76 citations · 163 across the 16 of their papers we have counts for
16 papers
Input-Adaptive Gating of a Dehazing Front-End for On-Device Perception in Smoke-Obscured Environments
Seongjun Kang, Ishaan Garg, Vishnu Bharadwaj
Two-stage vision pipelines often place an enhancement network before a task network, on the assumption that a cleaner input produces a better output. We evaluate this in a firefigh…
Engineering Practical Succinct Bit Vectors: A Space-Time Pareto Analysis on Apple Silicon ARM64 Cores
Ishant Garg
Succinct data structures use space close to the information-theoretic minimum while answering queries directly on the compressed representation. In this paper, we present a practic…
Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models
Pratham Singla, Shivank Garg, Ayush Singh +2
Recent advances in post-training techniques have endowed Large Language Models (LLMs) with enhanced capabilities for tackling complex, logic-intensive tasks through the generation…
Revealing the Utilized Rank of Subspaces of Learning in Neural Networks
Isha Garg, Christian Koguchi, Eshan Verma +1
In this work, we study how well the learned weights of a neural network utilize the space available to them. This notion is related to capacity, but additionally incorporates the i…
Pruning for Improved ADC Efficiency in Crossbar-based Analog In-memory Accelerators
Timur Ibrayev, Isha Garg, Indranil Chakraborty +1
Deep learning has proved successful in many applications but suffers from high computational demands and requires custom accelerators for deployment. Crossbar-based analog in-memor…
Memorization Through the Lens of Curvature of Loss Function Around Samples
Isha Garg, Deepak Ravikumar, Kaushik Roy
Deep neural networks are over-parameterized and easily overfit the datasets they train on. In the extreme case, it has been shown that these networks can memorize a training set wi…
TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data
Isha Garg, Manish Nagaraj, Kaushik Roy
Advances in Federated Learning and an abundance of user data have enabled rich collaborative learning between multiple clients, without sharing user data. This is done via a centra…
Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift
Amitangshu Mukherjee, Isha Garg, Kaushik Roy
Over the past decade, deep neural networks have proven to be adept in image classification tasks, often surpassing humans in terms of accuracy. However, standard neural networks of…
Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks
Sayeed Shafayet Chowdhury, Isha Garg, Kaushik Roy
Spiking Neural Networks (SNNs) are a promising alternative to traditional deep learning methods since they perform event-driven information processing. However, a major drawback of…
Gradient Projection Memory for Continual Learning
Gobinda Saha, Isha Garg, Kaushik Roy
The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial…
Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection
Deepak Ravikumar, Sangamesh Kodge, Isha Garg +1
Deep neural networks have found widespread adoption in solving complex tasks ranging from image recognition to natural language processing. However, these networks make confident m…
DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks
Isha Garg, Sayeed Shafayet Chowdhury, Kaushik Roy
Spiking Neural Networks (SNNs) offer a promising alternative to traditional deep learning frameworks, since they provide higher computational efficiency due to event-driven informa…
TREND: Transferability based Robust ENsemble Design
Deepak Ravikumar, Sangamesh Kodge, Isha Garg +1
Deep Learning models hold state-of-the-art performance in many fields, but their vulnerability to adversarial examples poses threat to their ubiquitous deployment in practical sett…
SPACE: Structured Compression and Sharing of Representational Space for Continual Learning
Gobinda Saha, Isha Garg, Aayush Ankit +1
Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned ab…
Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence
Indranil Chakraborty, Deboleena Roy, Isha Garg +2
The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles. Quantization is…
A Low Effort Approach to Structured CNN Design Using PCA
Isha Garg, Priyadarshini Panda, Kaushik Roy
Deep learning models hold state of the art performance in many fields, yet their design is still based on heuristics or grid search methods that often result in overparametrized ne…