Search Results for author: Simyung Chang

Found 24 papers, 2 papers with code

Broadcasted Residual Learning for Efficient Keyword Spotting

4 code implementations8 Jun 2021 Byeonggeun Kim, Simyung Chang, Jinkyu Lee, Dooyong Sung

We present a broadcasted residual learning method to achieve high accuracy with small model size and computational load.

Keyword Spotting

Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation

1 code implementation ICCV 2019 Simyung Chang, SeongUk Park, John Yang, Nojun Kwak

Recent advances in image-to-image translation have led to some ways to generate multiple domain images through a single network.

Image-to-Image Translation Translation

Broadcasting Convolutional Network for Visual Relational Reasoning

no code implementations ECCV 2018 Simyung Chang, John Yang, SeongUk Park, Nojun Kwak

In this paper, we propose the Broadcasting Convolutional Network (BCN) that extracts key object features from the global field of an entire input image and recognizes their relationship with local features.

Relation Relational Reasoning +1

BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning

no code implementations5 Sep 2017 Simyung Chang, Youngjoon Yoo, Jae-Seok Choi, Nojun Kwak

Our method learns hundreds to thousand times faster than the conventional methods by learning only a handful of core cluster information, which shows that deep RL agents can effectively learn through the shared knowledge from other agents.

Imitation Learning reinforcement-learning +1

Towards Governing Agent's Efficacy: Action-Conditional $β$-VAE for Deep Transparent Reinforcement Learning

no code implementations11 Nov 2018 John Yang, Gyujeong Lee, Minsung Hyun, Simyung Chang, Nojun Kwak

We tackle the blackbox issue of deep neural networks in the settings of reinforcement learning (RL) where neural agents learn towards maximizing reward gains in an uncontrollable way.

reinforcement-learning Reinforcement Learning (RL) +1

Genetic-Gated Networks for Deep Reinforcement Learning

no code implementations NeurIPS 2018 Simyung Chang, John Yang, Jaeseok Choi, Nojun Kwak

We introduce the Genetic-Gated Networks (G2Ns), simple neural networks that combine a gate vector composed of binary genetic genes in the hidden layer(s) of networks.

reinforcement-learning Reinforcement Learning (RL)

URNet : User-Resizable Residual Networks with Conditional Gating Module

no code implementations15 Jan 2019 Sang-ho Lee, Simyung Chang, Nojun Kwak

There are methods to reduce the cost by compressing networks or varying its computational path dynamically according to the input image.

Genetic-Gated Networks for Deep Reinforcement

no code implementations26 Nov 2018 Simyung Chang, John Yang, Jae-Seok Choi, Nojun Kwak

We introduce the Genetic-Gated Networks (G2Ns), simple neural networks that combine a gate vector composed of binary genetic genes in the hidden layer(s) of networks.

reinforcement-learning Reinforcement Learning (RL)

SubSpectral Normalization for Neural Audio Data Processing

no code implementations25 Mar 2021 Simyung Chang, Hyoungwoo Park, Janghoon Cho, Hyunsin Park, Sungrack Yun, Kyuwoong Hwang

In this work, we introduce SubSpectral Normalization (SSN), which splits the input frequency dimension into several groups (sub-bands) and performs a different normalization for each group.

Keyword Spotting

Prototype-based Personalized Pruning

no code implementations25 Mar 2021 Jangho Kim, Simyung Chang, Sungrack Yun, Nojun Kwak

We verify the usefulness of PPP on a couple of tasks in computer vision and Keyword spotting.

Keyword Spotting Model Compression

PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation

no code implementations25 Jun 2021 Jangho Kim, Simyung Chang, Nojun Kwak

Unlike traditional pruning and KD, PQK makes use of unimportant weights pruned in the pruning process to make a teacher network for training a better student network without pre-training the teacher model.

Keyword Spotting Knowledge Distillation +2

Self-Evolutionary Optimization for Pareto Front Learning

no code implementations7 Oct 2021 Simyung Chang, KiYoon Yoo, Jiho Jang, Nojun Kwak

Utilizing SEO for PFL, we also introduce self-evolutionary Pareto networks (SEPNet), enabling the unified model to approximate the entire Pareto front set that maximizes the hypervolume.

Multi-Task Learning

Towards Robust Domain Generalization in 2D Neural Audio Processing

no code implementations29 Sep 2021 Byeonggeun Kim, Seunghan Yang, Jangho Kim, Hyunsin Park, Jun-Tae Lee, Simyung Chang

While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to get domain-invariant features.

Acoustic Scene Classification Domain Generalization +3

Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation

no code implementations11 Nov 2021 John Yang, Yash Bhalgat, Simyung Chang, Fatih Porikli, Nojun Kwak

While hand pose estimation is a critical component of most interactive extended reality and gesture recognition systems, contemporary approaches are not optimized for computational and memory efficiency.

3D Hand Pose Estimation Gesture Recognition

Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization

no code implementations12 Nov 2021 Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang

Moreover, we introduce an efficient architecture, BC-ResNet-ASC, a modified version of the baseline architecture with a limited receptive field.

Acoustic Scene Classification Classification +5

Distribution Estimation to Automate Transformation Policies for Self-Supervision

no code implementations24 Nov 2021 Seunghan Yang, Debasmit Das, Simyung Chang, Sungrack Yun, Fatih Porikli

However, it is observed that image transformations already present in the dataset might be less effective in learning such self-supervised representations.

Generative Adversarial Network Self-Supervised Learning

Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification

no code implementations24 Jun 2022 Byeonggeun Kim, Seunghan Yang, Jangho Kim, Hyunsin Park, JunTae Lee, Simyung Chang

While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to get domain-invariant features.

Acoustic Scene Classification Domain Generalization +1

Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting

no code implementations28 Jun 2022 Byeonggeun Kim, Seunghan Yang, Inseop Chung, Simyung Chang

We also verify our method on a standard benchmark, miniImageNet, and D-ProtoNets shows the state-of-the-art open-set detection rate in FSOSR.

Keyword Spotting Metric Learning +1

Personalized Keyword Spotting through Multi-task Learning

no code implementations28 Jun 2022 Seunghan Yang, Byeonggeun Kim, Inseop Chung, Simyung Chang

We design two personalized KWS tasks; (1) Target user Biased KWS (TB-KWS) and (2) Target user Only KWS (TO-KWS).

Keyword Spotting Multi-Task Learning +1

Quadapter: Adapter for GPT-2 Quantization

no code implementations30 Nov 2022 Minseop Park, Jaeseong You, Markus Nagel, Simyung Chang

In that case, it is observed that quantization-aware training overfits the model to the fine-tuning data.

Quantization

Scalable Weight Reparametrization for Efficient Transfer Learning

no code implementations26 Feb 2023 Byeonggeun Kim, Jun-Tae Lee, Seunghan Yang, Simyung Chang

Efficient transfer learning involves utilizing a pre-trained model trained on a larger dataset and repurposing it for downstream tasks with the aim of maximizing the reuse of the pre-trained model.

Keyword Spotting Transfer Learning

Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer

no code implementations31 Aug 2023 Kyuhong Shim, Jinkyu Lee, Simyung Chang, Kyuwoong Hwang

Streaming automatic speech recognition (ASR) models are restricted from accessing future context, which results in worse performance compared to the non-streaming models.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data

no code implementations31 Aug 2023 Seunghan Yang, Byeonggeun Kim, Kyuhong Shim, Simyung Chang

Few-shot keyword spotting (FS-KWS) models usually require large-scale annotated datasets to generalize to unseen target keywords.

Keyword Spotting Multi-Task Learning +1

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