Search Results for author: Sung Ju Hwang

Found 89 papers, 47 papers with code

Meta Variance Transfer: Learning to Augment from the Others

no code implementations ICML 2020 Seong-Jin Park, Seungju Han, Ji-won Baek, Insoo Kim, Juhwan Song, Hae Beom Lee, Jae-Joon Han, Sung Ju Hwang

Humans have the ability to robustly recognize objects with various factors of variations such as nonrigid transformation, background noise, and change in lighting conditions.

Face Recognition Meta-Learning +1

Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning

1 code implementation NeurIPS 2021 Hayeon Lee, Sewoong Lee, Song Chong, Sung Ju Hwang

To overcome such limitations, we propose Hardware-adaptive Efficient Latency Predictor (HELP), which formulates the device-specific latency estimation problem as a meta-learning problem, such that we can estimate the latency of a model's performance for a given task on an unseen device with a few samples.

Meta-Learning Neural Architecture Search

DAPPER: Performance Estimation of Domain Adaptation in Mobile Sensing

no code implementations22 Nov 2021 Taesik Gong, Yewon Kim, Adiba Orzikulova, Yunxin Liu, Sung Ju Hwang, Jinwoo Shin, Sung-Ju Lee

We present DAPPER (Domain AdaPtation Performance EstimatoR) that estimates the adaptation performance in a target domain with only unlabeled target data.

Domain Adaptation

Rethinking the Representational Continuity: Towards Unsupervised Continual Learning

no code implementations13 Oct 2021 Divyam Madaan, Jaehong Yoon, Yuanchun Li, Yunxin Liu, Sung Ju Hwang

In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning.

Continual Learning

Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty

no code implementations12 Oct 2021 Jeffrey Ryan Willette, Hae Beom Lee, Juho Lee, Sung Ju Hwang

Numerous recent works utilize bi-Lipschitz regularization of neural network layers to preserve relative distances between data instances in the feature spaces of each layer.

Meta-Learning

Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning

no code implementations6 Oct 2021 Seanie Lee, Hae Beom Lee, Juho Lee, Sung Ju Hwang

Thanks to the gradients aligned between tasks by our method, the model becomes less vulnerable to negative transfer and catastrophic forgetting.

Continual Learning Multi-Task Learning +1

Online Hyperparameter Meta-Learning with Hypergradient Distillation

no code implementations6 Oct 2021 Hae Beom Lee, Hayeon Lee, Jaewoong Shin, Eunho Yang, Timothy Hospedales, Sung Ju Hwang

Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization, which can be considered as hyperparameters.

Hyperparameter Optimization Knowledge Distillation +1

Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

no code implementations NeurIPS 2021 Soojung Yang, Doyeong Hwang, Seul Lee, Seongok Ryu, Sung Ju Hwang

We further show with ablation studies that our method, predictive error-PER (FREED(PE)), significantly improves the model performance.

MOG: Molecular Out-of-distribution Generation with Energy-based Models

no code implementations29 Sep 2021 Seul Lee, Dong Bok Lee, Sung Ju Hwang

To validate the ability to explore the chemical space beyond the known molecular distribution, we experiment with MOG to generate molecules of high absolute values of docking score, which is the affinity score based on a physical binding simulation between a target protein and a given molecule.

Drug Discovery

Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss

no code implementations ICCV 2021 Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang

Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices.

Quantization

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets

1 code implementation ICLR 2021 Hayeon Lee, Eunyoung Hyung, Sung Ju Hwang

Despite the success of recent Neural Architecture Search (NAS) methods on various tasks which have shown to output networks that largely outperform human-designed networks, conventional NAS methods have mostly tackled the optimization of searching for the network architecture for a single task (dataset), which does not generalize well across multiple tasks (datasets).

Meta-Learning Neural Architecture Search

FedMix: Approximation of Mixup under Mean Augmented Federated Learning

no code implementations ICLR 2021 Tehrim Yoon, Sumin Shin, Sung Ju Hwang, Eunho Yang

Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to store data globally.

