no code implementations • 7 May 2024 • Sohini Roychowdhury, Marko Krema, Anvar Mahammad, Brian Moore, Arijit Mukherjee, Punit Prakashchandra
Large language models (LLMs) with residual augmented-generation (RAG) have been the optimal choice for scalable generative AI solutions in the recent past.
no code implementations • 18 Nov 2023 • Sohini Roychowdhury
In this work we present the three major stages in the journey of designing hallucination-minimized LLM-based solutions that are specialized for the decision makers of the financial domain, namely: prototyping, scaling and LLM evolution using human feedback.
no code implementations • 9 Nov 2023 • Sohini Roychowdhury, Andres Alvarez, Brian Moore, Marko Krema, Maria Paz Gelpi, Federico Martin Rodriguez, Angel Rodriguez, Jose Ramon Cabrejas, Pablo Martinez Serrano, Punit Agrawal, Arijit Mukherjee
Large Language Models (LLMs) have been applied to build several automation and personalized question-answering prototypes so far.
no code implementations • 5 Apr 2023 • Sohini Roychowdhury
In this work, we present a novel variant of the Unet model called the NUMSnet that transmits pixel neighborhood features across scans through nested layers to achieve accurate multi-class semantic segmentations with minimal training data.
no code implementations • 25 Mar 2022 • Sohini Roychowdhury
Automating video-based data and machine learning pipelines poses several challenges including metadata generation for efficient storage and retrieval and isolation of key-frames for scene understanding tasks.
1 code implementation • 27 Oct 2021 • Sohini Roychowdhury
In this work, we propose an automated two-step method that detects a minimal image subset required to train segmentation models by evaluating the quality of medical images from 3D image stacks using a U-net++ model.
1 code implementation • 15 Oct 2021 • Sohini Roychowdhury, James Y. Sato
In this work, we present a data pipeline framework that can automate this process of manual frame sifting in video sequences by controlling the fraction of frames that can be removed based on image quality and content type.
1 code implementation • 23 Feb 2021 • Sohini Roychowdhury, Kwok Sun Tang, Mohith Ashok, Anoop Sanka
We propose a novel active learning framework that identifies a minimal sub-sampled dataset containing the most uncertain OCT image samples using label propagation on the SimCLR latent encodings.
1 code implementation • 2 Feb 2021 • Sohini Roychowdhury, Ebrahim Alareqi, Wenxi Li
To support the recent increase in online shopping trends, in this work, we present a customer purchasing behavior analysis system using supervised, unsupervised and semi-supervised learning methods.
no code implementations • 5 Dec 2020 • Ze Wang, Sihao Ding, Ying Li, Jonas Fenn, Sohini Roychowdhury, Andreas Wallin, Lane Martin, Scott Ryvola, Guillermo Sapiro, Qiang Qiu
Point density varies significantly across such a long range, and different scanning patterns further diversify object representation in LiDAR.
1 code implementation • 6 Oct 2020 • Sohini Roychowdhury, Wenxi Li, Ebrahim Alareqi, Akhilesh Pandita, Ao Liu, Joakim Soderberg
A success factor for modern companies in the age of Digital Marketing is to understand how customers think and behave based on their online shopping patterns.
3 code implementations • 7 Aug 2020 • Sohini Roychowdhury
Also, the proposed framework with ParESN model minimizes manual annotation checking to 12-28% of the total number of images.
1 code implementation • 15 May 2020 • Francesco Piccoli, Rajarathnam Balakrishnan, Maria Jesus Perez, Moraldeepsingh Sachdeo, Carlos Nunez, Matthew Tang, Kajsa Andreasson, Kalle Bjurek, Ria Dass Raj, Ebba Davidsson, Colin Eriksson, Victor Hagman, Jonas Sjoberg, Ying Li, L. Srikar Muppirisetty, Sohini Roychowdhury
Pedestrian intention recognition is very important to develop robust and safe autonomous driving (AD) and advanced driver assistance systems (ADAS) functionalities for urban driving.
no code implementations • 26 Sep 2019 • Ze Wang, Sihao Ding, Ying Li, Minming Zhao, Sohini Roychowdhury, Andreas Wallin, Guillermo Sapiro, Qiang Qiu
To the best of our knowledge, this paper is the first attempt to study cross-range LiDAR adaptation for object detection in point clouds.
no code implementations • 17 Mar 2017 • Sohini Roychowdhury, Donny Sun, Matthew Bihis, Johnny Ren, Paul Hage, Humairat H. Rahman
Similarly, for the tongue pallor site images, the inner and outer tongue regions are segmented.
no code implementations • 24 Oct 2016 • Sohini Roychowdhury, Dara D. Koozekanani, Michael Reinsbach, Keshab K. Parhi
For estimating the sub-retinal layer thicknesses, the proposed system has an average error of 0. 2-2. 5 $\mu m$ and 1. 8-18 $\mu m$ in normal and abnormal images, respectively.
no code implementations • 13 Aug 2016 • Maitham D Naeemi, Adam M Alessio, Sohini Roychowdhury
In the proposed method, two windowed CT image subset regions are analyzed together to identify the extent of variation in the corresponding Fourier-domain spectrum.
no code implementations • 24 May 2016 • Sohini Roychowdhury, Nathan Hollraft, Adam Alessio
Methods: We propose novel performance metrics corresponding to the accuracy of noise and signal estimation.
no code implementations • 26 Mar 2016 • Matthew Bihis, Sohini Roychowdhury
The classification characteristics of the proposed flow are comparatively evaluated on 3 public data sets and a local data set with respect to existing state-of-the-art methods.
no code implementations • 26 Mar 2016 • Sohini Roychowdhury
For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90. 1% in 792 seconds.
no code implementations • 11 Nov 2015 • Sohini Roychowdhury
Automated facial expression detection problem pose two primary challenges that include variations in expression and facial occlusions (glasses, beard, mustache or face covers).
no code implementations • 7 Nov 2015 • Sohini Roychowdhury, Michelle Emmons
The evolution trends in databases and methodologies for facial and expression recognition can be useful for assessing the next-generation topics that may have applications in security systems or personal identification systems that involve "Quantitative face" assessments.
Facial Expression Recognition Facial Expression Recognition (FER)