182 citations · 359 across the 17 of their papers we have counts for
20 papers
On the Efficacy of Multi-scale Data Samplers for Vision Applications
Elvis Nunez, Thomas Merth, Anish Prabhu +4
Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faste…
Bytes Are All You Need: Transformers Operating Directly On File Bytes
Maxwell Horton, Sachin Mehta, Ali Farhadi +1
Modern deep learning approaches usually utilize modality-specific processing. For example, the most common deep learning approach to image classification involves decoding image fi…
APE: An Open and Shared Annotated Dataset for Learning Urban Pedestrian Path Networks
Yuxiang Zhang, Nicholas Bolten, Sachin Mehta +1
Inferring the full transportation network, including sidewalks and cycleways, is crucial for many automated systems, including autonomous driving, multi-modal navigation, trip plan…
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
Fartash Faghri, Hadi Pouransari, Sachin Mehta +4
We propose Dataset Reinforcement, a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no addition…
OASIS: Automated Assessment of Urban Pedestrian Paths at Scale
Yuxiang Zhang, Suresh Devalapalli, Sachin Mehta +1
The inspection of the Public Right of Way (PROW) for accessibility barriers is necessary for monitoring and maintaining the built environment for communities' walkability, rollabil…
RangeAugment: Efficient Online Augmentation with Range Learning
Sachin Mehta, Saeid Naderiparizi, Fartash Faghri +5
State-of-the-art automatic augmentation methods (e.g., AutoAugment and RandAugment) for visual recognition tasks diversify training data using a large set of augmentation operation…
SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks
Chien-Yu Lin, Anish Prabhu, Thomas Merth +4
Recent isotropic networks, such as ConvMixer and vision transformers, have found significant success across visual recognition tasks, matching or outperforming non-isotropic convol…
Separable Self-attention for Mobile Vision Transformers
Sachin Mehta, Mohammad Rastegari
Mobile vision transformers (MobileViT) can achieve state-of-the-art performance across several mobile vision tasks, including classification and detection. Though these models have…
CVNets: High Performance Library for Computer Vision
Sachin Mehta, Farzad Abdolhosseini, Mohammad Rastegari
We introduce CVNets, a high-performance open-source library for training deep neural networks for visual recognition tasks, including classification, detection, and segmentation. C…
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Sachin Mehta, Mohammad Rastegari
Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters…
DiCENet: Dimension-wise Convolutions for Efficient Networks
Sachin Mehta, Hannaneh Hajishirzi, Mohammad Rastegari
We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply lig…
A Facial Affect Analysis System for Autism Spectrum Disorder
Beibin Li, Sachin Mehta, Deepali Aneja +4
In this paper, we introduce an end-to-end machine learning-based system for classifying autism spectrum disorder (ASD) using facial attributes such as expressions, action units, ar…
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
Sachin Mehta, Mohammad Rastegari, Linda Shapiro +1
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise…
Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images
Sachin Mehta, Ezgi Mercan, Jamen Bartlett +3
In this paper, we introduce a conceptually simple network for generating discriminative tissue-level segmentation masks for the purpose of breast cancer diagnosis. Our method effic…
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
Sachin Mehta, Mohammad Rastegari, Anat Caspi +2
We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new con…
Identifying Most Walkable Direction for Navigation in an Outdoor Environment
Sachin Mehta, Hannaneh Hajishirzi, Linda Shapiro
We present an approach for identifying the most walkable direction for navigation using a hand-held camera. Our approach extracts semantically rich contextual information from the…
Learning to Segment Breast Biopsy Whole Slide Images
Sachin Mehta, Ezgi Mercan, Jamen Bartlett +3
We trained and applied an encoder-decoder model to semantically segment breast biopsy images into biologically meaningful tissue labels. Since conventional encoder-decoder networks…
DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels
Sachin Mehta, Amar P. Azad, Saneem A. Chemmengath +2
The impact of soiling on solar panels is an important and well-studied problem in renewable energy sector. In this paper, we present the first convolutional neural network (CNN) ba…
mPDF: Framework for Watermarking PDF Files using Image Watermarking Algorithms
Sachin Mehta, Balakrishnan Prabhakaran, Rajarathnam Nallusamy +1
The advancement in digital technologies have made it possible to produce perfect copies of digital content. In this environment, malicious users reproduce the digital content and s…
Region Graph Based Method for Multi-Object Detection and Tracking using Depth Cameras
Sachin Mehta, Balakrishnan Prabhakaran
In this paper, we propose a multi-object detection and tracking method using depth cameras. Depth maps are very noisy and obscure in object detection. We first propose a region-bas…