Search Results for author:
Found 2 papers, 0 papers with code
PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model.
Exploring Factors for Improving Low Resolution Face Recognition
By leveraging this information, we have utilized deep face models trained on MS-Celeb-1M and fine-tuned on VGGFace2 dataset and achieved state-of-the-art accuracies on the SCFace and ICB-RW benchmarks, even without using any training data from the datasets of these benchmarks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