Data Augmentation Federated Learning

Entropy Weighted Adversarial Training

no code implementations ICML Workshop AML 2021 Minseon Kim, Jihoon Tack, Jinwoo Shin, Sung Ju Hwang

Adversarial training methods, which minimizes the loss of adversarially-perturbed training examples, have been extensively studied as a solution to improve the robustness of the deep neural networks.

HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning

1 code implementation16 Jun 2021 Hayeon Lee, Sewoong Lee, Song Chong, Sung Ju Hwang

To overcome such limitations, we propose Hardware-adaptive Efficient Latency Predictor (HELP), which formulates the device-specific latency estimation problem as a meta-learning problem, such that we can estimate the latency of a model's performance for a given task on an unseen device with a few samples.

Meta-Learning Neural Architecture Search

Adversarial purification with Score-based generative models

1 code implementation11 Jun 2021 Jongmin Yoon, Sung Ju Hwang, Juho Lee

Recently, an Energy-Based Model (EBM) trained with Markov-Chain Monte-Carlo (MCMC) has been highlighted as a purification model, where an attacked image is purified by running a long Markov-chain using the gradients of the EBM.

Denoising

Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

2 code implementations6 Jun 2021 Dongchan Min, Dong Bok Lee, Eunho Yang, Sung Ju Hwang

In this work, we propose StyleSpeech, a new TTS model which not only synthesizes high-quality speech but also effectively adapts to new speakers.

Fine-tuning

Online Coreset Selection for Rehearsal-based Continual Learning

no code implementations2 Jun 2021 Jaehong Yoon, Divyam Madaan, Eunho Yang, Sung Ju Hwang

We validate the effectiveness of our coreset selection mechanism over various standard, imbalanced, and noisy datasets against strong continual learning baselines, demonstrating that it improves task adaptation and prevents catastrophic forgetting in a sample-efficient manner.

Continual Learning

Learning to Perturb Word Embeddings for Out-of-distribution QA

1 code implementation ACL 2021 Seanie Lee, Minki Kang, Juho Lee, Sung Ju Hwang

QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets. However, QA models do not generalize well to unseen data that falls outside the training distribution, due to distributional shifts. Data augmentation (DA) techniques which drop/replace words have shown to be effective in regularizing the model from overfitting to the training data. Yet, they may adversely affect the QA tasks since they incur semantic changes that may lead to wrong answers for the QA task.

Data Augmentation Domain Generalization +1

Consistency Regularization for Adversarial Robustness

1 code implementation ICML Workshop AML 2021 Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang, Jinwoo Shin

Our experimental results demonstrate that such a simple regularization technique brings significant improvements in the test robust accuracy of a wide range of AT methods.

Adversarial Robustness Data Augmentation

Task-Adaptive Neural Network Search with Meta-Contrastive Learning

1 code implementation NeurIPS 2021 Wonyong Jeong, Hayeon Lee, Gun Park, Eunyoung Hyung, Jinheon Baek, Sung Ju Hwang

To address such limitations, we introduce a novel problem of \emph{Neural Network Search} (NNS), whose goal is to search for the optimal pretrained network for a novel dataset and constraints (e. g. number of parameters), from a model zoo.

Contrastive Learning Meta-Learning +1

Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding

no code implementations NeurIPS 2021 Bruno Andreis, Jeffrey Willette, Juho Lee, Sung Ju Hwang

The proposed method adheres to the required symmetries of invariance and equivariance as well as maintaining MBC for any partition of the input set.

Accurate Learning of Graph Representations with Graph Multiset Pooling

1 code implementation ICLR 2021 Jinheon Baek, Minki Kang, Sung Ju Hwang

Graph neural networks have been widely used on modeling graph data, achieving impressive results on node classification and link prediction tasks.

