9 citations · 37 across the 20 of their papers we have counts for
23 papers
Domain Adaptation of SAM 2.1 for Building-Component Segmentation in Image-Based 3D Reconstruction
Ehsan Agha Ebrahimi, Yong-Cheol Lee, Keith G. Mills
3D reconstruction of building components using image-based scanning requires appropriate segmentation of the objects in the 2D building images. In order to benefit from consistent…
Segmentation of Bovid Dentition Under Imperfect Annotations: A Comparative Study of Convolutional and Attention Models
Keith G. Mills, Evan B. Sanders, Gregory J. Matthews +1
Semantic segmentation decomposes an image into distinct mask regions corresponding to different object categories, such as people, cars, signs or buildings. Advances in machine lea…
How Much Does Message Passing Matter? A Drop-In Study of GNN Layers for Neural Network Graph Regression
Keith G. Mills, Aedan J. DeFrates, Joong Ho Kim
Graph Neural Networks (GNNs) are widely used as regressors, for example to predict the accuracy of a neural architecture. Yet new message-passing (MP) layers are developed and benc…
Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?
Joong Ho Kim, Keith G. Mills
Diffusion Models (DM) have revolutionized text-driven generation by enabling the synthesis of high-quality, photorealistic visual content from user prompts. Whereas prior advances…
2D Pre-Training for 3D Pose Estimation
Liyao Jiang, Ruichen Chen, Keith G. Mills
Pre-training is a general method that is used in a range of deep learning tasks. By first training a model on one task, and then further training on the downstream task used for fi…
Naïve PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation
Joong Ho Kim, Nicholas Thai, Souhardya Saha Dip +2
Text-to-Image (T2I) generation is primarily driven by Diffusion Models (DM) which rely on random Gaussian noise. Thus, like playing the slots at a casino, a DM will produce differe…
Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence
Amirhosein Ghasemabadi, Keith G. Mills, Baochun Li +1
Test-Time Scaling (TTS) methods for enhancing Large Language Model (LLM) reasoning often incur substantial computational costs, primarily due to extensive reliance on external Proc…
Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape
Ruichen Chen, Keith G. Mills, Liyao Jiang +2
Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where co…
FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers
Ruichen Chen, Keith G. Mills, Di Niu
Diffusion Models (DM) have revolutionized the text-to-image visual generation process. However, the large computational cost and model footprint of DMs hinders practical deployment…
Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstruction
Shengyao Lu, Jiuding Yang, Aedan J. DeFrates +3
We propose a novel model-level GNN explanation framework that shifts the explanation target from class-wise rule extraction to rule-based logit reconstruction. Our method recasts t…
Applying Graph Explanation to Operator Fusion
Keith G. Mills, Muhammad Fetrat Qharabagh, Weichen Qiu +5
Layer fusion techniques are critical to improving the inference efficiency of deep neural networks (DNN) for deployment. Fusion aims to lower inference costs by reducing data trans…
QuaSeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
Keith G. Mills, Mohammad Salameh, Ruichen Chen +3
Diffusion Models (DM) have democratized AI image generation through an iterative denoising process. Quantization is a major technique to alleviate the inference cost and reduce the…
EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
Shengyao Lu, Bang Liu, Keith G. Mills +2
Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining att…
Building Optimal Neural Architectures using Interpretable Knowledge
Keith G. Mills, Fred X. Han, Mohammad Salameh +5
Neural Architecture Search is a costly practice. The fact that a search space can span a vast number of design choices with each architecture evaluation taking nontrivial overhead…
GOAt: Explaining Graph Neural Networks via Graph Output Attribution
Shengyao Lu, Keith G. Mills, Jiao He +2
Understanding the decision-making process of Graph Neural Networks (GNNs) is crucial to their interpretability. Most existing methods for explaining GNNs typically rely on training…
A General-Purpose Transferable Predictor for Neural Architecture Search
Fred X. Han, Keith G. Mills, Fabian Chudak +6
Understanding and modelling the performance of neural architectures is key to Neural Architecture Search (NAS). Performance predictors have seen widespread use in low-cost NAS and…
AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
Keith G. Mills, Di Niu, Mohammad Salameh +6
Evaluating neural network performance is critical to deep neural network design but a costly procedure. Neural predictors provide an efficient solution by treating architectures as…
GENNAPE: Towards Generalized Neural Architecture Performance Estimators
Keith G. Mills, Fred X. Han, Jialin Zhang +6
Predicting neural architecture performance is a challenging task and is crucial to neural architecture design and search. Existing approaches either rely on neural performance pred…
R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning
Shengyao Lu, Bang Liu, Keith G. Mills +2
Systematicity, i.e., the ability to recombine known parts and rules to form new sequences while reasoning over relational data, is critical to machine intelligence. A model with st…
Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search
Keith G. Mills, Fred X. Han, Jialin Zhang +6
Neural architecture search automates neural network design and has achieved state-of-the-art results in many deep learning applications. While recent literature has focused on desi…
LNAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning
Keith G. Mills, Fred X. Han, Mohammad Salameh +6
Neural architecture search (NAS) has achieved remarkable results in deep neural network design. Differentiable architecture search converts the search over discrete architectures i…
Generative Adversarial Neural Architecture Search
Seyed Saeed Changiz Rezaei, Fred X. Han, Di Niu +5
Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess. In t…
Android Malware Detection based on Factorization Machine
Chenglin Li, Keith Mills, Rui Zhu +3
As the popularity of Android smart phones has increased in recent years, so too has the number of malicious applications. Due to the potential for data theft mobile phone users fac…