64 citations · 147 across the 44 of their papers we have counts for
19 papers · 1 filter
RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
Jingqi Xu, Jingxi Lu, Chenghao Li +3
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vis…
Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
Sreetama Sarkar, Yue Che, Alex Gavin +2
Despite their remarkable progress in multimodal understanding tasks, large vision language models (LVLMs) often suffer from "hallucinations", generating texts misaligned with the v…
MaskVD: Region Masking for Efficient Video Object Detection
Sreetama Sarkar, Gourav Datta, Souvik Kundu +3
Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). S…
Block Selective Reprogramming for On-device Training of Vision Transformers
Sreetama Sarkar, Souvik Kundu, Kai Zheng +1
The ubiquity of vision transformers (ViTs) for various edge applications, including personalized learning, has created the demand for on-device fine-tuning. However, training with…
GenQ: Quantization in Low Data Regimes with Generative Synthetic Data
Yuhang Li, Youngeun Kim, Donghyun Lee +2
In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availabilit…
FireFly A Synthetic Dataset for Ember Detection in Wildfire
Yue Hu, Xinan Ye, Yifei Liu +7
This paper presents "FireFly", a synthetic dataset for ember detection created using Unreal Engine 4 (UE4), designed to overcome the current lack of ember-specific training resourc…
NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
Yonggan Fu, Ye Yuan, Souvik Kundu +3
Generalizable Neural Radiance Fields (GNeRF) are one of the most promising real-world solutions for novel view synthesis, thanks to their cross-scene generalization capability and…
Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs
Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar +3
Existing deep neural networks (DNNs) that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on either activation or weight condition…
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference
Souvik Kundu, Shunlin Lu, Yuke Zhang +2
The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce…
In-Sensor & Neuromorphic Computing are all you need for Energy Efficient Computer Vision
Gourav Datta, Zeyu Liu, Md Abdullah-Al Kaiser +6
Due to the high activation sparsity and use of accumulates (AC) instead of expensive multiply-and-accumulates (MAC), neuromorphic spiking neural networks (SNNs) have emerged as a p…
Self-Attentive Pooling for Efficient Deep Learning
Fang Chen, Gourav Datta, Souvik Kundu +1
Efficient custom pooling techniques that can aggressively trim the dimensions of a feature map and thereby reduce inference compute and memory footprint for resource-constrained co…
A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness
Souvik Kundu, Sairam Sundaresan, Massoud Pedram +1
Existing models that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on convolution operations conditioned with feature-wise linea…
BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch
Souvik Kundu, Shikai Wang, Qirui Sun +2
Large DNNs with mixed-precision quantization can achieve ultra-high compression while retaining high classification performance. However, because of the challenges in finding an ac…
HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise
Souvik Kundu, Massoud Pedram, Peter A. Beerel
Low-latency deep spiking neural networks (SNNs) have become a promising alternative to conventional artificial neural networks (ANNs) because of their potential for increased energ…
AttentionLite: Towards Efficient Self-Attention Models for Vision
Souvik Kundu, Sairam Sundaresan
We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has prim…
Attention-based Image Upsampling
Souvik Kundu, Hesham Mostafa, Sharath Nittur Sridhar +1
Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechani…
A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs
Souvik Kundu, Mahdi Nazemi, Peter A. Beerel +1
This paper presents a dynamic network rewiring (DNR) method to generate pruned deep neural network (DNN) models that are robust against adversarial attacks yet maintain high accura…
Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks
Souvik Kundu, Mahdi Nazemi, Massoud Pedram +2
The high energy cost of processing deep convolutional neural networks impedes their ubiquitous deployment in energy-constrained platforms such as embedded systems and IoT devices.…
A Pre-defined Sparse Kernel Based Convolution for Deep CNNs
Souvik Kundu, Saurav Prakash, Haleh Akrami +2
The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architec…