Search Results for author: Eunhyeok Park

Found 19 papers, 8 papers with code

HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization

no code implementations21 Jun 2024 Seonggon Kim, Eunhyeok Park

With the rapid increase in model size and the growing importance of various fine-tuning applications, lightweight training has become crucial.

Quantization

Task-Oriented Diffusion Model Compression

no code implementations31 Jan 2024 Geonung Kim, Beomsu Kim, Eunhyeok Park, Sunghyun Cho

As recent advancements in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged.

Denoising Image Generation +2

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

no code implementations6 Dec 2023 Junhyuk So, Jungwon Lee, Eunhyeok Park

The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to their widespread adoption.

Denoising Image Generation

Temporal Dynamic Quantization for Diffusion Models

no code implementations NeurIPS 2023 Junhyuk So, Jungwon Lee, Daehyun Ahn, HyungJun Kim, Eunhyeok Park

The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility.

Quantization

OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

2 code implementations4 Jun 2023 Changhun Lee, Jungyu Jin, Taesu Kim, HyungJun Kim, Eunhyeok Park

Large language models (LLMs) with hundreds of billions of parameters require powerful server-grade GPUs for inference, limiting their practical deployment.

Quantization

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

no code implementations31 Jul 2022 Sein Park, Yeongsang Jang, Eunhyeok Park

Robust quantization improves the tolerance of networks for various implementations, allowing reliable output in different bit-widths or fragmented low-precision arithmetic.

Quantization

NIPQ: Noise proxy-based Integrated Pseudo-Quantization

1 code implementation CVPR 2023 JunCheol Shin, Junhyuk So, Sein Park, Seungyeop Kang, Sungjoo Yoo, Eunhyeok Park

Recently, pseudoquantization training has been proposed as an alternative approach to updating the learnable parameters using the pseudo-quantization noise instead of STE.

Quantization

Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking

no code implementations23 May 2022 Ilchae Jung, Minji Kim, Eunhyeok Park, Bohyung Han

This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network.

Representation Learning Visual Tracking

INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold

no code implementations ICCV 2023 Changhun Lee, HyungJun Kim, Eunhyeok Park, Jae-Joon Kim

Binary Neural Networks (BNNs) have emerged as a promising solution for reducing the memory footprint and compute costs of deep neural networks, but they suffer from quality degradation due to the lack of freedom as activations and weights are constrained to the binary values.

Quantization

On the Overlooked Significance of Underutilized Contextual Features in Recent News Recommendation Models

no code implementations29 Dec 2021 Sungmin Cho, Hongjun Lim, Keunchan Park, Sungjoo Yoo, Eunhyeok Park

Personalized news recommendation aims to provide attractive articles for readers by predicting their likelihood of clicking on a certain article.

News Recommendation

MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation

1 code implementation19 Aug 2020 Sung Min Cho, Eunhyeok Park, Sungjoo Yoo

Following the custom from language processing, most of these models rely on a simple positional embedding to exploit the sequential nature of the user's history.

Diversity Sequential Recommendation

PROFIT: A Novel Training Method for sub-4-bit MobileNet Models

1 code implementation ECCV 2020 Eunhyeok Park, Sungjoo Yoo

In the ablation study of the 3-bit quantization of MobileNet-v3, our proposed method outperforms the state-of-the-art method by a large margin, 12. 86 % of top-1 accuracy.

Quantization

Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss

2 code implementations ICCV 2019 Hyunsu Kim, Ho Young Jhoo, Eunhyeok Park, Sungjoo Yoo

A GAN approach is proposed, called Tag2Pix, of line art colorization which takes as input a grayscale line art and color tag information and produces a quality colored image.

Line Art Colorization TAG

Precision Highway for Ultra Low-Precision Quantization

no code implementations ICLR 2019 Eunhyeok Park, Dongyoung Kim, Sungjoo Yoo, Peter Vajda

We also report that the proposed method significantly outperforms the existing method in the 2-bit quantization of an LSTM for language modeling.

Language Modelling Quantization

Value-aware Quantization for Training and Inference of Neural Networks

no code implementations ECCV 2018 Eunhyeok Park, Sungjoo Yoo, Peter Vajda

We propose a novel value-aware quantization which applies aggressively reduced precision to the majority of data while separately handling a small amount of large data in high precision, which reduces total quantization errors under very low precision.

Quantization

Weighted-Entropy-Based Quantization for Deep Neural Networks

no code implementations CVPR 2017 Eunhyeok Park, Junwhan Ahn, Sungjoo Yoo

Quantization is considered as one of the most effective methods to optimize the inference cost of neural network models for their deployment to mobile and embedded systems, which have tight resource constraints.

Image Classification Language Modelling +3

Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications

7 code implementations20 Nov 2015 Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin

Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging.

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