Search Results for author: Jonghyun Choi

Found 46 papers, 25 papers with code

An Information Theoretic Metric for Evaluating Unlearning Models

no code implementations28 May 2024 Dongjae Jeon, Wonje Jeung, Taeheon Kim, Albert No, Jonghyun Choi

The IDI provides a comprehensive evaluation of MU methods by efficiently analyzing the internal structure of DNNs.

CoLA Machine Unlearning +1

Learning Equi-angular Representations for Online Continual Learning

1 code implementation CVPR 2024 Minhyuk Seo, Hyunseo Koh, Wonje Jeung, Minjae Lee, San Kim, Hankook Lee, Sungjun Cho, Sungik Choi, Hyunwoo Kim, Jonghyun Choi

Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e. g., single-epoch training).

Continual Learning

Just Say the Name: Online Continual Learning with Category Names Only via Data Generation

no code implementations16 Mar 2024 Minhyuk Seo, Diganta Misra, Seongwon Cho, Minjae Lee, Jonghyun Choi

In real-world scenarios, extensive manual annotation for continual learning is impractical due to prohibitive costs.

Continual Learning

Online Continual Learning For Interactive Instruction Following Agents

1 code implementation12 Mar 2024 Byeonghwi Kim, Minhyuk Seo, Jonghyun Choi

To take a step towards a more realistic embodied agent learning scenario, we propose two continual learning setups for embodied agents; learning new behaviors (Behavior Incremental Learning, Behavior-IL) and new environments (Environment Incremental Learning, Environment-IL) For the tasks, previous 'data prior' based continual learning methods maintain logits for the past tasks.

Continual Learning Incremental Learning +1

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images

no code implementations20 Feb 2024 Jinsung Jeon, Hyundong Jin, Jonghyun Choi, Sanghyun Hong, Dongeun Lee, Kookjin Lee, Noseong Park

Extensively evaluating methods with seven image recognition benchmarks, we show that the proposed PAC-FNO improves the performance of existing baseline models on images with various resolutions by up to 77. 1% and various types of natural variations in the images at inference.

Operator-learning-inspired Modeling of Neural Ordinary Differential Equations

no code implementations16 Dec 2023 Woojin Cho, Seunghyeon Cho, Hyundong Jin, Jinsung Jeon, Kookjin Lee, Sanghyun Hong, Dongeun Lee, Jonghyun Choi, Noseong Park

Neural ordinary differential equations (NODEs), one of the most influential works of the differential equation-based deep learning, are to continuously generalize residual networks and opened a new field.

Image Classification Image Generation +3

Online Continual Learning on Hierarchical Label Expansion

no code implementations ICCV 2023 Byung Hyun Lee, Okchul Jung, Jonghyun Choi, Se Young Chun

To address this challenge, we propose a novel multi-level hierarchical class incremental task configuration with an online learning constraint, called hierarchical label expansion (HLE).

Continual Learning

Multi-Level Compositional Reasoning for Interactive Instruction Following

no code implementations18 Aug 2023 Suvaansh Bhambri, Byeonghwi Kim, Jonghyun Choi

At the middle level, we discriminatively control the agent's navigation by a master policy by alternating between a navigation policy and various independent interaction policies.

Instruction Following

Story Visualization by Online Text Augmentation with Context Memory

1 code implementation ICCV 2023 Daechul Ahn, Daneul Kim, Gwangmo Song, Seung Hwan Kim, Honglak Lee, Dongyeop Kang, Jonghyun Choi

Story visualization (SV) is a challenging text-to-image generation task for the difficulty of not only rendering visual details from the text descriptions but also encoding a long-term context across multiple sentences.

Sentence Story Visualization +2

EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models

1 code implementation11 Jun 2023 Hanwool Lee, Jonghyun Choi, Sohyeon Kwon, Sungbum Jung

These outcomes underscore the effectiveness of our methodology in identifying ESG issues in news articles across different languages.

Knowledge Distillation Position

MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds

1 code implementation4 Apr 2023 Ashish Sinha, Jonghyun Choi

Unsupervised domain adaptation (UDA) addresses the problem of distribution shift between the unlabelled target domain and labelled source domain.

