$ helps the learning algorithm to converge much faster without compromising on the generalization error.
STWalk: Learning Trajectory Representations in Temporal Graphs
In this paper, we present a novel approach, STWalk, for learning trajectory representations of nodes in temporal graphs.
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
Attentive Semantic Video Generation using Captions
This paper proposes a network architecture to perform variable length semantic video generation using captions.
Multiresolution Match Kernels for Gesture Video Classification
The emergence of depth imaging technologies like the Microsoft Kinect has renewed interest in computational methods for gesture classification based on videos.
Are Saddles Good Enough for Deep Learning?
However, in this work, we propose a new hypothesis based on recent theoretical findings and empirical studies that deep neural network models actually converge to saddle points with high degeneracy.
Community-based Outlier Detection for Edge-attributed Graphs
Although various kinds of outliers have been studied for graph data, there is not much work on anomaly detection from edge-attributed graphs.
Social and Information Networks G.2; G.3; H.2.8
Sync-DRAW: Automatic Video Generation using Deep Recurrent Attentive Architectures
This paper introduces a novel approach for generating videos called Synchronized Deep Recurrent Attentive Writer (Sync-DRAW).
Deep Model Compression: Distilling Knowledge from Noisy Teachers
The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems.
