Saif U Din
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Saif U Din has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Dmitry Ignatov
Computer Vision Lab, CAIDAS & IFI, University of W¨urzburg, Germany, Germany
2 shared publications - Faraz Kayani
Computer Vision Lab, CAIDAS & IFI, University of W¨urzburg, Germany, Germany
2 shared publications - Radu Timofte
University of Würzburg
2 shared publications - Alice Arslanian
Computer Vision Lab, Center for Artificial Intelligence and Data Science (CAIDAS) and Institute of Computer Science (IFI), University of Würzburg, John-Skilton-Straße 4a, 97074 Würzburg, Germany
1 shared publication - Divyesh Rameshbhai Dhanani
Computer Vision Lab, Center for Artificial Intelligence and Data Science (CAIDAS) and Institute of Computer Science (IFI), University of Würzburg, John-Skilton-Straße 4a, 97074 Würzburg, Germany
1 shared publication - Mohsin Ikram
Computer Vision Lab, CAIDAS & IFI, University of W¨urzburg, Germany, Germany
1 shared publication
Latest Publications
- Open Access
- 21 July 2026
- Published by MDPI AG in Preprints.org
AI on the Edge: An Automated Pipeline for PyTorch-to-Android Deployment and Benchmarking
On-device latency ultimately determines whether a vision model is deployable on smartphones, yet collecting real-device latency at scale is costly and fragile. We present AI on the Edge, an automated measurement pipeline and open dataset for large-scale delegate-resolved Android benchmarking. AI on the Edge converts a PyTorch model zoo to TensorFlow Lite in FP32 and full-integer INT8 precision, then benchmarks each model on physical phones with three forced execution paths: CPU (XNNPACK), GPU (TFLite GPU), and NPU (NNAPI), so every latency is attributable to a known backend. Using one workstation and five commodity phones, AI on the Edge measured 586 architectures and produced 5,826 model × device × precision records, comprising about 17 500 backend benchmarks and 351 600 timed inferences (586 × 5 × 3 × 2 × 20), in roughly 56 unattended device-hours (up to 201 models/h/phone). Campaigns include both end-to-end Stage A+Stage B runs and Stage B-only replay from prebuilt TFLite artifacts, with identical on-device benchmark settings. The pipeline is designed for unattended operation via USB-reconnection handling, thermal cool-down scheduling, and a resumable processing ledger. We release the full per-run dataset with documented schema, public model/code resources, and a reproducibility harness that regenerates headline statistics from raw records. AI on the Edge reduces the practical cost of real-device benchmarking and provides a reusable substrate for hardware-aware architecture research.
- 21 July 2026
- Published by MDPI AG in Preprints.org
Open AccessAI on the Edge: An Automated Pipeline for PyTorch-to-Android Deployment and Benchmarking
On-device latency ultimately determines whether a vision model is deployable on smartphones, yet collecting real-device latency at scale is costly and fragile. We present AI on the Edge, an automated measurement pipeline and open dataset for large-scale delegate-resolved Android benchmarking. AI on the Edge converts a PyTorch model zoo to TensorFlow Lite in FP32 and full-integer INT8 precision, then benchmarks each model on physical phones with three forced execution paths: CPU (XNNPACK), GPU (TFLite GPU), and NPU (NNAPI), so every latency is attributable to a known backend. Using one workstation and five commodity phones, AI on the Edge measured 586 architectures and produced 5,826 model × device × precision records, comprising about 17 500 backend benchmarks and 351 600 timed inferences (586 × 5 × 3 × 2 × 20), in roughly 56 unattended device-hours (up to 201 models/h/phone). Campaigns include both end-to-end Stage A+Stage B runs and Stage B-only replay from prebuilt TFLite artifacts, with identical on-device benchmark settings. The pipeline is designed for unattended operation via USB-reconnection handling, thermal cool-down scheduling, and a resumable processing ledger. We release the full per-run dataset with documented schema, public model/code resources, and a reproducibility harness that regenerates headline statistics from raw records. AI on the Edge reduces the practical cost of real-device benchmarking and provides a reusable substrate for hardware-aware architecture research.
- Open Access
Understanding the Performance of Deep Computer Vision Models: A Symbolic Regression Approach to Accuracy and Latency Prediction
Deploying deep vision models on edge hardware requires understanding how architecture and training hyperparameters jointly determine accuracy and inference latency, yet these relationships remain poorly characterized in a systematic, data-driven manner. This paper presents a two-stage statistical framework providing interpretable, closed-form insights into both. In the first stage, we apply distance correlation (dCor) and the maximal information coefficient (MIC) across seven image-classification datasets, revealing that batch size and total layer count are the strongest universal accuracy predictors (mean dCor: 0.228 and 0.174), while learning rate achieves the highest MIC (0.226), reflecting a non-monotonic relationship with accuracy. In the second stage, PySR symbolic regression (representing, to our knowledge, the first application to cross-dataset vision model accuracy prediction) derives compact, interpretable formulas. Dataset-specific models achieve from 0.20 to 0.45; a universal model achieves a mean leave-one-dataset-out of 0.23, remaining strictly positive on all held-out datasets, whereas ordinary linear regression collapses to . We further derive device-specific inference latency formulas for CPU, GPU, and NPU, outperforming classical baselines by – in and confirming fundamental device heterogeneity. Together, these results offer interpretable surrogate models for screening deep vision architectures under accuracy and latency constraints in edge deployment.Open AccessUnderstanding the Performance of Deep Computer Vision Models: A Symbolic Regression Approach to Accuracy and Latency Prediction
Deploying deep vision models on edge hardware requires understanding how architecture and training hyperparameters jointly determine accuracy and inference latency, yet these relationships remain poorly characterized in a systematic, data-driven manner. This paper presents a two-stage statistical framework providing interpretable, closed-form insights into both. In the first stage, we apply distance correlation (dCor) and the maximal information coefficient (MIC) across seven image-classification datasets, revealing that batch size and total layer count are the strongest universal accuracy predictors (mean dCor: 0.228 and 0.174), while learning rate achieves the highest MIC (0.226), reflecting a non-monotonic relationship with accuracy. In the second stage, PySR symbolic regression (representing, to our knowledge, the first application to cross-dataset vision model accuracy prediction) derives compact, interpretable formulas. Dataset-specific models achieve from 0.20 to 0.45; a universal model achieves a mean leave-one-dataset-out of 0.23, remaining strictly positive on all held-out datasets, whereas ordinary linear regression collapses to . We further derive device-specific inference latency formulas for CPU, GPU, and NPU, outperforming classical baselines by – in and confirming fundamental device heterogeneity. Together, these results offer interpretable surrogate models for screening deep vision architectures under accuracy and latency constraints in edge deployment.