Search Results for author:
Found 27 papers, 6 papers with code
OPTiML: Dense Semantic Invariance Using Optimal Transport for Self-Supervised Medical Image Representation
In response to these constraints, we introduce a novel SSL framework OPTiML, employing optimal transport (OT), to capture the dense semantic invariance and fine-grained details, thereby enhancing the overall effectiveness of SSL in medical image representation learning.
MLVICX: Multi-Level Variance-Covariance Exploration for Chest X-ray Self-Supervised Representation Learning
The performance enhancements we observe across various downstream tasks highlight the significance of the proposed approach in enhancing the utility of chest X-ray embeddings for precision medical diagnosis and comprehensive image analysis.
Multi-Agent Reinforcement Learning for Offloading Cellular Communications with Cooperating UAVs
Effective solutions for intelligent data collection in terrestrial cellular networks are crucial, especially in the context of Internet of Things applications.
Jointly Optimal RIS Placement and Power Allocation for Underlay D2D Communications: An Outage Probability Minimization Approach
In the transformed problem, an expression for the average value of the signal-to-interference-noise ratio (SINR) at the D2D receiver is derived in closed-form.
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
In this work, we explore the promises and challenges of developing multimodal foundation models for GeoAI.
Distilling Calibrated Student from an Uncalibrated Teacher
Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep.
GITz: Graphene-assisted IRS Design for THz Communication
Graphene-based intelligent reflecting surface (GIRS) has been proved to provide a promising propagation environment to enhance the quality of high frequency terahertz (THz) wireless communication.
Large Scale Time-Series Representation Learning via Simultaneous Low and High Frequency Feature Bootstrapping
To tackle these problems, we propose a non-contrastive self-supervised learning approach efficiently captures low and high-frequency time-varying features in a cost-effective manner.
Circuit Characterization of IRS to Control Beamforming Design for Efficient Wireless Communication
We have obtained closed-form expressions of PS, RA and $C$ in terms of transmission frequency of signal incident to IRS and various electrical parameters of IRS circuit, with a novel touch towards an accurate analytical model for a better beamforming design perspective.
Pose Invariant Person Re-Identification using Robust Pose-transformation GAN
The given instance of the person is modelled in varying poses and these features are effectively combined through the Feature Fusion Network.
Domain Adaptive Egocentric Person Re-identification
Machine learning models trained on the publicly available large scale re-ID datasets cannot be applied to egocentric re-ID due to the dataset bias problem.
Probabilistic Trust Intervals for Out of Distribution Detection
In this paper, we propose a very simple approach for enhancing the ability of a pretrained network to detect OOD inputs without even altering the original parameter values.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Neural Pooling for Graph Neural Networks
Our proposed methods have the ability to handle variable number of nodes in different graphs, and are also invariant to the isomorphic structures of graphs.
Indirect Supervision to Mitigate Perturbations
We propose to model this problem in indirect supervision framework, where we assume that the gold standard data is missing, however, a variable dependent on it is available and the dependency of the observed variable is stated by the considered downstream DNN.
Target-Independent Domain Adaptation for WBC Classification using Generative Latent Search
We prove the existence of such a clone given that infinite number of data points can be sampled from the source distribution.
Effect of The Latent Structure on Clustering with GANs
We derive from first principles, the necessary and sufficient conditions needed to achieve faithful clustering in the GAN framework: (i) presence of a multimodal latent space with adjustable priors, (ii) existence of a latent space inversion mechanism and (iii) imposition of the desired cluster priors on the latent space.
A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis
Generating photorealistic images of human subjects in any unseen pose have crucial applications in generating a complete appearance model of the subject.
Unsupervised Anomalous Trajectory Detection for Crowded Scenes
The proposed work is based on four major steps, namely, extraction of trajectories from crowded scene video, extraction of several features from these trajectories, independent mean-shift clustering and anomaly detection.
Learning Rotation Adaptive Correlation Filters in Robust Visual Object Tracking
Correlation Filter (CF) trackers are one of the most widely used categories in tracking.
Variational Inference with Latent Space Quantization for Adversarial Resilience
Specifically, we simultaneously auto-encode the data manifold and its perturbations implicitly through the perturbations of the regularized and quantized generative latent space, realized using variational inference.
How You See Me
Convolution Neural Networks is one of the most powerful tools in the present era of science.
Mode matching in GANs through latent space learning and inversion
Generative adversarial networks (GANs) have shown remarkable success in generation of unstructured data, such as, natural images.
Unsupervised Conditional Generation using noise engineered mode matching GAN
Conditional generation refers to the process of sampling from an unknown distribution conditioned on semantics of the data.
Stellar Cluster Detection using GMM with Deep Variational Autoencoder
Detecting stellar clusters have always been an important research problem in Astronomy.
Localization: A Missing Link in the Pipeline of Object Matching and Registration
These approaches require object-centric images to perform matching.
Unsupervised Despeckling
Contrast and quality of ultrasound images are adversely affected by the excessive presence of speckle.
Rotation Adaptive Visual Object Tracking with Motion Consistency
Therefore, one of the major aspects of this paper is to investigate the outcome of rotation adaptiveness in visual object tracking.
