Search Results - "Vasu, Bhavan"

Resilience and Plasticity of Deep Network Interpretations for Aerial Imagery by Vasu, Bhavan, Savakis, Andreas

“…This paper aims at visualizing deep convolutional neural network interpretations for aerial imagery and understanding how these interpretations change across…”
Get full text

XAITK: The explainable AI toolkit by Hu, Brian, Tunison, Paul, Vasu, Bhavan, Menon, Nitesh, Collins, Roddy, Hoogs, Anthony

“…Recent advances in artificial intelligence (AI), driven mainly by deep neural networks, have yielded remarkable progress in fields, such as computer vision,…”
Get full text

Explainable, interactive content‐based image retrieval by Vasu, Bhavan, Hu, Brian, Dong, Bo, Collins, Roddy, Hoogs, Anthony

“…Quantifying the value of explanations in a human‐in‐the‐loop (HITL) system is difficult. Previous methods either measure explanation‐specific values that do…”
Get full text

Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations by Vasu, Bhavan, Long, Chengjiang

“…Deep neural networks have achieved great success in many real-world applications, yet it remains unclear and difficult to explain their decision-making process…”
Get full text

X-MIR: EXplainable Medical Image Retrieval by Hu, Brian, Vasu, Bhavan, Hoogs, Anthony

“…Despite significant progress in the past few years, machine learning systems are still often viewed as "black boxes," which lack the ability to explain their…”
Get full text

Explainable, interactive c ontent‐based image retrieval by Vasu, Bhavan, Hu, Brian, Dong, Bo, Collins, Roddy, Hoogs, Anthony

“…Quantifying the value of explanations in a human‐in‐the‐loop (HITL) system is difficult. Previous methods either measure explanation‐specific values that do…”
Get full text

Resilience and Self-Healing of Deep Convolutional Object Detectors by Rahman, Faiz Ur, Vasu, Bhavan, Savakis, Andreas

“…The enormous success and popularity of deep convolutional neural networks for object detection has prompted their deployment in various real world…”
Get full text

Visualizing Resiliency Of Deep Convolutional Network Interpretations For Aerial Imagery by Vasu, Bhavan Kumar

“…This thesis aims at visualizing deep convolutional neural network interpretations for aerial imagery and understanding how these interpretations change when…”
Get full text

Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations by Vasu, Bhavan, Long, Chengjiang

“…Deep neural networks have achieved great success in many real-world applications, yet it remains unclear and difficult to explain their decision-making process…”
Get full text

SIAMESE NETWORK WITH MULTI-LEVEL FEATURES FOR PATCH-BASED CHANGE DETECTION IN SATELLITE IMAGERY by Rahman, Faiz, Vasu, Bhavan, Cor, Jared Van, Kerekes, John, Savakis, Andreas

“…We present a patch-based Siamese neural network for detecting structural changes in satellite imagery. The two channels of our Siamese network are based on the…”
Get full text

Interactive Mars Image Content-Based Search with Interpretable Machine Learning by Vasu, Bhavan, Lu, Steven, Dunkel, Emily, Wagstaff, Kiri L, Grimes, Kevin, McAuley, Michael

“…The NASA Planetary Data System (PDS) hosts millions of images of planets, moons, and other bodies collected throughout many missions. The ever-expanding nature…”
Get full text

Aerial-CAM: Salient Structures and Textures in Network Class Activation Maps of Aerial Imagery by Vasu, Bhavan, Rahman, Faiz Ur, Savakis, Andreas

“…This paper aims at visualizing how deep networks interpret aerial scenes by examining their internal representations. We utilize Class Activation Mapping (CAM)…”
Get full text