Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains

no code implementations • 28 Feb 2024 • Hafiz Tiomoko Ali, Umberto Michieli, Ji Joong Moon, Daehyun Kim, Mete Ozay

Inspired by NC properties, we explore in this paper the transferability of DNN models trained with their last layer weight fixed according to ETF.

Fine-Grained Image Classification Transfer Learning

A New Frontier of AI: On-Device AI Training and Personalization

1 code implementation • 9 Jun 2022 • Ji Joong Moon, Hyun Suk Lee, Jiho Chu, Donghak Park, Seungbaek Hong, Hyungjun Seo, Donghyeon Jeong, Sungsik Kong, MyungJoo Ham

Modern consumer electronic devices have started executing deep learning-based intelligence services on devices, not cloud servers, to keep personal data on devices and to reduce network and cloud costs.

Efficient Neural Network speech-recognition +1

NNStreamer: Stream Processing Paradigm for Neural Networks, Toward Efficient Development and Execution of On-Device AI Applications

1 code implementation • 12 Jan 2019 • MyungJoo Ham, Ji Joong Moon, Geunsik Lim, Wook Song, Jaeyun Jung, Hyoungjoo Ahn, Sangjung Woo, Youngchul Cho, Jinhyuck Park, Sewon Oh, Hong-Seok Kim

We propose nnstreamer, a software system that handles neural networks as filters of stream pipelines, applying the stream processing paradigm to neural network applications.