Merging Heterogeneous Deep Models and Learning Retrieval Features
異質性深度模型整合與檢索特徵學習

Academia Sinica Research Fellow Chu-Song Chen

計劃主持人：中央研究院資訊科學研究所 陳祝嵩教授

本計畫研發世界首見之方法：於推論端將多個已經充分訓練好之深度類神經網路模型，合成為單一模型。讓智慧型系統同時具備多元化智慧功能。可應用於多種智慧辨認功能之整合，例如不同的影像辨認及語音辨認模組、自然語言理解等。

Given different deep models that are well trained, we develop effective methods that can merge them into a single one. The merged model can handle the different tasks of the original ones simultaneously. Deep model merging has a great many potential of applications. Our approach can merge different deep models by removing the joint redundancy among them, so that a more compact model is obtainable for mobile or edge-computing usages. Besides, we also develop deep learning methods for constructing compact feature representations, so as to increase the retrieval efficiency in a large database.

↓相關連結：

https://www.csie.ntu.edu.tw/people/bio.php?PID=46736