Graph Classification Graph Clustering +5

Improving Uncertainty Calibration via Prior Augmented Data

no code implementations22 Feb 2021 Jeffrey Willette, Juho Lee, Sung Ju Hwang

Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators.

Large-Scale Meta-Learning with Continual Trajectory Shifting

no code implementations14 Feb 2021 Jaewoong Shin, Hae Beom Lee, Boqing Gong, Sung Ju Hwang

Meta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks.

Few-Shot Learning Fine-tuning +1

Model-Augmented Q-learning

no code implementations7 Feb 2021 Youngmin Oh, Jinwoo Shin, Eunho Yang, Sung Ju Hwang

We show that the proposed scheme, called Model-augmented $Q$-learning (MQL), obtains a policy-invariant solution which is identical to the solution obtained by learning with true reward.

Q-Learning

Improving Neural Network Accuracy and Calibration Under Distributional Shift with Prior Augmented Data

no code implementations1 Jan 2021 Jeffrey Ryan Willette, Juho Lee, Sung Ju Hwang

We demonstrate the effectiveness of our method and validate its performance on both classification and regression problems by applying it to the training of recent state-of-the-art neural network models.

Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bitwise Regularization

no code implementations1 Jan 2021 Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang

As a natural extension of DropBits, we further introduce the way of learning heterogeneous quantization levels to find proper bit-length for each layer using DropBits.

Quantization

Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing

no code implementations1 Jan 2021 Joonhyung Park, June Yong Yang, Jinwoo Shin, Sung Ju Hwang, Eunho Yang

By stochastically sampling the features and ‘grafting’ them onto another sample, our method effectively generates diverse yet meaningful samples.

Data Augmentation

Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning

1 code implementation ICLR 2021 Dong Bok Lee, Dongchan Min, Seanie Lee, Sung Ju Hwang

Then, the learned model can be used for downstream few-shot classification tasks, where we obtain task-specific parameters by performing semi-supervised EM on the latent representations of the support and query set, and predict labels of the query set by computing aggregated posteriors.

Meta-Learning Variational Inference

Meta-Learned Confidence for Transductive Few-shot Learning

no code implementations1 Jan 2021 Seong Min Kye, Hae Beom Lee, Hoirin Kim, Sung Ju Hwang

A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples, or confidence-weighted average of all the query samples.

Few-Shot Learning

Rapid Neural Pruning for Novel Datasets with Set-based Task-Adaptive Meta-Pruning

no code implementations1 Jan 2021 Minyoung Song, Jaehong Yoon, Eunho Yang, Sung Ju Hwang

As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of a given network.

Network Pruning

Contrastive Learning with Adversarial Perturbations for Conditional Text Generation

1 code implementation ICLR 2021 Seanie Lee, Dong Bok Lee, Sung Ju Hwang

In this work, we propose to mitigate the conditional text generation problem by contrasting positive pairs with negative pairs, such that the model is exposed to various valid or incorrect perturbations of the inputs, for improved generalization.

Conditional Text Generation Contrastive Learning +4

Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection

no code implementations7 Dec 2020 Byunggill Joe, Jihun Hamm, Sung Ju Hwang, Sooel Son, Insik Shin

Although deep neural networks have shown promising performances on various tasks, they are susceptible to incorrect predictions induced by imperceptibly small perturbations in inputs.

Attribution Preservation in Network Compression for Reliable Network Interpretation

1 code implementation NeurIPS 2020 Geondo Park, June Yong Yang, Sung Ju Hwang, Eunho Yang

Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for edge-computing.

Edge-computing Self-Driving Cars

Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation

1 code implementation EMNLP 2020 Minki Kang, Moonsu Han, Sung Ju Hwang

We propose a method to automatically generate a domain- and task-adaptive maskings of the given text for self-supervised pre-training, such that we can effectively adapt the language model to a particular target task (e. g. question answering).

