1 code implementation • 14 Mar 2024 • Dinh Phat Do, TaeHoon Kim, Jaemin Na, Jiwon Kim, Keonho Lee, Kyunghwan Cho, Wonjun Hwang
However, there are limited studies on adapting from the visible to the thermal domain, because the domain gap between the visible and thermal domains is much larger than expected, and traditional domain adaptation can not successfully facilitate learning in this situation.
1 code implementation • 27 Feb 2024 • Tyler L. Hayes, César R. de Souza, Namil Kim, Jiwon Kim, Riccardo Volpi, Diane Larlus
In this work, we look at ways to extend a detector trained for a set of base classes so it can i) spot the presence of novel classes, and ii) automatically enrich its repertoire to be able to detect those newly discovered classes together with the base ones.
no code implementations • 9 Jan 2024 • Binh M. Le, Jiwon Kim, Shahroz Tariq, Kristen Moore, Alsharif Abuadbba, Simon S. Woo
Our systematized analysis and experimentation lay the groundwork for a deeper understanding of deepfake detectors and their generalizability, paving the way for future research focused on creating detectors adept at countering various attack scenarios.
no code implementations • 30 Nov 2023 • Jiwon Kim, Byeongho Heo, Sangdoo Yun, Seungryong Kim, Dongyoon Han
Recent approaches for semantic correspondence have focused on obtaining high-quality correspondences using a complicated network, refining the ambiguous or noisy matching points.
no code implementations • 28 Nov 2023 • Daeun Lee, Minhyeok Heo, Jiwon Kim
Lane detection is a vital task for vehicles to navigate and localize their position on the road.
no code implementations • 24 May 2023 • Daehee Park, Hobin Ryu, Yunseo Yang, Jegyeong Cho, Jiwon Kim, Kuk-Jin Yoon
We also model the interaction using a probabilistic distribution, which allows for multiple possible future interactions.
Ranked #2 on Trajectory Prediction on nuScenes
no code implementations • 2 Jan 2023 • Jiwon Kim, Moon-Ju Kang, KangHun Lee, HyungJun Moon, Bo-Kwan Jeon
Recently, there are many trials to apply reinforcement learning in asset allocation for earning more stable profits.
no code implementations • 6 Dec 2022 • Jiwon Kim, Kai Zheng, Jonathan Corcoran, Sanghyung Ahn, Marty Papamanolis
First, we partition the entire network into a set of cells based on the spatial distribution of data points in individual trajectories, where the cells represent spatial regions between which aggregated traffic flows can be measured.
no code implementations • 14 Nov 2022 • Eren Arkangil, Mehmet Yildirimoglu, Jiwon Kim, Carlo Prato
Census and Household Travel Survey datasets are regularly collected from households and individuals and provide information on their daily travel behavior with demographic and economic characteristics.
1 code implementation • 18 Aug 2022 • Jiwon Kim, Youngjo Min, Daehwan Kim, Gyuseong Lee, Junyoung Seo, Kwangrok Ryoo, Seungryong Kim
We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label, dubbed ConMatch.
no code implementations • 26 Jun 2022 • Miner Zhong, Jiwon Kim, Zuduo Zheng
To ensure the generated population vehicle trajectories are consistent with the observed traffic volume and trajectory data, two methods based on Inverse Reinforcement Learning and Constrained Reinforcement Learning are proposed.
no code implementations • 5 Apr 2022 • Jiwon Kim, Youngjo Min, Mira Kim, Seungryong Kim
In this paper, we propose a novel framework for jointly learning feature extraction and cost aggregation for semantic correspondence.
no code implementations • CVPR 2022 • Jiwon Kim, Kwangrok Ryoo, Junyoung Seo, Gyuseong Lee, Daehwan Kim, Hansang Cho, Seungryong Kim
In this paper, we present a simple, but effective solution for semantic correspondence that learns the networks in a semi-supervised manner by supplementing few ground-truth correspondences via utilization of a large amount of confident correspondences as pseudo-labels, called SemiMatch.
no code implementations • 25 Jan 2022 • Jiwon Kim, Kwangrok Ryoo, Gyuseong Lee, Seokju Cho, Junyoung Seo, Daehwan Kim, Hansang Cho, Seungryong Kim
In this paper, we address this limitation with a novel SSL framework for aggregating pseudo labels, called AggMatch, which refines initial pseudo labels by using different confident instances.
1 code implementation • 26 Aug 2021 • Yoon Kyung Lee, Inju Lee, Jae Eun Park, Yoonwon Jung, Jiwon Kim, Sowon Hahn
Sentences that successfully take the perspective of others (the highest ToM level) were the most difficult to predict.
no code implementations • 1 Aug 2021 • Zhixiong Jin, Jiwon Kim, Hwasoo Yeo, Seongjin Choi
In many spatial trajectory-based applications, it is necessary to map raw trajectory data points onto road networks in digital maps, which is commonly referred to as a map-matching process.
