Search Results for author: Hyun Oh Song

Found 29 papers, 16 papers with code

Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning

no code implementations7 Jul 2023 Seungyong Moon, Junyoung Yeom, Bumsoo Park, Hyun Oh Song

Our method exhibits a strong capacity for discovering hierarchical achievements and shows state-of-the-art performance on the challenging Crafter environment using fewer model parameters in a sample-efficient regime.

Contrastive Learning reinforcement-learning

Query-Efficient Black-Box Red Teaming via Bayesian Optimization

1 code implementation27 May 2023 Deokjae Lee, JunYeong Lee, Jung-Woo Ha, Jin-Hwa Kim, Sang-Woo Lee, Hwaran Lee, Hyun Oh Song

To this end, we propose Bayesian red teaming (BRT), novel query-efficient black-box red teaming methods based on Bayesian optimization, which iteratively identify diverse positive test cases leading to model failures by utilizing the pre-defined user input pool and the past evaluations.

Bayesian Optimization Language Modelling

Designing an offline reinforcement learning objective from scratch

no code implementations30 Jan 2023 Gaon An, Junhyeok Lee, Xingdong Zuo, Norio Kosaka, Kyung-Min Kim, Hyun Oh Song

Offline reinforcement learning has developed rapidly over the recent years, but estimating the actual performance of offline policies still remains a challenge.

Contrastive Learning reinforcement-learning +1

Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data

no code implementations29 Jan 2023 Jang-Hyun Kim, Sangdoo Yun, Hyun Oh Song

In this paper, we propose a unified approach for identifying the problematic data by utilizing a largely ignored source of information: a relational structure of data in the feature-embedded space.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming

1 code implementation28 Jan 2023 Jinuk Kim, Yeonwoo Jeong, Deokjae Lee, Hyun Oh Song

We propose a subset selection problem that replaces inefficient activation layers with identity functions and optimally merges consecutive convolution operations into shallow equivalent convolution operations for efficient end-to-end inference latency.

Network Pruning Vocal Bursts Valence Prediction

Rethinking Value Function Learning for Generalization in Reinforcement Learning

1 code implementation18 Oct 2022 Seungyong Moon, JunYeong Lee, Hyun Oh Song

Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance.

reinforcement-learning Reinforcement Learning (RL)

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization

1 code implementation17 Jun 2022 Deokjae Lee, Seungyong Moon, Junhyeok Lee, Hyun Oh Song

We focus on the problem of adversarial attacks against models on discrete sequential data in the black-box setting where the attacker aims to craft adversarial examples with limited query access to the victim model.

Bayesian Optimization

Dataset Condensation via Efficient Synthetic-Data Parameterization

2 code implementations30 May 2022 Jang-Hyun Kim, Jinuk Kim, Seong Joon Oh, Sangdoo Yun, Hwanjun Song, JoonHyun Jeong, Jung-Woo Ha, Hyun Oh Song

The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning.

Dataset Condensation

Optimal channel selection with discrete QCQP

no code implementations24 Feb 2022 Yeonwoo Jeong, Deokjae Lee, Gaon An, Changyong Son, Hyun Oh Song

We first show the greedy approach of recent channel pruning methods ignores the inherent quadratic coupling between channels in the neighboring layers and cannot safely remove inactive weights during the pruning procedure.

Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks

1 code implementation10 Dec 2021 Seungyong Moon, Gaon An, Hyun Oh Song

However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these systems.

Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble

4 code implementations NeurIPS 2021 Gaon An, Seungyong Moon, Jang-Hyun Kim, Hyun Oh Song

However, prior methods typically require accurate estimation of the behavior policy or sampling from OOD data points, which themselves can be a non-trivial problem.

Adroid door-cloned Adroid door-human +18

Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity

1 code implementation ICLR 2021 Jang-Hyun Kim, Wonho Choo, Hosan Jeong, Hyun Oh Song

While deep neural networks show great performance on fitting to the training distribution, improving the networks' generalization performance to the test distribution and robustness to the sensitivity to input perturbations still remain as a challenge.

Exploiting Safe Spots in Neural Networks for Preemptive Robustness and Out-of-Distribution Detection

no code implementations1 Jan 2021 Seungyong Moon, Gaon An, Hyun Oh Song

Recent advances on adversarial defense mainly focus on improving the classifier’s robustness against adversarially perturbed inputs.

Adversarial Defense Out-of-Distribution Detection

Succinct Network Channel and Spatial Pruning via Discrete Variable QCQP

no code implementations1 Jan 2021 Yeonwoo Jeong, Deokjae Lee, Gaon An, Changyong Son, Hyun Oh Song

Reducing the heavy computational cost of large convolutional neural networks is crucial when deploying the networks to resource-constrained environments.

Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup

1 code implementation ICML 2020 Jang-Hyun Kim, Wonho Choo, Hyun Oh Song

While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks.

Adversarial Robustness Image Classification +1

Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

1 code implementation23 May 2019 Yeonwoo Jeong, Hyun Oh Song

Furthermore, we propose a method which avoids offloading the entire burden of jointly modeling the continuous and discrete factors to the variational encoder by employing a separate discrete inference procedure.


Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization

1 code implementation16 May 2019 Seungyong Moon, Gaon An, Hyun Oh Song

Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers.

Combinatorial Optimization

End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization

no code implementations CVPR 2019 Yeonwoo Jeong, Yoonsung Kim, Hyun Oh Song

We develop hierarchically quantized efficient embedding representations for similarity-based search and show that this representation provides not only the state of the art performance on the search accuracy but also provides several orders of speed up during inference.

Combinatorial Optimization Quantization +1

EMI: Exploration with Mutual Information

1 code implementation2 Oct 2018 Hyoungseok Kim, Jaekyeom Kim, Yeonwoo Jeong, Sergey Levine, Hyun Oh Song

Reinforcement learning algorithms struggle when the reward signal is very sparse.

Continuous Control Reinforcement Learning (RL)

EMI: Exploration with Mutual Information Maximizing State and Action Embeddings

no code implementations27 Sep 2018 HyoungSeok Kim, Jaekyeom Kim, Yeonwoo Jeong, Sergey Levine, Hyun Oh Song

Policy optimization struggles when the reward feedback signal is very sparse and essentially becomes a random search algorithm until the agent stumbles upon a rewarding or the goal state.

Continuous Control

Efficient end-to-end learning for quantizable representations

1 code implementation ICML 2018 Yeonwoo Jeong, Hyun Oh Song

To this end, we consider the problem of directly learning a quantizable embedding representation and the sparse binary hash code end-to-end which can be used to construct an efficient hash table not only providing significant search reduction in the number of data but also achieving the state of the art search accuracy outperforming previous state of the art deep metric learning methods.

Binarization Metric Learning +1

Semantic Instance Segmentation via Deep Metric Learning

1 code implementation30 Mar 2017 Alireza Fathi, Zbigniew Wojna, Vivek Rathod, Peng Wang, Hyun Oh Song, Sergio Guadarrama, Kevin P. Murphy

We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together.

Instance Segmentation Metric Learning +2

Deep Metric Learning via Facility Location

1 code implementation CVPR 2017 Hyun Oh Song, Stefanie Jegelka, Vivek Rathod, Kevin Murphy

Learning the representation and the similarity metric in an end-to-end fashion with deep networks have demonstrated outstanding results for clustering and retrieval.

Clustering Metric Learning +2

Learning Transferrable Representations for Unsupervised Domain Adaptation

no code implementations NeurIPS 2016 Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese

Supervised learning with large scale labelled datasets and deep layered models has caused a paradigm shift in diverse areas in learning and recognition.

Object Recognition Unsupervised Domain Adaptation

Unsupervised Transductive Domain Adaptation

no code implementations10 Feb 2016 Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese

We incorporate the domain shift and the transductive target inference into our framework by jointly solving for an asymmetric similarity metric and the optimal transductive target label assignment.

Object Recognition Unsupervised Domain Adaptation

Deep Metric Learning via Lifted Structured Feature Embedding

3 code implementations CVPR 2016 Hyun Oh Song, Yu Xiang, Stefanie Jegelka, Silvio Savarese

Additionally, we collected Online Products dataset: 120k images of 23k classes of online products for metric learning.

Metric Learning Structured Prediction

Weakly-supervised Discovery of Visual Pattern Configurations

no code implementations NeurIPS 2014 Hyun Oh Song, Yong Jae Lee, Stefanie Jegelka, Trevor Darrell

The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision.

object-detection Object Detection

Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition

no code implementations28 May 2014 Tim Althoff, Hyun Oh Song, Trevor Darrell

While low-level image features have proven to be effective representations for visual recognition tasks such as object recognition and scene classification, they are inadequate to capture complex semantic meaning required to solve high-level visual tasks such as multimedia event detection and recognition.

Event Detection object-detection +4

On learning to localize objects with minimal supervision

no code implementations5 Mar 2014 Hyun Oh Song, Ross Girshick, Stefanie Jegelka, Julien Mairal, Zaid Harchaoui, Trevor Darrell

Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain.

Weakly Supervised Object Detection

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