Search Results for author: Joonsang Yu

Found 6 papers, 3 papers with code

EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection

1 code implementation4 Apr 2022 JoonHyun Jeong, Beomyoung Kim, Joonsang Yu, Youngjoon Yoo

From the extensive experiments, we show that the proposed backbone can replace that of the state-of-the-art face detector with a faster inference speed.

Face Detection

NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference

no code implementations3 Dec 2021 Joonsang Yu, Junki Park, Seongmin Park, Minsoo Kim, Sihwa Lee, Dong Hyun Lee, Jungwook Choi

Non-linear operations such as GELU, Layer normalization, and Softmax are essential yet costly building blocks of Transformer models.

ConCoDE: Hard-constrained Differentiable Co-Exploration Method for Neural Architectures and Hardware Accelerators

no code implementations29 Sep 2021 Deokki Hong, Kanghyun Choi, Hey Yoon Lee, Joonsang Yu, Youngsok Kim, Noseong Park, Jinho Lee

To handle the hard constraint problem of differentiable co-exploration, we propose ConCoDE, which searches for hard-constrained solutions without compromising the global design objectives.

Neural Architecture Search

DANCE: Differentiable Accelerator/Network Co-Exploration

no code implementations14 Sep 2020 Kanghyun Choi, Deokki Hong, Hojae Yoon, Joonsang Yu, Youngsok Kim, Jinho Lee

In such circumstances, this work presents DANCE, a differentiable approach towards the co-exploration of the hardware accelerator and network architecture design.

Neural Architecture Search

Network Recasting: A Universal Method for Network Architecture Transformation

1 code implementation14 Sep 2018 Joonsang Yu, Sungbum Kang, Ki-Young Choi

The method is based on block-wise recasting; it recasts each source block in a pre-trained teacher network to a target block in a student network.

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