74 citations · 248 across the 25 of their papers we have counts for
12 papers · 1 filter
Action Segmentation with Mixed Temporal Domain Adaptation
Min-Hung Chen, Baopu Li, Yingze Bao +1
The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and cha…
Extracting Causal Visual Features for Limited label Classification
Mohit Prabhushankar, Ghassan AlRegib
Neural networks trained to classify images do so by identifying features that allow them to distinguish between classes. These sets of features are either causal or context depende…
Gradients as a Measure of Uncertainty in Neural Networks
Jinsol Lee, Ghassan AlRegib
Despite tremendous success of modern neural networks, they are known to be overconfident even when the model encounters inputs with unfamiliar conditions. Detecting such inputs is…
On the Structures of Representation for the Robustness of Semantic Segmentation to Input Corruption
Charles Lehman, Dogancan Temel, Ghassan AlRegib
Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential. Implicit Background Estimation (…
Robustness and Overfitting Behavior of Implicit Background Models
Shirley Liu, Charles Lehman, Ghassan AlRegib
In this paper, we examine the overfitting behavior of image classification models modified with Implicit Background Estimation (SCrIBE), which transforms them into weakly supervise…
Novelty Detection Through Model-Based Characterization of Neural Networks
Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel +1
In this paper, we propose a model-based characterization of neural networks to detect novel input types and conditions. Novelty detection is crucial to identify abnormal inputs tha…
Implicit Saliency in Deep Neural Networks
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 predi…
Contrastive Explanations in Neural Networks
Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel +1
Visual explanations are logical arguments based on visual features that justify the predictions made by neural networks. Current modes of visual explanations answer questions of th…
Backpropagated Gradient Representations for Anomaly Detection
Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel +1
Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use act…
Learning to Generate Grounded Visual Captions without Localization Supervision
Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib +3
When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the…
Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection
Tariq Alshawi, Zhiling Long, Ghassan AlRegib
In this paper, we address the problem of quantifying reliability of computational saliency for videos, which can be used to improve saliency-based video processing and enable more…
Subsurface structure analysis using computational interpretation and learning: A visual signal processing perspective
G. AlRegib, M. Deriche, Z. Long +5
Understanding Earth's subsurface structures has been and continues to be an essential component of various applications such as environmental monitoring, carbon sequestration, and…