Picture for Jinwoo Shin

Jinwoo Shin

IFSeg: Image-free Semantic Segmentation via Vision-Language Model

Mar 25, 2023
Sukmin Yun, Seong Hyeon Park, Paul Hongsuck Seo, Jinwoo Shin

Figure 1 for IFSeg: Image-free Semantic Segmentation via Vision-Language Model

Figure 2 for IFSeg: Image-free Semantic Segmentation via Vision-Language Model

Figure 3 for IFSeg: Image-free Semantic Segmentation via Vision-Language Model

Figure 4 for IFSeg: Image-free Semantic Segmentation via Vision-Language Model

* Accepted to CVPR 2023

Access Paper or Ask Questions

Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck

Mar 24, 2023
Jongheon Jeong, Sihyun Yu, Hankook Lee, Jinwoo Shin

Figure 1 for Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck

Figure 2 for Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck

Figure 3 for Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck

Figure 4 for Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck

* 25 pages; CVPR 2023

Access Paper or Ask Questions

Imitating Graph-Based Planning with Goal-Conditioned Policies

Mar 20, 2023
Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son, Jinwoo Shin

Figure 1 for Imitating Graph-Based Planning with Goal-Conditioned Policies

Figure 2 for Imitating Graph-Based Planning with Goal-Conditioned Policies

Figure 3 for Imitating Graph-Based Planning with Goal-Conditioned Policies

Figure 4 for Imitating Graph-Based Planning with Goal-Conditioned Policies

* Accepted to ICLR 2023

Access Paper or Ask Questions

Guiding Energy-based Models via Contrastive Latent Variables

Mar 06, 2023
Hankook Lee, Jongheon Jeong, Sejun Park, Jinwoo Shin

Figure 1 for Guiding Energy-based Models via Contrastive Latent Variables

Figure 2 for Guiding Energy-based Models via Contrastive Latent Variables

Figure 3 for Guiding Energy-based Models via Contrastive Latent Variables

Figure 4 for Guiding Energy-based Models via Contrastive Latent Variables

* Accepted to ICLR 2023 (Spotlight). The code is available at https://github.com/hankook/CLEL

Access Paper or Ask Questions

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

Mar 02, 2023
Huiwon Jang, Hankook Lee, Jinwoo Shin

Figure 1 for Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

Figure 2 for Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

Figure 3 for Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

Figure 4 for Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

* Accepted to ICLR 2023 (Spotlight). The first two authors contributed equally. The code is available at https://github.com/alinlab/PsCo

Access Paper or Ask Questions

Preference Transformer: Modeling Human Preferences using Transformers for RL

Mar 02, 2023
Changyeon Kim, Jongjin Park, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

Figure 1 for Preference Transformer: Modeling Human Preferences using Transformers for RL

Figure 2 for Preference Transformer: Modeling Human Preferences using Transformers for RL

Figure 3 for Preference Transformer: Modeling Human Preferences using Transformers for RL

Figure 4 for Preference Transformer: Modeling Human Preferences using Transformers for RL

* Project website: https://sites.google.com/view/preference-transformer. Accepted to ICLR 2023

Access Paper or Ask Questions

STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

Mar 02, 2023
Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, Jinwoo Shin

Figure 1 for STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

Figure 2 for STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

Figure 3 for STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

Figure 4 for STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

* ICLR 2023 (Spotlight)

Access Paper or Ask Questions

Video Probabilistic Diffusion Models in Projected Latent Space

Feb 15, 2023
Sihyun Yu, Kihyuk Sohn, Subin Kim, Jinwoo Shin

Figure 1 for Video Probabilistic Diffusion Models in Projected Latent Space

Figure 2 for Video Probabilistic Diffusion Models in Projected Latent Space

Figure 3 for Video Probabilistic Diffusion Models in Projected Latent Space

Figure 4 for Video Probabilistic Diffusion Models in Projected Latent Space

* Project page: https://sihyun.me/PVDM

Access Paper or Ask Questions

Multi-View Masked World Models for Visual Robotic Manipulation

Feb 05, 2023
Younggyo Seo, Junsu Kim, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel

Figure 1 for Multi-View Masked World Models for Visual Robotic Manipulation

Figure 2 for Multi-View Masked World Models for Visual Robotic Manipulation

Figure 3 for Multi-View Masked World Models for Visual Robotic Manipulation

Figure 4 for Multi-View Masked World Models for Visual Robotic Manipulation

* First two authors contributed equally. Project webpage: https://sites.google.com/view/mv-mwm

Access Paper or Ask Questions