1 code implementation • 2 Apr 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).
no code implementations • 16 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.
1 code implementation • 12 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.
no code implementations • 20 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.
no code implementations • 6 Feb 2024 • Daechul Ahn, Yura Choi, Youngjae Yu, Dongyeop Kang, Jonghyun Choi
Recent advancements in large language models have influenced the development of video large multimodal models (VLMMs).
no code implementations • 16 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.
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).
no code implementations • 18 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.
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.
no code implementations • ICCV 2023 • Byeonghwi Kim, Jinyeon Kim, Yuyeong Kim, Cheolhong Min, Jonghyun Choi
Accomplishing household tasks requires to plan step-by-step actions considering the consequences of previous actions.
1 code implementation • 11 Aug 2023 • Xinyue Ma, Suyeon Jeong, Minjia Zhang, Di Wang, Jonghyun Choi, Myeongjae Jeon
Continual learning (CL) trains NN models incrementally from a continuous stream of tasks.
1 code implementation • 11 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.
1 code implementation • 4 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.
1 code implementation • 18 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.
1 code implementation • CVPR 2022 • Junghun Oh, Heewon Kim, Seungjun Nah, Cheeun Hong, Jonghyun Choi, Kyoung Mu Lee
Image restoration tasks have witnessed great performance improvement in recent years by developing large deep models.
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.
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.
1 code implementation • EMNLP 2021 • Christopher Clark, Jordi Salvador, Dustin Schwenk, Derrick Bonafilia, Mark Yatskar, Eric Kolve, Alvaro Herrasti, Jonghyun Choi, Sachin Mehta, Sam Skjonsberg, Carissa Schoenick, Aaron Sarnat, Hannaneh Hajishirzi, Aniruddha Kembhavi, Oren Etzioni, Ali Farhadi
We investigate these challenges in the context of Iconary, a collaborative game of drawing and guessing based on Pictionary, that poses a novel challenge for the research community.
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.
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.
1 code implementation • 16 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.
1 code implementation • 14 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.
no code implementations • 29 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.
no code implementations • 29 Sep 2021 • Jihwan Bang, Hyunseo Koh, Seulki Park, Hwanjun Song, Jung-Woo Ha, Jonghyun Choi
Specifically, we argue the importance of both diversity and purity of examples in the episodic memory of continual learning models.
1 code implementation • ICCV 2021 • Yeonsik Jo, Se Young Chun, Jonghyun Choi
Deep image prior (DIP) serves as a good inductive bias for diverse inverse problems.
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.
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.
no code implementations • ICCV 2021 • Mohammad Mostafavi, Kuk-Jin Yoon, Jonghyun Choi
Event cameras can report scene movements as an asynchronous stream of data called the events.
no code implementations • 1 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.
Ranked #177 on Image Classification on CIFAR-100
no code implementations • 1 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.
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.
1 code implementation • 3 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.
Ranked #19 on Object Detection on PASCAL VOC 2007
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.
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.
no code implementations • 3 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.
no code implementations • 1 Jan 2019 • Tae-hoon Kim, Dongmin Kang, Kari Pulli, Jonghyun Choi
High-performance visual recognition systems generally require a large collection of labeled images to train.
no code implementations • 3 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.
no code implementations • CVPR 2018 • Jonghyun Choi, Jayant Krishnamurthy, Aniruddha Kembhavi, Ali Farhadi
Diagrams often depict complex phenomena and serve as a good test bed for visual and textual reasoning.
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.
no code implementations • 9 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.
Ranked #69 on Action Recognition on HMDB-51
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.
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.
Ranked #2 on Traffic Accident Detection on A3D
no code implementations • 5 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.
1 code implementation • 21 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.
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.