Reusing deep learning models: Challenges and directions in software engineering
Deep neural networks (DNNs) achieve state-of-the-art performance in many areas, including
computer vision, system configuration, and question-answering. However, DNNs are …
computer vision, system configuration, and question-answering. However, DNNs are …
What do we know about Hugging Face? A systematic literature review and quantitative validation of qualitative claims
Background: Software Package Registries (SPRs) are an integral part of the software supply
chain. These collaborative platforms unite contributors, users, and code for streamlined …
chain. These collaborative platforms unite contributors, users, and code for streamlined …
[HTML][HTML] A novel mamba architecture with a semantic transformer for efficient real-time remote sensing semantic segmentation
H Ding, B Xia, W Liu, Z Zhang, J Zhang, X Wang, S Xu - Remote Sensing, 2024 - mdpi.com
Real-time remote sensing segmentation technology is crucial for unmanned aerial vehicles
(UAVs) in battlefield surveillance, land characterization observation, earthquake disaster …
(UAVs) in battlefield surveillance, land characterization observation, earthquake disaster …
Challenges and practices of deep learning model reengineering: A case study on computer vision
Context Many engineering organizations are reimplementing and extending deep neural
networks from the research community. We describe this process as deep learning model …
networks from the research community. We describe this process as deep learning model …
Peatmoss: A dataset and initial analysis of pre-trained models in open-source software
The development and training of deep learning models have become increasingly costly
and complex. Consequently, software engineers are adopting pre-trained models (PTMs) for …
and complex. Consequently, software engineers are adopting pre-trained models (PTMs) for …
Test & evaluation best practices for machine learning-enabled systems
Machine learning (ML)-based software systems are rapidly gaining adoption across various
domains, making it increasingly essential to ensure they perform as intended. This report …
domains, making it increasingly essential to ensure they perform as intended. This report …
ONNXPruner: ONNX-Based General Model Pruning Adapter
Recent advancements in model pruning have focused on developing new algorithms and
improving upon benchmarks. However, the practical application of these algorithms across …
improving upon benchmarks. However, the practical application of these algorithms across …
A Partial Replication of MaskFormer in TensorFlow on TPUs for the TensorFlow Model Garden
This paper undertakes the task of replicating the MaskFormer model a universal image
segmentation model originally developed using the PyTorch framework, within the …
segmentation model originally developed using the PyTorch framework, within the …
A Comprehensive Crucial Review of Re-Purposing DNN-Based Systems: Significance, Challenges, and Future Directions.
YM Al-Hamzi, SB Sahibuddin - International Journal of …, 2024 - search.ebscohost.com
The fourth industrial revolution is marked by the significance of artificial intelligence (AI),
particularly the remarkable progress in deep neural networks (DNNs). These networks have …
particularly the remarkable progress in deep neural networks (DNNs). These networks have …
Testing Machine Learning: Best Practices for the Life Cycle
Artificial Intelligence (AI) enabled systems are becoming capable and widespread. The use
of AI in critical system functions warrants a review of existing test and evaluation (T&E) tools …
of AI in critical system functions warrants a review of existing test and evaluation (T&E) tools …