211 citations · 661 across the 23 of their papers we have counts for
24 papers
Query-Efficient Black-Box Red Teaming via Bayesian Optimization
Deokjae Lee, JunYeong Lee, Jung-Woo Ha +4
The deployment of large-scale generative models is often restricted by their potential risk of causing harm to users in unpredictable ways. We focus on the problem of black-box red…
Direct Preference-based Policy Optimization without Reward Modeling
Gaon An, Junhyeok Lee, Xingdong Zuo +3
Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is ch…
Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
Jang-Hyun Kim, Sangdoo Yun, Hyun Oh Song
Diagnosing and cleaning data is a crucial step for building robust machine learning systems. However, identifying problems within large-scale datasets with real-world distributions…
Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
Jinuk Kim, Yeonwoo Jeong, Deokjae Lee +1
Recent works on neural network pruning advocate that reducing the depth of the network is more effective in reducing run-time memory usage and accelerating inference latency than r…
Rethinking Value Function Learning for Generalization in Reinforcement Learning
Seungyong Moon, JunYeong Lee, Hyun Oh Song
Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance. In prior methods, policy and value networks ar…
Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Deokjae Lee, Seungyong Moon, Junhyeok Lee +1
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 limite…
Dataset Condensation via Efficient Synthetic-Data Parameterization
Jang-Hyun Kim, Jinuk Kim, Seong Joon Oh +5
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. Recent studies on dataset condens…
Optimal channel selection with discrete QCQP
Yeonwoo Jeong, Deokjae Lee, Gaon An +2
Reducing the high computational cost of large convolutional neural networks is crucial when deploying the networks to resource-constrained environments. We first show the greedy ap…
Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks
Seungyong Moon, Gaon An, Hyun Oh Song
Deep neural networks have become the driving force of modern image recognition systems. However, the vulnerability of neural networks against adversarial attacks poses a serious th…
Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble
Gaon An, Seungyong Moon, Jang-Hyun Kim +1
Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approxi…
Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
Jang-Hyun Kim, Wonho Choo, Hosan Jeong +1
While deep neural networks show great performance on fitting to the training distribution, improving the networks' generalization performance to the test distribution and robustnes…
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
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.…
Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
Yeonwoo Jeong, Hyun Oh Song
We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation…
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
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. However, in the black…
End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization
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 perform…
EMI: Exploration with Mutual Information
Hyoungseok Kim, Jaekyeom Kim, Yeonwoo Jeong +2
Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto…
Efficient end-to-end learning for quantizable representations
Yeonwoo Jeong, Hyun Oh Song
Embedding representation learning via neural networks is at the core foundation of modern similarity based search. While much effort has been put in developing algorithms for learn…
Semantic Instance Segmentation via Deep Metric Learning
Alireza Fathi, Zbigniew Wojna, Vivek Rathod +4
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.…
Deep Metric Learning via Facility Location
Hyun Oh Song, Stefanie Jegelka, Vivek Rathod +1
Learning the representation and the similarity metric in an end-to-end fashion with deep networks have demonstrated outstanding results for clustering and retrieval. However, these…
Unsupervised Transductive Domain Adaptation
Ozan Sener, Hyun Oh Song, Ashutosh Saxena +1
Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still s…
Deep Metric Learning via Lifted Structured Feature Embedding
Hyun Oh Song, Yu Xiang, Stefanie Jegelka +1
Learning the distance metric between pairs of examples is of great importance for learning and visual recognition. With the remarkable success from the state of the art convolution…
Weakly-supervised Discovery of Visual Pattern Configurations
Hyun Oh Song, Yong Jae Lee, Stefanie Jegelka +1
The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automati…
Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition
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…
On learning to localize objects with minimal supervision
Hyun Oh Song, Ross Girshick, Stefanie Jegelka +3
Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain. In this paper…