Language Modelling Question Answering +1

Bootstrapping Neural Processes

1 code implementation NeurIPS 2020 Juho Lee, Yoonho Lee, Jungtaek Kim, Eunho Yang, Sung Ju Hwang, Yee Whye Teh

While this "data-driven" way of learning stochastic processes has proven to handle various types of data, NPs still rely on an assumption that uncertainty in stochastic processes is modeled by a single latent variable, which potentially limits the flexibility.

Neural Complexity Measures

1 code implementation NeurIPS 2020 Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi

While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven challenging.

Meta-Learning

Few-shot Visual Reasoning with Meta-analogical Contrastive Learning

no code implementations NeurIPS 2020 Youngsung Kim, Jinwoo Shin, Eunho Yang, Sung Ju Hwang

While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same task.

Contrastive Learning Visual Reasoning

Time-Reversal Symmetric ODE Network

1 code implementation NeurIPS 2020 In Huh, Eunho Yang, Sung Ju Hwang, Jinwoo Shin

Time-reversal symmetry, which requires that the dynamics of a system should not change with the reversal of time axis, is a fundamental property that frequently holds in classical and quantum mechanics.

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

1 code implementation NeurIPS 2020 Jaehyung Kim, Youngbum Hur, Sejun Park, Eunho Yang, Sung Ju Hwang, Jinwoo Shin

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced.

Learning to Sample with Local and Global Contexts in Experience Replay Buffer

no code implementations ICLR 2021 Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang, Sung Ju Hwang

Experience replay, which enables the agents to remember and reuse experience from the past, has played a significant role in the success of off-policy reinforcement learning (RL).

Stochastic Subset Selection for Efficient Training and Inference of Neural Networks

no code implementations25 Jun 2020 Bruno Andreis, A. Tuan Nguyen, Seanie Lee, Juho Lee, Eunho Yang, Sung Ju Hwang

We also show in our experiments that our method enhances scalability of nonparametric models such as Neural Processes.

Feature Selection Meta-Learning

Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning

1 code implementation23 Jun 2020 A. Tuan Nguyen, Hyewon Jeong, Eunho Yang, Sung Ju Hwang

Existing asymmetric multi-task learning methods tackle this negative transfer problem by performing knowledge transfer from tasks with low loss to tasks with high loss.

Knowledge Graphs Multi-Task Learning +2

Rapid Structural Pruning of Neural Networks with Set-based Task-Adaptive Meta-Pruning

no code implementations22 Jun 2020 Minyoung Song, Jaehong Yoon, Eunho Yang, Sung Ju Hwang

As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of a given network.

Network Pruning

Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning

1 code implementation ICLR 2021 Wonyong Jeong, Jaehong Yoon, Eunho Yang, Sung Ju Hwang

Through extensive experimental validation of our method in the two different scenarios, we show that our method outperforms both local semi-supervised learning and baselines which naively combine federated learning with semi-supervised learning.

Federated Learning

Learning to Generate Noise for Multi-Attack Robustness

1 code implementation22 Jun 2020 Divyam Madaan, Jinwoo Shin, Sung Ju Hwang

Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations.

Meta-Learning

Adversarial Self-Supervised Contrastive Learning

1 code implementation NeurIPS 2020 Minseon Kim, Jihoon Tack, Sung Ju Hwang

In this paper, we propose a novel adversarial attack for unlabeled data, which makes the model confuse the instance-level identities of the perturbed data samples.

Adversarial Attack Contrastive Learning +3

MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures

1 code implementation NeurIPS 2020 Jeongun Ryu, Jaewoong Shin, Hae Beom Lee, Sung Ju Hwang

As MetaPerturb is a set-function trained over diverse distributions across layers and tasks, it can generalize to heterogeneous tasks and architectures.

