Search Results for author: Mohit Prabhushankar

Found 31 papers, 13 papers with code

FOCAL: A Cost-Aware Video Dataset for Active Learning

1 code implementation17 Nov 2023 Kiran Kokilepersaud, Yash-yee Logan, Ryan Benkert, Chen Zhou, Mohit Prabhushankar, Ghassan AlRegib, Enrique Corona, Kunjan Singh, Mostafa Parchami

In this paper, we introduce the FOCAL (Ford-OLIVES Collaboration on Active Learning) dataset which enables the study of the impact of annotation-cost within a video active learning setting.

Active Learning

Clinical Trial Active Learning

1 code implementation20 Jul 2023 Zoe Fowler, Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

There exists two types of clinical trials: retrospective and prospective.

Active Learning

Clinically Labeled Contrastive Learning for OCT Biomarker Classification

no code implementations24 May 2023 Kiran Kokilepersaud, Stephanie Trejo Corona, Mohit Prabhushankar, Ghassan AlRegib, Charles Wykoff

We exploit this relationship by using the clinical data as pseudo-labels for our data without biomarker labels in order to choose positive and negative instances for training a backbone network with a supervised contrastive loss.

Classification Contrastive Learning

Exploiting the Distortion-Semantic Interaction in Fisheye Data

no code implementations28 Apr 2023 Kiran Kokilepersaud, Mohit Prabhushankar, Yavuz Yarici, Ghassan AlRegib, Armin Parchami

In this work, we present a methodology to shape a fisheye-specific representation space that reflects the interaction between distortion and semantic context present in this data modality.

object-detection Object Detection +1

Probing the Purview of Neural Networks via Gradient Analysis

no code implementations6 Apr 2023 Jinsol Lee, Charlie Lehman, Mohit Prabhushankar, Ghassan AlRegib

We define purview as the additional capacity necessary to characterize inference samples that differ from the training data.

Gaussian Switch Sampling: A Second Order Approach to Active Learning

2 code implementations16 Feb 2023 Ryan Benkert, Mohit Prabhushankar, Ghassan AlRegib, Armin Pacharmi, Enrique Corona

To alleviate this issue, we propose a grounded second-order definition of information content and sample importance within the context of active learning.

Active Learning Informativeness

Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks

1 code implementation11 Feb 2023 Mohit Prabhushankar, Ghassan AlRegib

This paper conjectures and validates a framework that allows for action during inference in supervised neural networks.

Image Quality Assessment

Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data

no code implementations12 Jan 2023 Ryan Benkert, Mohit Prabhushankar, Ghassan AlRegib

However, existing strategies directly base the data selection on the data representation of the unlabeled data which is random for OOD samples by definition.

Active Learning Informativeness

On the Ramifications of Human Label Uncertainty

1 code implementation10 Nov 2022 Chen Zhou, Mohit Prabhushankar, Ghassan AlRegib

Our evaluation of existing uncertainty estimation algorithms, with the presence of HLU, indicates the limitations of existing uncertainty metrics and algorithms themselves in response to HLU.

Clinical Contrastive Learning for Biomarker Detection

no code implementations9 Nov 2022 Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

This is accomplished by leveraging the larger amount of clinical data as pseudo-labels for our data without biomarker labels in order to choose positive and negative instances for training a backbone network with a supervised contrastive loss.

Contrastive Learning

OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics

1 code implementation22 Sep 2022 Mohit Prabhushankar, Kiran Kokilepersaud, Yash-yee Logan, Stephanie Trejo Corona, Ghassan AlRegib, Charles Wykoff

The dataset consists of 1268 near-IR fundus images each with at least 49 OCT scans, and 16 biomarkers, along with 4 clinical labels and a disease diagnosis of DR or DME.

Time Series Analysis

Introspective Learning : A Two-Stage Approach for Inference in Neural Networks

1 code implementation17 Sep 2022 Mohit Prabhushankar, Ghassan AlRegib

Finally, we ground the proposed machine introspection to human introspection for the application of image quality assessment.

Active Learning Decision Making +4

DECAL: DEployable Clinical Active Learning

no code implementations21 Jun 2022 Yash-yee Logan, Mohit Prabhushankar, Ghassan AlRegib

Hence, active learning techniques that are developed for natural images are insufficient for handling medical data.

Active Learning

Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentation

no code implementations16 Jun 2022 Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

In seismic interpretation, pixel-level labels of various rock structures can be time-consuming and expensive to obtain.

Contrastive Learning Position +2

Gradient-Based Adversarial and Out-of-Distribution Detection

no code implementations16 Jun 2022 Jinsol Lee, Mohit Prabhushankar, Ghassan AlRegib

We propose to utilize gradients for detecting adversarial and out-of-distribution samples.

Out-of-Distribution Detection

Explanatory Paradigms in Neural Networks

2 code implementations24 Feb 2022 Ghassan AlRegib, Mohit Prabhushankar

With $P$ as the prediction from a neural network, these questions are `Why P?

Decision Making

Extracting Causal Visual Features for Limited label Classification

no code implementations23 Mar 2021 Mohit Prabhushankar, Ghassan AlRegib

Neural networks trained to classify images do so by identifying features that allow them to distinguish between classes.

Classification General Classification

Contrastive Reasoning in Neural Networks

no code implementations23 Mar 2021 Mohit Prabhushankar, Ghassan AlRegib

In this paper, we formalize the structure of contrastive reasoning and propose a methodology to extract a neural network's notion of contrast.

Object Recognition

Novelty Detection Through Model-Based Characterization of Neural Networks

no code implementations13 Aug 2020 Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

To articulate the significance of the model perspective in novelty detection, we utilize backpropagated gradients.

Novelty Detection

Implicit Saliency in Deep Neural Networks

no code implementations4 Aug 2020 Yutong Sun, Mohit Prabhushankar, Ghassan AlRegib

In this paper, we show that existing recognition and localization deep architectures, that have not been exposed to eye tracking data or any saliency datasets, are capable of predicting the human visual saliency.

Saliency Detection

Contrastive Explanations in Neural Networks

3 code implementations1 Aug 2020 Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib

Current modes of visual explanations answer questions of the form $`Why \text{ } P?'$.

Image Quality Assessment

Characterizing Missing Information in Deep Networks Using Backpropagated Gradients

no code implementations ICLR 2020 Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

To complement the learned information from activation-based representation, we propose utilizing a gradient-based representation that explicitly focuses on missing information.

Anomaly Detection Attribute +1

Distorted Representation Space Characterization Through Backpropagated Gradients

2 code implementations27 Aug 2019 Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms.

General Classification Image Quality Assessment

Semantically Interpretable and Controllable Filter Sets

no code implementations17 Feb 2019 Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib

In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion.

Image Quality Assessment

Generating Adaptive and Robust Filter Sets Using an Unsupervised Learning Framework

no code implementations21 Nov 2018 Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

While assessing image quality, the filters need to capture perceptual differences based on dissimilarities between a reference image and its distorted version.

Image Quality Assessment Retrieval

CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition

1 code implementation7 Dec 2017 Dogancan Temel, Gukyeong Kwon, Mohit Prabhushankar, Ghassan AlRegib

We benchmark the performance of existing solutions in real-world scenarios and analyze the performance variation with respect to challenging conditions.

Data Augmentation Traffic Sign Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.