Search Results for author:
Found 2 papers, 2 papers with code
Feature Normalized Knowledge Distillation for Image Classification
From this perspective, we systematically analyze the distillation mechanism and demonstrate that the L2-norm of the feature in penultimate layer would be too large under the influence of label noise, and the temperature T in KD could be regarded as a correction factor for L2-norm to suppress the impact of noise.
An Ultra-low Power TinyML System for Real-time Visual Processing at Edge
Tiny machine learning (TinyML), executing AI workloads on resource and power strictly restricted systems, is an important and challenging topic.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