Fine-tuning Meta-Learning +1

Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

1 code implementation NeurIPS 2020 Jinheon Baek, Dong Bok Lee, Sung Ju Hwang

For transductive link prediction, we further propose a stochastic embedding layer to model uncertainty in the link prediction between unseen entities.

graph construction Knowledge Graph Completion +2

Cost-effective Interactive Attention Learning with Neural Attention Processes

2 code implementations9 Jun 2020 Jay Heo, Junhyeon Park, Hyewon Jeong, Kwang Joon Kim, Juho Lee, Eunho Yang, Sung Ju Hwang

Moreover, it is almost infeasible for the human annotators to examine attentions on tons of instances and features.

Time Series

Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs

1 code implementation ACL 2020 Dong Bok Lee, Seanie Lee, Woo Tae Jeong, Donghwan Kim, Sung Ju Hwang

We validate our Information Maximizing Hierarchical Conditional Variational AutoEncoder (Info-HCVAE) on several benchmark datasets by evaluating the performance of the QA model (BERT-base) using only the generated QA pairs (QA-based evaluation) or by using both the generated and human-labeled pairs (semi-supervised learning) for training, against state-of-the-art baseline models.

Latent Variable Models Question-Answer-Generation +2

Meta Dropout: Learning to Perturb Latent Features for Generalization

2 code implementations ICLR 2020 Hae Beom Lee, Taewook Nam, Eunho Yang, Sung Ju Hwang

Specifically, we meta-learn a noise generator which outputs a multiplicative noise distribution for latent features, to obtain low errors on the test instances in an input-dependent manner.

Meta-Learning

Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs

1 code implementation6 Apr 2020 Seong Min Kye, Youngmoon Jung, Hae Beom Lee, Sung Ju Hwang, Hoirin Kim

By combining these two learning schemes, our model outperforms existing state-of-the-art speaker verification models learned with a standard supervised learning framework on short utterance (1-2 seconds) on the VoxCeleb datasets.

Meta-Learning Speaker Identification +2

Federated Continual Learning with Weighted Inter-client Transfer

1 code implementation6 Mar 2020 Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang

There has been a surge of interest in continual learning and federated learning, both of which are important in deep neural networks in real-world scenarios.

Continual Learning Federated Learning +1

Meta-Learned Confidence for Few-shot Learning

1 code implementation27 Feb 2020 Seong Min Kye, Hae Beom Lee, Hoirin Kim, Sung Ju Hwang

To tackle this issue, we propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries such that they improve the model's transductive inference performance on unseen tasks.

Few-Shot Image Classification

Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bit-wise Regularization

no code implementations29 Nov 2019 Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang

As a natural extension of DropBits, we further introduce the way of learning heterogeneous quantization levels to find proper bit-length for each layer using DropBits.

Quantization

Self-supervised Label Augmentation via Input Transformations

1 code implementation ICML 2020 Hankook Lee, Sung Ju Hwang, Jinwoo Shin

Our main idea is to learn a single unified task with respect to the joint distribution of the original and self-supervised labels, i. e., we augment original labels via self-supervision of input transformation.

Data Augmentation imbalanced classification +2

Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection

no code implementations10 Sep 2019 Byunggill Joe, Sung Ju Hwang, Insik Shin

Yet, most of them cannot effectively defend against whitebox attacks where an adversary has a knowledge of the model and defense.

Adversarial Neural Pruning with Latent Vulnerability Suppression

1 code implementation ICML 2020 Divyam Madaan, Jinwoo Shin, Sung Ju Hwang

Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical applications.

Adversarial Robustness

Learning to Generalize to Unseen Tasks with Bilevel Optimization

no code implementations5 Aug 2019 Hayeon Lee, Donghyun Na, Hae Beom Lee, Sung Ju Hwang

To tackle this issue, we propose a simple yet effective meta-learning framework for metricbased approaches, which we refer to as learning to generalize (L2G), that explicitly constrains the learning on a sampled classification task to reduce the classification error on a randomly sampled unseen classification task with a bilevel optimization scheme.

bilevel optimization Classification +2

Reliable Estimation of Individual Treatment Effect with Causal Information Bottleneck

no code implementations7 Jun 2019 Sungyub Kim, Yongsu Baek, Sung Ju Hwang, Eunho Yang

We also introduce an additional form of a regularizer from the perspective of understanding ITE in the semi-supervised learning framework to ensure more reliable representations.

