Search Results for author: Hong-Seok Kim

Found 5 papers, 2 papers with code

MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization

no code implementations12 Nov 2023 Han-Byul Kim, Joo Hyung Lee, Sungjoo Yoo, Hong-Seok Kim

Mixed-precision quantization of efficient networks often suffer from activation instability encountered in the exploration of bit selections.

Quantization

Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation

no code implementations10 Apr 2023 Inkyu Shin, Dahun Kim, Qihang Yu, Jun Xie, Hong-Seok Kim, Bradley Green, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen

The meta architecture of the proposed Video-kMaX consists of two components: within clip segmenter (for clip-level segmentation) and cross-clip associater (for association beyond clips).

Scene Understanding Segmentation +2

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

1 code implementation12 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.