1 code implementation • IEEE ROBOTICS AND AUTOMATION LETTERS 2021 • Jiwon Kim, Hyeongjun Kim, Taejoo Kim, Namil Kim, Yukyung Choi
In this letter, we tackle multispectral pedestrian detection, where all input data are not paired.
no code implementations • 1 Jan 2021 • Duhyeon Bang, Yunho Jeon, Jin-Hwa Kim, Jiwon Kim, Hyunjung Shim
When a person identifies objects, he or she can think by associating objects to many classes and conclude by taking inter-class relations into account.
no code implementations • 7 Aug 2020 • Youngeun Kim, Sungeun Hong, Seunghan Yang, Sungil Kang, Yunho Jeon, Jiwon Kim
Our Associative Partial Domain Adaptation (APDA) utilizes intra-domain association to actively select out non-trivial anomaly samples in each source-private class that sample-level weighting cannot handle.
1 code implementation • 28 Jul 2020 • Seongjin Choi, Jiwon Kim, Hwasoo Yeo
A generative model for urban vehicle trajectories can better generalize from training data by learning the underlying distribution of the training data and, thus, produce synthetic vehicle trajectories similar to real vehicle trajectories with limited observations.
no code implementations • 10 Jul 2020 • Yunho Jeon, Yongseok Choi, Jaesun Park, Subin Yi, Dong-Yeon Cho, Jiwon Kim
However, this is likely to restrict the potential of the target model and some transferred knowledge from the source can interfere with the training procedure.
no code implementations • 9 Mar 2020 • Seunghwan Lee, Dongkyu Lee, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim
However, these methods have limitations in using internal information available in a given test image.
no code implementations • CVPR 2021 • Seunghwan Lee, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim
We analyze the restoration performance of the fine-tuned video denoising networks with the proposed self-supervision-based learning algorithm, and demonstrate that the FCN can utilize recurring patches without requiring accurate registration among adjacent frames.
1 code implementation • ECCV 2020 • Seobin Park, Jinsu Yoo, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim
In the training stage, we train the network via meta-learning; thus, the network can quickly adapt to any input image at test time.
no code implementations • 9 Jan 2020 • Seunghwan Lee, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim
Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information available from the given input (i. e., internal statistics) at test time.
1 code implementation • 23 Jul 2019 • Linqing Feng, Jun Ho Song, Jiwon Kim, Soomin Jeong, Jin Sung Park, Jinhyun Kim
Quantitative analysis of cell nuclei in microscopic images is an essential yet still challenging source of biological and pathological information.
no code implementations • 18 Jun 2019 • Donghyeon Cho, Sungeun Hong, Sungil Kang, Jiwon Kim
After M-th frame, we select K IDs based on video saliency and frequency of appearance; then only these key IDs are tracked through the remaining frames.
no code implementations • 5 Jun 2019 • Junyoung Park, Subin Yi, Yongseok Choi, Dong-Yeon Cho, Jiwon Kim
Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy.
no code implementations • 18 Dec 2018 • Seongjin Choi, Jiwon Kim, Hwasoo Yeo
With the increasing deployment of diverse positioning devices and location-based services, a huge amount of spatial and temporal information has been collected and accumulated as trajectory data.
no code implementations • CONLL 2018 • Sangkeun Jung, Jinsik Lee, Jiwon Kim
While learning embedding models has yielded fruitful results in several NLP subfields, most notably Word2Vec, embedding correspondence has relatively not been well explored especially in the context of natural language understanding (NLU), a task that typically extracts structured semantic knowledge from a text.
no code implementations • 20 Jun 2018 • Jaehong Kim, Sungeun Hong, Yongseok Choi, Jiwon Kim
Slicing doubly nested network gives a working sub-network.
no code implementations • 11 Jun 2018 • Jaehong Kim, Sangyeul Lee, Sungwan Kim, Moonsu Cha, Jung Kwon Lee, Youngduck Choi, Yongseok Choi, Dong-Yeon Cho, Jiwon Kim
Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning.
no code implementations • 11 Jun 2018 • Risto Vuorio, Dong-Yeon Cho, Daejoong Kim, Jiwon Kim
This ability is limited in the current deep neural networks by a problem called catastrophic forgetting, where training on new tasks tends to severely degrade performance on previous tasks.
no code implementations • 31 Jul 2017 • Taeksoo Kim, Byoungjip Kim, Moonsu Cha, Jiwon Kim
To address the issue, we propose an unsupervised method to learn to transfer visual attribute.
1 code implementation • 26 Jun 2017 • Seong-Gyun Jeong, Jiwon Kim, Sujung Kim, Jaesik Min
We propose an image based end-to-end learning framework that helps lane-change decisions for human drivers and autonomous vehicles.
5 code implementations • NeurIPS 2017 • Hanul Shin, Jung Kwon Lee, Jaehong Kim, Jiwon Kim
Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting.
19 code implementations • ICML 2017 • Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, Jiwon Kim
While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations.
Ranked #10 on Facial Expression Translation on CelebA
1 code implementation • CVPR 2016 • Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN).
Ranked #20 on Image Super-Resolution on Urban100 - 2x upscaling
8 code implementations • CVPR 2016 • Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee
We present a highly accurate single-image super-resolution (SR) method.
Ranked #4 on Image Super-Resolution on WebFace - 8x upscaling
no code implementations • 15 Jun 2015 • Sang-Woo Lee, Min-Oh Heo, Jiwon Kim, Jeonghee Kim, Byoung-Tak Zhang
The proposed architecture consists of deep representation learners and fast learnable shallow kernel networks, both of which synergize to track the information of new data.