Search Results for author:
Found 3 papers, 2 papers with code
AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration
However, the common limitation is that while images are saved in a compressed format before being enhanced by IR, prior work does not consider the impact of compression on the IR quality.
TSPipe: Learn from Teacher Faster with Pipelines
The teacher-student (TS) framework, training a (student) network by utilizing an auxiliary superior (teacher) network, has been adopted as a popular training paradigm in many machine learning schemes, since the seminal work---Knowledge distillation (KD) for model compression and transfer learning.
NEMO: enabling neural-enhanced video streaming on commodity mobile devices
Our evaluation using a full system implementation on Android shows NEMO improves the overall processing throughput by x11. 5, reduces energy consumption by 88. 6%, and maintains device temperatures at acceptable levels compared to per-frame super-resolution, while ensuring high video quality.
