5 papers
Explainable Human-in-the-Loop Segmentation via Critic Feedback Signals
Pouya Shaeri, Ryan T. Woo, Yasaman Mohammadpour +1
Segmentation models achieve high accuracy on benchmarks but often fail in real-world domains by relying on spurious correlations instead of true object boundaries. We propose a hum…
Tri-Accel: Curvature-Aware Precision-Adaptive and Memory-Elastic Optimization for Efficient GPU Usage
Mohsen Sheibanian, Pouya Shaeri, Alimohammad Beigi +2
Deep neural networks are increasingly bottlenecked by the cost of optimization, both in terms of GPU memory and compute time. Existing acceleration techniques, such as mixed precis…
MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection
Pouya Shaeri, Ariane Middel
Modern neural networks often activate all neurons for every input, leading to unnecessary computation and inefficiency. We introduce Matrix-Interpolated Dropout Layer (MID-L), a no…
Sentiment and Social Signals in the Climate Crisis: A Survey on Analyzing Social Media Responses to Extreme Weather Events
Pouya Shaeri, Yasaman Mohammadpour, Alimohammad Beigi +1
Extreme weather events driven by climate change, such as wildfires, floods, and heatwaves, prompt significant public reactions on social media platforms. Analyzing the sentiment ex…
A Multimodal Physics-Informed Neural Network Approach for Mean Radiant Temperature Modeling
Pouya Shaeri, Saud AlKhaled, Ariane Middel
Outdoor thermal comfort is a critical determinant of urban livability, particularly in hot desert climates where extreme heat poses challenges to public health, energy consumption,…