Autonomous Driving Multi-target Domain Adaptation +1

Ask4Help: Learning to Leverage an Expert for Embodied Tasks

1 code implementation18 Nov 2022 Kunal Pratap Singh, Luca Weihs, Alvaro Herrasti, Jonghyun Choi, Aniruddha Kemhavi, Roozbeh Mottaghi

Embodied AI agents continue to become more capable every year with the advent of new models, environments, and benchmarks, but are still far away from being performant and reliable enough to be deployed in real, user-facing, applications.

Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries

2 code implementations CVPR 2022 Jihwan Bang, Hyunseo Koh, Seulki Park, Hwanjun Song, Jung-Woo Ha, Jonghyun Choi

A large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored.

Continual Learning

Stereo Depth From Events Cameras: Concentrate and Focus on the Future

1 code implementation CVPR 2022 Yeongwoo Nam, Mohammad Mostafavi, Kuk-Jin Yoon, Jonghyun Choi

To alleviate the event missing or overriding issue, we propose to learn to concentrate on the dense events to produce a compact event representation with high details for depth estimation.

Depth Estimation

Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference

1 code implementation ICLR 2022 Hyunseo Koh, Dahyun Kim, Jung-Woo Ha, Jonghyun Choi

For better practicality, we first propose a novel continual learning setup that is online, task-free, class-incremental, of blurry task boundaries and subject to inference queries at any moment.

Continual Learning Management

Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning

1 code implementation CVPR 2022 Dahyun Kim, Jonghyun Choi

To accelerate deployment of models with the benefit of unsupervised representation learning to such resource limited devices for various downstream tasks, we propose a self-supervised learning method for binary networks that uses a moving target network.

Representation Learning Self-Supervised Learning

BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements

1 code implementation16 Oct 2021 Dahyun Kim, Kunal Pratap Singh, Jonghyun Choi

Questioning that the architectures designed for FP networks might not be the best for binary networks, we propose to search architectures for binary networks (BNAS) by defining a new search space for binary architectures and a novel search objective.

Quantization

Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning

1 code implementation14 Oct 2021 Soobee Lee, Minindu Weerakoon, Jonghyun Choi, Minjia Zhang, Di Wang, Myeongjae Jeon

In particular, in mobile and IoT devices, real-time data can be stored not just in high-speed RAMs but in internal storage devices as well, which offer significantly larger capacity than the RAMs.

Continual Learning Management

Hierarchical Modular Framework for Long Horizon Instruction Following

no code implementations29 Sep 2021 Suvaansh Bhambri, Byeonghwi Kim, Roozbeh Mottaghi, Jonghyun Choi

To address such composite tasks, we propose a hierarchical modular approach to learn agents that navigate and manipulate objects in a divide-and-conquer manner for the diverse nature of the entailing tasks.

Instruction Following Navigate

Zero-shot Natural Language Video Localization

1 code implementation ICCV 2021 Jinwoo Nam, Daechul Ahn, Dongyeop Kang, Seong Jong Ha, Jonghyun Choi

Understanding videos to localize moments with natural language often requires large expensive annotated video regions paired with language queries.

Image Captioning

Rainbow Memory: Continual Learning with a Memory of Diverse Samples

1 code implementation CVPR 2021 Jihwan Bang, Heesu Kim, Youngjoon Yoo, Jung-Woo Ha, Jonghyun Choi

Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial.

Continual Learning Data Augmentation +1

Learning to Solve Nonlinear Partial Differential Equation Systems To Accelerate MOSFET Simulation

no code implementations1 Jan 2021 Seungcheol Han, Jonghyun Choi, Sung-Min Hong

In order to accelerate the semiconductor device simulation, we propose to use a neural network to learn an approximate solution for desired boundary conditions.

Learning the Connections in Direct Feedback Alignment

no code implementations1 Jan 2021 Matthew Bailey Webster, Jonghyun Choi, changwook Ahn

We propose to learn the backward weight matrices in DFA, adopting the methodology of Kolen-Pollack learning, to improve training and inference accuracy in deep convolutional neural networks by updating the direct feedback connections such that they come to estimate the forward path.

