In this paper, we show that leveraging NAS for incremental learning results in strong performance gains for classification tasks.
Computer vision publications
Dual-Key Multimodal Backdoors for Visual Question Answering
In this work, we show that multimodal networks are vulnerable to a novel type of attack that we refer to as Dual-Key Multimodal Backdoors.
Saccade Mechanisms for Image Classification, Object Detection and Tracking
We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual processing and saccades, miniature eye movements influenced by attention.
Conformal Prediction Intervals for Markov Decision Process Trajectories
This paper extends previous work on conformal prediction for functional data and conformalized quantile regression to provide conformal prediction intervals over the future behavior of an autonomous system executing a fixed control policy on a Markov Decision Process.
Optimized Simultaneous Aided Target Detection and Imagery based Navigation in GPS-Denied Environments
We describe and demonstrate a comprehensive optimized vision-based real-time solution to provide SATIN capabilities for current and future UAS in GPS-denied environments.
Conformal Prediction Intervals for Markov Decision Process Trajectories
This paper extends previous work on conformal prediction for functional data and conformalized quantile regression…
Cross-View and Cross-Modal Visual Geo-Localization for Augmented Reality and Robot/Vehicle Navigation Applications
We will present methods and results for estimation of geo-location and/ or orientation for dismounts and platforms for wide area, outdoor augmented reality and other applications under GPS denied/ challenged conditions.
Time-Space Processing for Small Ship Detection in SAR
This paper presents a new 3D time-space detector for small ships in single look complex (SLC) synthetic aperture radar (SAR) imagery, optimized for small targets around 5-15 m long that are unfocused due to target motion induced by ocean surface waves.
Striking the Right Balance: Recall Loss for Semantic Segmentation
We propose a hard-class mining loss by reshaping the vanilla cross entropy loss such that it weights the loss for each class dynamically based on instantaneous recall performance.