Causal Inference

Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks

1 code implementation ICLR 2020 Joonyoung Yi, Juhyuk Lee, Kwang Joon Kim, Sung Ju Hwang, Eunho Yang

Among many approaches, the simplest and most intuitive way is zero imputation, which treats the value of a missing entry simply as zero.

Collaborative Filtering Imputation

Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks

1 code implementation ICLR 2020 Hae Beom Lee, Hayeon Lee, Donghyun Na, Saehoon Kim, Minseop Park, Eunho Yang, Sung Ju Hwang

While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed.

Bayesian Inference Meta-Learning +1

Meta Dropout: Learning to Perturb Features for Generalization

1 code implementation30 May 2019 Hae Beom Lee, Taewook Nam, Eunho Yang, Sung Ju Hwang

Specifically, we meta-learn a noise generator which outputs a multiplicative noise distribution for latent features, to obtain low errors on the test instances in an input-dependent manner.

Meta-Learning

Learning What and Where to Transfer

4 code implementations15 May 2019 Yunhun Jang, Hankook Lee, Sung Ju Hwang, Jinwoo Shin

To address the issue, we propose a novel transfer learning approach based on meta-learning that can automatically learn what knowledge to transfer from the source network to where in the target network.

Meta-Learning Small Data Image Classification +1

Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data

1 code implementation ACL 2019 Moonsu Han, Minki Kang, Hyunwoo Jung, Sung Ju Hwang

We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, which is difficult to solve with existing QA methods due to their lack of scalability.

Question Answering Reading Comprehension

Scalable and Order-robust Continual Learning with Additive Parameter Decomposition

1 code implementation ICLR 2020 Jaehong Yoon, Saehoon Kim, Eunho Yang, Sung Ju Hwang

First, a continual learning model should effectively handle catastrophic forgetting and be efficient to train even with a large number of tasks.

Continual Learning Fairness +1

Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding

no code implementations NeurIPS 2018 Hajin Shim, Sung Ju Hwang, Eunho Yang

We consider the problem of active feature acquisition where the goal is to sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way at test time.

Classification General Classification

Learning the Compositional Spaces for Generalized Zero-shot Learning

no code implementations ICLR 2019 Hanze Dong, Yanwei Fu, Sung Ju Hwang, Leonid Sigal, xiangyang xue

This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time.

Generalized Zero-Shot Learning Open Set Learning

ADAPTIVE NETWORK SPARSIFICATION VIA DEPENDENT VARIATIONAL BETA-BERNOULLI DROPOUT

no code implementations27 Sep 2018 Juho Lee, Saehoon Kim, Jaehong Yoon, Hae Beom Lee, Eunho Yang, Sung Ju Hwang

With such input-independent dropout, each neuron is evolved to be generic across inputs, which makes it difficult to sparsify networks without accuracy loss.

Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss

no code implementations CVPR 2019 Sangil Jung, Changyong Son, Seohyung Lee, Jinwoo Son, Youngjun Kwak, Jae-Joon Han, Sung Ju Hwang, Changkyu Choi

We demonstrate the effectiveness of our trainable quantizer on ImageNet dataset with various network architectures such as ResNet-18, -34 and AlexNet, on which it outperforms existing methods to achieve the state-of-the-art accuracy.

Quantization

Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare

2 code implementations5 Jun 2018 Ingyo Chung, Saehoon Kim, Juho Lee, Kwang Joon Kim, Sung Ju Hwang, Eunho Yang

We present a personalized and reliable prediction model for healthcare, which can provide individually tailored medical services such as diagnosis, disease treatment, and prevention.