Image Classification

Factorizing Perception and Policy for Interactive Instruction Following

1 code implementation ICCV 2021 Kunal Pratap Singh, Suvaansh Bhambri, Byeonghwi Kim, Roozbeh Mottaghi, Jonghyun Choi

Performing simple household tasks based on language directives is very natural to humans, yet it remains an open challenge for AI agents.

Instruction Following Navigate

Learning Visual Representations for Transfer Learning by Suppressing Texture

1 code implementation3 Nov 2020 Shlok Mishra, Anshul Shah, Ankan Bansal, Janit Anjaria, Jonghyun Choi, Abhinav Shrivastava, Abhishek Sharma, David Jacobs

Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information.

Image Classification object-detection +3

Learning Architectures for Binary Networks

1 code implementation ECCV 2020 Dahyun Kim, Kunal Pratap Singh, Jonghyun Choi

Specifically, based on the cell based search method, we define the new search space of binary layer types, design a new cell template, and rediscover the utility of and propose to use the Zeroise layer instead of using it as a placeholder.

Quantization

Learning to Super Resolve Intensity Images from Events

1 code implementation CVPR 2020 S. Mohammad Mostafavi I., Jonghyun Choi, Kuk-Jin Yoon

An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic range, and low power consumption.

Image Reconstruction Super-Resolution

Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence

no code implementations3 Feb 2019 Dahyun Kim, Jihwan Bae, Yeonsik Jo, Jonghyun Choi

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge.

Incremental Learning Transfer Learning

ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks

no code implementations3 Jan 2018 Tae-hoon Kim, Jonghyun Choi

We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called ScreenerNet.

Q-Learning

Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension

no code implementations CVPR 2017 Aniruddha Kembhavi, Minjoon Seo, Dustin Schwenk, Jonghyun Choi, Ali Farhadi, Hannaneh Hajishirzi

Our analysis shows that a significant portion of questions require complex parsing of the text and the diagrams and reasoning, indicating that our dataset is more complex compared to previous machine comprehension and visual question answering datasets.

Question Answering Reading Comprehension +1

ActionFlowNet: Learning Motion Representation for Action Recognition

no code implementations9 Dec 2016 Joe Yue-Hei Ng, Jonghyun Choi, Jan Neumann, Larry S. Davis

Even with the recent advances in convolutional neural networks (CNN) in various visual recognition tasks, the state-of-the-art action recognition system still relies on hand crafted motion feature such as optical flow to achieve the best performance.

Action Recognition Optical Flow Estimation +1

Mining Discriminative Triplets of Patches for Fine-Grained Classification

no code implementations CVPR 2016 Yaming Wang, Jonghyun Choi, Vlad I. Morariu, Larry S. Davis

Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions; therefore, accurate localization of discriminative regions remains a major challenge.

Classification General Classification

Learning Temporal Regularity in Video Sequences

2 code implementations CVPR 2016 Mahmudul Hasan, Jonghyun Choi, Jan Neumann, Amit K. Roy-Chowdhury, Larry S. Davis

Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene.

Semi-supervised Anomaly Detection Video Anomaly Detection

Comparing apples to apples in the evaluation of binary coding methods

no code implementations5 May 2014 Mohammad Rastegari, Shobeir Fakhraei, Jonghyun Choi, David Jacobs, Larry S. Davis

We discuss methodological issues related to the evaluation of unsupervised binary code construction methods for nearest neighbor search.

Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition

1 code implementation21 Jan 2014 Changxing Ding, Jonghyun Choi, DaCheng Tao, Larry S. Davis

To perform unconstrained face recognition robust to variations in illumination, pose and expression, this paper presents a new scheme to extract "Multi-Directional Multi-Level Dual-Cross Patterns" (MDML-DCPs) from face images.

Face Identification Face Recognition +2

Adding Unlabeled Samples to Categories by Learned Attributes

no code implementations CVPR 2013 Jonghyun Choi, Mohammad Rastegari, Ali Farhadi, Larry S. Davis

We propose a method to expand the visual coverage of training sets that consist of a small number of labeled examples using learned attributes.

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