Gaussian Processes Time Series

Adaptive Network Sparsification with Dependent Variational Beta-Bernoulli Dropout

1 code implementation28 May 2018 Juho Lee, Saehoon Kim, Jaehong Yoon, Hae Beom Lee, Eunho Yang, Sung Ju Hwang

With such input-independent dropout, each neuron is evolved to be generic across inputs, which makes it difficult to sparsify networks without accuracy loss.

DropMax: Adaptive Stochastic Softmax

no code implementations ICLR 2018 Hae Beom Lee, Juho Lee, Eunho Yang, Sung Ju Hwang

Moreover, the learning of dropout probabilities for non-target classes on each instance allows the classifier to focus more on classification against the most confusing classes.

Classification General Classification +1

DropMax: Adaptive Variational Softmax

4 code implementations NeurIPS 2018 Hae Beom Lee, Juho Lee, Saehoon Kim, Eunho Yang, Sung Ju Hwang

Moreover, the learning of dropout rates for non-target classes on each instance allows the classifier to focus more on classification against the most confusing classes.

Classification General Classification +1

Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification

no code implementations18 Sep 2017 Hajin Shim, Sung Ju Hwang, Eunho Yang

We consider the problem of active feature acquisition, where we sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way.

General Classification

Lifelong Learning with Dynamically Expandable Networks

2 code implementations ICLR 2018 Jaehong Yoon, Eunho Yang, Jeongtae Lee, Sung Ju Hwang

We propose a novel deep network architecture for lifelong learning which we refer to as Dynamically Expandable Network (DEN), that can dynamically decide its network capacity as it trains on a sequence of tasks, to learn a compact overlapping knowledge sharing structure among tasks.

Deep Asymmetric Multi-task Feature Learning

1 code implementation ICML 2018 Hae Beom Lee, Eunho Yang, Sung Ju Hwang

We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process.

Image Classification Transfer Learning

Combined Group and Exclusive Sparsity for Deep Neural Networks

1 code implementation ICML 2017 Jaehong Yoon, Sung Ju Hwang

The number of parameters in a deep neural network is usually very large, which helps with its learning capacity but also hinders its scalability and practicality due to memory/time inefficiency and overfitting.

Expanding Object Detector's Horizon: Incremental Learning Framework for Object Detection in Videos

no code implementations CVPR 2015 Alina Kuznetsova, Sung Ju Hwang, Bodo Rosenhahn, Leonid Sigal

By incrementally detecting object instances in video and adding confident detections into the model, we are able to dynamically adjust the complexity of the detector over time by instantiating new prototypes to span all domains the model has seen.

Domain Adaptation Incremental Learning +1

Hierarchical Maximum-Margin Clustering

no code implementations6 Feb 2015 Guang-Tong Zhou, Sung Ju Hwang, Mark Schmidt, Leonid Sigal, Greg Mori

We present a hierarchical maximum-margin clustering method for unsupervised data analysis.

A Unified Semantic Embedding: Relating Taxonomies and Attributes

no code implementations NeurIPS 2014 Sung Ju Hwang, Leonid Sigal

We propose a method that learns a discriminative yet semantic space for object categorization, where we also embed auxiliary semantic entities such as supercategories and attributes.

Semantic Kernel Forests from Multiple Taxonomies

no code implementations NeurIPS 2012 Sung Ju Hwang, Kristen Grauman, Fei Sha

When learning features for complex visual recognition problems, labeled image exemplars alone can be insufficient.

Object Recognition

Learning a Tree of Metrics with Disjoint Visual Features

no code implementations NeurIPS 2011 Kristen Grauman, Fei Sha, Sung Ju Hwang

Given a hierarchical taxonomy that captures semantic similarity between the objects, we learn a corresponding tree of metrics (ToM).

Metric Learning Semantic Similarity +1

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